Compare commits

...

218 Commits

Author SHA1 Message Date
János Benjamin Antal
18edf17496 Some changes 2022-11-16 23:55:24 +01:00
gvolfing
eeb7ab6272 Initial sketch for making the simulator deterministic. 2022-11-16 18:40:12 +01:00
János Benjamin Antal
5c0e41ed44 Merge pull request #593 from memgraph/T1079-MG-add-simple-query-to-benchmark_v2
Add new dataset for mgbench
2022-11-09 16:21:56 +01:00
jeremy
6df2db0d19 Remove comment force github workflow 2022-11-09 16:02:59 +01:00
jeremy
968584a8fc Add comment force github workflow 2022-11-09 16:02:25 +01:00
jeremy
33add3ecd0 Force formatting 2022-11-09 15:38:51 +01:00
János Benjamin Antal
91b5092c71 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-09 13:05:30 +01:00
János Benjamin Antal
c0f576c187 Merge pull request #645 from memgraph/MG-add-python-checks-pineapples
Add python checks
2022-11-09 13:05:15 +01:00
jbajic
51fb4a6e7a Remove empty line 2022-11-09 11:32:54 +01:00
jbajic
cba183898a Update actions versions 2022-11-09 10:40:46 +01:00
jbajic
5f5fe7eb29 Add python checks 2022-11-09 10:39:29 +01:00
Jeremy B
efa4378fb4 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-09 08:26:25 +01:00
János Benjamin Antal
3c07a5dc04 Merge pull request #639 from memgraph/T1145-MG-handle-insertions-of-vertices-that-already-exist-in-a-better-way
Return an error for insertions of vertices that already exist
2022-11-08 17:11:22 +01:00
Jeremy B
e442963466 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-08 17:00:30 +01:00
János Benjamin Antal
32fe4d94d9 Merge branch 'project-pineapples' into T1145-MG-handle-insertions-of-vertices-that-already-exist-in-a-better-way 2022-11-08 16:35:38 +01:00
János Benjamin Antal
94b66a4e81 Merge pull request #638 from memgraph/T1148-MG-fix-expand-one-source-vertex
Fix setting the primary key of source vertex in ExpandOne
2022-11-08 16:35:30 +01:00
jeremy
61b9457718 Remove split-files logic from test code 2022-11-08 11:35:54 +01:00
János Benjamin Antal
159b30ba5f Merge branch 'project-pineapples' into T1148-MG-fix-expand-one-source-vertex 2022-11-08 08:20:25 +01:00
gvolfing
b67e5b9a6c Merge branch 'project-pineapples' into T1145-MG-handle-insertions-of-vertices-that-already-exist-in-a-better-way 2022-11-08 07:53:45 +01:00
gvolfing
79756ae6fb Modify unit test
Instead of Creating an exception that is would be only used in this
file, just assert the type of the error the double vertex insertion
operation should yield.
2022-11-08 07:31:01 +01:00
jeremy
a54bcb9819 Remove un-necessary rm in workflow 2022-11-07 17:32:09 +01:00
jeremy
c16f948de9 Delete cache folder before running benchmark test 2022-11-07 13:08:35 +01:00
jeremy
2a7ed1ad82 Add single e2e benchmark test 2022-11-07 12:55:08 +01:00
jeremy
5201db46d2 Add assert for split_file 2022-11-07 12:15:57 +01:00
gvolfing
91550128a5 Conform unit test with the new error-handling 2022-11-07 11:46:24 +01:00
jeremy
d5966101ad Merge branch 'T1079-MG-add-simple-query-to-benchmark_v2' of github.com:memgraph/memgraph into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-07 10:55:48 +01:00
jbajic
88487e2513 Extract vertex creation from FillUpSourceVertexSecondaryLabels 2022-11-07 10:54:28 +01:00
jeremy
b10b1eb239 Correct shard configuration 2022-11-07 10:33:24 +01:00
jeremy
dca94f42bb Update key type in shard configuration 2022-11-07 10:14:49 +01:00
gvolfing
39b40ecf00 Extend the Error enum instead of a separate type
The error representing that a vertex is already inserted into the
skip-list was represented by the struct AlreadyInseertedElement. Instead
of using that struct, extend the memgraph::storage::v3::Error scoped
enum and use that to represent the double-insertion error.
2022-11-07 10:00:34 +01:00
jeremy
baacc52a65 Add support for split file configuration 2022-11-07 09:54:14 +01:00
jeremy
5273d319e2 Add split file for access control 2022-11-07 09:53:29 +01:00
Jeremy B
23838b50ea Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-05 14:46:33 +01:00
Tyler Neely
d85fb94bc7 Merge pull request #634 from memgraph/T1122-MG-ShardManager-ThreadPool
Add shard manager thread pool
2022-11-04 16:41:53 +01:00
jbajic
4d2036249e Fix e2e test 2022-11-04 16:37:35 +01:00
Jure Bajic
d23643d4ff Merge branch 'project-pineapples' into T1148-MG-fix-expand-one-source-vertex 2022-11-04 16:19:55 +01:00
jbajic
e52ce1e363 Add expandone test 2022-11-04 16:18:18 +01:00
Tyler Neely
1abfe28806 Correctly use a moved transport interface while constructing CoordinatorWorker 2022-11-04 15:11:32 +00:00
jeremy
d17970f6d9 Update default value for --datasets 2022-11-04 16:04:45 +01:00
jeremy
9e72c7cb54 Add extra safe check to in case we call on dataset.py 2022-11-04 15:57:26 +01:00
Tyler Neely
528e30a9be Avoid warning for not using captured this. Use std::move instead of forward where appropriate 2022-11-04 14:13:15 +00:00
Tyler Neely
bb7c7f7627 Make popped messages non-const to allow for RVO 2022-11-04 14:07:49 +00:00
jbajic
bab5e1386a Address review comments 2022-11-04 15:05:55 +01:00
gvolfing
3d954e7abc Restructure SchemaResult type and uts usage
Rename SchemaResult to ShardOperationResult move it into a separate
header and add a new type to the underlying variant that indicates that
the vertex, the user would like to insert into the skip-list already
exist.
2022-11-04 15:04:25 +01:00
Tyler Neely
fa5c9a2568 Make items popped from *worker::Queue const. Use std::move instead of std::forward in one place 2022-11-04 11:33:02 +00:00
Tyler Neely
c745f8c877 Fix build after breaking code suggestion 2022-11-04 11:32:17 +00:00
Tyler Neely
486231b1b9 Update src/machine_manager/machine_manager.hpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-04 12:28:01 +01:00
Tyler Neely
43ad5855c4 Update src/machine_manager/machine_manager.hpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-04 12:27:40 +01:00
Tyler Neely
24864ff7d2 Update src/coordinator/coordinator_worker.hpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-04 12:17:57 +01:00
Tyler Neely
8598f6edf4 Fix a race condition that happens when logging from a detached thread in the cluster property test. Improve the ShardManager dtor and log statements 2022-11-04 11:14:39 +00:00
jeremy
e41073bc2c Update script to need single argument for local dataset 2022-11-04 09:17:09 +01:00
jeremy
14e3e72565 Correct badly written range 2022-11-04 08:52:47 +01:00
gvolfing
1cee7ecb8a Make ShardRsm aware of trying to write the same vertex into the skip-list 2022-11-04 08:12:37 +01:00
Jeremy B
690a389563 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-03 17:43:47 +01:00
Tyler Neely
9203616283 Merge branch 'project-pineapples' into T1122-MG-ShardManager-ThreadPool 2022-11-03 17:01:07 +01:00
Tyler Neely
d198819bf1 Merge pull request #637 from memgraph/tyler_remove_storage_v2_durability_test
Remove unit tests for storage v2
2022-11-03 17:00:46 +01:00
jbajic
3a8f01af79 Fix expand one source vertex pk setting 2022-11-03 16:29:28 +01:00
Tyler Neely
7e6ec8bb26 Capture this instead of all references in scope for call to std::visit to route CoordinatorWorker messages 2022-11-03 14:38:16 +00:00
Tyler Neely
6138d76690 Remove unit tests for storage v2 2022-11-03 14:21:17 +00:00
Tyler Neely
25fdb1a1f0 Make the high_density_shard_create_scan test run much faster 2022-11-03 13:48:11 +00:00
Tyler Neely
2de1d6c359 Fix UB due to integer overflow 2022-11-03 13:27:45 +00:00
Tyler Neely
0364311dd0 Log latency histograms in the high_density_shard_create_scan test 2022-11-03 12:44:47 +00:00
Tyler Neely
9235515dab Reduce high_density_shard_create_scan shard+thread combinations. Log Raft write request demangled names 2022-11-03 12:38:12 +00:00
Tyler Neely
b83fb287ad Apply feedback from clang-tidy 2022-11-03 11:00:07 +00:00
jeremy
70dc19dfdb Mgbench: apply filtering on results from client 2022-11-03 11:03:21 +01:00
Tyler Neely
b685a21171 Merge branch 'project-pineapples' of github.com:memgraph/memgraph into T1122-MG-ShardManager-ThreadPool 2022-11-03 09:42:28 +00:00
Tyler Neely
4db83b8159 Add a few safety checks to the new concurrent Queue structures and the promise maps in the transport layer 2022-11-03 09:41:28 +00:00
Tyler Neely
dd8dd4f6c4 Restructure responsibilities for assigning request ids to the transport handles. Simplify promise tracking to avoid replier addresses, enabling eventual direct server return (DSR) 2022-11-03 09:31:06 +00:00
Tyler Neely
fa1ddfea12 Fix a bug where the MachineManager's destructor became incorrect after being moved 2022-11-02 17:45:27 +00:00
Tyler Neely
a815ec9617 Handle Coordinator work on a separate thread, unblocking the MachineManager to route additional messages to Shards 2022-11-02 17:15:52 +00:00
Tyler Neely
78528bd609 Avoid the ShutDown explicit acknowledgement due to jthread already blocking on this 2022-11-02 17:12:21 +00:00
Tyler Neely
6239f4fc3e Simplify usage of PromiseKey in LocalTransportHandle to avoid replier address 2022-11-02 17:11:26 +00:00
Jeremy B
c5eb3ff2c0 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-02 17:01:08 +01:00
János Benjamin Antal
9f71ce0f78 Merge pull request #635 from memgraph/MG-expand-fixes 2022-11-02 15:55:49 +01:00
János Benjamin Antal
589dd36bf2 Make function parameter constant 2022-11-02 14:44:54 +01:00
János Benjamin Antal
57e7169203 Eliminate dangling reference from lambda 2022-11-02 14:22:01 +01:00
János Benjamin Antal
bb3b053375 Create edge in the correct direction 2022-11-02 14:22:01 +01:00
János Benjamin Antal
a96f489756 Count the number of requests per operator 2022-11-02 14:22:01 +01:00
jeremy
e909e7d2d8 Format 2022-11-02 14:18:04 +01:00
Jeremy B
2d91a7fd1e Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-02 14:14:24 +01:00
Jeremy B
1d18f1197f Update tests/mgbench/dataset_creator.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-11-02 14:14:16 +01:00
Jeremy B
edeebf46ec Update tests/mgbench/benchmark.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-11-02 14:13:58 +01:00
Jeremy B
1148fe9aad Update tests/mgbench/datasets.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-11-02 14:13:40 +01:00
János Benjamin Antal
c92c795b1a Merge pull request #632 from memgraph/MG-improve-parameters 2022-11-02 14:06:30 +01:00
János Benjamin Antal
0fee412f92 Merge branch 'project-pineapples' into MG-improve-parameters 2022-11-02 13:37:35 +01:00
Tyler Neely
7596e85358 When message conversion fails to happen, demangle the concrete type name and error log a useful message 2022-11-02 12:37:34 +00:00
Jeremy B
014836ca3c Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-02 12:51:12 +01:00
Tyler Neely
68654b5a19 Merge branch 'project-pineapples' of github.com:memgraph/memgraph into T1122-MG-ShardManager-ThreadPool 2022-11-02 10:55:18 +00:00
János Benjamin Antal
4d96bf5006 Merge pull request #628 from memgraph/T1138-MG-fix-edge-id-allocator
Fix passing of edge IdAllocator not by value but as pointer
2022-11-02 10:40:35 +01:00
Marko Budiselić
9bb70eb0b9 Merge branch 'project-pineapples' into T1138-MG-fix-edge-id-allocator 2022-11-01 19:38:10 +01:00
Jeremy B
7076788dd5 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-01 18:51:57 +01:00
Tyler Neely
ee4be9aa5b Merge pull request #631 from memgraph/tyler_remove_shard_map_from_machine_manager
Remove redundant ShardMap copy from MachineManager to avoid race conditions
2022-11-01 18:33:37 +01:00
Jeremy B
96a2ad4b63 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-01 18:21:36 +01:00
Tyler Neely
84509fa477 Fix merge conflict with MachineManager constructor 2022-11-01 17:07:14 +00:00
Tyler Neely
19b5fe3caf Merge branch 'project-pineapples' into tyler_remove_shard_map_from_machine_manager 2022-11-01 17:57:03 +01:00
Tyler Neely
74db669e23 Merge pull request #622 from memgraph/tyler_1k_shard_unit_test
Add test for 1k shards, 1k create vertices, and then a scan all
2022-11-01 17:56:42 +01:00
Tyler Neely
599802033f Reformat TODO comment 2022-11-01 17:21:15 +01:00
Tyler Neely
6dd57426f8 Revert broken code suggestion 2022-11-01 15:51:37 +00:00
Tyler Neely
3c9f0c48e9 Merge branch 'project-pineapples' into tyler_1k_shard_unit_test 2022-11-01 16:31:29 +01:00
Tyler Neely
9a1258a708 Update tests/unit/1k_shards_1k_create_scanall.cpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-01 16:31:14 +01:00
Tyler Neely
c55ca836a4 Update tests/unit/1k_shards_1k_create_scanall.cpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-01 16:31:06 +01:00
Tyler Neely
5674ef4016 Update tests/unit/1k_shards_1k_create_scanall.cpp
Co-authored-by: Kostas Kyrimis  <kostaskyrim@gmail.com>
2022-11-01 16:30:37 +01:00
Tyler Neely
77c2afc9e7 Add TODO about ID mapping improvements 2022-11-01 15:27:35 +00:00
Tyler Neely
27292dd921 Merge branch 'project-pineapples' into tyler_remove_shard_map_from_machine_manager 2022-11-01 16:20:54 +01:00
Jeremy B
e4f1fd8647 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-11-01 16:06:44 +01:00
János Benjamin Antal
4608af9d00 Merge branch 'project-pineapples' into MG-improve-parameters 2022-11-01 15:56:16 +01:00
János Benjamin Antal
50e72a7c28 Merge branch 'project-pineapples' into T1138-MG-fix-edge-id-allocator 2022-11-01 15:56:12 +01:00
János Benjamin Antal
17a104677d Merge pull request #617 from memgraph/T1105-MG-profile-query-in-distributed 2022-11-01 15:55:52 +01:00
Tyler Neely
a6add80fc9 Use static RSM partitioning function for achieving a smooth Shard->ShardWorker distribution 2022-11-01 14:52:38 +00:00
Tyler Neely
5d3eaf6a55 Rename 1k_shards_1k_create_scanall test to high_density_shard_create_scan 2022-11-01 14:02:07 +00:00
Tyler Neely
a13f260236 Parameterize shard worker threads in the MachineConfig and simplify test output 2022-11-01 13:57:57 +00:00
jeremy
1f778ba5f3 Add possibility to give extra tests arg to MGBench 2022-11-01 14:14:55 +01:00
jeremy
787987168c Make benchmark work with any customer datasets 2022-11-01 12:51:01 +01:00
János Benjamin Antal
7b4b1ba8ed Speed up Parameters::AtTokenPosition 2022-11-01 11:51:35 +01:00
Tyler Neely
bb1e8aa164 Improve histogram output by adding a pretty table printing function 2022-11-01 10:46:25 +00:00
Tyler Neely
27a1311966 Merge branch 'tyler_1k_shard_unit_test' of github.com:memgraph/memgraph into T1122-MG-ShardManager-ThreadPool 2022-11-01 09:49:15 +00:00
János Benjamin Antal
30ff6487f2 Merge remote-tracking branch 'origin/project-pineapples' into T1105-MG-profile-query-in-distributed 2022-11-01 10:32:44 +01:00
Tyler Neely
119da2d7a7 Update CMakeLists.txt 2022-11-01 09:51:43 +01:00
Tyler Neely
fa972813d2 Update src/coordinator/shard_map.cpp
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-10-31 19:05:19 +01:00
Tyler Neely
951b058116 Complete migration from single-threaded ShardManager to multi-threaded ShardWorker processing 2022-10-31 18:04:30 +00:00
Tyler Neely
d0cad6e6ba Temporarily duplicate shard management logic from ShardManger in ShardWorker 2022-10-31 17:25:08 +00:00
Tyler Neely
6138277972 Merge branch 'tyler_remove_shard_map_from_machine_manager' of github.com:memgraph/memgraph into T1122-MG-ShardManager-ThreadPool 2022-10-31 17:14:01 +00:00
Tyler Neely
2f77eb96ff Remove redundant ShardMap copy from MachineManager to avoid race conditions 2022-10-31 16:49:46 +00:00
Tyler Neely
d7bc93c55f Fill Cron next time promise from each worker thread 2022-10-31 16:17:34 +00:00
Tyler Neely
039d5f51d3 Merge branch 'project-pineapples' into T1122-MG-ShardManager-ThreadPool 2022-10-31 17:06:36 +01:00
Tyler Neely
cebe6f62fa Implement skeleton worker threadpool for the ShardManager 2022-10-31 16:03:47 +00:00
jbajic
6834ce01fe Fix edge id allocator 2022-10-31 16:26:56 +01:00
jeremy
4c5cd1f847 Add possibility to have MgBench working against local file 2022-10-31 16:10:04 +01:00
János Benjamin Antal
f9e2a66961 Add const qualifier to function parameters 2022-10-31 15:53:04 +01:00
János Benjamin Antal
d5700ab5ff Use [[unlikely]] attribute 2022-10-31 15:53:04 +01:00
Tyler Neely
b0aaba6765 Merge branch 'project-pineapples' into tyler_1k_shard_unit_test 2022-10-31 15:47:38 +01:00
jeremy
e1f18f3733 Update location of Pokec datasets on aws 2022-10-31 15:19:34 +01:00
jeremy
c90b38faf0 Update aws address for datasets 2022-10-31 14:49:32 +01:00
jeremy
acbf3c764c Remove arg from __init__ 2022-10-31 13:35:41 +01:00
jeremy
37df41796f git puMerge branch 'T1079-MG-add-simple-query-to-benchmark_v2' of github.com:memgraph/memgraph into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-31 13:02:12 +01:00
jeremy
f04e1cda4b Add function 2022-10-31 13:02:05 +01:00
Jeremy B
f28ba89584 Update tests/mgbench/dataset_creator.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-10-31 13:01:42 +01:00
jeremy
60485311c8 Merge branch 'T1079-MG-add-simple-query-to-benchmark_v2' of github.com:memgraph/memgraph into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-31 12:57:46 +01:00
Jeremy B
36a1c43851 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-31 12:57:41 +01:00
Jeremy B
bae8c084b1 Update tests/mgbench/datasets.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-10-31 12:56:02 +01:00
Jeremy B
2898120eeb Update tests/mgbench/datasets.py
Co-authored-by: Jure Bajic <jure.bajic@memgraph.com>
2022-10-31 12:55:42 +01:00
jeremy
d62a45752a Remove unused variable 2022-10-31 12:55:38 +01:00
jeremy
c5ee6ffbc2 Update dataset_creator script 2022-10-31 12:41:28 +01:00
jeremy
5ef08f841a Update Dataset creation script 2022-10-31 11:56:20 +01:00
Kostas Kyrimis
59c7d81ae8 [🍍 < T1086-MG] Test distributed operators e2e (#607)
* Fix Explain queries
* Add Vertex/Edge accessor support for properties
* Fix projections
* Fix expansions to fetch destination vertex properties
* Fix improper use of ShardMap on bolt and replaced it with the ShardRequestManager 
* Add NameToId mappers on ShardRequestManager
* Add e2e tests for operators
* Fix OPTIONAL MATCH
2022-10-31 11:52:20 +02:00
jeremy
03c095e780 Update assert 2022-10-31 10:52:06 +01:00
Jeremy B
b542e49b3e Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-31 09:44:34 +01:00
Jeremy B
ddb30f49ea Update datasets.py 2022-10-31 09:43:22 +01:00
János Benjamin Antal
d920d7c293 Merge branch 'project-pineapples' into T1105-MG-profile-query-in-distributed 2022-10-31 09:27:05 +01:00
Tyler Neely
6b0168cb3d Add LocalTransport::ResponseLatencies 2022-10-28 08:51:12 +00:00
Tyler Neely
03cf264b76 Add test for 1k shards, 1k create vertices, and then a scan all 2022-10-28 08:29:27 +00:00
Tyler Neely
9448e23dc9 Check-in basic shard scheduler skeleton 2022-10-27 13:36:53 +00:00
Tyler Neely
eafccaea84 Add a logarithmically bucketing histogram and record response latencies per message type (#616) 2022-10-26 15:57:11 +02:00
János Benjamin Antal
0c4f591b3c Merge branch 'project-pineapples' into T1105-MG-profile-query-in-distributed 2022-10-26 14:48:27 +02:00
János Benjamin Antal
534e365271 Suppress warning about exception escape for destructor 2022-10-26 11:22:27 +02:00
János Benjamin Antal
281ae158ec Make ReadTSC noexcept 2022-10-26 11:21:27 +02:00
János Benjamin Antal
39c9c215b1 Suppress clang-tidy warnings for 2022-10-26 11:14:24 +02:00
János Benjamin Antal
f6e78ce6da Fix TODOs in storage engine (#614)
Fixed various TODOs that were easy to fix to improve the code quality of the
newly implemented storage.
2022-10-26 10:40:35 +02:00
János Benjamin Antal
3cf79f5bbf Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-25 21:24:20 +02:00
János Benjamin Antal
6a31c49432 Flatten nested conditional statements 2022-10-25 20:30:29 +02:00
János Benjamin Antal
fea92f4829 Merge remote-tracking branch 'origin/project-pineapples' into T1105-MG-profile-query-in-distributed 2022-10-25 20:28:54 +02:00
János Benjamin Antal
1703cd039d Populate custom data of profile query with request wait times 2022-10-25 20:15:06 +02:00
gvolfing
ca2351124b Make primary labels act as label indices (#605)
Because of the lexicographical sharding, the primary labels themselves are
acting as indexes. If a primary label is specified in a MATCH query we can
safely narrow the range of shards we have to scan through based on that label.
This PR introduces the necessary changes in order to achieve that.
2022-10-25 19:48:17 +02:00
János Benjamin Antal
5784c0d473 Return the custom data for profile queries 2022-10-25 15:26:42 +02:00
János Benjamin Antal
8ebc704819 Fix profile queries with ScanAll 2022-10-25 14:37:18 +02:00
János Benjamin Antal
5939fb2b0c Start transaction properly 2022-10-25 14:35:26 +02:00
János Benjamin Antal
ee64684b0b Add ScopedCustomProfile 2022-10-25 13:37:57 +02:00
János Benjamin Antal
1e4c02f8a5 Make profile query work 2022-10-25 13:37:27 +02:00
János Benjamin Antal
8353228ba7 Upgrade json lib to 3.11.2 2022-10-25 13:10:03 +02:00
János Benjamin Antal
332afadf21 Split file parsing (#600)
Add temporary support for split files. This is only temporary solution until we
get the shard splitting implemented.
2022-10-25 10:27:13 +02:00
Tyler Neely
acc655f4fd Model-based testing of simulated full cluster (#584)
This PR adds support for generating randomized workloads that will be executed
against a simulated cluster, as well as against a correctness model. Initially
this just generates ScanAll and CreateVertex requests, and anything that it
creates, it also inserts into a `std::set`, and when we do a ScanAll, it asserts
that we get the same number of requests back. This will become much more
sophisticated over time, but it's already hitting pay-dirt.
2022-10-24 19:54:09 +02:00
Tyler Neely
12e7a261aa operator<< implementations for a few foundational types (#604) 2022-10-21 15:25:40 +02:00
Marko Budiselić
1c3bb969e9 Decouple interactive planning manual test (#585) 2022-10-21 13:34:13 +02:00
Jure Bajic
e5437080c5 Handle OrderBy in ScanVertices request (#594)
- Refactor shard_rsm and move function into expr.hpp/expr.cpp and request_helper.hpp/request_helper.cpp
2022-10-21 12:33:40 +02:00
Tyler Neely
17090dd8ac Load SPDLOG_LEVEL environment variable in unit tests binaries (#606)
Co-authored-by: János Benjamin Antal <antaljanosbenjamin@users.noreply.github.com>
2022-10-20 18:27:52 +02:00
gvolfing
281cebd386 Add filtering capabilities to ExpandOne request (#581) 2022-10-20 17:51:44 +02:00
János Benjamin Antal
f89a2bbf42 Make ExpandOne work in the query engine (#589) 2022-10-20 11:35:00 +02:00
gvolfing
85b8ce9101 Implement filtering capabilities for ScanAll (#578)
ScanVerticesrequest was not able to utilize filtering capabilities
before. With these modification it is now able to filter the scanned
vertices based on the filter_expressions field in the
ScanVerticesRequest message type.
2022-10-19 16:09:00 +02:00
Jure Bajic
6bb40a7f49 Create ExpandOne request (#580)
Refactor CreateEdge into CreateExpand
2022-10-19 13:55:46 +02:00
Jeremy B
1707ee648e Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-19 08:47:13 +02:00
gvolfing
07f34838bd Add e2e test to check ScanAll on new architecture (#603)
Add testing capabilities similar to what existed before on the older
architecture. With this test specifically, test if we can create
vertices and return them with ScanAll. There is a hard-coded 3s wait in
the test which is needed because the MachineManager need this time to
initialize itself.
2022-10-18 21:38:56 +02:00
Jeremy B
b6f8b5e130 Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-18 15:49:19 +02:00
jeremy
58243f4a26 Rename User->File
Use parser for argument i.o. simple variable in script
2022-10-18 15:47:13 +02:00
gvolfing
d06132cb33 Make ShardRequestManager work with futures (#588)
The communication between the ShardRequestManager and the RsmClient
used to be direct. In this PR this changes into a future-based
communication type. The RsmClient stores state about the currently
processed future (either read or write request) and exposes blocking
and non-blocking functionality to obtain the filled future. The
ShardRequestManager -for now- will send of the set of requests present
in the ExecutionState and block on each of them until the requests are
completed or the set of paginated responses(caused by, for example the
batch-limit in ScanAll) are ready for the next round.
2022-10-18 09:53:37 +02:00
Jeremy B
f063c1b1ad Merge branch 'project-pineapples' into T1079-MG-add-simple-query-to-benchmark_v2 2022-10-17 11:41:55 +02:00
Marko Budiselić
5347c06d76 Add shutdown of LocalSystem during the shutdown process (#592) 2022-10-14 11:59:50 +02:00
Tyler Neely
4634ac484a Optimize simulator RNG usage (#590)
This causes instructions for `basic_request.cpp` to drop from 281 million to 28 million
2022-10-12 19:19:06 +03:00
jeremy
a5dc818e19 Add new dataset for mgbench 2022-10-12 16:35:47 +02:00
Jeremy B
4cb3b064c4 Add filter to scan all (#575)
Add several versions of ScanAll with filters.
Add helper function to transform an expression into string that can be parsed again once on the storage.
2022-10-12 11:46:59 +02:00
Jure Bajic
23171e76b6 Integrate bolt server (#572)
* Use query-v2 in the main executable
* Set up machine manager in memgraph
* Add `ShardRequestManager` to `Interpreter`
* Make vertex creation work
* Make scan all work
* Add edge type map in shard request manager
* Send schema over request
* Empty out DbAccessor
* Store shard mapping at creation
* Remove failing CI steps

Cooltura is the best place in Zagreb!

Co-authored-by: János Benjamin Antal <benjamin.antal@memgraph.io>
2022-10-11 16:31:46 +02:00
Jeremy B
6fd64d31f2 Update usage of Shard (#574)
Updating tests to use new constructor of Shard
Commenting test shard_request_manager
2022-10-05 11:56:36 +02:00
gvolfing
87111b2f89 Implement missing message handlers (#563)
Implement the missing message handlers with basic functionality. The
implementation does not include any capabilities to filter based on
expressions.
2022-10-03 15:31:06 +02:00
Tyler Neely
b5c7078c7d Stitch request manager with shard (#570)
Fix various bugs
2022-09-23 20:07:41 +02:00
Kostas Kyrimis
925835b080 Implement query engine client (#531)
- Add shard request manager
2022-09-22 15:05:43 +02:00
Tyler Neely
ce788f5f65 Machine manager and shard stitch (#569) 2022-09-22 13:55:16 +02:00
János Benjamin Antal
b8186bea2e Lexicographically ordered storage (#454) 2022-09-21 18:58:31 +02:00
János Benjamin Antal
3c4856dcb7 Merge remote-tracking branch 'origin/project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-09-21 18:50:00 +02:00
Marko Budiselić
b4d6dc0930 Add proper transaction handling (#550) 2022-09-21 18:25:51 +02:00
Jure Bajic
817161a915 Implement expression evaluator in storage v3 (#534)
- Enable `mg-expr` in mg-storage-v3
-  Adapt id_mapper
- Change conversion function from PropertyValue to TypedValue
- Remove memgraph functions
- Enable expression tests on for storage
2022-09-21 17:26:55 +02:00
Tyler Neely
58eb2caf0f Add machine manager prototype (#533) 2022-09-21 16:57:25 +02:00
gvolfing
ecda71168c Implement message based actions (#538)
Create shard-side handlers for basic messages

Implement the handlers for CreateVertices, CreateEdges and ScanAll. Use
or modify the defined messages to interact with individual Shards and
test their behavior. Shard is currently being owned by ShardRsm
instances. The two top level dispatching functions Read() and Apply()
are responsible for read- and write operations respectively. Currently
there are a handful of messages that are defined but not utilized, these
will be used in the near future, as well as a couple of handler
functions with empty implementations.
2022-09-20 11:15:19 +02:00
János Benjamin Antal
8e1f83acc9 Reference vertices by id in edges (#532) 2022-09-14 13:11:14 +02:00
jbajic
f910cb770c Merge branch 'project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-09-09 12:39:28 +02:00
Kostas Kyrimis
38d0b89b04 Implement expression evaluator library (#486) 2022-09-07 18:15:32 +03:00
Jure Bajic
a2a6a3855b Remove primary label from vertex (#529)
- Remove the primary label from vertex
- Pass vertex_validator instead of schema validator
- Fix vertex ctors
2022-09-07 13:36:10 +02:00
Jure Bajic
e9f0360fb3 Enable indices for storage v3 (#528)
- Enable indices in storage v3
- Add new test cases
- Change `CreateVertexAndValidate` to call `SetProperty` and `AddLabel`
2022-09-06 22:48:25 +02:00
János Benjamin Antal
fe4955447e Merge branch 'project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-09-05 14:59:01 +02:00
Tyler Neely
1631c20df2 In memory shard map (#505) 2022-09-05 15:50:54 +03:00
János Benjamin Antal
947baedbe6 Merge remote-tracking branch 'origin/project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-09-02 11:41:03 +02:00
Kostas Kyrimis
c6447eb48b Add shard requests responses (#526) 2022-09-01 18:54:47 +03:00
Jure Bajic
7e84744d07 Split storage and shards (#519)
- Rename storage to shard
- Add primary label and range for shard
- Remove id_mapper functionality from shard
- Adapt tests
2022-09-01 09:10:40 +02:00
Tyler Neely
c0d03888f4 Implement basic raft version (#498) 2022-08-30 15:07:34 +02:00
János Benjamin Antal
efb3c8d03d Remove multi-threaded related logic and variables (#460)
* Remove logic that was necessary for optimal multi-threaded performance, such
  as accumulating deleted object in local containers and appending them to a
  global one, handling overlapping locking.
* Remove background GC thread.
* Remove mutexes, locks and atomics throughout storage.
2022-08-30 13:41:53 +02:00
Jure Bajic
95dbc022c0 Integrate schema and keystore (#497)
- Integrate schema and keystore on vertex creation
- Add GC test for storage v3
- Add tests for accessors
- Fix all tests related to this except for query v2
- Fix labels not returning primary label
2022-08-29 14:38:25 +02:00
Tyler Neely
a40403e3ce Add local transport (#512)
* Create LocalTransport Io provider for sending messages to components on the same machine
* Move src/io/simulation/message_conversion.hpp to src/io/message_conversion.hpp for use in other Io providers
2022-08-29 13:49:51 +02:00
jbajic
68b26275a3 Merge branch 'project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-08-08 11:34:46 +02:00
János Benjamin Antal
2891041468 Make storage use KeyStore (#455) 2022-08-03 18:10:58 +02:00
János Benjamin Antal
cc5ee6a496 Merge remote-tracking branch 'origin/project-pineapples' into E118-MG-lexicographically-ordered-storage 2022-08-02 08:19:43 +02:00
326 changed files with 41432 additions and 50060 deletions

View File

@@ -16,7 +16,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)

View File

@@ -26,7 +26,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -64,7 +64,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -75,14 +75,39 @@ jobs:
- name: Fetch all history for all tags and branches
run: git fetch
- name: Initialize deps
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
- name: Set base branch
if: ${{ github.event_name == 'pull_request' }}
run: |
echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
- name: Set base branch # if we manually dispatch or push to master
if: ${{ github.event_name != 'pull_request' }}
run: |
echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
- name: Python code analysis
run: |
CHANGED_FILES=$(git diff -U0 ${{ env.BASE_BRANCH }}... --name-only)
for file in ${CHANGED_FILES}; do
echo ${file}
if [[ ${file} == *.py ]]; then
python3 -m black --check --diff ${file}
python3 -m isort --check-only --diff ${file}
fi
done
- name: Build combined ASAN, UBSAN and coverage binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
cd build
cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
make -j$THREADS memgraph__unit
@@ -110,7 +135,7 @@ jobs:
tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
- name: Save code coverage
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/generated/code_coverage.tar.gz
@@ -130,7 +155,7 @@ jobs:
source /opt/toolchain-v4/activate
# Restrict clang-tidy results only to the modified parts
git diff -U0 ${{ env.BASE_BRANCH }}... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -path build | tee ./build/clang_tidy_output.txt
git diff -U0 ${{ env.BASE_BRANCH }}... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -path build | tee ./build/clang_tidy_output.txt
# Fail if any warning is reported
! cat ./build/clang_tidy_output.txt | ./tools/github/clang-tidy/grep_error_lines.sh > /dev/null
@@ -145,7 +170,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -164,52 +189,23 @@ jobs:
cmake ..
make -j$THREADS
- name: Run leftover CTest tests
- name: Run simulation tests
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run leftover CTest tests (all except unit and benchmark tests).
# Run simulation tests.
cd build
ctest -E "(memgraph__unit|memgraph__benchmark|memgraph__simulation)" --output-on-failure
ctest -R memgraph__simulation --output-on-failure -j$THREADS
- name: Run drivers tests
run: |
./tests/drivers/run.sh
- name: Run integration tests
run: |
cd tests/integration
for name in *; do
if [ ! -d $name ]; then continue; fi
pushd $name >/dev/null
echo "Running: $name"
if [ -x prepare.sh ]; then
./prepare.sh
fi
if [ -x runner.py ]; then
./runner.py
elif [ -x runner.sh ]; then
./runner.sh
fi
echo
popd >/dev/null
done
- name: Run cppcheck and clang-format
- name: Run single benchmark test
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run cppcheck and clang-format.
cd tools/github
./cppcheck_and_clang_format diff
- name: Save cppcheck and clang-format errors
uses: actions/upload-artifact@v2
with:
name: "Code coverage"
path: tools/github/cppcheck_and_clang_format.txt
# Run simulation tests.
cd tests/mgbench
./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
release_build:
name: "Release build"
@@ -221,7 +217,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -240,19 +236,6 @@ jobs:
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS
- name: Run GQL Behave tests
run: |
cd tests/gql_behave
./continuous_integration
- name: Save quality assurance status
uses: actions/upload-artifact@v2
with:
name: "GQL Behave Status"
path: |
tests/gql_behave/gql_behave_status.csv
tests/gql_behave/gql_behave_status.html
- name: Run unit tests
run: |
# Activate toolchain.
@@ -267,10 +250,19 @@ jobs:
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run unit tests.
# Run simulation tests.
cd build
ctest -R memgraph__simulation --output-on-failure -j$THREADS
- name: Run single benchmark test
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run simulation tests.
cd tests/mgbench
./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
- name: Run e2e tests
run: |
# TODO(gitbuda): Setup mgclient and pymgclient properly.
@@ -278,167 +270,4 @@ jobs:
./setup.sh
source ve3/bin/activate
cd e2e
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory .
- name: Run stress test (plain)
run: |
cd tests/stress
./continuous_integration
- name: Run stress test (SSL)
run: |
cd tests/stress
./continuous_integration --use-ssl
- name: Run durability test
run: |
cd tests/stress
source ve3/bin/activate
python3 durability --num-steps 5
- name: Create enterprise DEB package
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
cd build
# create mgconsole
# we use the -B to force the build
make -j$THREADS -B mgconsole
# Create enterprise DEB package.
mkdir output && cd output
cpack -G DEB --config ../CPackConfig.cmake
- name: Save enterprise DEB package
uses: actions/upload-artifact@v2
with:
name: "Enterprise DEB package"
path: build/output/memgraph*.deb
- name: Save test data
uses: actions/upload-artifact@v2
if: always()
with:
name: "Test data"
path: |
# multiple paths could be defined
build/logs
release_jepsen_test:
name: "Release Jepsen Test"
runs-on: [self-hosted, Linux, X64, Debian10, JepsenControl]
#continue-on-error: true
env:
THREADS: 24
MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
steps:
- name: Set up repository
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
fetch-depth: 0
- name: Build release binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
# Build only memgraph release binarie.
cd build
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS memgraph
- name: Run Jepsen tests
run: |
cd tests/jepsen
./run.sh test --binary ../../build/memgraph --run-args "test-all --node-configs resources/node-config.edn" --ignore-run-stdout-logs --ignore-run-stderr-logs
- name: Save Jepsen report
uses: actions/upload-artifact@v2
if: ${{ always() }}
with:
name: "Jepsen Report"
path: tests/jepsen/Jepsen.tar.gz
release_benchmarks:
name: "Release benchmarks"
runs-on: [self-hosted, Linux, X64, Diff, Gen7]
env:
THREADS: 24
MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
steps:
- name: Set up repository
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
fetch-depth: 0
- name: Build release binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
# Build only memgraph release binaries.
cd build
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS
- name: Run macro benchmarks
run: |
cd tests/macro_benchmark
./harness QuerySuite MemgraphRunner \
--groups aggregation 1000_create unwind_create dense_expand match \
--no-strict
- name: Get branch name (merge)
if: github.event_name != 'pull_request'
shell: bash
run: echo "BRANCH_NAME=$(echo ${GITHUB_REF#refs/heads/} | tr / -)" >> $GITHUB_ENV
- name: Get branch name (pull request)
if: github.event_name == 'pull_request'
shell: bash
run: echo "BRANCH_NAME=$(echo ${GITHUB_HEAD_REF} | tr / -)" >> $GITHUB_ENV
- name: Upload macro benchmark results
run: |
cd tools/bench-graph-client
virtualenv -p python3 ve3
source ve3/bin/activate
pip install -r requirements.txt
./main.py --benchmark-name "macro_benchmark" \
--benchmark-results-path "../../tests/macro_benchmark/.harness_summary" \
--github-run-id "${{ github.run_id }}" \
--github-run-number "${{ github.run_number }}" \
--head-branch-name "${{ env.BRANCH_NAME }}"
- name: Run mgbench
run: |
cd tests/mgbench
./benchmark.py --num-workers-for-benchmark 12 --export-results benchmark_result.json pokec/medium/*/*
- name: Upload mgbench results
run: |
cd tools/bench-graph-client
virtualenv -p python3 ve3
source ve3/bin/activate
pip install -r requirements.txt
./main.py --benchmark-name "mgbench" \
--benchmark-results-path "../../tests/mgbench/benchmark_result.json" \
--github-run-id "${{ github.run_id }}" \
--github-run-number "${{ github.run_number }}" \
--head-branch-name "${{ env.BRANCH_NAME }}"
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory ./distributed_queries

View File

@@ -14,7 +14,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -39,7 +39,7 @@ jobs:
source /opt/toolchain-v4/activate
# The results are also written to standard output in order to retain them in the logs
./tools/github/clang-tidy/run-clang-tidy.py -p build -j $THREADS -clang-tidy-binary=/opt/toolchain-v4/bin/clang-tidy "$PWD/src/*" |
./tools/github/clang-tidy/run-clang-tidy.py -p build -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -clang-tidy-binary=/opt/toolchain-v4/bin/clang-tidy "$PWD/src/*" |
tee ./build/full_clang_tidy_output.txt
- name: Summarize clang-tidy results

View File

@@ -17,7 +17,7 @@ jobs:
run: |
./release/package/run.sh package centos-7
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: centos-7
path: build/output/centos-7/memgraph*.rpm
@@ -34,7 +34,7 @@ jobs:
run: |
./release/package/run.sh package centos-9
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: centos-9
path: build/output/centos-9/memgraph*.rpm
@@ -51,7 +51,7 @@ jobs:
run: |
./release/package/run.sh package debian-10
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: debian-10
path: build/output/debian-10/memgraph*.deb
@@ -68,7 +68,7 @@ jobs:
run: |
./release/package/run.sh package debian-11
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: debian-11
path: build/output/debian-11/memgraph*.deb
@@ -87,7 +87,7 @@ jobs:
./run.sh package debian-11 --for-docker
./run.sh docker
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: docker
path: build/output/docker/memgraph*.tar.gz
@@ -104,7 +104,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-18.04
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ubuntu-1804
path: build/output/ubuntu-18.04/memgraph*.deb
@@ -121,7 +121,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-20.04
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ubuntu-2004
path: build/output/ubuntu-20.04/memgraph*.deb
@@ -138,7 +138,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-22.04
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: ubuntu-2204
path: build/output/ubuntu-22.04/memgraph*.deb
@@ -155,7 +155,7 @@ jobs:
run: |
./release/package/run.sh package debian-11 --for-platform
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: debian-11-platform
path: build/output/debian-11/memgraph*.deb
@@ -172,7 +172,7 @@ jobs:
run: |
./release/package/run.sh package debian-11-arm
- name: "Upload package"
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: debian-11-arm
path: build/output/debian-11-arm/memgraph*.deb

View File

@@ -17,7 +17,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
- name: Save code coverage
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
./cppcheck_and_clang_format diff
- name: Save cppcheck and clang-format errors
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -225,7 +225,7 @@ jobs:
rpmlint memgraph*.rpm
- name: Save enterprise RPM package
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Enterprise RPM package"
path: build/output/memgraph*.rpm
@@ -262,7 +262,7 @@ jobs:
./continuous_integration
- name: Save quality assurance status
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "GQL Behave Status"
path: |

View File

@@ -17,7 +17,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
- name: Save code coverage
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
./cppcheck_and_clang_format diff
- name: Save cppcheck and clang-format errors
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -224,7 +224,7 @@ jobs:
cpack -G DEB --config ../CPackConfig.cmake
- name: Save enterprise DEB package
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Enterprise DEB package"
path: build/output/memgraph*.deb
@@ -261,7 +261,7 @@ jobs:
./continuous_integration
- name: Save quality assurance status
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "GQL Behave Status"
path: |
@@ -324,7 +324,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -349,7 +349,7 @@ jobs:
./run.sh test --binary ../../build/memgraph --run-args "test-all --node-configs resources/node-config.edn" --ignore-run-stdout-logs --ignore-run-stderr-logs
- name: Save Jepsen report
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
if: ${{ always() }}
with:
name: "Jepsen Report"

View File

@@ -19,7 +19,7 @@ jobs:
DOCKER_REPOSITORY_NAME: memgraph
steps:
- name: Checkout
uses: actions/checkout@v2
uses: actions/checkout@v3
- name: Set up QEMU
uses: docker/setup-qemu-action@v1

View File

@@ -17,7 +17,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
- name: Save code coverage
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
./cppcheck_and_clang_format diff
- name: Save cppcheck and clang-format errors
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Code coverage"
path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v2
uses: actions/checkout@v3
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -224,7 +224,7 @@ jobs:
cpack -G DEB --config ../CPackConfig.cmake
- name: Save enterprise DEB package
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "Enterprise DEB package"
path: build/output/memgraph*.deb
@@ -261,7 +261,7 @@ jobs:
./continuous_integration
- name: Save quality assurance status
uses: actions/upload-artifact@v2
uses: actions/upload-artifact@v3
with:
name: "GQL Behave Status"
path: |

5
.gitignore vendored
View File

@@ -24,6 +24,7 @@ cmake/DownloadProject/
dist/
src/query/frontend/opencypher/generated/
src/query/v2/frontend/opencypher/generated/
src/parser/opencypher/generated
tags
ve/
ve3/
@@ -53,6 +54,7 @@ src/distributed/token_sharing_rpc_messages.hpp
src/distributed/updates_rpc_messages.hpp
src/query/v2/frontend/ast/ast.hpp
src/query/frontend/ast/ast.hpp
src/storage/v3/bindings/ast/ast.hpp
src/query/distributed/frontend/ast/ast_serialization.hpp
src/query/v2/distributed/frontend/ast/ast_serialization.hpp
src/durability/distributed/state_delta.hpp
@@ -60,12 +62,15 @@ src/durability/single_node/state_delta.hpp
src/durability/single_node_ha/state_delta.hpp
src/query/frontend/semantic/symbol.hpp
src/query/v2/frontend/semantic/symbol.hpp
src/expr/semantic/symbol.hpp
src/query/distributed/frontend/semantic/symbol_serialization.hpp
src/query/v2/distributed/frontend/semantic/symbol_serialization.hpp
src/query/distributed/plan/ops.hpp
src/query/v2/distributed/plan/ops.hpp
src/query/plan/operator.hpp
src/query/v2/plan/operator.hpp
src/parser/opencypher/generated
src/expr/semantic/symbol.hpp
src/raft/log_entry.hpp
src/raft/raft_rpc_messages.hpp
src/raft/snapshot_metadata.hpp

View File

@@ -6,18 +6,14 @@ repos:
- id: end-of-file-fixer
- id: trailing-whitespace
- repo: https://github.com/psf/black
rev: 22.3.0
rev: 22.10.0
hooks:
- id: black
args: # arguments to configure black
- --line-length=120
- --include='\.pyi?$'
# these folders wont be formatted by black
- --exclude="""\.git |
\.__pycache__|
build|
libs|
.cache"""
- repo: https://github.com/pycqa/isort
rev: 5.10.1
hooks:
- id: isort
name: isort (python)
- repo: https://github.com/pre-commit/mirrors-clang-format
rev: v13.0.0
hooks:

View File

@@ -4,7 +4,6 @@ cmake_minimum_required(VERSION 3.8)
# !! IMPORTANT !! run ./project_root/init.sh before cmake command
# to download dependencies
if(NOT UNIX)
message(FATAL_ERROR "Unsupported operating system.")
endif()
@@ -19,6 +18,7 @@ set_directory_properties(PROPERTIES CLEAN_NO_CUSTOM TRUE)
find_program(CCACHE_FOUND ccache)
option(USE_CCACHE "ccache:" ON)
message(STATUS "CCache: ${USE_CCACHE}")
if(CCACHE_FOUND AND USE_CCACHE)
set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
set_property(GLOBAL PROPERTY RULE_LAUNCH_LINK ccache)
@@ -28,7 +28,8 @@ endif(CCACHE_FOUND AND USE_CCACHE)
# NOTE: must be choosen before use of project() or enable_language()
find_program(CLANG_FOUND clang)
find_program(CLANGXX_FOUND clang++)
if (CLANG_FOUND AND CLANGXX_FOUND)
if(CLANG_FOUND AND CLANGXX_FOUND)
set(CMAKE_C_COMPILER ${CLANG_FOUND})
set(CMAKE_CXX_COMPILER ${CLANGXX_FOUND})
else()
@@ -36,12 +37,11 @@ else()
endif()
# -----------------------------------------------------------------------------
project(memgraph)
# Install licenses.
install(DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/licenses/
DESTINATION share/doc/memgraph)
DESTINATION share/doc/memgraph)
# For more information about how to release a new version of Memgraph, see
# `release/README.md`.
@@ -61,61 +61,65 @@ set(MEMGRAPH_OVERRIDE_VERSION "")
set(MEMGRAPH_OVERRIDE_VERSION_SUFFIX "")
# Variables used to generate the versions.
if (MG_ENTERPRISE)
if(MG_ENTERPRISE)
set(get_version_offering "")
else()
set(get_version_offering "--open-source")
endif()
set(get_version_script "${CMAKE_CURRENT_SOURCE_DIR}/release/get_version.py")
# Get version that should be used in the binary.
execute_process(
OUTPUT_VARIABLE MEMGRAPH_VERSION
RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
OUTPUT_VARIABLE MEMGRAPH_VERSION
RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
)
if(MEMGRAPH_VERSION_RESULT AND NOT MEMGRAPH_VERSION_RESULT EQUAL 0)
message(FATAL_ERROR "Unable to get Memgraph version.")
message(FATAL_ERROR "Unable to get Memgraph version.")
else()
MESSAGE(STATUS "Memgraph version: ${MEMGRAPH_VERSION}")
MESSAGE(STATUS "Memgraph version: ${MEMGRAPH_VERSION}")
endif()
# Get version that should be used in the DEB package.
execute_process(
OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
RESULT_VARIABLE MEMGRAPH_VERSION_DEB_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
--variant deb
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
RESULT_VARIABLE MEMGRAPH_VERSION_DEB_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
--variant deb
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
)
if(MEMGRAPH_VERSION_DEB_RESULT AND NOT MEMGRAPH_VERSION_DEB_RESULT EQUAL 0)
message(FATAL_ERROR "Unable to get Memgraph DEB version.")
message(FATAL_ERROR "Unable to get Memgraph DEB version.")
else()
MESSAGE(STATUS "Memgraph DEB version: ${MEMGRAPH_VERSION_DEB}")
MESSAGE(STATUS "Memgraph DEB version: ${MEMGRAPH_VERSION_DEB}")
endif()
# Get version that should be used in the RPM package.
execute_process(
OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
RESULT_VARIABLE MEMGRAPH_VERSION_RPM_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
--variant rpm
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
RESULT_VARIABLE MEMGRAPH_VERSION_RPM_RESULT
COMMAND "${get_version_script}" ${get_version_offering}
--variant rpm
"${MEMGRAPH_OVERRIDE_VERSION}"
"${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
"--memgraph-root-dir"
"${CMAKE_CURRENT_SOURCE_DIR}"
)
if(MEMGRAPH_VERSION_RPM_RESULT AND NOT MEMGRAPH_VERSION_RPM_RESULT EQUAL 0)
message(FATAL_ERROR "Unable to get Memgraph RPM version.")
message(FATAL_ERROR "Unable to get Memgraph RPM version.")
else()
MESSAGE(STATUS "Memgraph RPM version: ${MEMGRAPH_VERSION_RPM}")
MESSAGE(STATUS "Memgraph RPM version: ${MEMGRAPH_VERSION_RPM}")
endif()
# We want the above variables to be updated each time something is committed to
@@ -135,22 +139,24 @@ endif()
# unnecessary recalculations of the release version. The release version only
# changes on every `git commit` or `git checkout`. That is why we watch the
# following files for changes:
# - `.git/HEAD` -> changes each time a `git checkout` is issued
# - `.git/refs/heads/...` -> the value in `.git/HEAD` is a branch name (when
# you are on a branch) and you have to monitor the file of the specific
# branch to detect when a `git commit` was issued
# - `.git/HEAD` -> changes each time a `git checkout` is issued
# - `.git/refs/heads/...` -> the value in `.git/HEAD` is a branch name (when
# you are on a branch) and you have to monitor the file of the specific
# branch to detect when a `git commit` was issued
# More details about the contents of the `.git` directory and the specific
# files used can be seen here:
# https://git-scm.com/book/en/v2/Git-Internals-Git-References
set(git_directory "${CMAKE_SOURCE_DIR}/.git")
if (EXISTS "${git_directory}")
if(EXISTS "${git_directory}")
set_property(DIRECTORY APPEND PROPERTY
CMAKE_CONFIGURE_DEPENDS "${git_directory}/HEAD")
CMAKE_CONFIGURE_DEPENDS "${git_directory}/HEAD")
file(STRINGS "${git_directory}/HEAD" git_head_data)
if (git_head_data MATCHES "^ref: ")
if(git_head_data MATCHES "^ref: ")
string(SUBSTRING "${git_head_data}" 5 -1 git_head_ref)
set_property(DIRECTORY APPEND PROPERTY
CMAKE_CONFIGURE_DEPENDS "${git_directory}/${git_head_ref}")
CMAKE_CONFIGURE_DEPENDS "${git_directory}/${git_head_ref}")
endif()
endif()
@@ -159,16 +165,19 @@ endif()
# setup CMake module path, defines path for include() and find_package()
# https://cmake.org/cmake/help/latest/variable/CMAKE_MODULE_PATH.html
set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} ${PROJECT_SOURCE_DIR}/cmake)
# custom function definitions
include(functions)
# -----------------------------------------------------------------------------
# We want out of source builds, so that cmake generated files don't get mixed
# with source files. This allows for easier clean up.
disallow_in_source_build()
add_custom_target(clean_all
COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/clean_all.cmake
COMMENT "Removing all files in ${CMAKE_BINARY_DIR}")
COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/clean_all.cmake
COMMENT "Removing all files in ${CMAKE_BINARY_DIR}")
# -----------------------------------------------------------------------------
# build flags -----------------------------------------------------------------
@@ -179,17 +188,19 @@ set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
set(CMAKE_CXX_STANDARD 20)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
# c99-designator is disabled because of required mixture of designated and
# non-designated initializers in Python Query Module code (`py_module.cpp`).
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall \
-Werror=switch -Werror=switch-bool -Werror=return-type \
-Werror=return-stack-address \
-Wno-c99-designator \
-DBOOST_STACKTRACE_USE_ADDR2LINE \
-DBOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT")
# Don't omit frame pointer in RelWithDebInfo, for additional callchain debug.
set(CMAKE_CXX_FLAGS_RELWITHDEBINFO
"${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-omit-frame-pointer")
"${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-omit-frame-pointer")
# Statically link libgcc and libstdc++, the GCC allows this according to:
# https://gcc.gnu.org/onlinedocs/gcc-10.2.0/libstdc++/manual/manual/license.html
@@ -207,42 +218,47 @@ set(CMAKE_CXX_FLAGS_RELEASE "-O2 -DNDEBUG")
SET(CMAKE_CXX_LINK_FLAGS "${CMAKE_CXX_LINK_FLAGS} -pthread")
#debug flags
# debug flags
set(PREFERRED_DEBUGGER "gdb" CACHE STRING
"Tunes the debug output for your preferred debugger (gdb or lldb).")
if ("${PREFERRED_DEBUGGER}" STREQUAL "gdb" AND
"${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang|GNU")
set(CMAKE_CXX_FLAGS_DEBUG "-ggdb")
elseif ("${PREFERRED_DEBUGGER}" STREQUAL "lldb" AND
"${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(CMAKE_CXX_FLAGS_DEBUG "-glldb")
"Tunes the debug output for your preferred debugger (gdb or lldb).")
if("${PREFERRED_DEBUGGER}" STREQUAL "gdb" AND
"${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang|GNU")
set(CMAKE_CXX_FLAGS_DEBUG "-ggdb")
elseif("${PREFERRED_DEBUGGER}" STREQUAL "lldb" AND
"${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(CMAKE_CXX_FLAGS_DEBUG "-glldb")
else()
message(WARNING "Unable to tune for PREFERRED_DEBUGGER: "
"'${PREFERRED_DEBUGGER}' with compiler: '${CMAKE_CXX_COMPILER_ID}'")
set(CMAKE_CXX_FLAGS_DEBUG "-g")
message(WARNING "Unable to tune for PREFERRED_DEBUGGER: "
"'${PREFERRED_DEBUGGER}' with compiler: '${CMAKE_CXX_COMPILER_ID}'")
set(CMAKE_CXX_FLAGS_DEBUG "-g")
endif()
# -----------------------------------------------------------------------------
# default build type is debug
if (NOT CMAKE_BUILD_TYPE)
set(CMAKE_BUILD_TYPE "Debug")
if(NOT CMAKE_BUILD_TYPE)
set(CMAKE_BUILD_TYPE "Debug")
endif()
message(STATUS "CMake build type: ${CMAKE_BUILD_TYPE}")
# -----------------------------------------------------------------------------
message(STATUS "CMake build type: ${CMAKE_BUILD_TYPE}")
# -----------------------------------------------------------------------------
set(MG_ARCH "x86_64" CACHE STRING "Host architecture to build Memgraph on. Supported values are x86_64 (default), ARM64.")
# setup external dependencies -------------------------------------------------
# threading
find_package(Threads REQUIRED)
# optional readline
option(USE_READLINE "Use GNU Readline library if available (default ON). \
Set this to OFF to prevent linking with Readline even if it is available." ON)
if (USE_READLINE)
if(USE_READLINE)
find_package(Readline)
if (READLINE_FOUND)
if(READLINE_FOUND)
add_definitions(-DHAS_READLINE)
endif()
endif()
@@ -258,24 +274,27 @@ option(ASAN "Build with Address Sanitizer. To get a reasonable performance optio
option(TSAN "Build with Thread Sanitizer. To get a reasonable performance option should be used only in Release or RelWithDebInfo build " OFF)
option(UBSAN "Build with Undefined Behaviour Sanitizer" OFF)
if (TEST_COVERAGE)
if(TEST_COVERAGE)
string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
if (NOT lower_build_type STREQUAL "debug")
if(NOT lower_build_type STREQUAL "debug")
message(FATAL_ERROR "Generating test coverage unsupported in non Debug builds. Current build type is '${CMAKE_BUILD_TYPE}'")
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
endif()
if (MG_ENTERPRISE)
if(MG_ENTERPRISE)
add_definitions(-DMG_ENTERPRISE)
endif()
set(ENABLE_JEMALLOC ON)
if (ASAN)
if(ASAN)
message(WARNING "Disabling jemalloc as it doesn't work well with ASAN")
set(ENABLE_JEMALLOC OFF)
# Enable Addres sanitizer and get nicer stack traces in error messages.
# NOTE: AddressSanitizer uses llvm-symbolizer binary from the Clang
# distribution to symbolize the stack traces (note that ideally the
@@ -284,19 +303,20 @@ if (ASAN)
# provide it in separate ASAN_SYMBOLIZER_PATH environment variable.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address -fno-omit-frame-pointer")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=address")
# To detect Stack-use-after-return bugs set run-time flag:
# ASAN_OPTIONS=detect_stack_use_after_return=1
# ASAN_OPTIONS=detect_stack_use_after_return=1
# To check initialization order bugs set run-time flag:
# ASAN_OPTIONS=check_initialization_order=true
# This mode reports an error if initializer for a global variable accesses
# dynamically initialized global from another translation unit, which is
# not yet initialized
# ASAN_OPTIONS=strict_init_order=true
# This mode reports an error if initializer for a global variable accesses
# any dynamically initialized global from another translation unit.
# ASAN_OPTIONS=check_initialization_order=true
# This mode reports an error if initializer for a global variable accesses
# dynamically initialized global from another translation unit, which is
# not yet initialized
# ASAN_OPTIONS=strict_init_order=true
# This mode reports an error if initializer for a global variable accesses
# any dynamically initialized global from another translation unit.
endif()
if (TSAN)
if(TSAN)
# ThreadSanitizer generally requires all code to be compiled with -fsanitize=thread.
# If some code (e.g. dynamic libraries) is not compiled with the flag, it can
# lead to false positive race reports, false negative race reports and/or
@@ -309,19 +329,21 @@ if (TSAN)
# (unwinding stack on each memory access is too expensive).
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread")
# By default ThreadSanitizer uses addr2line utility to symbolize reports.
# llvm-symbolizer is faster, consumes less memory and produces much better
# reports. To use it set runtime flag:
# TSAN_OPTIONS="extern-symbolizer-path=~/llvm-symbolizer"
# TSAN_OPTIONS="extern-symbolizer-path=~/llvm-symbolizer"
# For more runtime flags see: https://github.com/google/sanitizers/wiki/ThreadSanitizerFlags
endif()
if (UBSAN)
if(UBSAN)
# Compile with UBSAN but disable vptr check. This is disabled because it
# requires linking with clang++ to make sure C++ specific parts of the
# runtime library and c++ standard libraries are present.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined -fno-omit-frame-pointer -fno-sanitize=vptr")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined -fno-sanitize=vptr")
# Run program with environment variable UBSAN_OPTIONS=print_stacktrace=1.
# Make sure llvm-symbolizer binary is in path.
# To make the program abort on undefined behavior, use UBSAN_OPTIONS=halt_on_error=1.
@@ -340,7 +362,7 @@ add_subdirectory(release)
option(MG_ENABLE_TESTING "Set this to OFF to disable building test binaries" ON)
message(STATUS "MG_ENABLE_TESTING: ${MG_ENABLE_TESTING}")
if (MG_ENABLE_TESTING)
if(MG_ENABLE_TESTING)
enable_testing()
add_subdirectory(tests)
endif()

View File

@@ -83,13 +83,9 @@ modifications:
value: "true"
override: true
- name: "query_modules_directory"
value: "/usr/lib/memgraph/query_modules"
override: true
- name: "auth_module_executable"
value: "/usr/lib/memgraph/auth_module/example.py"
override: false
# - name: "query_modules_directory"
# value: "/usr/lib/memgraph/query_modules"
# override: true
- name: "memory_limit"
value: "0"

7
init
View File

@@ -140,5 +140,12 @@ done;
python3 -m pip install pre-commit
python3 -m pre_commit install
# Install py format tools
echo "Install black formatter"
python3 -m pip install black==22.10.*
echo "Install isort"
python3 -m pip install isort==5.10.*
# Link `include/mgp.py` with `release/mgp/mgp.py`
ln -v -f include/mgp.py release/mgp/mgp.py

View File

@@ -116,7 +116,7 @@ declare -A primary_urls=(
["pymgclient"]="http://$local_cache_host/git/pymgclient.git"
["mgconsole"]="http://$local_cache_host/git/mgconsole.git"
["spdlog"]="http://$local_cache_host/git/spdlog"
["nlohmann"]="http://$local_cache_host/file/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
["nlohmann"]="http://$local_cache_host/file/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
["neo4j"]="http://$local_cache_host/file/neo4j-community-3.2.3-unix.tar.gz"
["librdkafka"]="http://$local_cache_host/git/librdkafka.git"
["protobuf"]="http://$local_cache_host/git/protobuf.git"
@@ -141,7 +141,7 @@ declare -A secondary_urls=(
["pymgclient"]="https://github.com/memgraph/pymgclient.git"
["mgconsole"]="http://github.com/memgraph/mgconsole.git"
["spdlog"]="https://github.com/gabime/spdlog"
["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
["neo4j"]="https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz"
["librdkafka"]="https://github.com/edenhill/librdkafka.git"
["protobuf"]="https://github.com/protocolbuffers/protobuf.git"

12
pyproject.toml Normal file
View File

@@ -0,0 +1,12 @@
[tool.black]
line-length = 120
include = '\.pyi?$'
extend-exclude = '''
/(
| .git
| .__pycache__
| build
| libs
| .cache
)/
'''

View File

@@ -18,6 +18,9 @@ add_subdirectory(query/v2)
add_subdirectory(slk)
add_subdirectory(rpc)
add_subdirectory(auth)
add_subdirectory(parser)
add_subdirectory(expr)
add_subdirectory(coordinator)
if (MG_ENTERPRISE)
add_subdirectory(audit)
@@ -34,13 +37,13 @@ include_directories(${CMAKE_CURRENT_BINARY_DIR})
# Memgraph Single Node v2 Executable
# ----------------------------------------------------------------------------
set(mg_single_node_v2_sources
glue/communication.cpp
memgraph.cpp
glue/auth.cpp
glue/v2/communication.cpp
memgraph.cpp
glue/v2/auth.cpp
)
set(mg_single_node_v2_libs stdc++fs Threads::Threads
telemetry_lib mg-query mg-communication mg-memory mg-utils mg-auth mg-license mg-settings)
telemetry_lib mg-query-v2 mg-communication mg-memory mg-utils mg-auth mg-license mg-settings mg-io mg-coordinator)
if (MG_ENTERPRISE)
# These are enterprise subsystems
set(mg_single_node_v2_libs ${mg_single_node_v2_libs} mg-audit)
@@ -123,19 +126,3 @@ install(CODE "file(MAKE_DIRECTORY \$ENV{DESTDIR}/var/log/memgraph
# ----------------------------------------------------------------------------
# Memgraph CSV Import Tool Executable
# ----------------------------------------------------------------------------
add_executable(mg_import_csv mg_import_csv.cpp)
target_link_libraries(mg_import_csv mg-storage-v2)
# Strip the executable in release build.
if (lower_build_type STREQUAL "release")
add_custom_command(TARGET mg_import_csv POST_BUILD
COMMAND strip -s mg_import_csv
COMMENT "Stripping symbols and sections from mg_import_csv")
endif()
install(TARGETS mg_import_csv RUNTIME DESTINATION bin)
# ----------------------------------------------------------------------------
# Memgraph CSV Import Tool Executable
# ----------------------------------------------------------------------------

View File

@@ -30,6 +30,7 @@
#include "communication/context.hpp"
#include "communication/v2/pool.hpp"
#include "communication/v2/session.hpp"
#include "utils/message.hpp"
#include "utils/spin_lock.hpp"
#include "utils/synchronized.hpp"
@@ -58,10 +59,10 @@ class Listener final : public std::enable_shared_from_this<Listener<TSession, TS
bool IsRunning() const noexcept { return alive_.load(std::memory_order_relaxed); }
private:
Listener(boost::asio::io_context &io_context, TSessionData *data, ServerContext *server_context,
Listener(boost::asio::io_context &io_context, TSessionData &data, ServerContext *server_context,
tcp::endpoint &endpoint, const std::string_view service_name, const uint64_t inactivity_timeout_sec)
: io_context_(io_context),
data_(data),
data_(&data),
server_context_(server_context),
acceptor_(io_context_),
endpoint_{endpoint},
@@ -110,7 +111,7 @@ class Listener final : public std::enable_shared_from_this<Listener<TSession, TS
return OnError(ec, "accept");
}
auto session = SessionHandler::Create(std::move(socket), data_, *server_context_, endpoint_, inactivity_timeout_,
auto session = SessionHandler::Create(std::move(socket), *data_, *server_context_, endpoint_, inactivity_timeout_,
service_name_);
session->Start();
DoAccept();

View File

@@ -72,7 +72,7 @@ class Server final {
* Constructs and binds server to endpoint, operates on session data and
* invokes workers_count workers
*/
Server(ServerEndpoint &endpoint, TSessionData *session_data, ServerContext *server_context,
Server(ServerEndpoint &endpoint, TSessionData &session_data, ServerContext *server_context,
const int inactivity_timeout_sec, const std::string_view service_name,
size_t workers_count = std::thread::hardware_concurrency())
: endpoint_{endpoint},

View File

@@ -41,6 +41,7 @@
#include <boost/beast/websocket/rfc6455.hpp>
#include <boost/system/detail/error_code.hpp>
#include "communication/buffer.hpp"
#include "communication/context.hpp"
#include "communication/exceptions.hpp"
#include "utils/logging.hpp"
@@ -139,7 +140,7 @@ class WebsocketSession : public std::enable_shared_from_this<WebsocketSession<TS
private:
// Take ownership of the socket
explicit WebsocketSession(tcp::socket &&socket, TSessionData *data, tcp::endpoint endpoint,
explicit WebsocketSession(tcp::socket &&socket, TSessionData &data, tcp::endpoint endpoint,
std::string_view service_name)
: ws_(std::move(socket)),
strand_{boost::asio::make_strand(ws_.get_executor())},
@@ -311,13 +312,13 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
}
private:
explicit Session(tcp::socket &&socket, TSessionData *data, ServerContext &server_context, tcp::endpoint endpoint,
explicit Session(tcp::socket &&socket, TSessionData &data, ServerContext &server_context, tcp::endpoint endpoint,
const std::chrono::seconds inactivity_timeout_sec, std::string_view service_name)
: socket_(CreateSocket(std::move(socket), server_context)),
strand_{boost::asio::make_strand(GetExecutor())},
output_stream_([this](const uint8_t *data, size_t len, bool have_more) { return Write(data, len, have_more); }),
session_(data, endpoint, input_buffer_.read_end(), &output_stream_),
data_{data},
data_{&data},
endpoint_{endpoint},
remote_endpoint_{GetRemoteEndpoint()},
service_name_{service_name},
@@ -373,7 +374,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
spdlog::info("Switching {} to websocket connection", remote_endpoint_);
if (std::holds_alternative<TCPSocket>(socket_)) {
auto sock = std::get<TCPSocket>(std::move(socket_));
WebsocketSession<TSession, TSessionData>::Create(std::move(sock), data_, endpoint_, service_name_)
WebsocketSession<TSession, TSessionData>::Create(std::move(sock), *data_, endpoint_, service_name_)
->DoAccept(parser.release());
execution_active_ = false;
return;
@@ -465,7 +466,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
if (timeout_timer_.expiry() <= boost::asio::steady_timer::clock_type::now()) {
// The deadline has passed. Stop the session. The other actors will
// terminate as soon as possible.
spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_);
spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_.count());
DoShutdown();
} else {
// Put the actor back to sleep.

View File

@@ -0,0 +1,9 @@
set(coordinator_src_files
coordinator.cpp
shard_map.cpp)
find_package(fmt REQUIRED)
find_package(Threads REQUIRED)
add_library(mg-coordinator STATIC ${coordinator_src_files})
target_link_libraries(mg-coordinator stdc++fs Threads::Threads fmt::fmt mg-utils mg-storage-v3)

View File

@@ -0,0 +1,129 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include <coordinator/coordinator.hpp>
namespace memgraph::coordinator {
CoordinatorWriteResponses Coordinator::ApplyWrite(HeartbeatRequest &&heartbeat_request) {
spdlog::info("Coordinator handling HeartbeatRequest");
// add this storage engine to any under-replicated shards that it is not already a part of
auto initializing_rsms_for_shard_manager =
shard_map_.AssignShards(heartbeat_request.from_storage_manager, heartbeat_request.initialized_rsms);
return HeartbeatResponse{
.shards_to_initialize = initializing_rsms_for_shard_manager,
};
}
CoordinatorWriteResponses Coordinator::ApplyWrite(HlcRequest &&hlc_request) {
HlcResponse res{};
auto hlc_shard_map = shard_map_.GetHlc();
MG_ASSERT(!(hlc_request.last_shard_map_version.logical_id > hlc_shard_map.logical_id));
res.new_hlc = Hlc{
.logical_id = ++highest_allocated_timestamp_,
// TODO(tyler) probably pass some more context to the Coordinator here
// so that we can use our wall clock and enforce monotonicity.
// .coordinator_wall_clock = io_.Now(),
};
// Allways return fresher shard_map for now.
res.fresher_shard_map = std::make_optional(shard_map_);
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(AllocateEdgeIdBatchRequest &&ahr) {
AllocateEdgeIdBatchResponse res{};
uint64_t low = highest_allocated_edge_id_;
highest_allocated_edge_id_ += ahr.batch_size;
uint64_t high = highest_allocated_edge_id_;
res.low = low;
res.high = high;
return res;
}
/// This splits the shard immediately beneath the provided
/// split key, keeping the assigned peers identical for now,
/// but letting them be gradually migrated over time.
CoordinatorWriteResponses Coordinator::ApplyWrite(SplitShardRequest &&split_shard_request) {
SplitShardResponse res{};
if (split_shard_request.previous_shard_map_version != shard_map_.shard_map_version) {
res.success = false;
} else {
res.success = shard_map_.SplitShard(split_shard_request.previous_shard_map_version, split_shard_request.label_id,
split_shard_request.split_key);
}
return res;
}
/// This adds the provided storage engine to the standby storage engine pool,
/// which can be used to rebalance storage over time.
CoordinatorWriteResponses Coordinator::ApplyWrite(
RegisterStorageEngineRequest && /* register_storage_engine_request */) {
RegisterStorageEngineResponse res{};
// TODO
return res;
}
/// This begins the process of draining the provided storage engine from all raft
/// clusters that it might be participating in.
CoordinatorWriteResponses Coordinator::ApplyWrite(
DeregisterStorageEngineRequest && /* register_storage_engine_request */) {
DeregisterStorageEngineResponse res{};
// TODO
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(InitializeLabelRequest &&initialize_label_request) {
InitializeLabelResponse res{};
std::optional<LabelId> new_label_id = shard_map_.InitializeNewLabel(
initialize_label_request.label_name, initialize_label_request.schema, initialize_label_request.replication_factor,
initialize_label_request.last_shard_map_version);
if (new_label_id) {
res.new_label_id = new_label_id.value();
res.fresher_shard_map = std::nullopt;
res.success = true;
} else {
res.fresher_shard_map = shard_map_;
res.success = false;
}
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request) {
AllocatePropertyIdsResponse res{};
auto property_ids = shard_map_.AllocatePropertyIds(allocate_property_ids_request.property_names);
res.property_ids = property_ids;
return res;
}
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,196 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <optional>
#include <set>
#include <string>
#include <unordered_set>
#include <variant>
#include <vector>
#include <boost/uuid/uuid.hpp>
#include <coordinator/hybrid_logical_clock.hpp>
#include <coordinator/shard_map.hpp>
#include <io/simulator/simulator.hpp>
#include <io/time.hpp>
#include <io/transport.hpp>
#include <storage/v3/id_types.hpp>
#include <storage/v3/schemas.hpp>
namespace memgraph::coordinator {
using memgraph::io::Address;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyId;
using memgraph::storage::v3::SchemaProperty;
using SimT = memgraph::io::simulator::SimulatorTransport;
using PrimaryKey = std::vector<PropertyValue>;
struct HlcRequest {
Hlc last_shard_map_version;
};
struct HlcResponse {
Hlc new_hlc;
std::optional<ShardMap> fresher_shard_map;
};
struct GetShardMapRequest {
// No state
};
struct GetShardMapResponse {
ShardMap shard_map;
};
struct AllocateHlcBatchRequest {
Hlc low;
Hlc high;
};
struct AllocateHlcBatchResponse {
bool success;
Hlc low;
Hlc high;
};
struct AllocateEdgeIdBatchRequest {
size_t batch_size;
};
struct AllocateEdgeIdBatchResponse {
uint64_t low;
uint64_t high;
};
struct AllocatePropertyIdsRequest {
std::vector<std::string> property_names;
};
struct AllocatePropertyIdsResponse {
std::map<std::string, PropertyId> property_ids;
};
struct SplitShardRequest {
Hlc previous_shard_map_version;
LabelId label_id;
PrimaryKey split_key;
};
struct SplitShardResponse {
bool success;
};
struct RegisterStorageEngineRequest {
Address address;
};
struct RegisterStorageEngineResponse {
bool success;
};
struct DeregisterStorageEngineRequest {
Address address;
};
struct DeregisterStorageEngineResponse {
bool success;
};
struct InitializeLabelRequest {
std::string label_name;
std::vector<SchemaProperty> schema;
size_t replication_factor;
Hlc last_shard_map_version;
};
struct InitializeLabelResponse {
bool success;
LabelId new_label_id;
std::optional<ShardMap> fresher_shard_map;
};
struct HeartbeatRequest {
Address from_storage_manager;
std::set<boost::uuids::uuid> initialized_rsms;
};
struct HeartbeatResponse {
std::vector<ShardToInitialize> shards_to_initialize;
};
using CoordinatorWriteRequests =
std::variant<HlcRequest, AllocateEdgeIdBatchRequest, SplitShardRequest, RegisterStorageEngineRequest,
DeregisterStorageEngineRequest, InitializeLabelRequest, AllocatePropertyIdsRequest, HeartbeatRequest>;
using CoordinatorWriteResponses = std::variant<HlcResponse, AllocateEdgeIdBatchResponse, SplitShardResponse,
RegisterStorageEngineResponse, DeregisterStorageEngineResponse,
InitializeLabelResponse, AllocatePropertyIdsResponse, HeartbeatResponse>;
using CoordinatorReadRequests = std::variant<GetShardMapRequest>;
using CoordinatorReadResponses = std::variant<GetShardMapResponse>;
class Coordinator {
public:
explicit Coordinator(ShardMap sm) : shard_map_{std::move(sm)} {}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static
CoordinatorReadResponses Read(CoordinatorReadRequests requests) {
return std::visit([&](auto &&request) { return HandleRead(std::forward<decltype(request)>(request)); },
std::move(requests)); // NOLINT(hicpp-move-const-arg,performance-move-const-arg)
}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static
CoordinatorWriteResponses Apply(CoordinatorWriteRequests requests) {
return std::visit([&](auto &&request) mutable { return ApplyWrite(std::forward<decltype(request)>(request)); },
std::move(requests));
}
private:
ShardMap shard_map_;
uint64_t highest_allocated_timestamp_{0};
/// Query engines need to periodically request batches of unique edge IDs.
uint64_t highest_allocated_edge_id_{0};
CoordinatorReadResponses HandleRead(GetShardMapRequest && /* get_shard_map_request */) {
GetShardMapResponse res;
res.shard_map = shard_map_;
return res;
}
CoordinatorWriteResponses ApplyWrite(HeartbeatRequest &&heartbeat_request);
CoordinatorWriteResponses ApplyWrite(HlcRequest &&hlc_request);
CoordinatorWriteResponses ApplyWrite(AllocateEdgeIdBatchRequest &&ahr);
/// This splits the shard immediately beneath the provided
/// split key, keeping the assigned peers identical for now,
/// but letting them be gradually migrated over time.
CoordinatorWriteResponses ApplyWrite(SplitShardRequest &&split_shard_request);
/// This adds the provided storage engine to the standby storage engine pool,
/// which can be used to rebalance storage over time.
static CoordinatorWriteResponses ApplyWrite(RegisterStorageEngineRequest && /* register_storage_engine_request */);
/// This begins the process of draining the provided storage engine from all raft
/// clusters that it might be participating in.
static CoordinatorWriteResponses ApplyWrite(DeregisterStorageEngineRequest && /* register_storage_engine_request */);
CoordinatorWriteResponses ApplyWrite(InitializeLabelRequest &&initialize_label_request);
CoordinatorWriteResponses ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request);
};
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,24 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator.hpp"
#include "io/rsm/rsm_client.hpp"
namespace memgraph::coordinator {
using memgraph::io::rsm::RsmClient;
template <typename IoImpl>
using CoordinatorClient = RsmClient<IoImpl, CoordinatorWriteRequests, CoordinatorWriteResponses,
CoordinatorReadRequests, CoordinatorReadResponses>;
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,23 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator.hpp"
#include "io/rsm/raft.hpp"
namespace memgraph::coordinator {
template <typename IoImpl>
using CoordinatorRsm = memgraph::io::rsm::Raft<IoImpl, Coordinator, CoordinatorWriteRequests, CoordinatorWriteResponses,
CoordinatorReadRequests, CoordinatorReadResponses>;
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,156 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <deque>
#include <memory>
#include <queue>
#include <variant>
#include "coordinator/coordinator.hpp"
#include "coordinator/coordinator_rsm.hpp"
#include "coordinator/shard_map.hpp"
#include "io/address.hpp"
#include "io/future.hpp"
#include "io/messages.hpp"
#include "io/rsm/raft.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
#include "query/v2/requests.hpp"
namespace memgraph::coordinator::coordinator_worker {
/// Obligations:
/// * ShutDown
/// * Cron
/// * RouteMessage
using coordinator::Coordinator;
using coordinator::CoordinatorRsm;
using io::Address;
using io::RequestId;
using io::Time;
using io::messages::CoordinatorMessages;
using msgs::ReadRequests;
using msgs::ReadResponses;
using msgs::WriteRequests;
using msgs::WriteResponses;
struct ShutDown {};
struct Cron {};
struct RouteMessage {
CoordinatorMessages message;
RequestId request_id;
Address to;
Address from;
};
using Message = std::variant<RouteMessage, Cron, ShutDown>;
struct QueueInner {
std::mutex mu{};
std::condition_variable cv;
// TODO(tyler) handle simulator communication std::shared_ptr<std::atomic<int>> blocked;
// TODO(tyler) investigate using a priority queue that prioritizes messages in a way that
// improves overall QoS. For example, maybe we want to schedule raft Append messages
// ahead of Read messages or generally writes before reads for lowering the load on the
// overall system faster etc... When we do this, we need to make sure to avoid
// starvation by sometimes randomizing priorities, rather than following a strict
// prioritization.
std::deque<Message> queue;
};
/// There are two reasons to implement our own Queue instead of using
/// one off-the-shelf:
/// 1. we will need to know in the simulator when all threads are waiting
/// 2. we will want to implement our own priority queue within this for QoS
class Queue {
std::shared_ptr<QueueInner> inner_ = std::make_shared<QueueInner>();
public:
void Push(Message &&message) {
{
MG_ASSERT(inner_.use_count() > 0);
std::unique_lock<std::mutex> lock(inner_->mu);
inner_->queue.emplace_back(std::move(message));
} // lock dropped before notifying condition variable
inner_->cv.notify_all();
}
Message Pop() {
MG_ASSERT(inner_.use_count() > 0);
std::unique_lock<std::mutex> lock(inner_->mu);
while (inner_->queue.empty()) {
inner_->cv.wait(lock);
}
Message message = std::move(inner_->queue.front());
inner_->queue.pop_front();
return message;
}
};
/// A CoordinatorWorker owns Raft<CoordinatorRsm> instances. receives messages from the MachineManager.
template <typename IoImpl>
class CoordinatorWorker {
io::Io<IoImpl> io_;
Queue queue_;
CoordinatorRsm<IoImpl> coordinator_;
bool Process(ShutDown && /*shut_down*/) { return false; }
bool Process(Cron && /* cron */) {
coordinator_.Cron();
return true;
}
bool Process(RouteMessage &&route_message) {
coordinator_.Handle(std::move(route_message.message), route_message.request_id, route_message.from);
return true;
}
public:
CoordinatorWorker(io::Io<IoImpl> io, Queue queue, Coordinator coordinator)
: io_(std::move(io)),
queue_(std::move(queue)),
coordinator_{std::move(io_.ForkLocal()), {}, std::move(coordinator)} {}
CoordinatorWorker(CoordinatorWorker &&) noexcept = default;
CoordinatorWorker &operator=(CoordinatorWorker &&) noexcept = default;
CoordinatorWorker(const CoordinatorWorker &) = delete;
CoordinatorWorker &operator=(const CoordinatorWorker &) = delete;
~CoordinatorWorker() = default;
void Run() {
while (true) {
Message message = queue_.Pop();
const bool should_continue = std::visit(
[this](auto &&msg) { return this->Process(std::forward<decltype(msg)>(msg)); }, std::move(message));
if (!should_continue) {
return;
}
}
}
};
} // namespace memgraph::coordinator::coordinator_worker

View File

@@ -0,0 +1,48 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <compare>
#include <ctime>
#include <iomanip>
#include "io/time.hpp"
namespace memgraph::coordinator {
using Time = memgraph::io::Time;
/// Hybrid-logical clock
struct Hlc {
uint64_t logical_id = 0;
Time coordinator_wall_clock = Time::min();
auto operator<=>(const Hlc &other) const { return logical_id <=> other.logical_id; }
bool operator==(const Hlc &other) const = default;
bool operator<(const Hlc &other) const = default;
bool operator==(const uint64_t other) const { return logical_id == other; }
bool operator<(const uint64_t other) const { return logical_id < other; }
bool operator>=(const uint64_t other) const { return logical_id >= other; }
friend std::ostream &operator<<(std::ostream &in, const Hlc &hlc) {
auto wall_clock = std::chrono::system_clock::to_time_t(hlc.coordinator_wall_clock);
in << "Hlc { logical_id: " << hlc.logical_id;
in << ", coordinator_wall_clock: " << std::put_time(std::localtime(&wall_clock), "%F %T");
in << " }";
return in;
}
};
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,552 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include <optional>
#include <unordered_map>
#include <vector>
#include "common/types.hpp"
#include "coordinator/shard_map.hpp"
#include "spdlog/spdlog.h"
#include "storage/v3/schemas.hpp"
#include "storage/v3/temporal.hpp"
#include "utils/cast.hpp"
#include "utils/exceptions.hpp"
#include "utils/string.hpp"
namespace memgraph::coordinator {
using memgraph::common::SchemaType;
using memgraph::storage::v3::TemporalData;
using memgraph::storage::v3::TemporalType;
PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema) {
PrimaryKey ret{};
const int64_t min_int = std::numeric_limits<int64_t>::min();
const TemporalData date{TemporalType::Date, min_int};
const TemporalData local_time{TemporalType::LocalTime, min_int};
const TemporalData local_date_time{TemporalType::LocalDateTime, min_int};
const TemporalData duration{TemporalType::Duration, min_int};
for (const auto &schema_property : schema) {
switch (schema_property.type) {
case SchemaType::BOOL:
ret.emplace_back(PropertyValue(false));
break;
case SchemaType::INT:
ret.emplace_back(PropertyValue(min_int));
break;
case SchemaType::STRING:
ret.emplace_back(PropertyValue(""));
break;
case SchemaType::DATE:
ret.emplace_back(PropertyValue(date));
break;
case SchemaType::LOCALTIME:
ret.emplace_back(PropertyValue(local_time));
break;
case SchemaType::LOCALDATETIME:
ret.emplace_back(PropertyValue(local_date_time));
break;
case SchemaType::DURATION:
ret.emplace_back(PropertyValue(duration));
break;
}
}
return ret;
}
ShardMap ShardMap::Parse(std::istream &input_stream) {
ShardMap shard_map;
const auto read_size = [&input_stream] {
size_t size{0};
input_stream >> size;
return size;
};
// Reads a string until the next whitespace
const auto read_word = [&input_stream] {
std::string word;
input_stream >> word;
return word;
};
const auto read_names = [&read_size, &read_word] {
const auto number_of_names = read_size();
spdlog::trace("Reading {} names", number_of_names);
std::vector<std::string> names;
names.reserve(number_of_names);
for (auto name_index = 0; name_index < number_of_names; ++name_index) {
names.push_back(read_word());
spdlog::trace("Read '{}'", names.back());
}
return names;
};
const auto read_line = [&input_stream] {
std::string line;
std::getline(input_stream, line);
return line;
};
const auto parse_type = [](const std::string &type) {
static const auto type_map = std::unordered_map<std::string, common::SchemaType>{
{"string", common::SchemaType::STRING}, {"int", common::SchemaType::INT}, {"bool", common::SchemaType::BOOL}};
const auto lower_case_type = utils::ToLowerCase(type);
auto it = type_map.find(lower_case_type);
MG_ASSERT(it != type_map.end(), "Invalid type in split files: {}", type);
return it->second;
};
const auto parse_property_value = [](std::string text, const common::SchemaType type) {
if (type == common::SchemaType::STRING) {
return storage::v3::PropertyValue{std::move(text)};
}
if (type == common::SchemaType::INT) {
size_t processed{0};
int64_t value = std::stoll(text, &processed);
MG_ASSERT(processed == text.size() || text[processed] == ' ', "Invalid integer format: '{}'", text);
return storage::v3::PropertyValue{value};
}
LOG_FATAL("Not supported type: {}", utils::UnderlyingCast(type));
};
spdlog::debug("Reading properties");
const auto properties = read_names();
MG_ASSERT(shard_map.AllocatePropertyIds(properties).size() == properties.size(),
"Unexpected number of properties created!");
spdlog::debug("Reading edge types");
const auto edge_types = read_names();
MG_ASSERT(shard_map.AllocateEdgeTypeIds(edge_types).size() == edge_types.size(),
"Unexpected number of properties created!");
spdlog::debug("Reading primary labels");
const auto number_of_primary_labels = read_size();
spdlog::debug("Reading {} primary labels", number_of_primary_labels);
for (auto label_index = 0; label_index < number_of_primary_labels; ++label_index) {
const auto primary_label = read_word();
spdlog::debug("Reading primary label named '{}'", primary_label);
const auto number_of_primary_properties = read_size();
spdlog::debug("Reading {} primary properties", number_of_primary_properties);
std::vector<std::string> pp_names;
std::vector<common::SchemaType> pp_types;
pp_names.reserve(number_of_primary_properties);
pp_types.reserve(number_of_primary_properties);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
pp_names.push_back(read_word());
spdlog::debug("Reading primary property named '{}'", pp_names.back());
pp_types.push_back(parse_type(read_word()));
}
auto pp_mapping = shard_map.AllocatePropertyIds(pp_names);
std::vector<SchemaProperty> schema;
schema.reserve(number_of_primary_properties);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
schema.push_back(storage::v3::SchemaProperty{pp_mapping.at(pp_names[property_index]), pp_types[property_index]});
}
const auto hlc = shard_map.GetHlc();
MG_ASSERT(shard_map.InitializeNewLabel(primary_label, schema, 1, hlc).has_value(),
"Cannot initialize new label: {}", primary_label);
const auto number_of_split_points = read_size();
spdlog::debug("Reading {} split points", number_of_split_points);
[[maybe_unused]] const auto remainder_from_last_line = read_line();
for (auto split_point_index = 0; split_point_index < number_of_split_points; ++split_point_index) {
const auto line = read_line();
spdlog::debug("Read split point '{}'", line);
MG_ASSERT(line.front() == '[', "Invalid split file format!");
MG_ASSERT(line.back() == ']', "Invalid split file format!");
std::string_view line_view{line};
line_view.remove_prefix(1);
line_view.remove_suffix(1);
static constexpr std::string_view kDelimiter{","};
auto pk_values_as_text = utils::Split(line_view, kDelimiter);
std::vector<PropertyValue> pk;
pk.reserve(number_of_primary_properties);
MG_ASSERT(pk_values_as_text.size() == number_of_primary_properties,
"Split point contains invalid number of values '{}'", line);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
pk.push_back(parse_property_value(std::move(pk_values_as_text[property_index]), schema[property_index].type));
}
shard_map.SplitShard(shard_map.GetHlc(), shard_map.labels.at(primary_label), pk);
}
}
return shard_map;
}
std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map) {
using utils::print_helpers::operator<<;
in << "ShardMap { shard_map_version: " << shard_map.shard_map_version;
in << ", max_property_id: " << shard_map.max_property_id;
in << ", max_edge_type_id: " << shard_map.max_edge_type_id;
in << ", properties: " << shard_map.properties;
in << ", edge_types: " << shard_map.edge_types;
in << ", max_label_id: " << shard_map.max_label_id;
in << ", labels: " << shard_map.labels;
in << ", label_spaces: " << shard_map.label_spaces;
in << ", schemas: " << shard_map.schemas;
in << "}";
return in;
}
Shards ShardMap::GetShardsForLabel(const LabelName &label) const {
const auto id = labels.at(label);
const auto &shards = label_spaces.at(id).shards;
return shards;
}
std::vector<Shards> ShardMap::GetAllShards() const {
std::vector<Shards> all_shards;
all_shards.reserve(label_spaces.size());
std::transform(label_spaces.begin(), label_spaces.end(), std::back_inserter(all_shards),
[](const auto &label_space) { return label_space.second.shards; });
return all_shards;
}
// TODO(gabor) later we will want to update the wallclock time with
// the given Io<impl>'s time as well
Hlc ShardMap::IncrementShardMapVersion() noexcept {
++shard_map_version.logical_id;
return shard_map_version;
}
// TODO(antaljanosbenjamin) use a single map for all name id
// mapping and a single counter to maintain the next id
std::unordered_map<uint64_t, std::string> ShardMap::IdToNames() {
std::unordered_map<uint64_t, std::string> id_to_names;
const auto map_type_ids = [&id_to_names](const auto &name_to_id_type) {
for (const auto &[name, id] : name_to_id_type) {
id_to_names.emplace(id.AsUint(), name);
}
};
map_type_ids(edge_types);
map_type_ids(labels);
map_type_ids(properties);
return id_to_names;
}
Hlc ShardMap::GetHlc() const noexcept { return shard_map_version; }
std::vector<ShardToInitialize> ShardMap::AssignShards(Address storage_manager,
std::set<boost::uuids::uuid> initialized) {
std::vector<ShardToInitialize> ret{};
bool mutated = false;
for (auto &[label_id, label_space] : label_spaces) {
for (auto it = label_space.shards.begin(); it != label_space.shards.end(); it++) {
auto &[low_key, shard] = *it;
std::optional<PrimaryKey> high_key;
if (const auto next_it = std::next(it); next_it != label_space.shards.end()) {
high_key = next_it->first;
}
// TODO(tyler) avoid these triple-nested loops by having the heartbeat include better info
bool machine_contains_shard = false;
for (auto &aas : shard) {
if (initialized.contains(aas.address.unique_id)) {
machine_contains_shard = true;
if (aas.status != Status::CONSENSUS_PARTICIPANT) {
spdlog::info("marking shard as full consensus participant: {}", aas.address.unique_id);
aas.status = Status::CONSENSUS_PARTICIPANT;
}
} else {
const bool same_machine = aas.address.last_known_ip == storage_manager.last_known_ip &&
aas.address.last_known_port == storage_manager.last_known_port;
if (same_machine) {
machine_contains_shard = true;
spdlog::info("reminding shard manager that they should begin participating in shard");
ret.push_back(ShardToInitialize{
.uuid = aas.address.unique_id,
.label_id = label_id,
.min_key = low_key,
.max_key = high_key,
.schema = schemas[label_id],
.config = Config{},
.id_to_names = IdToNames(),
});
}
}
}
if (!machine_contains_shard && shard.size() < label_space.replication_factor) {
Address address = storage_manager;
// TODO(tyler) use deterministic UUID so that coordinators don't diverge here
address.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
spdlog::info("assigning shard manager to shard");
ret.push_back(ShardToInitialize{
.uuid = address.unique_id,
.label_id = label_id,
.min_key = low_key,
.max_key = high_key,
.schema = schemas[label_id],
.config = Config{},
.id_to_names = IdToNames(),
});
AddressAndStatus aas = {
.address = address,
.status = Status::INITIALIZING,
};
shard.emplace_back(aas);
}
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
bool ShardMap::SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key) {
if (previous_shard_map_version != shard_map_version) {
return false;
}
auto &label_space = label_spaces.at(label_id);
auto &shards_in_map = label_space.shards;
MG_ASSERT(!shards_in_map.empty());
MG_ASSERT(!shards_in_map.contains(key));
MG_ASSERT(label_spaces.contains(label_id));
// Finding the Shard that the new PrimaryKey should map to.
auto prev = std::prev(shards_in_map.upper_bound(key));
Shard duplicated_shard = prev->second;
// Apply the split
shards_in_map[key] = duplicated_shard;
IncrementShardMapVersion();
return true;
}
std::optional<LabelId> ShardMap::InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
size_t replication_factor, Hlc last_shard_map_version) {
if (shard_map_version != last_shard_map_version || labels.contains(label_name)) {
return std::nullopt;
}
const LabelId label_id = LabelId::FromUint(++max_label_id);
labels.emplace(std::move(label_name), label_id);
PrimaryKey initial_key = SchemaToMinKey(schema);
Shard empty_shard = {};
Shards shards = {
{initial_key, empty_shard},
};
LabelSpace label_space{
.schema = schema,
.shards = shards,
.replication_factor = replication_factor,
};
schemas[label_id] = std::move(schema);
label_spaces.emplace(label_id, label_space);
IncrementShardMapVersion();
return label_id;
}
void ShardMap::AddServer(Address server_address) {
// Find a random place for the server to plug in
}
std::optional<LabelId> ShardMap::GetLabelId(const std::string &label) const {
if (const auto it = labels.find(label); it != labels.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetLabelName(const LabelId label) const {
if (const auto it =
std::ranges::find_if(labels, [label](const auto &name_id_pair) { return name_id_pair.second == label; });
it != labels.end()) {
return it->first;
}
throw utils::BasicException("GetLabelName fails on the given label id!");
}
std::optional<PropertyId> ShardMap::GetPropertyId(const std::string &property_name) const {
if (const auto it = properties.find(property_name); it != properties.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetPropertyName(const PropertyId property) const {
if (const auto it = std::ranges::find_if(
properties, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
it != properties.end()) {
return it->first;
}
throw utils::BasicException("PropertyId not found!");
}
std::optional<EdgeTypeId> ShardMap::GetEdgeTypeId(const std::string &edge_type) const {
if (const auto it = edge_types.find(edge_type); it != edge_types.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetEdgeTypeName(const EdgeTypeId property) const {
if (const auto it = std::ranges::find_if(
edge_types, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
it != edge_types.end()) {
return it->first;
}
throw utils::BasicException("EdgeTypeId not found!");
}
Shards ShardMap::GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key,
const PrimaryKey &end_key) const {
MG_ASSERT(start_key <= end_key);
MG_ASSERT(labels.contains(label_name));
LabelId label_id = labels.at(label_name);
const auto &label_space = label_spaces.at(label_id);
const auto &shards_for_label = label_space.shards;
MG_ASSERT(shards_for_label.begin()->first <= start_key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
auto it = std::prev(shards_for_label.upper_bound(start_key));
const auto end_it = shards_for_label.upper_bound(end_key);
Shards shards{};
std::copy(it, end_it, std::inserter(shards, shards.end()));
return shards;
}
Shard ShardMap::GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const {
MG_ASSERT(labels.contains(label_name));
LabelId label_id = labels.at(label_name);
const auto &label_space = label_spaces.at(label_id);
MG_ASSERT(label_space.shards.begin()->first <= key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
return std::prev(label_space.shards.upper_bound(key))->second;
}
Shard ShardMap::GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const {
MG_ASSERT(label_spaces.contains(label_id));
const auto &label_space = label_spaces.at(label_id);
MG_ASSERT(label_space.shards.begin()->first <= key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
return std::prev(label_space.shards.upper_bound(key))->second;
}
PropertyMap ShardMap::AllocatePropertyIds(const std::vector<PropertyName> &new_properties) {
PropertyMap ret{};
bool mutated = false;
for (const auto &property_name : new_properties) {
if (properties.contains(property_name)) {
auto property_id = properties.at(property_name);
ret.emplace(property_name, property_id);
} else {
mutated = true;
const PropertyId property_id = PropertyId::FromUint(++max_property_id);
ret.emplace(property_name, property_id);
properties.emplace(property_name, property_id);
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
EdgeTypeIdMap ShardMap::AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types) {
EdgeTypeIdMap ret;
bool mutated = false;
for (const auto &edge_type_name : new_edge_types) {
if (edge_types.contains(edge_type_name)) {
auto edge_type_id = edge_types.at(edge_type_name);
ret.emplace(edge_type_name, edge_type_id);
} else {
mutated = true;
const EdgeTypeId edge_type_id = EdgeTypeId::FromUint(++max_edge_type_id);
ret.emplace(edge_type_name, edge_type_id);
edge_types.emplace(edge_type_name, edge_type_id);
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
bool ShardMap::ClusterInitialized() const {
for (const auto &[label_id, label_space] : label_spaces) {
for (const auto &[low_key, shard] : label_space.shards) {
if (shard.size() < label_space.replication_factor) {
spdlog::info("label_space below desired replication factor");
return false;
}
for (const auto &aas : shard) {
if (aas.status != Status::CONSENSUS_PARTICIPANT) {
spdlog::info("shard member not yet a CONSENSUS_PARTICIPANT");
return false;
}
}
}
}
return true;
}
} // namespace memgraph::coordinator

View File

@@ -0,0 +1,177 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <algorithm>
#include <limits>
#include <map>
#include <set>
#include <vector>
#include <boost/uuid/uuid.hpp>
#include <boost/uuid/uuid_generators.hpp>
#include "common/types.hpp"
#include "coordinator/hybrid_logical_clock.hpp"
#include "io/address.hpp"
#include "storage/v3/config.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/name_id_mapper.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/schemas.hpp"
#include "storage/v3/temporal.hpp"
#include "utils/exceptions.hpp"
#include "utils/print_helpers.hpp"
namespace memgraph::coordinator {
constexpr int64_t kNotExistingId{0};
using memgraph::io::Address;
using memgraph::storage::v3::Config;
using memgraph::storage::v3::EdgeTypeId;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyId;
using memgraph::storage::v3::PropertyValue;
using memgraph::storage::v3::SchemaProperty;
enum class Status : uint8_t {
CONSENSUS_PARTICIPANT,
INITIALIZING,
// TODO(tyler) this will possibly have more states,
// depending on the reconfiguration protocol that we
// implement.
};
struct AddressAndStatus {
memgraph::io::Address address;
Status status;
friend bool operator<(const AddressAndStatus &lhs, const AddressAndStatus &rhs) { return lhs.address < rhs.address; }
friend std::ostream &operator<<(std::ostream &in, const AddressAndStatus &address_and_status) {
in << "AddressAndStatus { address: ";
in << address_and_status.address;
if (address_and_status.status == Status::CONSENSUS_PARTICIPANT) {
in << ", status: CONSENSUS_PARTICIPANT }";
} else {
in << ", status: INITIALIZING }";
}
return in;
}
friend bool operator==(const AddressAndStatus &lhs, const AddressAndStatus &rhs) {
return lhs.address == rhs.address;
}
};
using PrimaryKey = std::vector<PropertyValue>;
using Shard = std::vector<AddressAndStatus>;
using Shards = std::map<PrimaryKey, Shard>;
using LabelName = std::string;
using PropertyName = std::string;
using EdgeTypeName = std::string;
using PropertyMap = std::map<PropertyName, PropertyId>;
using EdgeTypeIdMap = std::map<EdgeTypeName, EdgeTypeId>;
struct ShardToInitialize {
boost::uuids::uuid uuid;
LabelId label_id;
PrimaryKey min_key;
std::optional<PrimaryKey> max_key;
std::vector<SchemaProperty> schema;
Config config;
std::unordered_map<uint64_t, std::string> id_to_names;
};
PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema);
struct LabelSpace {
std::vector<SchemaProperty> schema;
// Maps between the smallest primary key stored in the shard and the shard
std::map<PrimaryKey, Shard> shards;
size_t replication_factor;
friend std::ostream &operator<<(std::ostream &in, const LabelSpace &label_space) {
using utils::print_helpers::operator<<;
in << "LabelSpace { schema: ";
in << label_space.schema;
in << ", shards: ";
in << label_space.shards;
in << ", replication_factor: " << label_space.replication_factor << "}";
return in;
}
};
struct ShardMap {
Hlc shard_map_version;
uint64_t max_property_id{kNotExistingId};
uint64_t max_edge_type_id{kNotExistingId};
std::map<PropertyName, PropertyId> properties;
std::map<EdgeTypeName, EdgeTypeId> edge_types;
uint64_t max_label_id{kNotExistingId};
std::map<LabelId, LabelSpace> label_spaces;
std::map<LabelId, std::vector<SchemaProperty>> schemas;
std::map<LabelName, LabelId> labels;
[[nodiscard]] static ShardMap Parse(std::istream &input_stream);
friend std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map);
Shards GetShardsForLabel(const LabelName &label) const;
std::vector<Shards> GetAllShards() const;
// TODO(gabor) later we will want to update the wallclock time with
// the given Io<impl>'s time as well
Hlc IncrementShardMapVersion() noexcept;
Hlc GetHlc() const noexcept;
std::unordered_map<uint64_t, std::string> IdToNames();
// Returns the shard UUIDs that have been assigned but not yet acknowledged for this storage manager
std::vector<ShardToInitialize> AssignShards(Address storage_manager, std::set<boost::uuids::uuid> initialized);
bool SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key);
std::optional<LabelId> InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
size_t replication_factor, Hlc last_shard_map_version);
void AddServer(Address server_address);
std::optional<LabelId> GetLabelId(const std::string &label) const;
// TODO(antaljanosbenjamin): Remove this and instead use NameIdMapper
const std::string &GetLabelName(LabelId label) const;
std::optional<PropertyId> GetPropertyId(const std::string &property_name) const;
const std::string &GetPropertyName(PropertyId property) const;
std::optional<EdgeTypeId> GetEdgeTypeId(const std::string &edge_type) const;
const std::string &GetEdgeTypeName(EdgeTypeId property) const;
Shards GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key, const PrimaryKey &end_key) const;
Shard GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const;
Shard GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const;
PropertyMap AllocatePropertyIds(const std::vector<PropertyName> &new_properties);
EdgeTypeIdMap AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types);
/// Returns true if all shards have the desired number of replicas and they are in
/// the CONSENSUS_PARTICIPANT state. Note that this does not necessarily mean that
/// there is also an active leader for each shard.
bool ClusterInitialized() const;
};
} // namespace memgraph::coordinator

20
src/expr/CMakeLists.txt Normal file
View File

@@ -0,0 +1,20 @@
define_add_lcp(add_lcp_expr lcp_expr_cpp_files generated_lcp_expr_files)
add_lcp_expr(semantic/symbol.lcp)
add_custom_target(generate_lcp_expr DEPENDS ${generated_lcp_expr_files})
set(mg_expr_sources
${lcp_expr_cpp_files}
parsing.cpp)
find_package(Boost REQUIRED)
add_library(mg-expr STATIC ${mg_expr_sources})
add_dependencies(mg-expr generate_lcp_expr)
target_include_directories(mg-expr PUBLIC ${CMAKE_SOURCE_DIR}/include)
target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/ast)
target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/interpret)
target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/semantic)
target_link_libraries(mg-expr cppitertools Boost::headers mg-utils mg-parser)

33
src/expr/ast.hpp Normal file
View File

@@ -0,0 +1,33 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#ifndef MG_AST_INCLUDE_PATH
#ifdef MG_CLANG_TIDY_CHECK
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#include "query/v2/bindings/bindings.hpp"
#else
#error Missing AST include path
#endif
#endif
#ifndef MG_INJECTED_NAMESPACE_NAME
#ifdef MG_CLANG_TIDY_CHECK
#else
#error Missing AST namespace
#endif
#endif
#include MG_AST_INCLUDE_PATH
namespace memgraph::expr {
using namespace MG_INJECTED_NAMESPACE_NAME; // NOLINT(google-build-using-namespace)
} // namespace memgraph::expr

View File

@@ -13,7 +13,7 @@
#include "utils/visitor.hpp"
namespace memgraph::query::v2 {
namespace MG_INJECTED_NAMESPACE_NAME {
// Forward declares for Tree visitors.
class CypherQuery;
@@ -96,7 +96,7 @@ class VersionQuery;
class Foreach;
class SchemaQuery;
using TreeCompositeVisitor = utils::CompositeVisitor<
using TreeCompositeVisitor = memgraph::utils::CompositeVisitor<
SingleQuery, CypherUnion, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
@@ -105,7 +105,7 @@ using TreeCompositeVisitor = utils::CompositeVisitor<
Create, Match, Return, With, Pattern, NodeAtom, EdgeAtom, Delete, Where, SetProperty, SetProperties, SetLabels,
RemoveProperty, RemoveLabels, Merge, Unwind, RegexMatch, LoadCsv, Foreach>;
using TreeLeafVisitor = utils::LeafVisitor<Identifier, PrimitiveLiteral, ParameterLookup>;
using TreeLeafVisitor = memgraph::utils::LeafVisitor<Identifier, PrimitiveLiteral, ParameterLookup>;
class HierarchicalTreeVisitor : public TreeCompositeVisitor, public TreeLeafVisitor {
public:
@@ -117,7 +117,7 @@ class HierarchicalTreeVisitor : public TreeCompositeVisitor, public TreeLeafVisi
template <class TResult>
class ExpressionVisitor
: public utils::Visitor<
: public memgraph::utils::Visitor<
TResult, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
@@ -126,9 +126,10 @@ class ExpressionVisitor
None, ParameterLookup, Identifier, PrimitiveLiteral, RegexMatch> {};
template <class TResult>
class QueryVisitor : public utils::Visitor<TResult, CypherQuery, ExplainQuery, ProfileQuery, IndexQuery, AuthQuery,
InfoQuery, ConstraintQuery, DumpQuery, ReplicationQuery, LockPathQuery,
FreeMemoryQuery, TriggerQuery, IsolationLevelQuery, CreateSnapshotQuery,
StreamQuery, SettingQuery, VersionQuery, SchemaQuery> {};
class QueryVisitor
: public memgraph::utils::Visitor<TResult, CypherQuery, ExplainQuery, ProfileQuery, IndexQuery, AuthQuery,
InfoQuery, ConstraintQuery, DumpQuery, ReplicationQuery, LockPathQuery,
FreeMemoryQuery, TriggerQuery, IsolationLevelQuery, CreateSnapshotQuery,
StreamQuery, SettingQuery, VersionQuery, SchemaQuery> {};
} // namespace memgraph::query::v2
} // namespace MG_INJECTED_NAMESPACE_NAME

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,271 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <type_traits>
#include "expr/ast.hpp"
#include "expr/typed_value.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
namespace memgraph::expr {
namespace detail {
template <typename T>
void PrintObject(std::ostream *out, const T &arg) {
static_assert(!std::is_convertible<T, Expression *>::value,
"This overload shouldn't be called with pointers convertible "
"to Expression *. This means your other PrintObject overloads aren't "
"being called for certain AST nodes when they should (or perhaps such "
"overloads don't exist yet).");
*out << arg;
}
inline void PrintObject(std::ostream *out, const std::string &str) { *out << utils::Escape(str); }
inline void PrintObject(std::ostream *out, Aggregation::Op op) { *out << Aggregation::OpToString(op); }
inline void PrintObject(std::ostream *out, Expression *expr);
inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T> &vec) {
*out << "[";
utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
*out << "]";
}
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T, utils::Allocator<T>> &vec) {
*out << "[";
utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
*out << "]";
}
template <typename K, typename V>
void PrintObject(std::ostream *out, const std::map<K, V> &map) {
*out << "{";
utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
PrintObject(&stream, item.first);
stream << ": ";
PrintObject(&stream, item.second);
});
*out << "}";
}
template <typename T>
void PrintObject(std::ostream *out, const utils::pmr::map<utils::pmr::string, T> &map) {
*out << "{";
utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
PrintObject(&stream, item.first);
stream << ": ";
PrintObject(&stream, item.second);
});
*out << "}";
}
template <typename T1, typename T2, typename T3>
inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
using TypedValue = TypedValueT<T1, T2, T3>;
switch (value.type()) {
case TypedValue::Type::Null:
*out << "null";
break;
case TypedValue::Type::String:
PrintObject(out, value.ValueString());
break;
case TypedValue::Type::Bool:
*out << (value.ValueBool() ? "true" : "false");
break;
case TypedValue::Type::Int:
PrintObject(out, value.ValueInt());
break;
case TypedValue::Type::Double:
PrintObject(out, value.ValueDouble());
break;
case TypedValue::Type::List:
PrintObject(out, value.ValueList());
break;
case TypedValue::Type::Map:
PrintObject(out, value.ValueMap());
break;
case TypedValue::Type::Date:
PrintObject(out, value.ValueDate());
break;
case TypedValue::Type::Duration:
PrintObject(out, value.ValueDuration());
break;
case TypedValue::Type::LocalTime:
PrintObject(out, value.ValueLocalTime());
break;
case TypedValue::Type::LocalDateTime:
PrintObject(out, value.ValueLocalDateTime());
break;
default:
MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
}
}
template <typename T>
void PrintOperatorArgs(std::ostream *out, const T &arg) {
*out << " ";
PrintObject(out, arg);
*out << ")";
}
template <typename T, typename... Ts>
void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
*out << " ";
PrintObject(out, arg);
PrintOperatorArgs(out, args...);
}
template <typename... Ts>
void PrintOperator(std::ostream *out, const std::string &name, const Ts &...args) {
*out << "(" << name;
PrintOperatorArgs(out, args...);
}
} // namespace detail
class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
public:
explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
// Unary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression_); }
UNARY_OPERATOR_VISIT(NotOperator, "Not");
UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
#undef UNARY_OPERATOR_VISIT
// Binary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression1_, op.expression2_); }
BINARY_OPERATOR_VISIT(OrOperator, "Or");
BINARY_OPERATOR_VISIT(XorOperator, "Xor");
BINARY_OPERATOR_VISIT(AndOperator, "And");
BINARY_OPERATOR_VISIT(AdditionOperator, "+");
BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
BINARY_OPERATOR_VISIT(DivisionOperator, "/");
BINARY_OPERATOR_VISIT(ModOperator, "%");
BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
BINARY_OPERATOR_VISIT(EqualOperator, "==");
BINARY_OPERATOR_VISIT(LessOperator, "<");
BINARY_OPERATOR_VISIT(GreaterOperator, ">");
BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
BINARY_OPERATOR_VISIT(InListOperator, "In");
BINARY_OPERATOR_VISIT(SubscriptOperator, "Subscript");
#undef BINARY_OPERATOR_VISIT
// Other
void Visit(ListSlicingOperator &op) override {
detail::PrintOperator(out_, "ListSlicing", op.list_, op.lower_bound_, op.upper_bound_);
}
void Visit(IfOperator &op) override {
detail::PrintOperator(out_, "If", op.condition_, op.then_expression_, op.else_expression_);
}
void Visit(ListLiteral &op) override { detail::PrintOperator(out_, "ListLiteral", op.elements_); }
void Visit(MapLiteral &op) override {
std::map<std::string, Expression *> map;
for (const auto &kv : op.elements_) {
map[kv.first.name] = kv.second;
}
detail::PrintObject(out_, map);
}
void Visit(LabelsTest &op) override { detail::PrintOperator(out_, "LabelsTest", op.expression_); }
void Visit(Aggregation &op) override { detail::PrintOperator(out_, "Aggregation", op.op_); }
void Visit(Function &op) override { detail::PrintOperator(out_, "Function", op.function_name_, op.arguments_); }
void Visit(Reduce &op) override {
detail::PrintOperator(out_, "Reduce", op.accumulator_, op.initializer_, op.identifier_, op.list_, op.expression_);
}
void Visit(Coalesce &op) override { detail::PrintOperator(out_, "Coalesce", op.expressions_); }
void Visit(Extract &op) override { detail::PrintOperator(out_, "Extract", op.identifier_, op.list_, op.expression_); }
void Visit(All &op) override {
detail::PrintOperator(out_, "All", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Single &op) override {
detail::PrintOperator(out_, "Single", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Any &op) override {
detail::PrintOperator(out_, "Any", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(None &op) override {
detail::PrintOperator(out_, "None", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Identifier &op) override { detail::PrintOperator(out_, "Identifier", op.name_); }
void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
void Visit(PropertyLookup &op) override {
detail::PrintOperator(out_, "PropertyLookup", op.expression_, op.property_.name);
}
void Visit(ParameterLookup &op) override { detail::PrintOperator(out_, "ParameterLookup", op.token_position_); }
void Visit(NamedExpression &op) override { detail::PrintOperator(out_, "NamedExpression", op.name_, op.expression_); }
void Visit(RegexMatch &op) override { detail::PrintOperator(out_, "=~", op.string_expr_, op.regex_); }
private:
std::ostream *out_;
};
namespace detail {
inline void PrintObject(std::ostream *out, Expression *expr) {
if (expr) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
} else {
*out << "<null>";
}
}
} // namespace detail
inline void PrintExpression(Expression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
inline void PrintExpression(NamedExpression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
} // namespace memgraph::expr

View File

@@ -0,0 +1,279 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <type_traits>
#include "expr/ast.hpp"
#include "expr/typed_value.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
namespace memgraph::expr {
inline constexpr const char *identifier_node_symbol = "MG_SYMBOL_NODE";
inline constexpr const char *identifier_edge_symbol = "MG_SYMBOL_EDGE";
namespace detail {
template <typename T>
void PrintObject(std::ostream *out, const T &arg) {
static_assert(!std::is_convertible<T, Expression *>::value,
"This overload shouldn't be called with pointers convertible "
"to Expression *. This means your other PrintObject overloads aren't "
"being called for certain AST nodes when they should (or perhaps such "
"overloads don't exist yet).");
*out << arg;
}
inline void PrintObject(std::ostream *out, const std::string &str) { *out << str; }
inline void PrintObject(std::ostream * /*out*/, Aggregation::Op /*op*/) {
throw utils::NotYetImplemented("PrintObject: Aggregation::Op");
}
inline void PrintObject(std::ostream * /*out*/, Expression * /*expr*/);
inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
template <typename T>
void PrintObject(std::ostream * /*out*/, const std::vector<T> & /*vec*/) {
throw utils::NotYetImplemented("PrintObject: vector<T>");
}
template <typename T>
void PrintObject(std::ostream * /*out*/, const std::vector<T, utils::Allocator<T>> & /*vec*/) {
throw utils::NotYetImplemented("PrintObject: vector<T, utils::Allocator<T>>");
}
template <typename K, typename V>
void PrintObject(std::ostream * /*out*/, const std::map<K, V> & /*map*/) {
throw utils::NotYetImplemented("PrintObject: map<K, V>");
}
template <typename T>
void PrintObject(std::ostream * /*out*/, const utils::pmr::map<utils::pmr::string, T> & /*map*/) {
throw utils::NotYetImplemented("PrintObject: map<utils::pmr::string, V>");
}
template <typename T1, typename T2, typename T3>
inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
using TypedValue = TypedValueT<T1, T2, T3>;
switch (value.type()) {
case TypedValue::Type::Null:
*out << "null";
break;
case TypedValue::Type::String:
PrintObject(out, value.ValueString());
break;
case TypedValue::Type::Bool:
*out << (value.ValueBool() ? "true" : "false");
break;
case TypedValue::Type::Int:
PrintObject(out, value.ValueInt());
break;
case TypedValue::Type::Double:
PrintObject(out, value.ValueDouble());
break;
case TypedValue::Type::List:
PrintObject(out, value.ValueList());
break;
case TypedValue::Type::Map:
PrintObject(out, value.ValueMap());
break;
case TypedValue::Type::Date:
PrintObject(out, value.ValueDate());
break;
case TypedValue::Type::Duration:
PrintObject(out, value.ValueDuration());
break;
case TypedValue::Type::LocalTime:
PrintObject(out, value.ValueLocalTime());
break;
case TypedValue::Type::LocalDateTime:
PrintObject(out, value.ValueLocalDateTime());
break;
default:
MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
}
}
template <typename T>
void PrintOperatorArgs(const std::string & /*name*/, std::ostream *out, bool with_parenthesis, const T &arg) {
PrintObject(out, arg);
if (with_parenthesis) {
*out << ")";
}
}
template <typename T, typename... Ts>
void PrintOperatorArgs(const std::string &name, std::ostream *out, bool with_parenthesis, const T &arg,
const Ts &...args) {
PrintObject(out, arg);
*out << " " << name << " ";
PrintOperatorArgs(name, out, with_parenthesis, args...);
}
template <typename... Ts>
void PrintOperator(const std::string &name, std::ostream *out, bool with_parenthesis, const Ts &...args) {
if (with_parenthesis) {
*out << "(";
}
PrintOperatorArgs(name, out, with_parenthesis, args...);
}
// new
template <typename T>
void PrintOperatorArgs(std::ostream *out, const T &arg) {
PrintObject(out, arg);
}
template <typename T, typename... Ts>
void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
PrintObject(out, arg);
PrintOperatorArgs(out, args...);
}
template <typename... Ts>
void PrintOperator(std::ostream *out, const Ts &...args) {
PrintOperatorArgs(out, args...);
}
} // namespace detail
class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
public:
explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
// Unary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(OP_STR, out_, false /*with_parenthesis*/, op.expression_); }
UNARY_OPERATOR_VISIT(NotOperator, "Not");
UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
#undef UNARY_OPERATOR_VISIT
// Binary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { \
detail::PrintOperator(OP_STR, out_, true /*with_parenthesis*/, op.expression1_, op.expression2_); \
}
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT_NOT_IMPL(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE & /*op*/) override { throw utils::NotYetImplemented("OP_NODE"); }
BINARY_OPERATOR_VISIT(OrOperator, "Or");
BINARY_OPERATOR_VISIT(XorOperator, "Xor");
BINARY_OPERATOR_VISIT(AndOperator, "And");
BINARY_OPERATOR_VISIT(AdditionOperator, "+");
BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
BINARY_OPERATOR_VISIT(DivisionOperator, "/");
BINARY_OPERATOR_VISIT(ModOperator, "%");
BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
BINARY_OPERATOR_VISIT(EqualOperator, "=");
BINARY_OPERATOR_VISIT(LessOperator, "<");
BINARY_OPERATOR_VISIT(GreaterOperator, ">");
BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
BINARY_OPERATOR_VISIT_NOT_IMPL(InListOperator, "In");
BINARY_OPERATOR_VISIT_NOT_IMPL(SubscriptOperator, "Subscript");
#undef BINARY_OPERATOR_VISIT
#undef BINARY_OPERATOR_VISIT_NOT_IMPL
// Other
void Visit(ListSlicingOperator & /*op*/) override { throw utils::NotYetImplemented("ListSlicingOperator"); }
void Visit(IfOperator & /*op*/) override { throw utils::NotYetImplemented("IfOperator"); }
void Visit(ListLiteral & /*op*/) override { throw utils::NotYetImplemented("ListLiteral"); }
void Visit(MapLiteral & /*op*/) override { throw utils::NotYetImplemented("MapLiteral"); }
void Visit(LabelsTest & /*op*/) override { throw utils::NotYetImplemented("LabelsTest"); }
void Visit(Aggregation & /*op*/) override { throw utils::NotYetImplemented("Aggregation"); }
void Visit(Function & /*op*/) override { throw utils::NotYetImplemented("Function"); }
void Visit(Reduce & /*op*/) override { throw utils::NotYetImplemented("Reduce"); }
void Visit(Coalesce & /*op*/) override { throw utils::NotYetImplemented("Coalesce"); }
void Visit(Extract & /*op*/) override { throw utils::NotYetImplemented("Extract"); }
void Visit(All & /*op*/) override { throw utils::NotYetImplemented("All"); }
void Visit(Single & /*op*/) override { throw utils::NotYetImplemented("Single"); }
void Visit(Any & /*op*/) override { throw utils::NotYetImplemented("Any"); }
void Visit(None & /*op*/) override { throw utils::NotYetImplemented("None"); }
void Visit(Identifier &op) override {
auto is_node = true;
auto is_edge = false;
auto is_other = false;
if (is_node) {
detail::PrintOperator(out_, identifier_node_symbol);
} else if (is_edge) {
detail::PrintOperator(out_, identifier_edge_symbol);
} else {
MG_ASSERT(is_other);
detail::PrintOperator(out_, op.name_);
}
}
void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
void Visit(PropertyLookup &op) override { detail::PrintOperator(out_, op.expression_, ".", op.property_.name); }
void Visit(ParameterLookup & /*op*/) override { throw utils::NotYetImplemented("ParameterLookup"); }
void Visit(NamedExpression & /*op*/) override { throw utils::NotYetImplemented("NamedExpression"); }
void Visit(RegexMatch & /*op*/) override { throw utils::NotYetImplemented("RegexMatch"); }
private:
std::ostream *out_;
};
namespace detail {
inline void PrintObject(std::ostream *out, Expression *expr) {
if (expr) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
} else {
*out << "<null>";
}
}
} // namespace detail
inline void PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(Expression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
inline std::string ExpressiontoStringWhileReplacingNodeAndEdgeSymbols(Expression *expr) {
std::ostringstream ss;
expr::PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(expr, &ss);
return ss.str();
}
} // namespace memgraph::expr

52
src/expr/exceptions.hpp Normal file
View File

@@ -0,0 +1,52 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "utils/exceptions.hpp"
namespace memgraph::expr {
class SyntaxException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
SyntaxException() : SyntaxException("") {}
};
class SemanticException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
SemanticException() : BasicException("") {}
};
class ExpressionRuntimeException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
};
class RedeclareVariableError : public SemanticException {
public:
explicit RedeclareVariableError(const std::string &name) : SemanticException("Redeclaring variable: " + name + ".") {}
};
class UnboundVariableError : public SemanticException {
public:
explicit UnboundVariableError(const std::string &name) : SemanticException("Unbound variable: " + name + ".") {}
};
class TypeMismatchError : public SemanticException {
public:
TypeMismatchError(const std::string &name, const std::string &datum, const std::string &expected)
: SemanticException(fmt::format("Type mismatch: {} already defined as {}, expected {}.", name, datum, expected)) {
}
};
} // namespace memgraph::expr

View File

@@ -17,24 +17,26 @@
#include <map>
#include <optional>
#include <regex>
#include <type_traits>
#include <vector>
#include "query/v2/common.hpp"
#include "query/v2/context.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/frontend/semantic/symbol_table.hpp"
#include "query/v2/interpret/frame.hpp"
#include "query/v2/typed_value.hpp"
#include "expr/ast.hpp"
#include "expr/exceptions.hpp"
#include "expr/interpret/frame.hpp"
#include "expr/semantic/symbol_table.hpp"
#include "utils/exceptions.hpp"
namespace memgraph::query::v2 {
namespace memgraph::expr {
struct StorageTag {};
struct QueryEngineTag {};
template <typename TypedValue, typename EvaluationContext, typename DbAccessor, typename StorageView, typename LabelId,
typename PropertyValue, typename ConvFunctor, typename Error, typename Tag = StorageTag>
class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
public:
ExpressionEvaluator(Frame *frame, const SymbolTable &symbol_table, const EvaluationContext &ctx, DbAccessor *dba,
storage::v3::View view)
ExpressionEvaluator(Frame<TypedValue> *frame, const SymbolTable &symbol_table, const EvaluationContext &ctx,
DbAccessor *dba, StorageView view)
: frame_(frame), symbol_table_(&symbol_table), ctx_(&ctx), dba_(dba), view_(view) {}
using ExpressionVisitor<TypedValue>::Visit;
@@ -52,25 +54,29 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(frame_->at(symbol_table_->at(ident)), ctx_->memory);
}
#define BINARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP) \
TypedValue Visit(OP_NODE &op) override { \
auto val1 = op.expression1_->Accept(*this); \
auto val2 = op.expression2_->Accept(*this); \
try { \
return val1 CPP_OP val2; \
} catch (const TypedValueException &) { \
throw QueryRuntimeException("Invalid types: {} and {} for '{}'.", val1.type(), val2.type(), #CYPHER_OP); \
} \
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
TypedValue Visit(OP_NODE &op) override { \
auto val1 = op.expression1_->Accept(*this); \
auto val2 = op.expression2_->Accept(*this); \
try { \
return val1 CPP_OP val2; \
} catch (const TypedValueException &) { \
throw ExpressionRuntimeException("Invalid types: {} and {} for '{}'.", val1.type(), val2.type(), #CYPHER_OP); \
} \
}
#define UNARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP) \
TypedValue Visit(OP_NODE &op) override { \
auto val = op.expression_->Accept(*this); \
try { \
return CPP_OP val; \
} catch (const TypedValueException &) { \
throw QueryRuntimeException("Invalid type {} for '{}'.", val.type(), #CYPHER_OP); \
} \
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define UNARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
TypedValue Visit(OP_NODE &op) override { \
auto val = op.expression_->Accept(*this); \
try { \
return CPP_OP val; \
} catch (const TypedValueException &) { \
throw ExpressionRuntimeException("Invalid type {} for '{}'.", val.type(), #CYPHER_OP); \
} \
}
BINARY_OPERATOR_VISITOR(OrOperator, ||, OR);
@@ -104,18 +110,18 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
try {
return value1 && value2;
} catch (const TypedValueException &) {
throw QueryRuntimeException("Invalid types: {} and {} for AND.", value1.type(), value2.type());
throw ExpressionRuntimeException("Invalid types: {} and {} for AND.", value1.type(), value2.type());
}
}
TypedValue Visit(IfOperator &if_operator) override {
auto condition = if_operator.condition_->Accept(*this);
if (condition.IsNull()) {
return if_operator.then_expression_->Accept(*this);
return if_operator.else_expression_->Accept(*this);
}
if (condition.type() != TypedValue::Type::Bool) {
// At the moment IfOperator is used only in CASE construct.
throw QueryRuntimeException("CASE expected boolean expression, got {}.", condition.type());
throw ExpressionRuntimeException("CASE expected boolean expression, got {}.", condition.type());
}
if (condition.ValueBool()) {
return if_operator.then_expression_->Accept(*this);
@@ -132,7 +138,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
// Exceptions have higher priority than returning nulls when list expression
// is not null.
if (_list.type() != TypedValue::Type::List) {
throw QueryRuntimeException("IN expected a list, got {}.", _list.type());
throw ExpressionRuntimeException("IN expected a list, got {}.", _list.type());
}
const auto &list = _list.ValueList();
@@ -162,13 +168,14 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
auto lhs = list_indexing.expression1_->Accept(*this);
auto index = list_indexing.expression2_->Accept(*this);
if (!lhs.IsList() && !lhs.IsMap() && !lhs.IsVertex() && !lhs.IsEdge() && !lhs.IsNull())
throw QueryRuntimeException(
throw ExpressionRuntimeException(
"Expected a list, a map, a node or an edge to index with '[]', got "
"{}.",
lhs.type());
if (lhs.IsNull() || index.IsNull()) return TypedValue(ctx_->memory);
if (lhs.IsList()) {
if (!index.IsInt()) throw QueryRuntimeException("Expected an integer as a list index, got {}.", index.type());
if (!index.IsInt())
throw ExpressionRuntimeException("Expected an integer as a list index, got {}.", index.type());
auto index_int = index.ValueInt();
// NOTE: Take non-const reference to list, so that we can move out the
// indexed element as the result.
@@ -183,7 +190,8 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
}
if (lhs.IsMap()) {
if (!index.IsString()) throw QueryRuntimeException("Expected a string as a map index, got {}.", index.type());
if (!index.IsString())
throw ExpressionRuntimeException("Expected a string as a map index, got {}.", index.type());
// NOTE: Take non-const reference to map, so that we can move out the
// looked-up element as the result.
auto &map = lhs.ValueMap();
@@ -195,12 +203,14 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
}
if (lhs.IsVertex()) {
if (!index.IsString()) throw QueryRuntimeException("Expected a string as a property name, got {}.", index.type());
if (!index.IsString())
throw ExpressionRuntimeException("Expected a string as a property name, got {}.", index.type());
return TypedValue(GetProperty(lhs.ValueVertex(), index.ValueString()), ctx_->memory);
}
if (lhs.IsEdge()) {
if (!index.IsString()) throw QueryRuntimeException("Expected a string as a property name, got {}.", index.type());
if (!index.IsString())
throw ExpressionRuntimeException("Expected a string as a property name, got {}.", index.type());
return TypedValue(GetProperty(lhs.ValueEdge(), index.ValueString()), ctx_->memory);
}
@@ -218,7 +228,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (bound.type() == TypedValue::Type::Null) {
is_null = true;
} else if (bound.type() != TypedValue::Type::Int) {
throw QueryRuntimeException("Expected an integer for a bound in list slicing, got {}.", bound.type());
throw ExpressionRuntimeException("Expected an integer for a bound in list slicing, got {}.", bound.type());
}
return bound;
}
@@ -231,7 +241,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (_list.type() == TypedValue::Type::Null) {
is_null = true;
} else if (_list.type() != TypedValue::Type::List) {
throw QueryRuntimeException("Expected a list to slice, got {}.", _list.type());
throw ExpressionRuntimeException("Expected a list to slice, got {}.", _list.type());
}
if (is_null) {
@@ -247,9 +257,10 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
auto lower_bound = normalise_bound(_lower_bound.ValueInt());
auto upper_bound = normalise_bound(_upper_bound.ValueInt());
if (upper_bound <= lower_bound) {
return TypedValue(TypedValue::TVector(ctx_->memory), ctx_->memory);
return TypedValue(typename TypedValue::TVector(ctx_->memory), ctx_->memory);
}
return TypedValue(TypedValue::TVector(list.begin() + lower_bound, list.begin() + upper_bound, ctx_->memory));
return TypedValue(
typename TypedValue::TVector(list.begin() + lower_bound, list.begin() + upper_bound, ctx_->memory));
}
TypedValue Visit(IsNullOperator &is_null) override {
@@ -317,9 +328,9 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
case TypedValue::Type::Null:
return TypedValue(ctx_->memory);
case TypedValue::Type::Vertex:
return TypedValue(GetProperty(expression_result.ValueVertex(), property_lookup.property_), ctx_->memory);
return GetProperty(expression_result.ValueVertex(), property_lookup.property_);
case TypedValue::Type::Edge:
return TypedValue(GetProperty(expression_result.ValueEdge(), property_lookup.property_), ctx_->memory);
return GetProperty(expression_result.ValueEdge(), property_lookup.property_);
case TypedValue::Type::Map: {
// NOTE: Take non-const reference to map, so that we can move out the
// looked-up element as the result.
@@ -336,7 +347,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (auto dur_field = maybe_duration(dur, prop_name); dur_field) {
return std::move(*dur_field);
}
throw QueryRuntimeException("Invalid property name {} for Duration", prop_name);
throw ExpressionRuntimeException("Invalid property name {} for Duration", prop_name);
}
case TypedValue::Type::Date: {
const auto &prop_name = property_lookup.property_.name;
@@ -344,7 +355,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (auto date_field = maybe_date(date, prop_name); date_field) {
return std::move(*date_field);
}
throw QueryRuntimeException("Invalid property name {} for Date", prop_name);
throw ExpressionRuntimeException("Invalid property name {} for Date", prop_name);
}
case TypedValue::Type::LocalTime: {
const auto &prop_name = property_lookup.property_.name;
@@ -352,7 +363,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (auto lt_field = maybe_local_time(lt, prop_name); lt_field) {
return std::move(*lt_field);
}
throw QueryRuntimeException("Invalid property name {} for LocalTime", prop_name);
throw ExpressionRuntimeException("Invalid property name {} for LocalTime", prop_name);
}
case TypedValue::Type::LocalDateTime: {
const auto &prop_name = property_lookup.property_.name;
@@ -363,13 +374,51 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
if (auto lt_field = maybe_local_time(ldt.local_time, prop_name); lt_field) {
return std::move(*lt_field);
}
throw QueryRuntimeException("Invalid property name {} for LocalDateTime", prop_name);
throw ExpressionRuntimeException("Invalid property name {} for LocalDateTime", prop_name);
}
default:
throw QueryRuntimeException("Only nodes, edges, maps and temporal types have properties to be looked-up.");
throw ExpressionRuntimeException("Only nodes, edges, maps and temporal types have properties to be looked-up.");
}
}
template <typename VertexAccessor, typename TTag = Tag,
typename TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, bool>>
TReturnType HasLabelImpl(const VertexAccessor &vertex, const LabelIx &label, StorageTag /*tag*/) {
auto has_label = vertex.HasLabel(view_, GetLabel(label));
if (has_label.HasError() && has_label.GetError() == Error::NONEXISTENT_OBJECT) {
// This is a very nasty and temporary hack in order to make MERGE
// work. The old storage had the following logic when returning an
// `OLD` view: `return old ? old : new`. That means that if the
// `OLD` view didn't exist, it returned the NEW view. With this hack
// we simulate that behavior.
// TODO (mferencevic, teon.banek): Remove once MERGE is
// reimplemented.
has_label = vertex.HasLabel(StorageView::NEW, GetLabel(label));
}
if (has_label.HasError()) {
switch (has_label.GetError()) {
case Error::DELETED_OBJECT:
throw ExpressionRuntimeException("Trying to access labels on a deleted node.");
case Error::NONEXISTENT_OBJECT:
throw ExpressionRuntimeException("Trying to access labels from a node that doesn't exist.");
case Error::SERIALIZATION_ERROR:
case Error::VERTEX_HAS_EDGES:
case Error::PROPERTIES_DISABLED:
case Error::VERTEX_ALREADY_INSERTED:
throw ExpressionRuntimeException("Unexpected error when accessing labels.");
}
}
return *has_label;
}
template <typename VertexAccessor, typename TTag = Tag,
typename TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, bool>>
TReturnType HasLabelImpl(const VertexAccessor &vertex, const LabelIx &label_ix, QueryEngineTag /*tag*/) {
auto label = typename VertexAccessor::Label{LabelId::FromUint(label_ix.ix)};
auto has_label = vertex.HasLabel(label);
return !has_label;
}
TypedValue Visit(LabelsTest &labels_test) override {
auto expression_result = labels_test.expression_->Accept(*this);
switch (expression_result.type()) {
@@ -377,38 +426,15 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
case TypedValue::Type::Vertex: {
const auto &vertex = expression_result.ValueVertex();
for (const auto &label : labels_test.labels_) {
auto has_label = vertex.HasLabel(view_, GetLabel(label));
if (has_label.HasError() && has_label.GetError() == storage::v3::Error::NONEXISTENT_OBJECT) {
// This is a very nasty and temporary hack in order to make MERGE
// work. The old storage had the following logic when returning an
// `OLD` view: `return old ? old : new`. That means that if the
// `OLD` view didn't exist, it returned the NEW view. With this hack
// we simulate that behavior.
// TODO (mferencevic, teon.banek): Remove once MERGE is
// reimplemented.
has_label = vertex.HasLabel(storage::v3::View::NEW, GetLabel(label));
}
if (has_label.HasError()) {
switch (has_label.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw QueryRuntimeException("Trying to access labels on a deleted node.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to access labels from a node that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw QueryRuntimeException("Unexpected error when accessing labels.");
}
}
if (!*has_label) {
return TypedValue(false, ctx_->memory);
}
if (std::ranges::all_of(labels_test.labels_, [&vertex, this](const auto label_test) {
return this->HasLabelImpl(vertex, label_test, Tag{});
})) {
return TypedValue(true, ctx_->memory);
}
return TypedValue(true, ctx_->memory);
return TypedValue(false, ctx_->memory);
}
default:
throw QueryRuntimeException("Only nodes have labels.");
throw ExpressionRuntimeException("Only nodes have labels.");
}
}
@@ -419,14 +445,14 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
}
TypedValue Visit(ListLiteral &literal) override {
TypedValue::TVector result(ctx_->memory);
typename TypedValue::TVector result(ctx_->memory);
result.reserve(literal.elements_.size());
for (const auto &expression : literal.elements_) result.emplace_back(expression->Accept(*this));
return TypedValue(result, ctx_->memory);
}
TypedValue Visit(MapLiteral &literal) override {
TypedValue::TMap result(ctx_->memory);
typename TypedValue::TMap result(ctx_->memory);
for (const auto &pair : literal.elements_) result.emplace(pair.first.name, pair.second->Accept(*this));
return TypedValue(result, ctx_->memory);
}
@@ -439,7 +465,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
auto &exprs = coalesce.expressions_;
if (exprs.size() == 0) {
throw QueryRuntimeException("'coalesce' requires at least one argument.");
throw ExpressionRuntimeException("'coalesce' requires at least one argument.");
}
for (int64_t i = 0; i < exprs.size(); ++i) {
@@ -466,7 +492,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
MG_ASSERT(res.GetMemoryResource() == ctx_->memory);
return res;
} else {
TypedValue::TVector arguments(ctx_->memory);
typename TypedValue::TVector arguments(ctx_->memory);
arguments.reserve(function.arguments_.size());
for (const auto &argument : function.arguments_) {
arguments.emplace_back(argument->Accept(*this));
@@ -483,7 +509,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("REDUCE expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("REDUCE expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &element_symbol = symbol_table_->at(*reduce.identifier_);
@@ -503,11 +529,11 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("EXTRACT expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("EXTRACT expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &element_symbol = symbol_table_->at(*extract.identifier_);
TypedValue::TVector result(ctx_->memory);
typename TypedValue::TVector result(ctx_->memory);
result.reserve(list.size());
for (const auto &element : list) {
if (element.IsNull()) {
@@ -526,7 +552,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("ALL expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("ALL expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &symbol = symbol_table_->at(*all.identifier_);
@@ -536,7 +562,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
frame_->at(symbol) = element;
auto result = all.where_->expression_->Accept(*this);
if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
throw QueryRuntimeException("Predicate of ALL must evaluate to boolean, got {}.", result.type());
throw ExpressionRuntimeException("Predicate of ALL must evaluate to boolean, got {}.", result.type());
}
if (!result.IsNull()) {
has_value = true;
@@ -563,7 +589,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("SINGLE expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("SINGLE expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &symbol = symbol_table_->at(*single.identifier_);
@@ -573,7 +599,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
frame_->at(symbol) = element;
auto result = single.where_->expression_->Accept(*this);
if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
throw QueryRuntimeException("Predicate of SINGLE must evaluate to boolean, got {}.", result.type());
throw ExpressionRuntimeException("Predicate of SINGLE must evaluate to boolean, got {}.", result.type());
}
if (result.type() == TypedValue::Type::Bool) {
has_value = true;
@@ -601,7 +627,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("ANY expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("ANY expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &symbol = symbol_table_->at(*any.identifier_);
@@ -610,7 +636,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
frame_->at(symbol) = element;
auto result = any.where_->expression_->Accept(*this);
if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
throw QueryRuntimeException("Predicate of ANY must evaluate to boolean, got {}.", result.type());
throw ExpressionRuntimeException("Predicate of ANY must evaluate to boolean, got {}.", result.type());
}
if (!result.IsNull()) {
has_value = true;
@@ -633,7 +659,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (list_value.type() != TypedValue::Type::List) {
throw QueryRuntimeException("NONE expected a list, got {}.", list_value.type());
throw ExpressionRuntimeException("NONE expected a list, got {}.", list_value.type());
}
const auto &list = list_value.ValueList();
const auto &symbol = symbol_table_->at(*none.identifier_);
@@ -642,7 +668,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
frame_->at(symbol) = element;
auto result = none.where_->expression_->Accept(*this);
if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
throw QueryRuntimeException("Predicate of NONE must evaluate to boolean, got {}.", result.type());
throw ExpressionRuntimeException("Predicate of NONE must evaluate to boolean, got {}.", result.type());
}
if (!result.IsNull()) {
has_value = true;
@@ -660,7 +686,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
}
TypedValue Visit(ParameterLookup &param_lookup) override {
return TypedValue(ctx_->parameters.AtTokenPosition(param_lookup.token_position_), ctx_->memory);
return TypedValue(conv_(ctx_->parameters.AtTokenPosition(param_lookup.token_position_)), ctx_->memory);
}
TypedValue Visit(RegexMatch &regex_match) override {
@@ -670,7 +696,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
return TypedValue(ctx_->memory);
}
if (regex_value.type() != TypedValue::Type::String) {
throw QueryRuntimeException("Regular expression must evaluate to a string, got {}.", regex_value.type());
throw ExpressionRuntimeException("Regular expression must evaluate to a string, got {}.", regex_value.type());
}
if (target_string_value.type() != TypedValue::Type::String) {
// Instead of error, we return Null which makes it compatible in case we
@@ -683,42 +709,61 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
std::regex regex(regex_value.ValueString());
return TypedValue(std::regex_match(target_string, regex), ctx_->memory);
} catch (const std::regex_error &e) {
throw QueryRuntimeException("Regex error in '{}': {}", regex_value.ValueString(), e.what());
throw ExpressionRuntimeException("Regex error in '{}': {}", regex_value.ValueString(), e.what());
}
}
private:
template <class TRecordAccessor>
storage::v3::PropertyValue GetProperty(const TRecordAccessor &record_accessor, PropertyIx prop) {
template <class TRecordAccessor, class TTag = Tag,
class TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, TypedValue>>
TReturnType GetProperty(const TRecordAccessor &record_accessor, PropertyIx prop) {
auto maybe_prop = record_accessor.GetProperty(prop.name);
// Handler non existent property
return conv_(maybe_prop, dba_);
}
template <class TRecordAccessor, class TTag = Tag,
class TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, TypedValue>>
TReturnType GetProperty(const TRecordAccessor &record_accessor, const std::string_view name) {
auto maybe_prop = record_accessor.GetProperty(std::string(name));
// Handler non existent property
return conv_(maybe_prop, dba_);
}
template <class TRecordAccessor, class TTag = Tag,
class TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, TypedValue>>
TypedValue GetProperty(const TRecordAccessor &record_accessor, PropertyIx prop) {
auto maybe_prop = record_accessor.GetProperty(view_, ctx_->properties[prop.ix]);
if (maybe_prop.HasError() && maybe_prop.GetError() == storage::v3::Error::NONEXISTENT_OBJECT) {
if (maybe_prop.HasError() && maybe_prop.GetError() == Error::NONEXISTENT_OBJECT) {
// This is a very nasty and temporary hack in order to make MERGE work.
// The old storage had the following logic when returning an `OLD` view:
// `return old ? old : new`. That means that if the `OLD` view didn't
// exist, it returned the NEW view. With this hack we simulate that
// behavior.
// TODO (mferencevic, teon.banek): Remove once MERGE is reimplemented.
maybe_prop = record_accessor.GetProperty(storage::v3::View::NEW, ctx_->properties[prop.ix]);
maybe_prop = record_accessor.GetProperty(StorageView::NEW, ctx_->properties[prop.ix]);
}
if (maybe_prop.HasError()) {
switch (maybe_prop.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw QueryRuntimeException("Trying to get a property from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get a property from an object that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw QueryRuntimeException("Unexpected error when getting a property.");
case Error::DELETED_OBJECT:
throw ExpressionRuntimeException("Trying to get a property from a deleted object.");
case Error::NONEXISTENT_OBJECT:
throw ExpressionRuntimeException("Trying to get a property from an object that doesn't exist.");
case Error::SERIALIZATION_ERROR:
case Error::VERTEX_HAS_EDGES:
case Error::PROPERTIES_DISABLED:
case Error::VERTEX_ALREADY_INSERTED:
throw ExpressionRuntimeException("Unexpected error when getting a property.");
}
}
return *maybe_prop;
return conv_(*maybe_prop, ctx_->memory);
}
template <class TRecordAccessor>
storage::v3::PropertyValue GetProperty(const TRecordAccessor &record_accessor, const std::string_view name) {
template <class TRecordAccessor, class TTag = Tag,
class TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, TypedValue>>
TypedValue GetProperty(const TRecordAccessor &record_accessor, const std::string_view name) {
auto maybe_prop = record_accessor.GetProperty(view_, dba_->NameToProperty(name));
if (maybe_prop.HasError() && maybe_prop.GetError() == storage::v3::Error::NONEXISTENT_OBJECT) {
if (maybe_prop.HasError() && maybe_prop.GetError() == Error::NONEXISTENT_OBJECT) {
// This is a very nasty and temporary hack in order to make MERGE work.
// The old storage had the following logic when returning an `OLD` view:
// `return old ? old : new`. That means that if the `OLD` view didn't
@@ -729,36 +774,56 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
}
if (maybe_prop.HasError()) {
switch (maybe_prop.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw QueryRuntimeException("Trying to get a property from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get a property from an object that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw QueryRuntimeException("Unexpected error when getting a property.");
case Error::DELETED_OBJECT:
throw ExpressionRuntimeException("Trying to get a property from a deleted object.");
case Error::NONEXISTENT_OBJECT:
throw ExpressionRuntimeException("Trying to get a property from an object that doesn't exist.");
case Error::SERIALIZATION_ERROR:
case Error::VERTEX_HAS_EDGES:
case Error::PROPERTIES_DISABLED:
case Error::VERTEX_ALREADY_INSERTED:
throw ExpressionRuntimeException("Unexpected error when getting a property.");
}
}
return *maybe_prop;
return conv_(*maybe_prop, ctx_->memory);
}
storage::v3::LabelId GetLabel(LabelIx label) { return ctx_->labels[label.ix]; }
LabelId GetLabel(LabelIx label) { return ctx_->labels[label.ix]; }
Frame *frame_;
Frame<TypedValue> *frame_;
const SymbolTable *symbol_table_;
const EvaluationContext *ctx_;
DbAccessor *dba_;
// which switching approach should be used when evaluating
storage::v3::View view_;
StorageView view_;
ConvFunctor conv_;
};
/// A helper function for evaluating an expression that's an int.
///
/// @param what - Name of what's getting evaluated. Used for user feedback (via
/// exception) when the evaluated value is not an int.
/// @throw QueryRuntimeException if expression doesn't evaluate to an int.
int64_t EvaluateInt(ExpressionEvaluator *evaluator, Expression *expr, const std::string &what);
/// @throw ExpressionRuntimeException if expression doesn't evaluate to an int.
template <typename ExpressionEvaluator>
int64_t EvaluateInt(ExpressionEvaluator *evaluator, Expression *expr, const std::string &what) {
TypedValue value = expr->Accept(*evaluator);
try {
return value.ValueInt();
} catch (TypedValueException &e) {
throw ExpressionRuntimeException(what + " must be an int");
}
}
std::optional<size_t> EvaluateMemoryLimit(ExpressionEvaluator *eval, Expression *memory_limit, size_t memory_scale);
template <typename ExpressionEvaluator>
std::optional<size_t> EvaluateMemoryLimit(ExpressionEvaluator *eval, Expression *memory_limit, size_t memory_scale) {
if (!memory_limit) return std::nullopt;
auto limit_value = memory_limit->Accept(*eval);
if (!limit_value.IsInt() || limit_value.ValueInt() <= 0)
throw ExpressionRuntimeException("Memory limit must be a non-negative integer.");
size_t limit = limit_value.ValueInt();
if (std::numeric_limits<size_t>::max() / memory_scale < limit)
throw ExpressionRuntimeException("Memory limit overflow.");
return limit * memory_scale;
}
} // namespace memgraph::query::v2
} // namespace memgraph::expr

View File

@@ -13,14 +13,14 @@
#include <vector>
#include "query/v2/frontend/semantic/symbol_table.hpp"
#include "query/v2/typed_value.hpp"
#include "expr/semantic/symbol_table.hpp"
#include "utils/logging.hpp"
#include "utils/memory.hpp"
#include "utils/pmr/vector.hpp"
namespace memgraph::query::v2 {
namespace memgraph::expr {
template <typename TypedValue>
class Frame {
public:
/// Create a Frame of given size backed by a utils::NewDeleteResource()
@@ -42,4 +42,4 @@ class Frame {
utils::pmr::vector<TypedValue> elems_;
};
} // namespace memgraph::query::v2
} // namespace memgraph::expr

View File

@@ -9,18 +9,18 @@
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/frontend/parsing.hpp"
#include "expr/parsing.hpp"
#include <cctype>
#include <codecvt>
#include <locale>
#include <stdexcept>
#include "query/v2/exceptions.hpp"
#include "expr/exceptions.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
namespace memgraph::query::v2::frontend {
namespace memgraph::expr {
int64_t ParseIntegerLiteral(const std::string &s) {
try {
@@ -181,4 +181,4 @@ std::string ParseParameter(const std::string &s) {
return out;
}
} // namespace memgraph::query::v2::frontend
} // namespace memgraph::expr

View File

@@ -15,7 +15,7 @@
#include <cstdint>
#include <string>
namespace memgraph::query::v2::frontend {
namespace memgraph::expr {
// These are the functions for parsing literals and parameter names from
// opencypher query.
@@ -24,4 +24,4 @@ std::string ParseStringLiteral(const std::string &s);
double ParseDoubleLiteral(const std::string &s);
std::string ParseParameter(const std::string &s);
} // namespace memgraph::query::v2::frontend
} // namespace memgraph::expr

View File

@@ -18,8 +18,7 @@
cpp<#
(lcp:namespace memgraph)
(lcp:namespace query)
(lcp:namespace v2)
(lcp:namespace expr)
(lcp:define-class symbol ()
((name "std::string" :scope :public)
@@ -66,16 +65,15 @@ cpp<#
cpp<#)
(:serialize (:slk)))
(lcp:pop-namespace) ;; v2
(lcp:pop-namespace) ;; query
(lcp:pop-namespace) ;; expr
(lcp:pop-namespace) ;; memgraph
#>cpp
namespace std {
template <>
struct hash<memgraph::query::v2::Symbol> {
size_t operator()(const memgraph::query::v2::Symbol &symbol) const {
struct hash<memgraph::expr::Symbol> {
size_t operator()(const memgraph::expr::Symbol &symbol) const {
size_t prime = 265443599u;
size_t hash = std::hash<int>{}(symbol.position());
hash ^= prime * std::hash<std::string>{}(symbol.name());

View File

@@ -0,0 +1,712 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
// Copyright 2017 Memgraph
//
// Created by Teon Banek on 11-03-2017
#pragma once
#include <algorithm>
#include <optional>
#include <ranges>
#include <unordered_map>
#include <unordered_set>
#include <variant>
#include <vector>
#include "expr/ast.hpp"
#include "expr/ast/ast_visitor.hpp"
#include "expr/exceptions.hpp"
#include "expr/semantic/symbol_table.hpp"
namespace memgraph::expr {
namespace detail {
inline std::unordered_map<std::string, Identifier *> GeneratePredefinedIdentifierMap(
const std::vector<Identifier *> &predefined_identifiers) {
std::unordered_map<std::string, Identifier *> identifier_map;
for (const auto &identifier : predefined_identifiers) {
identifier_map.emplace(identifier->name_, identifier);
}
return identifier_map;
}
} // namespace detail
/// Visits the AST and generates symbols for variables.
///
/// During the process of symbol generation, simple semantic checks are
/// performed. Such as, redeclaring a variable or conflicting expectations of
/// variable types.
class SymbolGenerator : public HierarchicalTreeVisitor {
public:
explicit SymbolGenerator(SymbolTable *symbol_table, const std::vector<Identifier *> &predefined_identifiers)
: symbol_table_(symbol_table),
predefined_identifiers_{detail::GeneratePredefinedIdentifierMap(predefined_identifiers)},
scopes_(1, Scope()) {}
using HierarchicalTreeVisitor::PostVisit;
using HierarchicalTreeVisitor::PreVisit;
using HierarchicalTreeVisitor::Visit;
using typename HierarchicalTreeVisitor::ReturnType;
// Query
bool PreVisit(SingleQuery & /*unused*/) override {
prev_return_names_ = curr_return_names_;
curr_return_names_.clear();
return true;
}
// Union
bool PreVisit(CypherUnion & /*unused*/) override {
scopes_.back() = Scope();
return true;
}
bool PostVisit(CypherUnion &cypher_union) override {
if (prev_return_names_ != curr_return_names_) {
throw SemanticException("All subqueries in an UNION must have the same column names.");
}
// create new symbols for the result of the union
for (const auto &name : curr_return_names_) {
auto symbol = CreateSymbol(name, false);
cypher_union.union_symbols_.push_back(symbol);
}
return true;
}
// Clauses
bool PreVisit(Create & /*unused*/) override {
scopes_.back().in_create = true;
return true;
}
bool PostVisit(Create & /*unused*/) override {
scopes_.back().in_create = false;
return true;
}
bool PreVisit(CallProcedure &call_proc) override {
for (auto *expr : call_proc.arguments_) {
expr->Accept(*this);
}
return false;
}
bool PostVisit(CallProcedure &call_proc) override {
for (auto *ident : call_proc.result_identifiers_) {
if (HasSymbolLocalScope(ident->name_)) {
throw RedeclareVariableError(ident->name_);
}
ident->MapTo(CreateSymbol(ident->name_, true));
}
return true;
}
bool PreVisit(LoadCsv & /*unused*/) override { return false; }
bool PostVisit(LoadCsv &load_csv) override {
if (HasSymbolLocalScope(load_csv.row_var_->name_)) {
throw RedeclareVariableError(load_csv.row_var_->name_);
}
load_csv.row_var_->MapTo(CreateSymbol(load_csv.row_var_->name_, true));
return true;
}
bool PreVisit(Return &ret) override {
auto &scope = scopes_.back();
scope.in_return = true;
VisitReturnBody(ret.body_);
scope.in_return = false;
return false; // We handled the traversal ourselves.
}
bool PostVisit(Return & /*unused*/) override {
for (const auto &name_symbol : scopes_.back().symbols) curr_return_names_.insert(name_symbol.first);
return true;
}
bool PreVisit(With &with) override {
auto &scope = scopes_.back();
scope.in_with = true;
VisitReturnBody(with.body_, with.where_);
scope.in_with = false;
return false; // We handled the traversal ourselves.
}
bool PreVisit(Where & /*unused*/) override {
scopes_.back().in_where = true;
return true;
}
bool PostVisit(Where & /*unused*/) override {
scopes_.back().in_where = false;
return true;
}
bool PreVisit(Merge & /*unused*/) override {
scopes_.back().in_merge = true;
return true;
}
bool PostVisit(Merge & /*unused*/) override {
scopes_.back().in_merge = false;
return true;
}
bool PostVisit(Unwind &unwind) override {
const auto &name = unwind.named_expression_->name_;
if (HasSymbolLocalScope(name)) {
throw RedeclareVariableError(name);
}
unwind.named_expression_->MapTo(CreateSymbol(name, true));
return true;
}
bool PreVisit(Match & /*unused*/) override {
scopes_.back().in_match = true;
return true;
}
bool PostVisit(Match & /*unused*/) override {
auto &scope = scopes_.back();
scope.in_match = false;
// Check variables in property maps after visiting Match, so that they can
// reference symbols out of bind order.
for (auto &ident : scope.identifiers_in_match) {
if (!HasSymbolLocalScope(ident->name_) && !ConsumePredefinedIdentifier(ident->name_))
throw UnboundVariableError(ident->name_);
ident->MapTo(scope.symbols[ident->name_]);
}
scope.identifiers_in_match.clear();
return true;
}
bool PreVisit(Foreach &for_each) override {
const auto &name = for_each.named_expression_->name_;
scopes_.emplace_back(Scope());
scopes_.back().in_foreach = true;
for_each.named_expression_->MapTo(
CreateSymbol(name, true, Symbol::Type::ANY, for_each.named_expression_->token_position_));
return true;
}
bool PostVisit(Foreach & /*unused*/) override {
scopes_.pop_back();
return true;
}
// Expressions
ReturnType Visit(Identifier &ident) override {
auto &scope = scopes_.back();
if (scope.in_skip || scope.in_limit) {
throw SemanticException("Variables are not allowed in {}.", scope.in_skip ? "SKIP" : "LIMIT");
}
Symbol symbol;
if (scope.in_pattern && !(scope.in_node_atom || scope.visiting_edge)) {
// If we are in the pattern, and outside of a node or an edge, the
// identifier is the pattern name.
symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, Symbol::Type::PATH);
} else if (scope.in_pattern && scope.in_pattern_atom_identifier) {
// Patterns used to create nodes and edges cannot redeclare already
// established bindings. Declaration only happens in single node
// patterns and in edge patterns. OpenCypher example,
// `MATCH (n) CREATE (n)` should throw an error that `n` is already
// declared. While `MATCH (n) CREATE (n) -[:R]-> (n)` is allowed,
// since `n` now references the bound node instead of declaring it.
if ((scope.in_create_node || scope.in_create_edge) && HasSymbolLocalScope(ident.name_)) {
throw RedeclareVariableError(ident.name_);
}
auto type = Symbol::Type::VERTEX;
if (scope.visiting_edge) {
// Edge referencing is not allowed (like in Neo4j):
// `MATCH (n) - [r] -> (n) - [r] -> (n) RETURN r` is not allowed.
if (HasSymbolLocalScope(ident.name_)) {
throw RedeclareVariableError(ident.name_);
}
type = scope.visiting_edge->IsVariable() ? Symbol::Type::EDGE_LIST : Symbol::Type::EDGE;
}
symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, type);
} else if (scope.in_pattern && !scope.in_pattern_atom_identifier && scope.in_match) {
if (scope.in_edge_range && scope.visiting_edge->identifier_->name_ == ident.name_) {
// Prevent variable path bounds to reference the identifier which is bound
// by the variable path itself.
throw UnboundVariableError(ident.name_);
}
// Variables in property maps or bounds of variable length path during MATCH
// can reference symbols bound later in the same MATCH. We collect them
// here, so that they can be checked after visiting Match.
scope.identifiers_in_match.emplace_back(&ident);
} else {
// Everything else references a bound symbol.
if (!HasSymbol(ident.name_) && !ConsumePredefinedIdentifier(ident.name_)) throw UnboundVariableError(ident.name_);
symbol = GetOrCreateSymbol(ident.name_, ident.user_declared_, Symbol::Type::ANY);
}
ident.MapTo(symbol);
return true;
}
ReturnType Visit(PrimitiveLiteral & /*unused*/) override { return true; }
ReturnType Visit(ParameterLookup & /*unused*/) override { return true; }
bool PreVisit(Aggregation &aggr) override {
auto &scope = scopes_.back();
// Check if the aggregation can be used in this context. This check should
// probably move to a separate phase, which checks if the query is well
// formed.
if ((!scope.in_return && !scope.in_with) || scope.in_order_by || scope.in_skip || scope.in_limit ||
scope.in_where) {
throw SemanticException("Aggregation functions are only allowed in WITH and RETURN.");
}
if (scope.in_aggregation) {
throw SemanticException(
"Using aggregation functions inside aggregation functions is not "
"allowed.");
}
if (scope.num_if_operators) {
// Neo allows aggregations here and produces very interesting behaviors.
// To simplify implementation at this moment we decided to completely
// disallow aggregations inside of the CASE.
// However, in some cases aggregation makes perfect sense, for example:
// CASE count(n) WHEN 10 THEN "YES" ELSE "NO" END.
// TODO: Rethink of allowing aggregations in some parts of the CASE
// construct.
throw SemanticException("Using aggregation functions inside of CASE is not allowed.");
}
// Create a virtual symbol for aggregation result.
// Currently, we only have aggregation operators which return numbers.
auto aggr_name = Aggregation::OpToString(aggr.op_) + std::to_string(aggr.symbol_pos_);
aggr.MapTo(CreateSymbol(aggr_name, false, Symbol::Type::NUMBER));
scope.in_aggregation = true;
scope.has_aggregation = true;
return true;
}
bool PostVisit(Aggregation & /*unused*/) override {
scopes_.back().in_aggregation = false;
return true;
}
bool PreVisit(IfOperator & /*unused*/) override {
++scopes_.back().num_if_operators;
return true;
}
bool PostVisit(IfOperator & /*unused*/) override {
--scopes_.back().num_if_operators;
return true;
}
bool PreVisit(All &all) override {
all.list_expression_->Accept(*this);
VisitWithIdentifiers(all.where_->expression_, {all.identifier_});
return false;
}
bool PreVisit(Single &single) override {
single.list_expression_->Accept(*this);
VisitWithIdentifiers(single.where_->expression_, {single.identifier_});
return false;
}
bool PreVisit(Any &any) override {
any.list_expression_->Accept(*this);
VisitWithIdentifiers(any.where_->expression_, {any.identifier_});
return false;
}
bool PreVisit(None &none) override {
none.list_expression_->Accept(*this);
VisitWithIdentifiers(none.where_->expression_, {none.identifier_});
return false;
}
bool PreVisit(Reduce &reduce) override {
reduce.initializer_->Accept(*this);
reduce.list_->Accept(*this);
VisitWithIdentifiers(reduce.expression_, {reduce.accumulator_, reduce.identifier_});
return false;
}
bool PreVisit(Extract &extract) override {
extract.list_->Accept(*this);
VisitWithIdentifiers(extract.expression_, {extract.identifier_});
return false;
}
// Pattern and its subparts.
bool PreVisit(Pattern &pattern) override {
auto &scope = scopes_.back();
scope.in_pattern = true;
if ((scope.in_create || scope.in_merge) && pattern.atoms_.size() == 1U) {
MG_ASSERT(utils::IsSubtype(*pattern.atoms_[0], NodeAtom::kType), "Expected a single NodeAtom in Pattern");
scope.in_create_node = true;
}
return true;
}
bool PostVisit(Pattern & /*unused*/) override {
auto &scope = scopes_.back();
scope.in_pattern = false;
scope.in_create_node = false;
return true;
}
bool PreVisit(NodeAtom &node_atom) override {
auto &scope = scopes_.back();
auto check_node_semantic = [&node_atom, &scope, this](const bool props_or_labels) {
const auto &node_name = node_atom.identifier_->name_;
if ((scope.in_create || scope.in_merge) && props_or_labels && HasSymbolLocalScope(node_name)) {
throw SemanticException("Cannot create node '" + node_name +
"' with labels or properties, because it is already declared.");
}
scope.in_pattern_atom_identifier = true;
node_atom.identifier_->Accept(*this);
scope.in_pattern_atom_identifier = false;
};
scope.in_node_atom = true;
if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&node_atom.properties_)) {
bool props_or_labels = !properties->empty() || !node_atom.labels_.empty();
check_node_semantic(props_or_labels);
for (auto kv : *properties) {
kv.second->Accept(*this);
}
return false;
}
auto &properties_parameter = std::get<ParameterLookup *>(node_atom.properties_);
bool props_or_labels = !properties_parameter || !node_atom.labels_.empty();
check_node_semantic(props_or_labels);
properties_parameter->Accept(*this);
return false;
}
bool PostVisit(NodeAtom & /*unused*/) override {
scopes_.back().in_node_atom = false;
return true;
}
bool PreVisit(EdgeAtom &edge_atom) override {
auto &scope = scopes_.back();
scope.visiting_edge = &edge_atom;
if (scope.in_create || scope.in_merge) {
scope.in_create_edge = true;
if (edge_atom.edge_types_.size() != 1U) {
throw SemanticException(
"A single relationship type must be specified "
"when creating an edge.");
}
if (scope.in_create && // Merge allows bidirectionality
edge_atom.direction_ == EdgeAtom::Direction::BOTH) {
throw SemanticException(
"Bidirectional relationship are not supported "
"when creating an edge");
}
if (edge_atom.IsVariable()) {
throw SemanticException(
"Variable length relationships are not supported when creating an "
"edge.");
}
}
if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&edge_atom.properties_)) {
for (auto kv : *properties) {
kv.second->Accept(*this);
}
} else {
std::get<ParameterLookup *>(edge_atom.properties_)->Accept(*this);
}
if (edge_atom.IsVariable()) {
scope.in_edge_range = true;
if (edge_atom.lower_bound_) {
edge_atom.lower_bound_->Accept(*this);
}
if (edge_atom.upper_bound_) {
edge_atom.upper_bound_->Accept(*this);
}
scope.in_edge_range = false;
scope.in_pattern = false;
if (edge_atom.filter_lambda_.expression) {
VisitWithIdentifiers(edge_atom.filter_lambda_.expression,
{edge_atom.filter_lambda_.inner_edge, edge_atom.filter_lambda_.inner_node});
} else {
// Create inner symbols, but don't bind them in scope, since they are to
// be used in the missing filter expression.
auto *inner_edge = edge_atom.filter_lambda_.inner_edge;
inner_edge->MapTo(
symbol_table_->CreateSymbol(inner_edge->name_, inner_edge->user_declared_, Symbol::Type::EDGE));
auto *inner_node = edge_atom.filter_lambda_.inner_node;
inner_node->MapTo(
symbol_table_->CreateSymbol(inner_node->name_, inner_node->user_declared_, Symbol::Type::VERTEX));
}
if (edge_atom.weight_lambda_.expression) {
VisitWithIdentifiers(edge_atom.weight_lambda_.expression,
{edge_atom.weight_lambda_.inner_edge, edge_atom.weight_lambda_.inner_node});
}
scope.in_pattern = true;
}
scope.in_pattern_atom_identifier = true;
edge_atom.identifier_->Accept(*this);
scope.in_pattern_atom_identifier = false;
if (edge_atom.total_weight_) {
if (HasSymbolLocalScope(edge_atom.total_weight_->name_)) {
throw RedeclareVariableError(edge_atom.total_weight_->name_);
}
edge_atom.total_weight_->MapTo(GetOrCreateSymbolLocalScope(
edge_atom.total_weight_->name_, edge_atom.total_weight_->user_declared_, Symbol::Type::NUMBER));
}
return false;
}
bool PostVisit(EdgeAtom & /*unused*/) override {
auto &scope = scopes_.back();
scope.visiting_edge = nullptr;
scope.in_create_edge = false;
return true;
}
private:
// Scope stores the state of where we are when visiting the AST and a map of
// names to symbols.
struct Scope {
bool in_pattern{false};
bool in_merge{false};
bool in_create{false};
// in_create_node is true if we are creating or merging *only* a node.
// Therefore, it is *not* equivalent to (in_create || in_merge) &&
// in_node_atom.
bool in_create_node{false};
// True if creating an edge;
// shortcut for (in_create || in_merge) && visiting_edge.
bool in_create_edge{false};
bool in_node_atom{false};
EdgeAtom *visiting_edge{nullptr};
bool in_aggregation{false};
bool in_return{false};
bool in_with{false};
bool in_skip{false};
bool in_limit{false};
bool in_order_by{false};
bool in_where{false};
bool in_match{false};
bool in_foreach{false};
// True when visiting a pattern atom (node or edge) identifier, which can be
// reused or created in the pattern itself.
bool in_pattern_atom_identifier{false};
// True when visiting range bounds of a variable path.
bool in_edge_range{false};
// True if the return/with contains an aggregation in any named expression.
bool has_aggregation{false};
// Map from variable names to symbols.
std::map<std::string, Symbol> symbols;
// Identifiers found in property maps of patterns or as variable length path
// bounds in a single Match clause. They need to be checked after visiting
// Match. Identifiers created by naming vertices, edges and paths are *not*
// stored in here.
std::vector<Identifier *> identifiers_in_match;
// Number of nested IfOperators.
int num_if_operators{0};
};
inline static std::optional<Symbol> FindSymbolInScope(const std::string &name, const Scope &scope,
Symbol::Type type) {
if (auto it = scope.symbols.find(name); it != scope.symbols.end()) {
const auto &symbol = it->second;
// Unless we have `ANY` type, check that types match.
if (type != Symbol::Type::ANY && symbol.type() != Symbol::Type::ANY && type != symbol.type()) {
throw TypeMismatchError(name, Symbol::TypeToString(symbol.type()), Symbol::TypeToString(type));
}
return symbol;
}
return std::nullopt;
}
bool HasSymbol(const std::string &name) const {
return std::ranges::any_of(scopes_, [&name](const auto &scope) { return scope.symbols.contains(name); });
}
bool HasSymbolLocalScope(const std::string &name) const { return scopes_.back().symbols.contains(name); }
// @return true if it added a predefined identifier with that name
bool ConsumePredefinedIdentifier(const std::string &name) {
auto it = predefined_identifiers_.find(name);
if (it == predefined_identifiers_.end()) {
return false;
}
// we can only use the predefined identifier in a single scope so we remove it after creating
// a symbol for it
auto &identifier = it->second;
MG_ASSERT(!identifier->user_declared_, "Predefined symbols cannot be user declared!");
identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
predefined_identifiers_.erase(it);
return true;
}
// Returns a freshly generated symbol. Previous mapping of the same name to a
// different symbol is replaced with the new one.
Symbol CreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY,
int token_position = -1) {
auto symbol = symbol_table_->CreateSymbol(name, user_declared, type, token_position);
scopes_.back().symbols[name] = symbol;
return symbol;
}
Symbol GetOrCreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY) {
// NOLINTNEXTLINE
for (auto scope = scopes_.rbegin(); scope != scopes_.rend(); ++scope) {
if (auto maybe_symbol = FindSymbolInScope(name, *scope, type); maybe_symbol) {
return *maybe_symbol;
}
}
return CreateSymbol(name, user_declared, type);
}
// Returns the symbol by name. If the mapping already exists, checks if the
// types match. Otherwise, returns a new symbol.
Symbol GetOrCreateSymbolLocalScope(const std::string &name, bool user_declared,
Symbol::Type type = Symbol::Type::ANY) {
auto &scope = scopes_.back();
if (auto maybe_symbol = FindSymbolInScope(name, scope, type); maybe_symbol) {
return *maybe_symbol;
}
return CreateSymbol(name, user_declared, type);
}
void VisitReturnBody(ReturnBody &body, Where *where = nullptr) {
auto &scope = scopes_.back();
for (auto &expr : body.named_expressions) {
expr->Accept(*this);
}
std::vector<Symbol> user_symbols;
if (body.all_identifiers) {
// Carry over user symbols because '*' appeared.
for (const auto &sym_pair : scope.symbols) {
if (!sym_pair.second.user_declared()) {
continue;
}
user_symbols.emplace_back(sym_pair.second);
}
if (user_symbols.empty()) {
throw SemanticException("There are no variables in scope to use for '*'.");
}
}
// WITH/RETURN clause removes declarations of all the previous variables and
// declares only those established through named expressions. New declarations
// must not be visible inside named expressions themselves.
bool removed_old_names = false;
if ((!where && body.order_by.empty()) || scope.has_aggregation) {
// WHERE and ORDER BY need to see both the old and new symbols, unless we
// have an aggregation. Therefore, we can clear the symbols immediately if
// there is neither ORDER BY nor WHERE, or we have an aggregation.
scope.symbols.clear();
removed_old_names = true;
}
// Create symbols for named expressions.
std::unordered_set<std::string> new_names;
for (const auto &user_sym : user_symbols) {
new_names.insert(user_sym.name());
scope.symbols[user_sym.name()] = user_sym;
}
for (auto &named_expr : body.named_expressions) {
const auto &name = named_expr->name_;
if (!new_names.insert(name).second) {
throw SemanticException("Multiple results with the same name '{}' are not allowed.", name);
}
// An improvement would be to infer the type of the expression, so that the
// new symbol would have a more specific type.
named_expr->MapTo(CreateSymbol(name, true, Symbol::Type::ANY, named_expr->token_position_));
}
scope.in_order_by = true;
for (const auto &order_pair : body.order_by) {
order_pair.expression->Accept(*this);
}
scope.in_order_by = false;
if (body.skip) {
scope.in_skip = true;
body.skip->Accept(*this);
scope.in_skip = false;
}
if (body.limit) {
scope.in_limit = true;
body.limit->Accept(*this);
scope.in_limit = false;
}
if (where) where->Accept(*this);
if (!removed_old_names) {
// We have an ORDER BY or WHERE, but no aggregation, which means we didn't
// clear the old symbols, so do it now. We cannot just call clear, because
// we've added new symbols.
for (auto sym_it = scope.symbols.begin(); sym_it != scope.symbols.end();) {
if (new_names.find(sym_it->first) == new_names.end()) {
sym_it = scope.symbols.erase(sym_it);
} else {
sym_it++;
}
}
}
scopes_.back().has_aggregation = false;
}
void VisitWithIdentifiers(Expression *expr, const std::vector<Identifier *> &identifiers) {
auto &scope = scopes_.back();
std::vector<std::pair<std::optional<Symbol>, Identifier *>> prev_symbols;
// Collect previous symbols if they exist.
for (const auto &identifier : identifiers) {
std::optional<Symbol> prev_symbol;
auto prev_symbol_it = scope.symbols.find(identifier->name_);
if (prev_symbol_it != scope.symbols.end()) {
prev_symbol = prev_symbol_it->second;
}
identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
prev_symbols.emplace_back(prev_symbol, identifier);
}
// Visit the expression with the new symbols bound.
expr->Accept(*this);
// Restore back to previous symbols.
for (const auto &prev : prev_symbols) {
const auto &prev_symbol = prev.first;
const auto &identifier = prev.second;
if (prev_symbol) {
scope.symbols[identifier->name_] = *prev_symbol;
} else {
scope.symbols.erase(identifier->name_);
}
}
}
SymbolTable *symbol_table_;
// Identifiers which are injected from outside the query. Each identifier
// is mapped by its name.
std::unordered_map<std::string, Identifier *> predefined_identifiers_;
std::vector<Scope> scopes_;
std::unordered_set<std::string> prev_return_names_;
std::unordered_set<std::string> curr_return_names_;
};
inline SymbolTable MakeSymbolTable(CypherQuery *query, const std::vector<Identifier *> &predefined_identifiers = {}) {
SymbolTable symbol_table;
SymbolGenerator symbol_generator(&symbol_table, predefined_identifiers);
query->single_query_->Accept(symbol_generator);
for (auto *cypher_union : query->cypher_unions_) {
cypher_union->Accept(symbol_generator);
}
return symbol_table;
}
} // namespace memgraph::expr

View File

@@ -14,11 +14,11 @@
#include <map>
#include <string>
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/frontend/semantic/symbol.hpp"
#include "expr/ast.hpp"
#include "expr/semantic/symbol.hpp"
#include "utils/logging.hpp"
namespace memgraph::query::v2 {
namespace memgraph::expr {
class SymbolTable final {
public:
@@ -61,4 +61,4 @@ class SymbolTable final {
std::map<int32_t, Symbol> table_;
};
} // namespace memgraph::query::v2
} // namespace memgraph::expr

1505
src/expr/typed_value.hpp Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -13,11 +13,14 @@
#include "utils/exceptions.hpp"
namespace memgraph::storage::v3::durability {
/// Exception used to handle errors during recovery.
class RecoveryFailure : public utils::BasicException {
namespace memgraph::expr {
/**
* An exception raised by the TypedValue system. Typically when
* trying to perform operations (such as addition) on TypedValues
* of incompatible Types.
*/
class TypedValueException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
};
} // namespace memgraph::storage::v3::durability
} // namespace memgraph::expr

View File

@@ -15,9 +15,17 @@
#include <string>
#include <vector>
#include "coordinator/shard_map.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/requests.hpp"
#include "query/v2/shard_request_manager.hpp"
#include "storage/v3/edge_accessor.hpp"
#include "storage/v3/storage.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/shard.hpp"
#include "storage/v3/vertex_accessor.hpp"
#include "storage/v3/view.hpp"
#include "utils/exceptions.hpp"
#include "utils/temporal.hpp"
using memgraph::communication::bolt::Value;
@@ -63,17 +71,52 @@ query::v2::TypedValue ToTypedValue(const Value &value) {
}
}
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const query::v2::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view) {
return ToBoltVertex(vertex.impl_, db, view);
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(
const query::v2::accessors::VertexAccessor &vertex, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View /*view*/) {
auto id = communication::bolt::Id::FromUint(0);
auto labels = vertex.Labels();
std::vector<std::string> new_labels;
new_labels.reserve(labels.size());
for (const auto &label : labels) {
new_labels.push_back(shard_request_manager->LabelToName(label.id));
}
auto properties = vertex.Properties();
std::map<std::string, Value> new_properties;
for (const auto &[prop, property_value] : properties) {
new_properties[shard_request_manager->PropertyToName(prop)] = ToBoltValue(property_value);
}
return communication::bolt::Vertex{id, new_labels, new_properties};
}
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const query::v2::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view) {
return ToBoltEdge(edge.impl_, db, view);
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(
const query::v2::accessors::EdgeAccessor &edge, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View /*view*/) {
// TODO(jbajic) Fix bolt communication
auto id = communication::bolt::Id::FromUint(0);
auto from = communication::bolt::Id::FromUint(0);
auto to = communication::bolt::Id::FromUint(0);
const auto &type = shard_request_manager->EdgeTypeToName(edge.EdgeType());
auto properties = edge.Properties();
std::map<std::string, Value> new_properties;
for (const auto &[prop, property_value] : properties) {
new_properties[shard_request_manager->PropertyToName(prop)] = ToBoltValue(property_value);
}
return communication::bolt::Edge{id, from, to, type, new_properties};
}
storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value, const storage::v3::Storage &db,
storage::v3::Result<communication::bolt::Path> ToBoltPath(
const query::v2::accessors::Path & /*edge*/, const msgs::ShardRequestManagerInterface * /*shard_request_manager*/,
storage::v3::View /*view*/) {
// TODO(jbajic) Fix bolt communication
return {storage::v3::Error::DELETED_OBJECT};
}
storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value,
const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view) {
switch (value.type()) {
case query::v2::TypedValue::Type::Null:
@@ -90,7 +133,7 @@ storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value, const
std::vector<Value> values;
values.reserve(value.ValueList().size());
for (const auto &v : value.ValueList()) {
auto maybe_value = ToBoltValue(v, db, view);
auto maybe_value = ToBoltValue(v, shard_request_manager, view);
if (maybe_value.HasError()) return maybe_value.GetError();
values.emplace_back(std::move(*maybe_value));
}
@@ -99,24 +142,24 @@ storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value, const
case query::v2::TypedValue::Type::Map: {
std::map<std::string, Value> map;
for (const auto &kv : value.ValueMap()) {
auto maybe_value = ToBoltValue(kv.second, db, view);
auto maybe_value = ToBoltValue(kv.second, shard_request_manager, view);
if (maybe_value.HasError()) return maybe_value.GetError();
map.emplace(kv.first, std::move(*maybe_value));
}
return Value(std::move(map));
}
case query::v2::TypedValue::Type::Vertex: {
auto maybe_vertex = ToBoltVertex(value.ValueVertex(), db, view);
auto maybe_vertex = ToBoltVertex(value.ValueVertex(), shard_request_manager, view);
if (maybe_vertex.HasError()) return maybe_vertex.GetError();
return Value(std::move(*maybe_vertex));
}
case query::v2::TypedValue::Type::Edge: {
auto maybe_edge = ToBoltEdge(value.ValueEdge(), db, view);
auto maybe_edge = ToBoltEdge(value.ValueEdge(), shard_request_manager, view);
if (maybe_edge.HasError()) return maybe_edge.GetError();
return Value(std::move(*maybe_edge));
}
case query::v2::TypedValue::Type::Path: {
auto maybe_path = ToBoltPath(value.ValuePath(), db, view);
auto maybe_path = ToBoltPath(value.ValuePath(), shard_request_manager, view);
if (maybe_path.HasError()) return maybe_path.GetError();
return Value(std::move(*maybe_path));
}
@@ -131,57 +174,41 @@ storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value, const
}
}
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const storage::v3::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view) {
auto id = communication::bolt::Id::FromUint(vertex.Gid().AsUint());
auto maybe_labels = vertex.Labels(view);
if (maybe_labels.HasError()) return maybe_labels.GetError();
std::vector<std::string> labels;
labels.reserve(maybe_labels->size());
for (const auto &label : *maybe_labels) {
labels.push_back(db.LabelToName(label));
Value ToBoltValue(msgs::Value value) {
switch (value.type) {
case msgs::Value::Type::Null:
return {};
case msgs::Value::Type::Bool:
return {value.bool_v};
case msgs::Value::Type::Int64:
return {value.int_v};
case msgs::Value::Type::Double:
return {value.double_v};
case msgs::Value::Type::String:
return {std::string(value.string_v)};
case msgs::Value::Type::List: {
std::vector<Value> values;
values.reserve(value.list_v.size());
for (const auto &v : value.list_v) {
auto maybe_value = ToBoltValue(v);
values.emplace_back(std::move(maybe_value));
}
return Value{std::move(values)};
}
case msgs::Value::Type::Map: {
std::map<std::string, Value> map;
for (const auto &kv : value.map_v) {
auto maybe_value = ToBoltValue(kv.second);
map.emplace(kv.first, std::move(maybe_value));
}
return Value{std::move(map)};
}
case msgs::Value::Type::Vertex:
case msgs::Value::Type::Edge: {
throw utils::BasicException("Vertex and Edge not supported!");
}
// TODO Value to Date types not supported
}
auto maybe_properties = vertex.Properties(view);
if (maybe_properties.HasError()) return maybe_properties.GetError();
std::map<std::string, Value> properties;
for (const auto &prop : *maybe_properties) {
properties[db.PropertyToName(prop.first)] = ToBoltValue(prop.second);
}
return communication::bolt::Vertex{id, labels, properties};
}
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const storage::v3::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view) {
auto id = communication::bolt::Id::FromUint(edge.Gid().AsUint());
auto from = communication::bolt::Id::FromUint(edge.FromVertex().Gid().AsUint());
auto to = communication::bolt::Id::FromUint(edge.ToVertex().Gid().AsUint());
const auto &type = db.EdgeTypeToName(edge.EdgeType());
auto maybe_properties = edge.Properties(view);
if (maybe_properties.HasError()) return maybe_properties.GetError();
std::map<std::string, Value> properties;
for (const auto &prop : *maybe_properties) {
properties[db.PropertyToName(prop.first)] = ToBoltValue(prop.second);
}
return communication::bolt::Edge{id, from, to, type, properties};
}
storage::v3::Result<communication::bolt::Path> ToBoltPath(const query::v2::Path &path, const storage::v3::Storage &db,
storage::v3::View view) {
std::vector<communication::bolt::Vertex> vertices;
vertices.reserve(path.vertices().size());
for (const auto &v : path.vertices()) {
auto maybe_vertex = ToBoltVertex(v, db, view);
if (maybe_vertex.HasError()) return maybe_vertex.GetError();
vertices.emplace_back(std::move(*maybe_vertex));
}
std::vector<communication::bolt::Edge> edges;
edges.reserve(path.edges().size());
for (const auto &e : path.edges()) {
auto maybe_edge = ToBoltEdge(e, db, view);
if (maybe_edge.HasError()) return maybe_edge.GetError();
edges.emplace_back(std::move(*maybe_edge));
}
return communication::bolt::Path(vertices, edges);
}
storage::v3::PropertyValue ToPropertyValue(const Value &value) {

View File

@@ -13,9 +13,12 @@
#pragma once
#include "communication/bolt/v1/value.hpp"
#include "query/v2/typed_value.hpp"
#include "coordinator/shard_map.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/shard_request_manager.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/shard.hpp"
#include "storage/v3/view.hpp"
namespace memgraph::storage::v3 {
@@ -28,36 +31,40 @@ namespace memgraph::glue::v2 {
/// @param storage::v3::VertexAccessor for converting to
/// communication::bolt::Vertex.
/// @param storage::v3::Storage for getting label and property names.
/// @param msgs::ShardRequestManagerInterface *shard_request_manager getting label and property names.
/// @param storage::v3::View for deciding which vertex attributes are visible.
///
/// @throw std::bad_alloc
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const storage::v3::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view);
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(
const storage::v3::VertexAccessor &vertex, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view);
/// @param storage::v3::EdgeAccessor for converting to communication::bolt::Edge.
/// @param storage::v3::Storage for getting edge type and property names.
/// @param msgs::ShardRequestManagerInterface *shard_request_manager getting edge type and property names.
/// @param storage::v3::View for deciding which edge attributes are visible.
///
/// @throw std::bad_alloc
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const storage::v3::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view);
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(
const storage::v3::EdgeAccessor &edge, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view);
/// @param query::v2::Path for converting to communication::bolt::Path.
/// @param storage::v3::Storage for ToBoltVertex and ToBoltEdge.
/// @param msgs::ShardRequestManagerInterface *shard_request_manager ToBoltVertex and ToBoltEdge.
/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
///
/// @throw std::bad_alloc
storage::v3::Result<communication::bolt::Path> ToBoltPath(const query::v2::Path &path, const storage::v3::Storage &db,
storage::v3::View view);
storage::v3::Result<communication::bolt::Path> ToBoltPath(
const query::v2::accessors::Path &path, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view);
/// @param query::v2::TypedValue for converting to communication::bolt::Value.
/// @param storage::v3::Storage for ToBoltVertex and ToBoltEdge.
/// @param msgs::ShardRequestManagerInterface *shard_request_manager ToBoltVertex and ToBoltEdge.
/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
///
/// @throw std::bad_alloc
storage::v3::Result<communication::bolt::Value> ToBoltValue(const query::v2::TypedValue &value,
const storage::v3::Storage &db, storage::v3::View view);
storage::v3::Result<communication::bolt::Value> ToBoltValue(
const query::v2::TypedValue &value, const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view);
query::v2::TypedValue ToTypedValue(const communication::bolt::Value &value);
@@ -65,4 +72,10 @@ communication::bolt::Value ToBoltValue(const storage::v3::PropertyValue &value);
storage::v3::PropertyValue ToPropertyValue(const communication::bolt::Value &value);
communication::bolt::Value ToBoltValue(msgs::Value value);
communication::bolt::Value ToBoltValue(msgs::Value value,
const msgs::ShardRequestManagerInterface *shard_request_manager,
storage::v3::View view);
} // namespace memgraph::glue::v2

View File

@@ -15,10 +15,36 @@
#include <fmt/format.h>
#include <boost/asio/ip/tcp.hpp>
#include <boost/functional/hash.hpp>
#include <boost/uuid/uuid.hpp>
#include <boost/uuid/uuid_generators.hpp>
#include <boost/uuid/uuid_io.hpp>
namespace memgraph::io {
struct PartialAddress {
boost::asio::ip::address ip;
uint16_t port;
friend bool operator==(const PartialAddress &lhs, const PartialAddress &rhs) = default;
/// unique_id is most dominant for ordering, then ip, then port
friend bool operator<(const PartialAddress &lhs, const PartialAddress &rhs) {
if (lhs.ip != rhs.ip) {
return lhs.ip < rhs.ip;
}
return lhs.port < rhs.port;
}
std::string ToString() const { return fmt::format("PartialAddress {{ ip: {}, port: {} }}", ip.to_string(), port); }
friend std::ostream &operator<<(std::ostream &in, const PartialAddress &partial_address) {
in << partial_address.ToString();
return in;
}
};
struct Address {
// It's important for all participants to have a
// unique identifier - IP and port alone are not
@@ -32,9 +58,32 @@ struct Address {
uint16_t last_known_port;
static Address TestAddress(uint16_t port) {
Address ret;
ret.last_known_port = port;
return ret;
return Address{
.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
.last_known_port = port,
};
}
static Address UniqueLocalAddress() {
return Address{
.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
};
}
/// Returns a new ID with the same IP and port but a unique UUID.
Address ForkUniqueAddress() {
return Address{
.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
.last_known_ip = last_known_ip,
.last_known_port = last_known_port,
};
}
PartialAddress ToPartialAddress() const {
return PartialAddress{
.ip = last_known_ip,
.port = last_known_port,
};
}
friend bool operator==(const Address &lhs, const Address &rhs) = default;
@@ -56,5 +105,36 @@ struct Address {
return fmt::format("Address {{ unique_id: {}, last_known_ip: {}, last_known_port: {} }}",
boost::uuids::to_string(unique_id), last_known_ip.to_string(), last_known_port);
}
friend std::ostream &operator<<(std::ostream &in, const Address &address) {
in << address.ToString();
return in;
}
};
}; // namespace memgraph::io
namespace std {
template <>
struct hash<memgraph::io::PartialAddress> {
size_t operator()(const memgraph::io::PartialAddress &pa) const {
using boost::hash_combine;
using boost::hash_value;
// Start with a hash value of 0 .
std::size_t seed = 0;
if (pa.ip.is_v4()) {
auto h = std::hash<boost::asio::ip::address_v4>()(pa.ip.to_v4());
hash_combine(seed, h);
} else {
auto h = std::hash<boost::asio::ip::address_v6>()(pa.ip.to_v6());
hash_combine(seed, h);
}
hash_combine(seed, hash_value(pa.port));
// Return the result.
return seed;
}
};
} // namespace std

View File

@@ -99,7 +99,7 @@ class Shared {
bool IsReady() const {
std::unique_lock<std::mutex> lock(mu_);
return item_;
return item_.has_value();
}
std::optional<T> TryGet() {
@@ -151,7 +151,9 @@ class Future {
Future &operator=(Future &&old) noexcept {
MG_ASSERT(!old.consumed_or_moved_, "Future moved from after already being moved from or consumed.");
shared_ = std::move(old.shared_);
consumed_or_moved_ = old.consumed_or_moved_;
old.consumed_or_moved_ = true;
return *this;
}
Future(const Future &) = delete;
@@ -198,7 +200,7 @@ class Future {
template <typename T>
class Promise {
std::shared_ptr<details::Shared<T>> shared_;
bool filled_or_moved_ = false;
bool filled_or_moved_{false};
public:
explicit Promise(std::shared_ptr<details::Shared<T>> shared) : shared_(shared) {}
@@ -218,6 +220,7 @@ class Promise {
Promise(const Promise &) = delete;
Promise &operator=(const Promise &) = delete;
// NOLINTNEXTLINE(clang-analyzer-core.uninitialized.Branch)
~Promise() { MG_ASSERT(filled_or_moved_, "Promise destroyed before its associated Future was filled!"); }
// Fill the expected item into the Future.

View File

@@ -0,0 +1,35 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <random>
#include "io/address.hpp"
#include "io/local_transport/local_transport.hpp"
#include "io/local_transport/local_transport_handle.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalSystem {
std::shared_ptr<LocalTransportHandle> local_transport_handle_ = std::make_shared<LocalTransportHandle>();
public:
Io<LocalTransport> Register(Address address) {
LocalTransport local_transport(local_transport_handle_);
return Io{local_transport, address};
}
void ShutDown() { local_transport_handle_->ShutDown(); }
};
} // namespace memgraph::io::local_transport

View File

@@ -0,0 +1,61 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <memory>
#include <random>
#include <utility>
#include "io/address.hpp"
#include "io/local_transport/local_transport_handle.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalTransport {
std::shared_ptr<LocalTransportHandle> local_transport_handle_;
public:
explicit LocalTransport(std::shared_ptr<LocalTransportHandle> local_transport_handle)
: local_transport_handle_(std::move(local_transport_handle)) {}
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, Address from_address, RequestT request, Duration timeout) {
return local_transport_handle_->template SubmitRequest<RequestT, ResponseT>(to_address, from_address,
std::move(request), timeout);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address receiver_address, Duration timeout) {
return local_transport_handle_->template Receive<Ms...>(receiver_address, timeout);
}
template <Message M>
void Send(Address to_address, Address from_address, RequestId request_id, M &&message) {
return local_transport_handle_->template Send<M>(to_address, from_address, request_id, std::forward<M>(message));
}
Time Now() const { return local_transport_handle_->Now(); }
bool ShouldShutDown() const { return local_transport_handle_->ShouldShutDown(); }
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
std::random_device rng;
return distrib(rng);
}
LatencyHistogramSummaries ResponseLatencies() { return local_transport_handle_->ResponseLatencies(); }
};
}; // namespace memgraph::io::local_transport

View File

@@ -0,0 +1,173 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <condition_variable>
#include <iostream>
#include <map>
#include <mutex>
#include "io/errors.hpp"
#include "io/message_conversion.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalTransportHandle {
mutable std::mutex mu_{};
mutable std::condition_variable cv_;
bool should_shut_down_ = false;
MessageHistogramCollector histograms_;
RequestId request_id_counter_ = 0;
// the responses to requests that are being waited on
std::map<PromiseKey, DeadlineAndOpaquePromise> promises_;
// messages that are sent to servers that may later receive them
std::vector<OpaqueMessage> can_receive_;
public:
~LocalTransportHandle() {
for (auto &&[pk, promise] : promises_) {
std::move(promise.promise).TimeOut();
}
promises_.clear();
}
void ShutDown() {
std::unique_lock<std::mutex> lock(mu_);
should_shut_down_ = true;
cv_.notify_all();
}
bool ShouldShutDown() const {
std::unique_lock<std::mutex> lock(mu_);
return should_shut_down_;
}
LatencyHistogramSummaries ResponseLatencies() {
std::unique_lock<std::mutex> lock(mu_);
return histograms_.ResponseLatencies();
}
static Time Now() {
auto nano_time = std::chrono::system_clock::now();
return std::chrono::time_point_cast<std::chrono::microseconds>(nano_time);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address /* receiver_address */, Duration timeout) {
std::unique_lock lock(mu_);
Time before = Now();
spdlog::info("can_receive_ size: {}", can_receive_.size());
while (can_receive_.empty()) {
Time now = Now();
// protection against non-monotonic timesources
auto maxed_now = std::max(now, before);
auto elapsed = maxed_now - before;
if (timeout < elapsed) {
return TimedOut{};
}
Duration relative_timeout = timeout - elapsed;
std::cv_status cv_status_value = cv_.wait_for(lock, relative_timeout);
if (cv_status_value == std::cv_status::timeout) {
return TimedOut{};
}
}
auto current_message = std::move(can_receive_.back());
can_receive_.pop_back();
auto m_opt = std::move(current_message).Take<Ms...>();
return std::move(m_opt).value();
}
template <Message M>
void Send(Address to_address, Address from_address, RequestId request_id, M &&message) {
auto type_info = TypeInfoFor(message);
std::any message_any(std::forward<M>(message));
OpaqueMessage opaque_message{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message_any),
.type_info = type_info};
PromiseKey promise_key{.requester_address = to_address, .request_id = opaque_message.request_id};
{
std::unique_lock<std::mutex> lock(mu_);
if (promises_.contains(promise_key)) {
spdlog::info("using message to fill promise");
// complete waiting promise if it's there
DeadlineAndOpaquePromise dop = std::move(promises_.at(promise_key));
promises_.erase(promise_key);
Duration response_latency = Now() - dop.requested_at;
dop.promise.Fill(std::move(opaque_message), response_latency);
histograms_.Measure(type_info, response_latency);
} else {
spdlog::info("placing message in can_receive_");
can_receive_.emplace_back(std::move(opaque_message));
}
} // lock dropped
cv_.notify_all();
}
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> SubmitRequest(Address to_address, Address from_address, RequestT &&request,
Duration timeout) {
auto [future, promise] = memgraph::io::FuturePromisePair<ResponseResult<ResponseT>>();
const bool port_matches = to_address.last_known_port == from_address.last_known_port;
const bool ip_matches = to_address.last_known_ip == from_address.last_known_ip;
MG_ASSERT(port_matches && ip_matches);
const auto now = Now();
const Time deadline = now + timeout;
RequestId request_id = 0;
{
std::unique_lock<std::mutex> lock(mu_);
request_id = ++request_id_counter_;
PromiseKey promise_key{.requester_address = from_address, .request_id = request_id};
OpaquePromise opaque_promise(std::move(promise).ToUnique());
DeadlineAndOpaquePromise dop{.requested_at = now, .deadline = deadline, .promise = std::move(opaque_promise)};
MG_ASSERT(!promises_.contains(promise_key));
promises_.emplace(std::move(promise_key), std::move(dop));
} // lock dropped
Send(to_address, from_address, request_id, std::forward<RequestT>(request));
return std::move(future);
}
};
} // namespace memgraph::io::local_transport

View File

@@ -11,18 +11,33 @@
#pragma once
#include <boost/core/demangle.hpp>
#include "io/transport.hpp"
#include "utils/type_info_ref.hpp"
namespace memgraph::io::simulator {
namespace memgraph::io {
using memgraph::io::Duration;
using memgraph::io::Message;
using memgraph::io::Time;
struct PromiseKey {
Address requester_address;
uint64_t request_id;
public:
friend bool operator<(const PromiseKey &lhs, const PromiseKey &rhs) {
if (lhs.requester_address != rhs.requester_address) {
return lhs.requester_address < rhs.requester_address;
}
return lhs.request_id < rhs.request_id;
}
};
struct OpaqueMessage {
Address to_address;
Address from_address;
uint64_t request_id;
std::any message;
utils::TypeInfoRef type_info;
/// Recursively tries to match a specific type from the outer
/// variant's parameter pack against the type of the std::any,
@@ -65,10 +80,15 @@ struct OpaqueMessage {
return RequestEnvelope<Ms...>{
.message = std::move(*m_opt),
.request_id = request_id,
.to_address = to_address,
.from_address = from_address,
};
}
std::string demangled_name = "\"" + boost::core::demangle(message.type().name()) + "\"";
spdlog::error("failed to cast message of type {} to expected request type (probably in Receive argument types)",
demangled_name);
return std::nullopt;
}
};
@@ -77,7 +97,7 @@ class OpaquePromiseTraitBase {
public:
virtual const std::type_info *TypeInfo() const = 0;
virtual bool IsAwaited(void *ptr) const = 0;
virtual void Fill(void *ptr, OpaqueMessage &&) const = 0;
virtual void Fill(void *ptr, OpaqueMessage &&, Duration) const = 0;
virtual void TimeOut(void *ptr) const = 0;
virtual ~OpaquePromiseTraitBase() = default;
@@ -95,11 +115,13 @@ class OpaquePromiseTrait : public OpaquePromiseTraitBase {
bool IsAwaited(void *ptr) const override { return static_cast<ResponsePromise<T> *>(ptr)->IsAwaited(); };
void Fill(void *ptr, OpaqueMessage &&opaque_message) const override {
void Fill(void *ptr, OpaqueMessage &&opaque_message, Duration response_latency) const override {
T message = std::any_cast<T>(std::move(opaque_message.message));
auto response_envelope = ResponseEnvelope<T>{.message = std::move(message),
.request_id = opaque_message.request_id,
.from_address = opaque_message.from_address};
.to_address = opaque_message.to_address,
.from_address = opaque_message.from_address,
.response_latency = response_latency};
auto promise = static_cast<ResponsePromise<T> *>(ptr);
auto unique_promise = std::unique_ptr<ResponsePromise<T>>(promise);
unique_promise->Fill(std::move(response_envelope));
@@ -163,9 +185,9 @@ class OpaquePromise {
ptr_ = nullptr;
}
void Fill(OpaqueMessage &&opaque_message) {
void Fill(OpaqueMessage &&opaque_message, Duration response_latency) {
MG_ASSERT(ptr_ != nullptr);
trait_->Fill(ptr_, std::move(opaque_message));
trait_->Fill(ptr_, std::move(opaque_message), response_latency);
ptr_ = nullptr;
}
@@ -174,4 +196,41 @@ class OpaquePromise {
}
};
} // namespace memgraph::io::simulator
struct DeadlineAndOpaquePromise {
Time requested_at;
Time deadline;
OpaquePromise promise;
};
template <class From>
std::type_info const &TypeInfoForVariant(From const &from) {
return std::visit([](auto &&x) -> decltype(auto) { return typeid(x); }, from);
}
template <class T>
utils::TypeInfoRef TypeInfoFor(const T & /* t */) {
return typeid(T);
}
template <typename From, typename Return, typename Head, typename... Rest>
std::optional<Return> ConvertVariantInner(From &&a) {
if (typeid(Head) == TypeInfoForVariant(a)) {
Head concrete = std::get<Head>(std::forward<From>(a));
return concrete;
}
if constexpr (sizeof...(Rest) > 0) {
return ConvertVariantInner<From, Return, Rest...>(std::forward<From>(a));
} else {
return std::nullopt;
}
}
/// This function converts a variant to another variant holding a subset OR superset of
/// possible types.
template <class From, class... Ms>
requires(sizeof...(Ms) > 0) std::optional<std::variant<Ms...>> ConvertVariant(From &&from) {
return ConvertVariantInner<From, std::variant<Ms...>, Ms...>(std::forward<From>(from));
}
} // namespace memgraph::io

View File

@@ -0,0 +1,127 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <cmath>
#include <unordered_map>
#include <boost/core/demangle.hpp>
#include "io/time.hpp"
#include "utils/histogram.hpp"
#include "utils/logging.hpp"
#include "utils/print_helpers.hpp"
#include "utils/type_info_ref.hpp"
namespace memgraph::io {
struct LatencyHistogramSummary {
uint64_t count;
Duration p0;
Duration p50;
Duration p75;
Duration p90;
Duration p95;
Duration p975;
Duration p99;
Duration p999;
Duration p9999;
Duration p100;
Duration sum;
friend std::ostream &operator<<(std::ostream &in, const LatencyHistogramSummary &histo) {
in << "{ \"count\": " << histo.count;
in << ", \"p0\": " << histo.p0.count();
in << ", \"p50\": " << histo.p50.count();
in << ", \"p75\": " << histo.p75.count();
in << ", \"p90\": " << histo.p90.count();
in << ", \"p95\": " << histo.p95.count();
in << ", \"p975\": " << histo.p975.count();
in << ", \"p99\": " << histo.p99.count();
in << ", \"p999\": " << histo.p999.count();
in << ", \"p9999\": " << histo.p9999.count();
in << ", \"p100\": " << histo.p100.count();
in << ", \"sum\": " << histo.sum.count();
in << " }";
return in;
}
};
struct LatencyHistogramSummaries {
std::unordered_map<std::string, LatencyHistogramSummary> latencies;
std::string SummaryTable() {
std::string output;
const auto row = [&output](const auto &c1, const auto &c2, const auto &c3, const auto &c4, const auto &c5,
const auto &c6, const auto &c7) {
output +=
fmt::format("{: >50} | {: >8} | {: >8} | {: >8} | {: >8} | {: >8} | {: >8}\n", c1, c2, c3, c4, c5, c6, c7);
};
row("name", "count", "min (μs)", "med (μs)", "p99 (μs)", "max (μs)", "sum (ms)");
for (const auto &[name, histo] : latencies) {
row(name, histo.count, histo.p0.count(), histo.p50.count(), histo.p99.count(), histo.p100.count(),
histo.sum.count() / 1000);
}
output += "\n";
return output;
}
friend std::ostream &operator<<(std::ostream &in, const LatencyHistogramSummaries &histo) {
using memgraph::utils::print_helpers::operator<<;
in << histo.latencies;
return in;
}
};
class MessageHistogramCollector {
std::unordered_map<utils::TypeInfoRef, utils::Histogram, utils::TypeInfoHasher, utils::TypeInfoEqualTo> histograms_;
public:
void Measure(const std::type_info &type_info, const Duration &duration) {
auto &histo = histograms_[type_info];
histo.Measure(duration.count());
}
LatencyHistogramSummaries ResponseLatencies() {
std::unordered_map<std::string, LatencyHistogramSummary> ret{};
for (const auto &[type_id, histo] : histograms_) {
std::string demangled_name = "\"" + boost::core::demangle(type_id.get().name()) + "\"";
LatencyHistogramSummary latency_histogram_summary{
.count = histo.Count(),
.p0 = Duration(static_cast<int64_t>(histo.Percentile(0.0))),
.p50 = Duration(static_cast<int64_t>(histo.Percentile(50.0))),
.p75 = Duration(static_cast<int64_t>(histo.Percentile(75.0))),
.p90 = Duration(static_cast<int64_t>(histo.Percentile(90.0))),
.p95 = Duration(static_cast<int64_t>(histo.Percentile(95.0))),
.p975 = Duration(static_cast<int64_t>(histo.Percentile(97.5))),
.p99 = Duration(static_cast<int64_t>(histo.Percentile(99.0))),
.p999 = Duration(static_cast<int64_t>(histo.Percentile(99.9))),
.p9999 = Duration(static_cast<int64_t>(histo.Percentile(99.99))),
.p100 = Duration(static_cast<int64_t>(histo.Percentile(100.0))),
.sum = Duration(histo.Sum()),
};
ret.emplace(demangled_name, latency_histogram_summary);
}
return LatencyHistogramSummaries{.latencies = ret};
}
};
} // namespace memgraph::io

46
src/io/messages.hpp Normal file
View File

@@ -0,0 +1,46 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <variant>
#include <coordinator/coordinator.hpp>
#include <io/rsm/raft.hpp>
#include "query/v2/requests.hpp"
#include "utils/concepts.hpp"
namespace memgraph::io::messages {
using memgraph::coordinator::CoordinatorReadRequests;
using memgraph::coordinator::CoordinatorWriteRequests;
using memgraph::coordinator::CoordinatorWriteResponses;
using StorageReadRequest = msgs::ReadRequests;
using StorageWriteRequest = msgs::WriteRequests;
using memgraph::io::rsm::AppendRequest;
using memgraph::io::rsm::AppendResponse;
using memgraph::io::rsm::ReadRequest;
using memgraph::io::rsm::VoteRequest;
using memgraph::io::rsm::VoteResponse;
using memgraph::io::rsm::WriteRequest;
using memgraph::io::rsm::WriteResponse;
using CoordinatorMessages =
std::variant<ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse>;
using ShardMessages = std::variant<ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>, AppendResponse,
WriteRequest<StorageWriteRequest>, VoteRequest, VoteResponse>;
using ShardManagerMessages = std::variant<WriteResponse<CoordinatorWriteResponses>>;
} // namespace memgraph::io::messages

968
src/io/rsm/raft.hpp Normal file
View File

@@ -0,0 +1,968 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
// TODO(tyler) buffer out-of-order Append buffers on the Followers to reassemble more quickly
// TODO(tyler) handle granular batch sizes based on simple flow control
#pragma once
#include <deque>
#include <iostream>
#include <map>
#include <set>
#include <thread>
#include <unordered_map>
#include <vector>
#include <boost/core/demangle.hpp>
#include "io/message_conversion.hpp"
#include "io/simulator/simulator.hpp"
#include "io/transport.hpp"
#include "utils/concepts.hpp"
namespace memgraph::io::rsm {
/// Timeout and replication tunables
using namespace std::chrono_literals;
static constexpr auto kMinimumElectionTimeout = 100ms;
static constexpr auto kMaximumElectionTimeout = 200ms;
static constexpr auto kMinimumBroadcastTimeout = 40ms;
static constexpr auto kMaximumBroadcastTimeout = 60ms;
static constexpr auto kMinimumCronInterval = 1ms;
static constexpr auto kMaximumCronInterval = 2ms;
static constexpr auto kMinimumReceiveTimeout = 40ms;
static constexpr auto kMaximumReceiveTimeout = 60ms;
static_assert(kMinimumElectionTimeout > kMaximumBroadcastTimeout,
"The broadcast timeout has to be smaller than the election timeout!");
static_assert(kMinimumElectionTimeout < kMaximumElectionTimeout,
"The minimum election timeout has to be smaller than the maximum election timeout!");
static_assert(kMinimumBroadcastTimeout < kMaximumBroadcastTimeout,
"The minimum broadcast timeout has to be smaller than the maximum broadcast timeout!");
static_assert(kMinimumCronInterval < kMaximumCronInterval,
"The minimum cron interval has to be smaller than the maximum cron interval!");
static_assert(kMinimumReceiveTimeout < kMaximumReceiveTimeout,
"The minimum receive timeout has to be smaller than the maximum receive timeout!");
static constexpr size_t kMaximumAppendBatchSize = 1024;
using Term = uint64_t;
using LogIndex = uint64_t;
using LogSize = uint64_t;
template <typename WriteOperation>
struct WriteRequest {
WriteOperation operation;
};
/// WriteResponse is returned to a client after
/// their WriteRequest was entered in to the raft
/// log and it reached consensus.
///
/// WriteReturn is the result of applying the WriteRequest to
/// ReplicatedState, and if the ReplicatedState::write
/// method is deterministic, all replicas will
/// have the same ReplicatedState after applying
/// the submitted WriteRequest.
template <typename WriteReturn>
struct WriteResponse {
bool success;
WriteReturn write_return;
std::optional<Address> retry_leader;
LogIndex raft_index;
};
template <typename ReadOperation>
struct ReadRequest {
ReadOperation operation;
};
template <typename ReadReturn>
struct ReadResponse {
bool success;
ReadReturn read_return;
std::optional<Address> retry_leader;
};
template <class... ReadReturn>
utils::TypeInfoRef TypeInfoFor(const ReadResponse<std::variant<ReadReturn...>> &read_response) {
return TypeInfoForVariant(read_response.read_return);
}
template <class ReadReturn>
utils::TypeInfoRef TypeInfoFor(const ReadResponse<ReadReturn> & /* read_response */) {
return typeid(ReadReturn);
}
template <class... WriteReturn>
utils::TypeInfoRef TypeInfoFor(const WriteResponse<std::variant<WriteReturn...>> &write_response) {
return TypeInfoForVariant(write_response.write_return);
}
template <class WriteReturn>
utils::TypeInfoRef TypeInfoFor(const WriteResponse<WriteReturn> & /* write_response */) {
return typeid(WriteReturn);
}
template <class WriteOperation>
utils::TypeInfoRef TypeInfoFor(const WriteRequest<WriteOperation> & /* write_request */) {
return typeid(WriteOperation);
}
template <class... WriteOperations>
utils::TypeInfoRef TypeInfoFor(const WriteRequest<std::variant<WriteOperations...>> &write_request) {
return TypeInfoForVariant(write_request.operation);
}
/// AppendRequest is a raft-level message that the Leader
/// periodically broadcasts to all Follower peers. This
/// serves three main roles:
/// 1. acts as a heartbeat from the Leader to the Follower
/// 2. replicates new data that the Leader has received to the Follower
/// 3. informs Follower peers when the commit index has increased,
/// signalling that it is now safe to apply log items to the
/// replicated state machine
template <typename WriteRequest>
struct AppendRequest {
Term term = 0;
LogIndex batch_start_log_index;
Term last_log_term;
std::vector<std::pair<Term, WriteRequest>> entries;
LogSize leader_commit;
};
struct AppendResponse {
bool success;
Term term;
Term last_log_term;
// a small optimization over the raft paper, tells
// the leader the offset that we are interested in
// to send log offsets from for us. This will only
// be useful at the beginning of a leader's term.
LogSize log_size;
};
struct VoteRequest {
Term term = 0;
LogSize log_size;
Term last_log_term;
};
struct VoteResponse {
Term term = 0;
LogSize committed_log_size;
bool vote_granted = false;
};
template <typename WriteRequest>
struct CommonState {
Term term = 0;
std::vector<std::pair<Term, WriteRequest>> log;
LogSize committed_log_size = 0;
LogSize applied_size = 0;
};
struct FollowerTracker {
LogIndex next_index = 0;
LogSize confirmed_log_size = 0;
};
struct PendingClientRequest {
RequestId request_id;
Address address;
Time received_at;
};
struct Leader {
std::map<Address, FollowerTracker> followers;
std::unordered_map<LogIndex, PendingClientRequest> pending_client_requests;
Time last_broadcast = Time::min();
std::string static ToString() { return "\tLeader \t"; }
};
struct Candidate {
std::map<Address, LogSize> successful_votes;
Time election_began = Time::min();
std::set<Address> outstanding_votes;
std::string static ToString() { return "\tCandidate\t"; }
};
struct Follower {
Time last_received_append_entries_timestamp;
Address leader_address;
std::string static ToString() { return "\tFollower \t"; }
};
using Role = std::variant<Candidate, Leader, Follower>;
template <typename Role>
concept AllRoles = memgraph::utils::SameAsAnyOf<Role, Leader, Follower, Candidate>;
template <typename Role>
concept LeaderOrFollower = memgraph::utils::SameAsAnyOf<Role, Leader, Follower>;
template <typename Role>
concept FollowerOrCandidate = memgraph::utils::SameAsAnyOf<Role, Follower, Candidate>;
/*
all ReplicatedState classes should have an Apply method
that returns our WriteResponseValue after consensus, and
a Read method that returns our ReadResponseValue without
requiring consensus.
ReadResponse Read(ReadOperation);
WriteResponseValue ReplicatedState::Apply(WriteRequest);
For example:
If the state is uint64_t, and WriteRequest is `struct PlusOne {};`,
and WriteResponseValue is also uint64_t (the new value), then
each call to state.Apply(PlusOne{}) will return the new value
after incrementing it. 0, 1, 2, 3... and this will be sent back
to the client that requested the mutation.
In practice, these mutations will usually be predicated on some
previous value, so that they are idempotent, functioning similarly
to a CAS operation.
*/
template <typename WriteOperation, typename ReadOperation, typename ReplicatedState, typename WriteResponseValue,
typename ReadResponseValue>
concept Rsm = requires(ReplicatedState state, WriteOperation w, ReadOperation r) {
{ state.Read(r) } -> std::same_as<ReadResponseValue>;
{ state.Apply(w) } -> std::same_as<WriteResponseValue>;
};
/// Parameter Purpose
/// --------------------------
/// IoImpl the concrete Io provider - SimulatorTransport, ThriftTransport, etc...
/// ReplicatedState the high-level data structure that is managed by the raft-backed replicated state machine
/// WriteOperation the individual operation type that is applied to the ReplicatedState in identical order
/// across each replica
/// WriteResponseValue the return value of calling ReplicatedState::Apply(WriteOperation), which is executed in
/// identical order across all replicas after an WriteOperation reaches consensus.
/// ReadOperation the type of operations that do not require consensus before executing directly
/// on a const ReplicatedState &
/// ReadResponseValue the return value of calling ReplicatedState::Read(ReadOperation), which is executed directly
/// without going through consensus first
template <typename IoImpl, typename ReplicatedState, typename WriteOperation, typename WriteResponseValue,
typename ReadOperation, typename ReadResponseValue>
requires Rsm<WriteOperation, ReadOperation, ReplicatedState, WriteResponseValue, ReadResponseValue>
class Raft {
CommonState<WriteOperation> state_;
Role role_ = Candidate{};
Io<IoImpl> io_;
std::vector<Address> peers_;
ReplicatedState replicated_state_;
Time next_cron_;
public:
Raft(Io<IoImpl> &&io, std::vector<Address> peers, ReplicatedState &&replicated_state)
: io_(std::forward<Io<IoImpl>>(io)),
peers_(peers),
replicated_state_(std::forward<ReplicatedState>(replicated_state)) {
if (peers.empty()) {
role_ = Leader{};
}
}
/// Periodic protocol maintenance. Returns the time that Cron should be called again
/// in the future.
Time Cron() {
// dispatch periodic logic based on our role to a specific Cron method.
std::optional<Role> new_role = std::visit([&](auto &role) { return Cron(role); }, role_);
if (new_role) {
role_ = std::move(new_role).value();
}
const Duration random_cron_interval = RandomTimeout(kMinimumCronInterval, kMaximumCronInterval);
return io_.Now() + random_cron_interval;
}
/// Returns the Address for our underlying Io implementation
Address GetAddress() { return io_.GetAddress(); }
using ReceiveVariant = std::variant<ReadRequest<ReadOperation>, AppendRequest<WriteOperation>, AppendResponse,
WriteRequest<WriteOperation>, VoteRequest, VoteResponse>;
void Handle(ReceiveVariant &&message_variant, RequestId request_id, Address from_address) {
// dispatch the message to a handler based on our role,
// which can be specified in the Handle first argument,
// or it can be `auto` if it's a handler for several roles
// or messages.
std::optional<Role> new_role = std::visit(
[&](auto &&msg, auto &role) mutable {
return Handle(role, std::forward<decltype(msg)>(msg), request_id, from_address);
},
std::forward<ReceiveVariant>(message_variant), role_);
// TODO(tyler) (M3) maybe replace std::visit with get_if for explicit prioritized matching, [[likely]] etc...
if (new_role) {
role_ = std::move(new_role).value();
}
}
void Run() {
// debug - gvolfing
uint64_t tick_count = 0;
while (!io_.ShouldShutDown()) {
const auto now = io_.Now();
if (now >= next_cron_) {
next_cron_ = Cron();
}
// debug - gvolfing
spdlog::info("Raft::Run() awakened on thread {}, Cron tick: {}", std::this_thread::get_id(), tick_count);
tick_count++;
const Duration receive_timeout = RandomTimeout(kMinimumReceiveTimeout, kMaximumReceiveTimeout);
auto request_result =
io_.template ReceiveWithTimeout<ReadRequest<ReadOperation>, AppendRequest<WriteOperation>, AppendResponse,
WriteRequest<WriteOperation>, VoteRequest, VoteResponse>(receive_timeout);
if (request_result.HasError()) {
continue;
}
auto request = std::move(request_result.GetValue());
Handle(std::move(request.message), request.request_id, request.from_address);
}
}
private:
// Raft paper - 5.3
// When the entry has been safely replicated, the leader applies the
// entry to its state machine and returns the result of that
// execution to the client.
//
// "Safely replicated" is defined as being known to be present
// on at least a majority of all peers (inclusive of the Leader).
void BumpCommitIndexAndReplyToClients(Leader &leader) {
auto confirmed_log_sizes = std::vector<LogSize>{};
// We include our own log size in the calculation of the log
// confirmed log size that is present on at least a majority of all peers.
confirmed_log_sizes.push_back(state_.log.size());
for (const auto &[addr, f] : leader.followers) {
confirmed_log_sizes.push_back(f.confirmed_log_size);
Log("Follower at port ", addr.last_known_port, " has confirmed log size of: ", f.confirmed_log_size);
}
// reverse sort from highest to lowest (using std::ranges::greater)
std::ranges::sort(confirmed_log_sizes, std::ranges::greater());
// This is a particularly correctness-critical calculation because it
// determines the committed log size that will be broadcast in
// the next AppendRequest.
//
// If the following sizes are recorded for clusters of different numbers of peers,
// these are the expected sizes that are considered to have reached consensus:
//
// state | expected value | (confirmed_log_sizes.size() / 2)
// [1] 1 (1 / 2) => 0
// [2, 1] 1 (2 / 2) => 1
// [3, 2, 1] 2 (3 / 2) => 1
// [4, 3, 2, 1] 2 (4 / 2) => 2
// [5, 4, 3, 2, 1] 3 (5 / 2) => 2
const size_t majority_index = confirmed_log_sizes.size() / 2;
const LogSize new_committed_log_size = confirmed_log_sizes[majority_index];
// We never go backwards in history.
MG_ASSERT(state_.committed_log_size <= new_committed_log_size,
"as a Leader, we have previously set our committed_log_size to {}, but our Followers have a majority "
"committed_log_size of {}",
state_.committed_log_size, new_committed_log_size);
state_.committed_log_size = new_committed_log_size;
// For each size between the old size and the new one (inclusive),
// Apply that log's WriteOperation to our replicated_state_,
// and use the specific return value of the ReplicatedState::Apply
// method (WriteResponseValue) to respond to the requester.
for (; state_.applied_size < state_.committed_log_size; state_.applied_size++) {
const LogIndex apply_index = state_.applied_size;
const auto &write_request = state_.log[apply_index].second;
const WriteResponseValue write_return = replicated_state_.Apply(write_request);
if (leader.pending_client_requests.contains(apply_index)) {
const PendingClientRequest client_request = std::move(leader.pending_client_requests.at(apply_index));
leader.pending_client_requests.erase(apply_index);
const WriteResponse<WriteResponseValue> resp{
.success = true,
.write_return = std::move(write_return),
.raft_index = apply_index,
};
io_.Send(client_request.address, client_request.request_id, std::move(resp));
}
}
Log("committed_log_size is now ", state_.committed_log_size);
}
// Raft paper - 5.1
// AppendEntries RPCs are initiated by leaders to replicate log entries and to provide a form of heartbeat
void BroadcastAppendEntries(std::map<Address, FollowerTracker> &followers) {
for (auto &[address, follower] : followers) {
const LogIndex next_index = follower.next_index;
const auto missing = state_.log.size() - next_index;
const auto batch_size = std::min(missing, kMaximumAppendBatchSize);
const auto start_index = next_index;
const auto end_index = start_index + batch_size;
// advance follower's next index
follower.next_index += batch_size;
std::vector<std::pair<Term, WriteOperation>> entries;
entries.insert(entries.begin(), state_.log.begin() + start_index, state_.log.begin() + end_index);
const Term previous_term_from_index = PreviousTermFromIndex(start_index);
Log("sending ", entries.size(), " entries to Follower ", address.last_known_port,
" which are above its next_index of ", next_index);
AppendRequest<WriteOperation> ar{
.term = state_.term,
.batch_start_log_index = start_index,
.last_log_term = previous_term_from_index,
.entries = std::move(entries),
.leader_commit = state_.committed_log_size,
};
// request_id not necessary to set because it's not a Future-backed Request.
static constexpr RequestId request_id = 0;
io_.Send(address, request_id, std::move(ar));
}
}
// Raft paper - 5.2
// Raft uses randomized election timeouts to ensure that split votes are rare and that they are resolved quickly
Duration RandomTimeout(Duration min, Duration max) {
std::uniform_int_distribution time_distrib(min.count(), max.count());
const auto rand_micros = io_.Rand(time_distrib);
return Duration{rand_micros};
}
Duration RandomTimeout(int min_micros, int max_micros) {
std::uniform_int_distribution time_distrib(min_micros, max_micros);
const int rand_micros = io_.Rand(time_distrib);
return std::chrono::microseconds{rand_micros};
}
Term PreviousTermFromIndex(LogIndex index) const {
if (index == 0 || state_.log.size() + 1 <= index) {
return 0;
}
const auto &[term, data] = state_.log.at(index - 1);
return term;
}
Term CommittedLogTerm() {
MG_ASSERT(state_.log.size() >= state_.committed_log_size);
if (state_.log.empty() || state_.committed_log_size == 0) {
return 0;
}
const auto &[term, data] = state_.log.at(state_.committed_log_size - 1);
return term;
}
Term LastLogTerm() const {
if (state_.log.empty()) {
return 0;
}
const auto &[term, data] = state_.log.back();
return term;
}
template <typename... Ts>
void Log(Ts &&...args) {
const Time now = io_.Now();
const auto micros = std::chrono::duration_cast<std::chrono::milliseconds>(now.time_since_epoch()).count();
const Term term = state_.term;
const std::string role_string = std::visit([&](const auto &role) { return role.ToString(); }, role_);
std::ostringstream out;
out << '\t' << static_cast<int>(micros) << "\t" << term << "\t" << io_.GetAddress().last_known_port;
out << role_string;
(out << ... << args);
spdlog::info(out.str());
}
/////////////////////////////////////////////////////////////
/// Raft-related Cron methods
///
/// Cron + std::visit is how events are dispatched
/// to certain code based on Raft role.
///
/// Cron(role) takes as the first argument a reference to its
/// role, and as the second argument, the message that has
/// been received.
/////////////////////////////////////////////////////////////
// Raft paper - 5.2
// Candidates keep sending Vote to peers until:
// 1. receiving Append with a higher term (become Follower)
// 2. receiving Vote with a higher term (become a Follower)
// 3. receiving a quorum of responses to our last batch of Vote (become a Leader)
std::optional<Role> Cron(Candidate &candidate) {
const auto now = io_.Now();
const Duration election_timeout = RandomTimeout(kMinimumElectionTimeout, kMaximumElectionTimeout);
const auto election_timeout_us = std::chrono::duration_cast<std::chrono::milliseconds>(election_timeout).count();
if (now - candidate.election_began > election_timeout) {
state_.term++;
Log("becoming Candidate for term ", state_.term, " after leader timeout of ", election_timeout_us,
"ms elapsed since last election attempt");
const VoteRequest request{
.term = state_.term,
.log_size = state_.log.size(),
.last_log_term = LastLogTerm(),
};
auto outstanding_votes = std::set<Address>();
for (const auto &peer : peers_) {
// request_id not necessary to set because it's not a Future-backed Request.
static constexpr auto request_id = 0;
io_.template Send<VoteRequest>(peer, request_id, request);
outstanding_votes.insert(peer);
}
return Candidate{
.successful_votes = std::map<Address, LogIndex>(),
.election_began = now,
.outstanding_votes = outstanding_votes,
};
}
return std::nullopt;
}
// Raft paper - 5.2
// Followers become candidates if we haven't heard from the leader
// after a randomized timeout.
std::optional<Role> Cron(Follower &follower) {
const auto now = io_.Now();
const auto time_since_last_append_entries = now - follower.last_received_append_entries_timestamp;
// randomized follower timeout
const Duration election_timeout = RandomTimeout(kMinimumElectionTimeout, kMaximumElectionTimeout);
if (time_since_last_append_entries > election_timeout) {
// become a Candidate if we haven't heard from the Leader after this timeout
return Candidate{};
}
return std::nullopt;
}
// Leaders (re)send AppendRequest to followers.
std::optional<Role> Cron(Leader &leader) {
const Time now = io_.Now();
const Duration broadcast_timeout = RandomTimeout(kMinimumBroadcastTimeout, kMaximumBroadcastTimeout);
if (now > leader.last_broadcast + broadcast_timeout) {
BroadcastAppendEntries(leader.followers);
leader.last_broadcast = now;
}
return std::nullopt;
}
/////////////////////////////////////////////////////////////
/// Raft-related Handle methods
///
/// Handle + std::visit is how events are dispatched
/// to certain code based on Raft role.
///
/// Handle(role, message, ...)
/// takes as the first argument a reference
/// to its role, and as the second argument, the
/// message that has been received.
/////////////////////////////////////////////////////////////
// all roles can receive Vote and possibly become a follower
template <AllRoles ALL>
std::optional<Role> Handle(ALL & /* variable */, VoteRequest &&req, RequestId request_id, Address from_address) {
Log("received VoteRequest from ", from_address.last_known_port, " with term ", req.term);
const bool last_log_term_dominates = req.last_log_term >= LastLogTerm();
const bool term_dominates = req.term > state_.term;
const bool log_size_dominates = req.log_size >= state_.log.size();
const bool new_leader = last_log_term_dominates && term_dominates && log_size_dominates;
if (new_leader) {
MG_ASSERT(req.term > state_.term);
MG_ASSERT(std::max(req.term, state_.term) == req.term);
}
const VoteResponse res{
.term = std::max(req.term, state_.term),
.committed_log_size = state_.committed_log_size,
.vote_granted = new_leader,
};
io_.Send(from_address, request_id, res);
if (new_leader) {
// become a follower
state_.term = req.term;
return Follower{
.last_received_append_entries_timestamp = io_.Now(),
.leader_address = from_address,
};
}
if (term_dominates) {
Log("received a vote from an inferior candidate. Becoming Candidate");
state_.term = std::max(state_.term, req.term) + 1;
return Candidate{};
}
return std::nullopt;
}
std::optional<Role> Handle(Candidate &candidate, VoteResponse &&res, RequestId /* variable */, Address from_address) {
Log("received VoteResponse");
if (!res.vote_granted || res.term != state_.term) {
Log("received unsuccessful VoteResponse from term ", res.term, " when our candidacy term is ", state_.term);
// we received a delayed VoteResponse from the past, which has to do with an election that is
// no longer valid. We can simply drop this.
return std::nullopt;
}
MG_ASSERT(candidate.outstanding_votes.contains(from_address),
"Received unexpected VoteResponse from server not present in Candidate's outstanding_votes!");
candidate.outstanding_votes.erase(from_address);
MG_ASSERT(!candidate.successful_votes.contains(from_address),
"Received unexpected VoteResponse from server already in Candidate's successful_votes!");
candidate.successful_votes.insert({from_address, res.committed_log_size});
if (candidate.successful_votes.size() >= candidate.outstanding_votes.size()) {
std::map<Address, FollowerTracker> followers{};
for (const auto &[address, committed_log_size] : candidate.successful_votes) {
FollowerTracker follower{
.next_index = committed_log_size,
.confirmed_log_size = committed_log_size,
};
followers.insert({address, follower});
}
for (const auto &address : candidate.outstanding_votes) {
FollowerTracker follower{
.next_index = state_.log.size(),
.confirmed_log_size = 0,
};
followers.insert({address, follower});
}
Log("becoming Leader at term ", state_.term);
BroadcastAppendEntries(followers);
return Leader{
.followers = std::move(followers),
.pending_client_requests = std::unordered_map<LogIndex, PendingClientRequest>(),
};
}
return std::nullopt;
}
template <LeaderOrFollower LOF>
std::optional<Role> Handle(LOF & /* variable */, VoteResponse && /* variable */, RequestId /* variable */,
Address /* variable */) {
Log("non-Candidate received VoteResponse");
return std::nullopt;
}
template <AllRoles ALL>
std::optional<Role> Handle(ALL &role, AppendRequest<WriteOperation> &&req, RequestId request_id,
Address from_address) {
// log size starts out as state_.committed_log_size and only if everything is successful do we
// switch it to the log length.
AppendResponse res{
.success = false,
.term = state_.term,
.last_log_term = CommittedLogTerm(),
.log_size = state_.log.size(),
};
if constexpr (std::is_same<ALL, Leader>()) {
MG_ASSERT(req.term != state_.term, "Multiple leaders are acting under the term ", req.term);
}
const bool is_candidate = std::is_same<ALL, Candidate>();
const bool is_failed_competitor = is_candidate && req.term == state_.term;
const Time now = io_.Now();
// Raft paper - 5.2
// While waiting for votes, a candidate may receive an
// AppendEntries RPC from another server claiming to be leader. If
// the leaders term (included in its RPC) is at least as large as
// the candidates current term, then the candidate recognizes the
// leader as legitimate and returns to follower state.
if (req.term > state_.term || is_failed_competitor) {
// become follower of this leader, reply with our log status
state_.term = req.term;
io_.Send(from_address, request_id, res);
Log("becoming Follower of Leader ", from_address.last_known_port, " at term ", req.term);
return Follower{
.last_received_append_entries_timestamp = now,
.leader_address = from_address,
};
}
if (req.term < state_.term) {
// nack this request from an old leader
io_.Send(from_address, request_id, res);
return std::nullopt;
}
// at this point, we're dealing with our own leader
if constexpr (std::is_same<ALL, Follower>()) {
// small specialization for when we're already a Follower
MG_ASSERT(role.leader_address == from_address, "Multiple Leaders are acting under the same term number!");
role.last_received_append_entries_timestamp = now;
} else {
Log("Somehow entered Follower-specific logic as a non-Follower");
MG_ASSERT(false, "Somehow entered Follower-specific logic as a non-Follower");
}
// Handle steady-state conditions.
if (req.batch_start_log_index != state_.log.size()) {
Log("req.batch_start_log_index of ", req.batch_start_log_index, " does not match our log size of ",
state_.log.size());
} else if (req.last_log_term != LastLogTerm()) {
Log("req.last_log_term differs from our leader term at that slot, expected: ", LastLogTerm(), " but got ",
req.last_log_term);
} else {
// happy path - Apply log
Log("applying batch of ", req.entries.size(), " entries to our log starting at index ",
req.batch_start_log_index);
const auto resize_length = req.batch_start_log_index;
MG_ASSERT(resize_length >= state_.committed_log_size,
"Applied history from Leader which goes back in time from our commit_index");
// possibly chop-off stuff that was replaced by
// things with different terms (we got data that
// hasn't reached consensus yet, which is normal)
state_.log.resize(resize_length);
if (req.entries.size() > 0) {
auto &[first_term, op] = req.entries.at(0);
MG_ASSERT(LastLogTerm() <= first_term);
}
state_.log.insert(state_.log.end(), std::make_move_iterator(req.entries.begin()),
std::make_move_iterator(req.entries.end()));
MG_ASSERT(req.leader_commit >= state_.committed_log_size);
state_.committed_log_size = std::min(req.leader_commit, state_.log.size());
for (; state_.applied_size < state_.committed_log_size; state_.applied_size++) {
const auto &write_request = state_.log[state_.applied_size].second;
replicated_state_.Apply(write_request);
}
res.success = true;
}
res.last_log_term = LastLogTerm();
res.log_size = state_.log.size();
Log("returning log_size of ", res.log_size);
io_.Send(from_address, request_id, res);
return std::nullopt;
}
std::optional<Role> Handle(Leader &leader, AppendResponse &&res, RequestId /* variable */, Address from_address) {
if (res.term != state_.term) {
Log("received AppendResponse related to a previous term when we (presumably) were the leader");
return std::nullopt;
}
// TODO(tyler) when we have dynamic membership, this assert will become incorrect, but we should
// keep it in-place until then because it has bug finding value.
MG_ASSERT(leader.followers.contains(from_address), "received AppendResponse from unknown Follower");
// at this point, we know the term matches and we know this Follower
FollowerTracker &follower = leader.followers.at(from_address);
if (res.success) {
Log("got successful AppendResponse from ", from_address.last_known_port, " with log_size of ", res.log_size);
follower.next_index = std::max(follower.next_index, res.log_size);
} else {
Log("got unsuccessful AppendResponse from ", from_address.last_known_port, " with log_size of ", res.log_size);
follower.next_index = res.log_size;
}
follower.confirmed_log_size = std::max(follower.confirmed_log_size, res.log_size);
BumpCommitIndexAndReplyToClients(leader);
return std::nullopt;
}
template <FollowerOrCandidate FOC>
std::optional<Role> Handle(FOC & /* variable */, AppendResponse && /* variable */, RequestId /* variable */,
Address /* variable */) {
// we used to be the leader, and are getting old delayed responses
return std::nullopt;
}
/////////////////////////////////////////////////////////////
/// RSM-related handle methods
/////////////////////////////////////////////////////////////
// Leaders are able to immediately respond to the requester (with a ReadResponseValue) applied to the ReplicatedState
std::optional<Role> Handle(Leader & /* variable */, ReadRequest<ReadOperation> &&req, RequestId request_id,
Address from_address) {
Log("handling ReadOperation");
ReadOperation read_operation = req.operation;
ReadResponseValue read_return = replicated_state_.Read(read_operation);
const ReadResponse<ReadResponseValue> resp{
.success = true,
.read_return = std::move(read_return),
.retry_leader = std::nullopt,
};
io_.Send(from_address, request_id, resp);
return std::nullopt;
}
// Candidates should respond with a failure, similar to the Candidate + WriteRequest failure below
std::optional<Role> Handle(Candidate & /* variable */, ReadRequest<ReadOperation> && /* variable */,
RequestId request_id, Address from_address) {
Log("received ReadOperation - not redirecting because no Leader is known");
const ReadResponse<ReadResponseValue> res{
.success = false,
};
io_.Send(from_address, request_id, res);
Cron();
return std::nullopt;
}
// Followers should respond with a redirection, similar to the Follower + WriteRequest response below
std::optional<Role> Handle(Follower &follower, ReadRequest<ReadOperation> && /* variable */, RequestId request_id,
Address from_address) {
Log("redirecting client to known Leader with port ", follower.leader_address.last_known_port);
const ReadResponse<ReadResponseValue> res{
.success = false,
.retry_leader = follower.leader_address,
};
io_.Send(from_address, request_id, res);
return std::nullopt;
}
// Raft paper - 8
// When a client first starts up, it connects to a randomly chosen
// server. If the clients first choice is not the leader, that
// server will reject the clients request and supply information
// about the most recent leader it has heard from.
std::optional<Role> Handle(Follower &follower, WriteRequest<WriteOperation> && /* variable */, RequestId request_id,
Address from_address) {
Log("redirecting client to known Leader with port ", follower.leader_address.last_known_port);
const WriteResponse<WriteResponseValue> res{
.success = false,
.retry_leader = follower.leader_address,
};
io_.Send(from_address, request_id, res);
return std::nullopt;
}
std::optional<Role> Handle(Candidate & /* variable */, WriteRequest<WriteOperation> && /* variable */,
RequestId request_id, Address from_address) {
Log("received WriteRequest - not redirecting because no Leader is known");
const WriteResponse<WriteResponseValue> res{
.success = false,
};
io_.Send(from_address, request_id, res);
Cron();
return std::nullopt;
}
// only leaders actually handle replication requests from clients
std::optional<Role> Handle(Leader &leader, WriteRequest<WriteOperation> &&req, RequestId request_id,
Address from_address) {
auto type_info = TypeInfoFor(req);
std::string demangled_name = boost::core::demangle(type_info.get().name());
Log("handling WriteRequest<" + demangled_name + ">");
// we are the leader. add item to log and send Append to peers
MG_ASSERT(state_.term >= LastLogTerm());
state_.log.emplace_back(std::pair(state_.term, std::move(req.operation)));
LogIndex log_index = state_.log.size() - 1;
PendingClientRequest pcr{
.request_id = request_id,
.address = from_address,
.received_at = io_.Now(),
};
leader.pending_client_requests.emplace(log_index, pcr);
if (peers_.empty()) {
BumpCommitIndexAndReplyToClients(leader);
} else {
BroadcastAppendEntries(leader.followers);
}
return std::nullopt;
}
};
}; // namespace memgraph::io::rsm

270
src/io/rsm/rsm_client.hpp Normal file
View File

@@ -0,0 +1,270 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <optional>
#include <type_traits>
#include <vector>
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/rsm/raft.hpp"
#include "utils/result.hpp"
namespace memgraph::io::rsm {
using memgraph::io::Address;
using memgraph::io::Duration;
using memgraph::io::ResponseEnvelope;
using memgraph::io::ResponseFuture;
using memgraph::io::ResponseResult;
using memgraph::io::Time;
using memgraph::io::TimedOut;
using memgraph::io::rsm::ReadRequest;
using memgraph::io::rsm::ReadResponse;
using memgraph::io::rsm::WriteRequest;
using memgraph::io::rsm::WriteResponse;
using memgraph::utils::BasicResult;
template <typename IoImpl, typename WriteRequestT, typename WriteResponseT, typename ReadRequestT,
typename ReadResponseT>
class RsmClient {
using ServerPool = std::vector<Address>;
Io<IoImpl> io_;
Address leader_;
ServerPool server_addrs_;
/// State for single async read/write operations. In the future this could become a map
/// of async operations that can be accessed via an ID etc...
std::optional<Time> async_read_before_;
std::optional<ResponseFuture<ReadResponse<ReadResponseT>>> async_read_;
ReadRequestT current_read_request_;
std::optional<Time> async_write_before_;
std::optional<ResponseFuture<WriteResponse<WriteResponseT>>> async_write_;
WriteRequestT current_write_request_;
void SelectRandomLeader() {
std::uniform_int_distribution<size_t> addr_distrib(0, (server_addrs_.size() - 1));
size_t addr_index = io_.Rand(addr_distrib);
leader_ = server_addrs_[addr_index];
spdlog::debug(
"client NOT redirected to leader server despite our success failing to be processed (it probably was sent to "
"a RSM Candidate) trying a random one at index {} with address {}",
addr_index, leader_.ToString());
}
template <typename ResponseT>
void PossiblyRedirectLeader(const ResponseT &response) {
if (response.retry_leader) {
MG_ASSERT(!response.success, "retry_leader should never be set for successful responses");
leader_ = response.retry_leader.value();
spdlog::debug("client redirected to leader server {}", leader_.ToString());
}
if (!response.success) {
SelectRandomLeader();
}
}
public:
RsmClient(Io<IoImpl> io, Address leader, ServerPool server_addrs)
: io_{io}, leader_{leader}, server_addrs_{server_addrs} {}
RsmClient(const RsmClient &) = delete;
RsmClient &operator=(const RsmClient &) = delete;
RsmClient(RsmClient &&) noexcept = default;
RsmClient &operator=(RsmClient &&) noexcept = default;
RsmClient() = delete;
~RsmClient() = default;
BasicResult<TimedOut, WriteResponseT> SendWriteRequest(WriteRequestT req) {
WriteRequest<WriteRequestT> client_req;
client_req.operation = req;
const Duration overall_timeout = io_.GetDefaultTimeout();
const Time before = io_.Now();
do {
spdlog::debug("client sending WriteRequest to Leader {}", leader_.ToString());
ResponseFuture<WriteResponse<WriteResponseT>> response_future =
io_.template Request<WriteRequest<WriteRequestT>, WriteResponse<WriteResponseT>>(leader_, client_req);
ResponseResult<WriteResponse<WriteResponseT>> response_result = std::move(response_future).Wait();
if (response_result.HasError()) {
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
return response_result.GetError();
}
ResponseEnvelope<WriteResponse<WriteResponseT>> &&response_envelope = std::move(response_result.GetValue());
WriteResponse<WriteResponseT> &&write_response = std::move(response_envelope.message);
if (write_response.success) {
return std::move(write_response.write_return);
}
PossiblyRedirectLeader(write_response);
} while (io_.Now() < before + overall_timeout);
return TimedOut{};
}
BasicResult<TimedOut, ReadResponseT> SendReadRequest(ReadRequestT req) {
ReadRequest<ReadRequestT> read_req;
read_req.operation = req;
const Duration overall_timeout = io_.GetDefaultTimeout();
const Time before = io_.Now();
do {
spdlog::debug("client sending ReadRequest to Leader {}", leader_.ToString());
ResponseFuture<ReadResponse<ReadResponseT>> get_response_future =
io_.template Request<ReadRequest<ReadRequestT>, ReadResponse<ReadResponseT>>(leader_, read_req);
// receive response
ResponseResult<ReadResponse<ReadResponseT>> get_response_result = std::move(get_response_future).Wait();
if (get_response_result.HasError()) {
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
return get_response_result.GetError();
}
ResponseEnvelope<ReadResponse<ReadResponseT>> &&get_response_envelope = std::move(get_response_result.GetValue());
ReadResponse<ReadResponseT> &&read_get_response = std::move(get_response_envelope.message);
if (read_get_response.success) {
return std::move(read_get_response.read_return);
}
PossiblyRedirectLeader(read_get_response);
} while (io_.Now() < before + overall_timeout);
return TimedOut{};
}
/// AsyncRead methods
void SendAsyncReadRequest(const ReadRequestT &req) {
MG_ASSERT(!async_read_);
ReadRequest<ReadRequestT> read_req = {.operation = req};
if (!async_read_before_) {
async_read_before_ = io_.Now();
}
current_read_request_ = std::move(req);
async_read_ = io_.template Request<ReadRequest<ReadRequestT>, ReadResponse<ReadResponseT>>(leader_, read_req);
}
std::optional<BasicResult<TimedOut, ReadResponseT>> PollAsyncReadRequest() {
MG_ASSERT(async_read_);
if (!async_read_->IsReady()) {
return std::nullopt;
}
return AwaitAsyncReadRequest();
}
std::optional<BasicResult<TimedOut, ReadResponseT>> AwaitAsyncReadRequest() {
ResponseResult<ReadResponse<ReadResponseT>> get_response_result = std::move(*async_read_).Wait();
async_read_.reset();
const Duration overall_timeout = io_.GetDefaultTimeout();
const bool past_time_out = io_.Now() < *async_read_before_ + overall_timeout;
const bool result_has_error = get_response_result.HasError();
if (result_has_error && past_time_out) {
// TODO static assert the exact type of error.
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
async_read_before_ = std::nullopt;
return TimedOut{};
}
if (!result_has_error) {
ResponseEnvelope<ReadResponse<ReadResponseT>> &&get_response_envelope = std::move(get_response_result.GetValue());
ReadResponse<ReadResponseT> &&read_get_response = std::move(get_response_envelope.message);
PossiblyRedirectLeader(read_get_response);
if (read_get_response.success) {
async_read_before_ = std::nullopt;
return std::move(read_get_response.read_return);
}
SendAsyncReadRequest(current_read_request_);
} else if (result_has_error) {
SelectRandomLeader();
SendAsyncReadRequest(current_read_request_);
}
return std::nullopt;
}
/// AsyncWrite methods
void SendAsyncWriteRequest(const WriteRequestT &req) {
MG_ASSERT(!async_write_);
WriteRequest<WriteRequestT> write_req = {.operation = req};
if (!async_write_before_) {
async_write_before_ = io_.Now();
}
current_write_request_ = std::move(req);
async_write_ = io_.template Request<WriteRequest<WriteRequestT>, WriteResponse<WriteResponseT>>(leader_, write_req);
}
std::optional<BasicResult<TimedOut, WriteResponseT>> PollAsyncWriteRequest() {
MG_ASSERT(async_write_);
if (!async_write_->IsReady()) {
return std::nullopt;
}
return AwaitAsyncWriteRequest();
}
std::optional<BasicResult<TimedOut, WriteResponseT>> AwaitAsyncWriteRequest() {
ResponseResult<WriteResponse<WriteResponseT>> get_response_result = std::move(*async_write_).Wait();
async_write_.reset();
const Duration overall_timeout = io_.GetDefaultTimeout();
const bool past_time_out = io_.Now() < *async_write_before_ + overall_timeout;
const bool result_has_error = get_response_result.HasError();
if (result_has_error && past_time_out) {
// TODO static assert the exact type of error.
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
async_write_before_ = std::nullopt;
return TimedOut{};
}
if (!result_has_error) {
ResponseEnvelope<WriteResponse<WriteResponseT>> &&get_response_envelope =
std::move(get_response_result.GetValue());
WriteResponse<WriteResponseT> &&write_get_response = std::move(get_response_envelope.message);
PossiblyRedirectLeader(write_get_response);
if (write_get_response.success) {
async_write_before_ = std::nullopt;
return std::move(write_get_response.write_return);
}
SendAsyncWriteRequest(current_write_request_);
} else if (result_has_error) {
SelectRandomLeader();
SendAsyncWriteRequest(current_write_request_);
}
return std::nullopt;
}
};
} // namespace memgraph::io::rsm

155
src/io/rsm/shard_rsm.hpp Normal file
View File

@@ -0,0 +1,155 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
/// The ShardRsm is a simple in-memory raft-backed kv store that can be used for simple testing
/// and implementation of some query engine logic before storage engines are fully implemented.
///
/// To implement multiple read and write commands, change the StorageRead* and StorageWrite* requests
/// and responses to a std::variant of the different options, and route them to specific handlers in
/// the ShardRsm's Read and Apply methods. Remember that Read is called immediately when the Raft
/// leader receives the request, and does not replicate anything over Raft. Apply is called only
/// AFTER the StorageWriteRequest is replicated to a majority of Raft peers, and the result of calling
/// ShardRsm::Apply(StorageWriteRequest) is returned to the client that submitted the request.
#include <deque>
#include <iostream>
#include <map>
#include <optional>
#include <set>
#include <thread>
#include <vector>
#include "coordinator/hybrid_logical_clock.hpp"
#include "io/address.hpp"
#include "io/rsm/raft.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/property_value.hpp"
#include "utils/logging.hpp"
namespace memgraph::io::rsm {
using memgraph::coordinator::Hlc;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyValue;
using ShardRsmKey = std::vector<PropertyValue>;
struct StorageWriteRequest {
LabelId label_id;
Hlc transaction_id;
ShardRsmKey key;
std::optional<int> value;
};
struct StorageWriteResponse {
bool shard_rsm_success;
std::optional<int> last_value;
// Only has a value if the given shard does not contain the requested key
std::optional<Hlc> latest_known_shard_map_version{std::nullopt};
};
struct StorageReadRequest {
LabelId label_id;
Hlc transaction_id;
ShardRsmKey key;
};
struct StorageReadResponse {
bool shard_rsm_success;
std::optional<int> value;
// Only has a value if the given shard does not contain the requested key
std::optional<Hlc> latest_known_shard_map_version{std::nullopt};
};
class ShardRsm {
std::map<ShardRsmKey, int> state_;
ShardRsmKey minimum_key_;
std::optional<ShardRsmKey> maximum_key_{std::nullopt};
Hlc shard_map_version_;
// The key is not located in this shard
bool IsKeyInRange(const ShardRsmKey &key) const {
if (maximum_key_) [[likely]] {
return (key >= minimum_key_ && key <= maximum_key_);
}
return key >= minimum_key_;
}
public:
StorageReadResponse Read(StorageReadRequest request) const {
StorageReadResponse ret;
if (!IsKeyInRange(request.key)) {
ret.latest_known_shard_map_version = shard_map_version_;
ret.shard_rsm_success = false;
} else if (state_.contains(request.key)) {
ret.value = state_.at(request.key);
ret.shard_rsm_success = true;
} else {
ret.shard_rsm_success = false;
ret.value = std::nullopt;
}
return ret;
}
StorageWriteResponse Apply(StorageWriteRequest request) {
StorageWriteResponse ret;
// Key is outside the prohibited range
if (!IsKeyInRange(request.key)) {
ret.latest_known_shard_map_version = shard_map_version_;
ret.shard_rsm_success = false;
}
// Key exist
else if (state_.contains(request.key)) {
auto &val = state_[request.key];
/*
* Delete
*/
if (!request.value) {
ret.shard_rsm_success = true;
ret.last_value = val;
state_.erase(state_.find(request.key));
}
/*
* Update
*/
// Does old_value match?
if (request.value == val) {
ret.last_value = val;
ret.shard_rsm_success = true;
val = request.value.value();
} else {
ret.last_value = val;
ret.shard_rsm_success = false;
}
}
/*
* Create
*/
else {
ret.last_value = std::nullopt;
ret.shard_rsm_success = true;
state_.emplace(request.key, request.value.value());
}
return ret;
}
};
} // namespace memgraph::io::rsm

View File

@@ -23,13 +23,21 @@ namespace memgraph::io::simulator {
class Simulator {
std::mt19937 rng_;
std::shared_ptr<SimulatorHandle> simulator_handle_;
uint16_t auto_port_ = 0;
public:
explicit Simulator(SimulatorConfig config)
: rng_(std::mt19937{config.rng_seed}), simulator_handle_{std::make_shared<SimulatorHandle>(config)} {}
~Simulator() { ShutDown(); }
void ShutDown() { simulator_handle_->ShutDown(); }
Io<SimulatorTransport> RegisterNew() {
Address address = Address::TestAddress(auto_port_++);
return Register(address);
}
Io<SimulatorTransport> Register(Address address) {
std::uniform_int_distribution<uint64_t> seed_distrib;
uint64_t seed = seed_distrib(rng_);

View File

@@ -16,12 +16,10 @@
#include "io/simulator/simulator_stats.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
#include "utils/exceptions.hpp"
namespace memgraph::io::simulator {
using memgraph::io::Duration;
using memgraph::io::Time;
void SimulatorHandle::ShutDown() {
std::unique_lock<std::mutex> lock(mu_);
should_shut_down_ = true;
@@ -33,12 +31,17 @@ bool SimulatorHandle::ShouldShutDown() const {
return should_shut_down_;
}
LatencyHistogramSummaries SimulatorHandle::ResponseLatencies() {
std::unique_lock<std::mutex> lock(mu_);
return histograms_.ResponseLatencies();
}
void SimulatorHandle::IncrementServerCountAndWaitForQuiescentState(Address address) {
std::unique_lock<std::mutex> lock(mu_);
server_addresses_.insert(address);
while (true) {
const size_t blocked_servers = BlockedServers();
const size_t blocked_servers = blocked_on_receive_.size();
const bool all_servers_blocked = blocked_servers == server_addresses_.size();
@@ -50,23 +53,25 @@ void SimulatorHandle::IncrementServerCountAndWaitForQuiescentState(Address addre
}
}
size_t SimulatorHandle::BlockedServers() {
size_t blocked_servers = blocked_on_receive_;
for (auto &[promise_key, opaque_promise] : promises_) {
if (opaque_promise.promise.IsAwaited() && server_addresses_.contains(promise_key.requester_address)) {
blocked_servers++;
}
}
return blocked_servers;
}
bool SimulatorHandle::MaybeTickSimulator() {
std::unique_lock<std::mutex> lock(mu_);
const size_t blocked_servers = BlockedServers();
const size_t blocked_servers = blocked_on_receive_.size();
// Don't judge, this is a workaround for poc. gvolfing
server_count_++;
if (server_count_ == 3) {
is_quiescent_state_achieved_ = true;
}
// if (!is_quiescent_state_achieved_) {
if (!is_quiescent_state_achieved_) {
// return SimulatorProgression::DidSetUpOneServer;
cv_.notify_all(); // -> deadlock
// return false;// -> deadlock
return true; // -> deadlock
}
// if (blocked_servers < server_addresses_.size() && is_quiescent_state_achieved_) {
if (blocked_servers < server_addresses_.size()) {
// we only need to advance the simulator when all
// servers have reached a quiescent state, blocked
@@ -80,44 +85,63 @@ bool SimulatorHandle::MaybeTickSimulator() {
TimeoutPromisesPastDeadline();
auto sort_based_on_message_id = [](const std::pair<Address, OpaqueMessage> &lhs,
const std::pair<Address, OpaqueMessage> &rhs) {
// return a.second.request_id < b.second.request_id;
if (lhs.second.from_address != rhs.second.from_address) {
return lhs.second.from_address < rhs.second.from_address;
}
return lhs.second.request_id < rhs.second.request_id;
};
std::sort(in_flight_.begin(), in_flight_.end(), sort_based_on_message_id);
if (in_flight_.empty()) {
// return early here because there are no messages to schedule
// We tick the clock forward when all servers are blocked but
// there are no in-flight messages to schedule delivery of.
std::poisson_distribution<> time_distrib(50);
Duration clock_advance = std::chrono::microseconds{time_distrib(rng_)};
cluster_wide_time_microseconds_ += clock_advance;
// const Duration clock_advance = std::chrono::microseconds{Rand(time_distrib_)};
// cluster_wide_time_microseconds_ += clock_advance;
MG_ASSERT(cluster_wide_time_microseconds_ < config_.abort_time,
"Cluster has executed beyond its configured abort_time, and something may be failing to make progress "
"in an expected amount of time.");
if (cluster_wide_time_microseconds_ >= config_.abort_time) {
if (should_shut_down_) {
return false;
}
spdlog::error(
"Cluster has executed beyond its configured abort_time, and something may be failing to make progress "
"in an expected amount of time.");
throw utils::BasicException{"Cluster has executed beyond its configured abort_time"};
}
// spdlog::info(
// "Time increased with {} to {}", clock_advance.count(),
// std::chrono::duration_cast<std::chrono::milliseconds>(cluster_wide_time_microseconds_.time_since_epoch())
// .count());
return true;
}
if (config_.scramble_messages) {
// scramble messages
std::uniform_int_distribution<size_t> swap_distrib(0, in_flight_.size() - 1);
const size_t swap_index = swap_distrib(rng_);
const size_t swap_index = RandLocked(swap_distrib);
std::swap(in_flight_[swap_index], in_flight_.back());
}
auto [to_address, opaque_message] = std::move(in_flight_.back());
in_flight_.pop_back();
event_log_.AddAndLog(opaque_message, "Handle ");
std::uniform_int_distribution<int> drop_distrib(0, 99);
const int drop_threshold = drop_distrib(rng_);
const int drop_threshold = RandLocked(drop_distrib_);
const bool should_drop = drop_threshold < config_.drop_percent;
if (should_drop) {
stats_.dropped_messages++;
}
PromiseKey promise_key{.requester_address = to_address,
.request_id = opaque_message.request_id,
.replier_address = opaque_message.from_address};
PromiseKey promise_key{.requester_address = to_address, .request_id = opaque_message.request_id};
if (promises_.contains(promise_key)) {
event_log_.AddAndLog(opaque_message, "Promise contains");
// complete waiting promise if it's there
DeadlineAndOpaquePromise dop = std::move(promises_.at(promise_key));
promises_.erase(promise_key);
@@ -129,13 +153,24 @@ bool SimulatorHandle::MaybeTickSimulator() {
dop.promise.TimeOut();
} else {
stats_.total_responses++;
dop.promise.Fill(std::move(opaque_message));
Duration response_latency = cluster_wide_time_microseconds_ - dop.requested_at;
auto type_info = opaque_message.type_info;
dop.promise.Fill(std::move(opaque_message), response_latency);
histograms_.Measure(type_info, response_latency);
}
} else if (should_drop) {
event_log_.AddAndLog(opaque_message, "Dropped");
// don't add it anywhere, let it drop
} else {
event_log_.AddAndLog(opaque_message, "To can_receive");
// add to can_receive_ if not
const auto &[om_vec, inserted] = can_receive_.try_emplace(to_address, std::vector<OpaqueMessage>());
// This might be needed I am not sure, it can cause deadlock if you uncomment. Didn't find the issue yet.
// MG_ASSERT(server_addresses_.contains(to_address));
// MG_ASSERT(blocked_on_receive_.contains(to_address));
// blocked_on_receive_.erase(to_address);
const auto &[om_vec, inserted] =
can_receive_.try_emplace(to_address.ToPartialAddress(), std::vector<OpaqueMessage>());
om_vec->second.emplace_back(std::move(opaque_message));
}
@@ -147,6 +182,11 @@ Time SimulatorHandle::Now() const {
return cluster_wide_time_microseconds_;
}
Time SimulatorHandle::NowLocked() const {
// std::unique_lock<std::mutex> lock(mu_);
return cluster_wide_time_microseconds_;
}
SimulatorStats SimulatorHandle::Stats() {
std::unique_lock<std::mutex> lock(mu_);
return stats_;

View File

@@ -17,48 +17,70 @@
#include <map>
#include <memory>
#include <optional>
#include <queue>
#include <set>
#include <string>
#include <utility>
#include <variant>
#include <vector>
#include <sstream>
#include <boost/lexical_cast.hpp>
#include <boost/stacktrace.hpp>
#include <boost/uuid/uuid_io.hpp>
#include "fmt/format.h"
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/simulator/message_conversion.hpp"
#include "io/message_conversion.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/simulator/simulator_config.hpp"
#include "io/simulator/simulator_stats.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
#include "spdlog/spdlog.h"
namespace memgraph::io::simulator {
using memgraph::io::Duration;
using memgraph::io::Time;
struct PromiseKey {
Address requester_address;
struct EventDescriptor {
boost::asio::ip::address from_address_ip;
uint16_t from_address_port;
boost::asio::ip::address to_address_ip;
uint16_t to_address_port;
uint64_t request_id;
// TODO(tyler) possibly remove replier_address from promise key
// once we want to support DSR.
Address replier_address;
public:
friend bool operator<(const PromiseKey &lhs, const PromiseKey &rhs) {
if (lhs.requester_address != rhs.requester_address) {
return lhs.requester_address < rhs.requester_address;
}
if (lhs.request_id != rhs.request_id) {
return lhs.request_id < rhs.request_id;
}
return lhs.replier_address < rhs.replier_address;
}
std::string_view caller;
utils::TypeInfoRef type_info;
uint64_t event_id;
Time time;
};
struct DeadlineAndOpaquePromise {
Time deadline;
OpaquePromise promise;
class SimulatorHandle;
class EventLog {
std::vector<EventDescriptor> event_log_;
static constexpr const char *eventlog_signal_string_ = "EVENTLOG_UPDATE";
void LogEvent(const EventDescriptor &event) const {
spdlog::info(
fmt::format("{} ({})-> caller: {}, from_address: {}:{}, to_address: {}:{}, request_id: {}, type: {}, event_id: "
"{}, thread_id: {}",
eventlog_signal_string_,
std::chrono::duration_cast<std::chrono::milliseconds>(event.time.time_since_epoch()).count(),
event.caller, event.from_address_ip.to_string(), event.from_address_port,
event.to_address_ip.to_string(), event.to_address_port, event.request_id,
event.type_info.get().name(), event.event_id, std::this_thread::get_id()));
}
public:
SimulatorHandle *handle{nullptr};
void AddAndLog(const OpaqueMessage &message, std::string_view caller);
void LogAllEvents() const {
for (const auto &event : event_log_) {
LogEvent(event);
}
}
};
class SimulatorHandle {
@@ -72,42 +94,60 @@ class SimulatorHandle {
std::map<PromiseKey, DeadlineAndOpaquePromise> promises_;
// messages that are sent to servers that may later receive them
std::map<Address, std::vector<OpaqueMessage>> can_receive_;
std::map<PartialAddress, std::vector<OpaqueMessage>> can_receive_;
// maybe a boolean here
bool is_quiescent_state_achieved_ = false;
std::atomic<int> server_count_;
Time cluster_wide_time_microseconds_;
bool should_shut_down_ = false;
SimulatorStats stats_;
size_t blocked_on_receive_ = 0;
std::set<Address> blocked_on_receive_;
std::set<Address> server_addresses_;
std::mt19937 rng_;
std::uniform_int_distribution<int> time_distrib_{5, 50};
std::uniform_int_distribution<int> drop_distrib_{0, 99};
SimulatorConfig config_;
/// Returns the number of servers currently blocked on Receive, plus
/// the servers that are blocked on Futures that were created through
/// SimulatorTransport::Request.
///
/// TODO(tyler) investigate whether avoiding consideration of Futures
/// increases determinism.
size_t BlockedServers();
MessageHistogramCollector histograms_;
RequestId request_id_counter_{0};
EventLog event_log_;
void TimeoutPromisesPastDeadline() {
const Time now = cluster_wide_time_microseconds_;
for (auto &[promise_key, dop] : promises_) {
if (dop.deadline < now) {
spdlog::debug("timing out request from requester {} to replier {}.", promise_key.requester_address.ToString(),
promise_key.replier_address.ToString());
for (auto it = promises_.begin(); it != promises_.end();) {
auto &[promise_key, dop] = *it;
const bool timed_out = dop.deadline < now;
if (timed_out && config_.perform_timeouts) {
// spdlog::info("timing out request from requester {}.", promise_key.requester_address.ToString());
spdlog::info("timing out request from requester {}. bool timed_out: {}",
promise_key.requester_address.ToString(), timed_out);
std::move(dop).promise.TimeOut();
promises_.erase(promise_key);
it = promises_.erase(it);
stats_.timed_out_requests++;
} else {
++it;
}
}
}
public:
explicit SimulatorHandle(SimulatorConfig config)
: cluster_wide_time_microseconds_(config.start_time), rng_(config.rng_seed), config_(config) {}
: server_count_(0), cluster_wide_time_microseconds_(config.start_time), rng_(config.rng_seed), config_(config) {
spdlog::info("SimulatorHandle constructed.");
event_log_.handle = this;
}
LatencyHistogramSummaries ResponseLatencies();
~SimulatorHandle() {
for (auto it = promises_.begin(); it != promises_.end();) {
auto &[promise_key, dop] = *it;
std::move(dop).promise.TimeOut();
it = promises_.erase(it);
}
}
void IncrementServerCountAndWaitForQuiescentState(Address address);
@@ -122,70 +162,102 @@ class SimulatorHandle {
bool ShouldShutDown() const;
template <Message Request, Message Response>
void SubmitRequest(Address to_address, Address from_address, uint64_t request_id, Request &&request, Duration timeout,
ResponsePromise<Response> &&promise) {
ResponseFuture<Response> SubmitRequest(Address to_address, Address from_address, Request &&request, Duration timeout,
std::function<bool()> &&maybe_tick_simulator) {
auto type_info = TypeInfoFor(request);
auto [future, promise] = memgraph::io::FuturePromisePairWithNotifier<ResponseResult<Response>>(
std::forward<std::function<bool()>>(maybe_tick_simulator));
std::unique_lock<std::mutex> lock(mu_);
RequestId request_id = ++request_id_counter_;
const Time deadline = cluster_wide_time_microseconds_ + timeout;
std::any message(request);
OpaqueMessage om{.from_address = from_address, .request_id = request_id, .message = std::move(message)};
OpaqueMessage om{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message),
.type_info = type_info};
event_log_.AddAndLog(om, "SubmitRequest");
in_flight_.emplace_back(std::make_pair(to_address, std::move(om)));
PromiseKey promise_key{.requester_address = from_address, .request_id = request_id, .replier_address = to_address};
PromiseKey promise_key{.requester_address = from_address, .request_id = request_id};
OpaquePromise opaque_promise(std::move(promise).ToUnique());
DeadlineAndOpaquePromise dop{.deadline = deadline, .promise = std::move(opaque_promise)};
DeadlineAndOpaquePromise dop{
.requested_at = cluster_wide_time_microseconds_,
.deadline = deadline,
.promise = std::move(opaque_promise),
};
MG_ASSERT(!promises_.contains(promise_key));
promises_.emplace(std::move(promise_key), std::move(dop));
stats_.total_messages++;
stats_.total_requests++;
cv_.notify_all();
return std::move(future);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(const Address &receiver, Duration timeout) {
std::unique_lock<std::mutex> lock(mu_);
blocked_on_receive_ += 1;
blocked_on_receive_.emplace(receiver);
const Time deadline = cluster_wide_time_microseconds_ + timeout;
auto partial_address = receiver.ToPartialAddress();
while (!should_shut_down_ && (cluster_wide_time_microseconds_ < deadline)) {
if (can_receive_.contains(receiver)) {
std::vector<OpaqueMessage> &can_rx = can_receive_.at(receiver);
if (can_receive_.contains(partial_address)) {
std::vector<OpaqueMessage> &can_rx = can_receive_.at(partial_address);
if (!can_rx.empty()) {
OpaqueMessage message = std::move(can_rx.back());
can_rx.pop_back();
event_log_.AddAndLog(message, "Receivexxxxxx");
// TODO(tyler) search for item in can_receive_ that matches the desired types, rather
// than asserting that the last item in can_rx matches.
auto m_opt = std::move(message).Take<Ms...>();
MG_ASSERT(m_opt.has_value(), "Wrong message type received compared to the expected type");
blocked_on_receive_ -= 1;
blocked_on_receive_.erase(receiver);
return std::move(m_opt).value();
}
}
lock.unlock();
bool made_progress = MaybeTickSimulator();
auto simulator_progress = MaybeTickSimulator();
lock.lock();
if (!should_shut_down_ && !made_progress) {
if (!should_shut_down_ && !simulator_progress) {
cv_.wait(lock);
}
}
blocked_on_receive_ -= 1;
blocked_on_receive_.erase(receiver);
return TimedOut{};
}
template <Message M>
void Send(Address to_address, Address from_address, uint64_t request_id, M message) {
void Send(Address to_address, Address from_address, RequestId request_id, M message) {
auto type_info = TypeInfoFor(message);
std::unique_lock<std::mutex> lock(mu_);
std::any message_any(std::move(message));
OpaqueMessage om{.from_address = from_address, .request_id = request_id, .message = std::move(message_any)};
OpaqueMessage om{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message_any),
.type_info = type_info};
event_log_.AddAndLog(om, "Sendxxxxxxxxx");
in_flight_.emplace_back(std::make_pair(std::move(to_address), std::move(om)));
stats_.total_messages++;
@@ -195,12 +267,37 @@ class SimulatorHandle {
Time Now() const;
Time NowLocked() const;
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
std::unique_lock<std::mutex> lock(mu_);
return distrib(rng_);
return RandLocked<D, Return>(std::forward<D>(distrib));
}
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return RandLocked(D distrib) {
Return res = distrib(rng_);
spdlog::info("Getting random value from thread {}: {}. Stacktrace:\n{}", std::this_thread::get_id(), res,
boost::stacktrace::stacktrace());
return res;
}
SimulatorStats Stats();
};
inline void EventLog::AddAndLog(const OpaqueMessage &message, std::string_view caller) {
EventDescriptor event{.from_address_ip = message.from_address.last_known_ip,
.from_address_port = message.from_address.last_known_port,
.to_address_ip = message.to_address.last_known_ip,
.to_address_port = message.to_address.last_known_port,
.request_id = message.request_id,
.caller = caller,
.type_info = message.type_info,
.event_id = event_log_.size(),
.time = handle->NowLocked()};
event_log_.push_back(event);
LogEvent(event);
}
}; // namespace memgraph::io::simulator

View File

@@ -32,34 +32,35 @@ class SimulatorTransport {
SimulatorTransport(std::shared_ptr<SimulatorHandle> simulator_handle, Address address, uint64_t seed)
: simulator_handle_(simulator_handle), address_(address), rng_(std::mt19937{seed}) {}
template <Message Request, Message Response>
ResponseFuture<Response> Request(Address address, uint64_t request_id, Request request, Duration timeout) {
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, Address from_address, RequestT request, Duration timeout) {
std::function<bool()> maybe_tick_simulator = [this] { return simulator_handle_->MaybeTickSimulator(); };
auto [future, promise] =
memgraph::io::FuturePromisePairWithNotifier<ResponseResult<Response>>(maybe_tick_simulator);
simulator_handle_->SubmitRequest(address, address_, request_id, std::move(request), timeout, std::move(promise));
return std::move(future);
return simulator_handle_->template SubmitRequest<RequestT, ResponseT>(to_address, from_address, std::move(request),
timeout, std::move(maybe_tick_simulator));
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Duration timeout) {
return simulator_handle_->template Receive<Ms...>(address_, timeout);
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address receiver_address, Duration timeout) {
return simulator_handle_->template Receive<Ms...>(receiver_address, timeout);
}
template <Message M>
void Send(Address address, uint64_t request_id, M message) {
return simulator_handle_->template Send<M>(address, address_, request_id, message);
void Send(Address to_address, Address from_address, uint64_t request_id, M message) {
return simulator_handle_->template Send<M>(to_address, from_address, request_id, message);
}
Time Now() const { return simulator_handle_->Now(); }
bool ShouldShutDown() const { return simulator_handle_->ShouldShutDown(); }
template <class D = std::poisson_distribution<>, class Return = uint64_t>
template <class D = std::poisson_distribution<uint64_t>, class Return = uint64_t>
Return Rand(D distrib) {
return distrib(rng_);
// debug - gvolfing
auto ret = distrib(rng_);
return ret;
}
LatencyHistogramSummaries ResponseLatencies() { return simulator_handle_->ResponseLatencies(); }
};
}; // namespace memgraph::io::simulator

View File

@@ -16,6 +16,6 @@
namespace memgraph::io {
using Duration = std::chrono::microseconds;
using Time = std::chrono::time_point<std::chrono::local_t, Duration>;
using Time = std::chrono::time_point<std::chrono::system_clock, Duration>;
} // namespace memgraph::io

View File

@@ -19,6 +19,7 @@
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/future.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/time.hpp"
#include "utils/result.hpp"
@@ -32,11 +33,15 @@ using memgraph::utils::BasicResult;
template <typename T>
concept Message = std::same_as<T, std::decay_t<T>>;
using RequestId = uint64_t;
template <Message M>
struct ResponseEnvelope {
M message;
uint64_t request_id;
RequestId request_id;
Address to_address;
Address from_address;
Duration response_latency;
};
template <Message M>
@@ -51,7 +56,8 @@ using ResponsePromise = memgraph::io::Promise<ResponseResult<M>>;
template <Message... Ms>
struct RequestEnvelope {
std::variant<Ms...> message;
uint64_t request_id;
RequestId request_id;
Address to_address;
Address from_address;
};
@@ -62,8 +68,7 @@ template <typename I>
class Io {
I implementation_;
Address address_;
uint64_t request_id_counter_ = 0;
Duration default_timeout_ = std::chrono::microseconds{50000};
Duration default_timeout_ = std::chrono::microseconds{100000};
public:
Io(I io, Address address) : implementation_(io), address_(address) {}
@@ -72,27 +77,30 @@ class Io {
/// without an explicit timeout set.
void SetDefaultTimeout(Duration timeout) { default_timeout_ = timeout; }
/// Returns the current default timeout for this Io instance.
Duration GetDefaultTimeout() { return default_timeout_; }
/// Issue a request with an explicit timeout in microseconds provided. This tends to be used by clients.
template <Message Request, Message Response>
ResponseFuture<Response> RequestWithTimeout(Address address, Request request, Duration timeout) {
const uint64_t request_id = ++request_id_counter_;
return implementation_.template Request<Request, Response>(address, request_id, request, timeout);
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> RequestWithTimeout(Address address, RequestT request, Duration timeout) {
const Address from_address = address_;
return implementation_.template Request<RequestT, ResponseT>(address, from_address, request, timeout);
}
/// Issue a request that times out after the default timeout. This tends
/// to be used by clients.
template <Message Request, Message Response>
ResponseFuture<Response> Request(Address address, Request request) {
const uint64_t request_id = ++request_id_counter_;
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, RequestT request) {
const Duration timeout = default_timeout_;
return implementation_.template Request<Request, Response>(address, request_id, std::move(request), timeout);
const Address from_address = address_;
return implementation_.template Request<RequestT, ResponseT>(to_address, from_address, std::move(request), timeout);
}
/// Wait for an explicit number of microseconds for a request of one of the
/// provided types to arrive. This tends to be used by servers.
template <Message... Ms>
RequestResult<Ms...> ReceiveWithTimeout(Duration timeout) {
return implementation_.template Receive<Ms...>(timeout);
return implementation_.template Receive<Ms...>(address_, timeout);
}
/// Wait the default number of microseconds for a request of one of the
@@ -100,15 +108,16 @@ class Io {
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive() {
const Duration timeout = default_timeout_;
return implementation_.template Receive<Ms...>(timeout);
return implementation_.template Receive<Ms...>(address_, timeout);
}
/// Send a message in a best-effort fashion. This is used for messaging where
/// responses are not necessarily expected, and for servers to respond to requests.
/// If you need reliable delivery, this must be built on-top. TCP is not enough for most use cases.
template <Message M>
void Send(Address address, uint64_t request_id, M message) {
return implementation_.template Send<M>(address, request_id, std::move(message));
void Send(Address to_address, RequestId request_id, M message) {
Address from_address = address_;
return implementation_.template Send<M>(to_address, from_address, request_id, std::move(message));
}
/// The current system time. This time source should be preferred over any other,
@@ -126,5 +135,10 @@ class Io {
}
Address GetAddress() { return address_; }
void SetAddress(Address address) { address_ = address; }
Io<I> ForkLocal() { return Io(implementation_, address_.ForkUniqueAddress()); }
LatencyHistogramSummaries ResponseLatencies() { return implementation_.ResponseLatencies(); }
};
}; // namespace memgraph::io

View File

@@ -0,0 +1,47 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <algorithm>
#include <thread>
#include <boost/asio/ip/tcp.hpp>
#include "io/address.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/schemas.hpp"
namespace memgraph::machine_manager {
using memgraph::io::Address;
using memgraph::storage::v3::SchemaProperty;
using CompoundKey = std::vector<memgraph::storage::v3::PropertyValue>;
struct InitialLabelSpace {
std::string label_name;
std::vector<SchemaProperty> schema;
size_t replication_factor;
std::vector<CompoundKey> split_points;
};
struct MachineConfig {
std::vector<InitialLabelSpace> initial_label_spaces;
std::vector<Address> coordinator_addresses;
bool is_storage;
bool is_coordinator;
bool is_query_engine;
boost::asio::ip::address listen_ip;
uint16_t listen_port;
size_t shard_worker_threads = std::max(static_cast<unsigned int>(1), std::thread::hardware_concurrency());
};
} // namespace memgraph::machine_manager

View File

@@ -0,0 +1,204 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator_rsm.hpp"
#include "coordinator/coordinator_worker.hpp"
#include "io/message_conversion.hpp"
#include "io/messages.hpp"
#include "io/rsm/rsm_client.hpp"
#include "io/time.hpp"
#include "machine_manager/machine_config.hpp"
#include "storage/v3/shard_manager.hpp"
namespace memgraph::machine_manager {
using coordinator::Coordinator;
using coordinator::CoordinatorReadRequests;
using coordinator::CoordinatorReadResponses;
using coordinator::CoordinatorRsm;
using coordinator::CoordinatorWriteRequests;
using coordinator::CoordinatorWriteResponses;
using coordinator::coordinator_worker::CoordinatorWorker;
using CoordinatorRouteMessage = coordinator::coordinator_worker::RouteMessage;
using CoordinatorQueue = coordinator::coordinator_worker::Queue;
using io::ConvertVariant;
using io::Duration;
using io::RequestId;
using io::Time;
using io::messages::CoordinatorMessages;
using io::messages::ShardManagerMessages;
using io::messages::ShardMessages;
using io::messages::StorageReadRequest;
using io::messages::StorageWriteRequest;
using io::rsm::AppendRequest;
using io::rsm::AppendResponse;
using io::rsm::ReadRequest;
using io::rsm::VoteRequest;
using io::rsm::VoteResponse;
using io::rsm::WriteRequest;
using io::rsm::WriteResponse;
using storage::v3::ShardManager;
/// The MachineManager is responsible for:
/// * starting the entire system and ensuring that high-level
/// operational requirements continue to be met
/// * acting as a machine's single caller of Io::Receive
/// * routing incoming messages from the Io interface to the
/// appropriate Coordinator or to the StorageManager
/// (it's not necessary to route anything in this layer
/// to the query engine because the query engine only
/// communicates using higher-level Futures that will
/// be filled immediately when the response comes in
/// at the lower-level transport layer.
///
/// Every storage engine has exactly one RsmEngine.
template <typename IoImpl>
class MachineManager {
io::Io<IoImpl> io_;
MachineConfig config_;
Address coordinator_address_;
CoordinatorQueue coordinator_queue_;
std::jthread coordinator_handle_;
ShardManager<IoImpl> shard_manager_;
Time next_cron_ = Time::min();
public:
// TODO initialize ShardManager with "real" coordinator addresses instead of io.GetAddress
// which is only true for single-machine config.
MachineManager(io::Io<IoImpl> io, MachineConfig config, Coordinator coordinator)
: io_(io),
config_(config),
coordinator_address_(io.GetAddress().ForkUniqueAddress()),
shard_manager_{io.ForkLocal(), config.shard_worker_threads, coordinator_address_} {
auto coordinator_io = io.ForkLocal();
coordinator_io.SetAddress(coordinator_address_);
CoordinatorWorker coordinator_worker{coordinator_io, coordinator_queue_, coordinator};
coordinator_handle_ = std::jthread([coordinator = std::move(coordinator_worker)]() mutable { coordinator.Run(); });
}
MachineManager(MachineManager &&) noexcept = default;
MachineManager &operator=(MachineManager &&) noexcept = default;
MachineManager(const MachineManager &) = delete;
MachineManager &operator=(const MachineManager &) = delete;
~MachineManager() {
if (coordinator_handle_.joinable()) {
coordinator_queue_.Push(coordinator::coordinator_worker::ShutDown{});
coordinator_handle_.join();
}
}
Address CoordinatorAddress() { return coordinator_address_; }
void Run() {
while (!io_.ShouldShutDown()) {
const auto now = io_.Now();
if (now >= next_cron_) {
next_cron_ = Cron();
}
Duration receive_timeout = std::max(next_cron_, now) - now;
// Note: this parameter pack must be kept in-sync with the ReceiveWithTimeout parameter pack below
using AllMessages =
std::variant<ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse,
WriteResponse<CoordinatorWriteResponses>, ReadRequest<StorageReadRequest>,
AppendRequest<StorageWriteRequest>, WriteRequest<StorageWriteRequest>>;
spdlog::info("MM waiting on Receive on address {}", io_.GetAddress().ToString());
// Note: this parameter pack must be kept in-sync with the AllMessages parameter pack above
auto request_result = io_.template ReceiveWithTimeout<
ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse, WriteResponse<CoordinatorWriteResponses>,
ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>, WriteRequest<StorageWriteRequest>>(
receive_timeout);
if (request_result.HasError()) {
// time to do Cron
continue;
}
auto &&request_envelope = std::move(request_result.GetValue());
spdlog::info("MM got message to {}", request_envelope.to_address.ToString());
// If message is for the coordinator, cast it to subset and pass it to the coordinator
bool to_coordinator = coordinator_address_ == request_envelope.to_address;
if (to_coordinator) {
std::optional<CoordinatorMessages> conversion_attempt =
ConvertVariant<AllMessages, ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>,
AppendResponse, WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse>(
std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "coordinator message conversion failed");
spdlog::info("got coordinator message");
CoordinatorMessages &&cm = std::move(conversion_attempt.value());
CoordinatorRouteMessage route_message{
.message = std::move(cm),
.request_id = request_envelope.request_id,
.to = request_envelope.to_address,
.from = request_envelope.from_address,
};
coordinator_queue_.Push(std::move(route_message));
continue;
}
bool to_sm = shard_manager_.GetAddress() == request_envelope.to_address;
spdlog::info("smm: {}", shard_manager_.GetAddress().ToString());
if (to_sm) {
std::optional<ShardManagerMessages> conversion_attempt =
ConvertVariant<AllMessages, WriteResponse<CoordinatorWriteResponses>>(std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "shard manager message conversion failed");
spdlog::info("got shard manager message");
ShardManagerMessages &&smm = std::move(conversion_attempt.value());
shard_manager_.Receive(std::forward<ShardManagerMessages>(smm), request_envelope.request_id,
request_envelope.from_address);
continue;
}
// treat this as a message to a specific shard rsm and cast it accordingly
std::optional<ShardMessages> conversion_attempt =
ConvertVariant<AllMessages, ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>,
AppendResponse, WriteRequest<StorageWriteRequest>, VoteRequest, VoteResponse>(
std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "shard rsm message conversion failed for {} - incorrect message type",
request_envelope.to_address.ToString());
spdlog::info("got shard rsm message");
ShardMessages &&sm = std::move(conversion_attempt.value());
shard_manager_.Route(std::forward<ShardMessages>(sm), request_envelope.request_id, request_envelope.to_address,
request_envelope.from_address);
}
}
private:
Time Cron() {
spdlog::info("running MachineManager::Cron, address {}", io_.GetAddress().ToString());
coordinator_queue_.Push(coordinator::coordinator_worker::Cron{});
return shard_manager_.Cron();
}
};
} // namespace memgraph::machine_manager

File diff suppressed because it is too large Load Diff

41
src/parser/CMakeLists.txt Normal file
View File

@@ -0,0 +1,41 @@
## Generate Antlr openCypher parser
set(opencypher_frontend ${CMAKE_CURRENT_SOURCE_DIR}/opencypher)
set(opencypher_generated ${opencypher_frontend}/generated)
set(opencypher_lexer_grammar ${opencypher_frontend}/grammar/MemgraphCypherLexer.g4)
set(opencypher_parser_grammar ${opencypher_frontend}/grammar/MemgraphCypher.g4)
set(antlr_opencypher_generated_src
${opencypher_generated}/MemgraphCypherLexer.cpp
${opencypher_generated}/MemgraphCypher.cpp
${opencypher_generated}/MemgraphCypherBaseVisitor.cpp
${opencypher_generated}/MemgraphCypherVisitor.cpp
)
set(antlr_opencypher_generated_include
${opencypher_generated}/MemgraphCypherLexer.h
${opencypher_generated}/MemgraphCypher.h
${opencypher_generated}/MemgraphCypherBaseVisitor.h
${opencypher_generated}/MemgraphCypherVisitor.h
)
add_custom_command(
OUTPUT ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include}
COMMAND ${CMAKE_COMMAND} -E make_directory ${opencypher_generated}
COMMAND
java -jar ${CMAKE_SOURCE_DIR}/libs/antlr-4.10.1-complete.jar
-Dlanguage=Cpp -visitor -package antlropencypher
-o ${opencypher_generated}
${opencypher_lexer_grammar} ${opencypher_parser_grammar}
WORKING_DIRECTORY "${CMAKE_BINARY_DIR}"
DEPENDS
${opencypher_lexer_grammar} ${opencypher_parser_grammar}
${opencypher_frontend}/grammar/CypherLexer.g4
${opencypher_frontend}/grammar/Cypher.g4)
add_custom_target(generated_opencypher_parser
DEPENDS ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include})
add_library(mg-parser STATIC ${antlr_opencypher_generated_src})
add_dependencies(mg-parser generated_opencypher_parser)
target_include_directories(mg-parser PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
target_link_libraries(mg-parser antlr4)

View File

@@ -1,6 +1,6 @@
/*
* When changing this grammar make sure to update constants in
* src/query/frontend/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* src/parser/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* and bitsets) if needed.
*/

View File

@@ -15,7 +15,7 @@
/*
* When changing this grammar make sure to update constants in
* src/query/frontend/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* src/parser/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* and bitsets) if needed.
*/

View File

@@ -14,17 +14,29 @@
#include <string>
#include "antlr4-runtime.h"
#include "query/v2/exceptions.hpp"
#include "query/v2/frontend/opencypher/generated/MemgraphCypher.h"
#include "query/v2/frontend/opencypher/generated/MemgraphCypherLexer.h"
#include "utils/exceptions.hpp"
#include "parser/opencypher/generated/MemgraphCypher.h"
#include "parser/opencypher/generated/MemgraphCypherLexer.h"
#include "utils/concepts.hpp"
namespace memgraph::query::v2::frontend::opencypher {
namespace memgraph::frontend::opencypher {
class SyntaxException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
SyntaxException() : SyntaxException("") {}
};
/**
* Generates openCypher AST
* This thing must me a class since parser.cypher() returns pointer and there is
* no way for us to get ownership over the object.
*/
enum class ParserOpTag : uint8_t {
CYPHER, EXPRESSION
};
template<ParserOpTag Tag = ParserOpTag::CYPHER>
class Parser {
public:
/**
@@ -34,9 +46,14 @@ class Parser {
Parser(const std::string query) : query_(std::move(query)) {
parser_.removeErrorListeners();
parser_.addErrorListener(&error_listener_);
tree_ = parser_.cypher();
if constexpr(Tag == ParserOpTag::CYPHER) {
tree_ = parser_.cypher();
}
else {
tree_ = parser_.expression();
}
if (parser_.getNumberOfSyntaxErrors()) {
throw query::v2::SyntaxException(error_listener_.error_);
throw SyntaxException(error_listener_.error_);
}
}
@@ -65,4 +82,4 @@ class Parser {
antlropencypher::MemgraphCypher parser_{&tokens_};
antlr4::tree::ParseTree *tree_ = nullptr;
};
} // namespace memgraph::query::v2::frontend::opencypher
} // namespace memgraph::frontend::opencypher

View File

@@ -17,7 +17,7 @@
#include <unordered_set>
#include <vector>
namespace memgraph::query::v2 {
namespace parser {
namespace lexer_constants {
namespace trie {
@@ -2922,4 +2922,4 @@ const trie::Trie kSpecialTokens = {";",
"\xEF\xB9\xA3", // u8"\ufe63"
"\xEF\xBC\x8D"}; // u8"\uff0d"
} // namespace lexer_constants
} // namespace memgraph::query::v2
} // namespace parser

View File

@@ -1,7 +1,6 @@
define_add_lcp(add_lcp_query lcp_query_v2_cpp_files generated_lcp_query_v2_files)
add_lcp_query(frontend/ast/ast.lcp)
add_lcp_query(frontend/semantic/symbol.lcp)
add_lcp_query(plan/operator.lcp)
add_custom_target(generate_lcp_query_v2 DEPENDS ${generated_lcp_query_v2_files})
@@ -10,15 +9,9 @@ set(mg_query_v2_sources
${lcp_query_v2_cpp_files}
common.cpp
cypher_query_interpreter.cpp
dump.cpp
frontend/ast/cypher_main_visitor.cpp
frontend/ast/pretty_print.cpp
frontend/parsing.cpp
frontend/semantic/required_privileges.cpp
frontend/semantic/symbol_generator.cpp
frontend/stripped.cpp
interpret/awesome_memgraph_functions.cpp
interpret/eval.cpp
interpreter.cpp
metadata.cpp
plan/operator.cpp
@@ -29,25 +22,19 @@ set(mg_query_v2_sources
plan/rewrite/index_lookup.cpp
plan/rule_based_planner.cpp
plan/variable_start_planner.cpp
procedure/mg_procedure_impl.cpp
procedure/mg_procedure_helpers.cpp
procedure/module.cpp
procedure/py_module.cpp
serialization/property_value.cpp
stream/streams.cpp
stream/sources.cpp
stream/common.cpp
trigger.cpp
trigger_context.cpp
typed_value.cpp)
bindings/typed_value.cpp
accessors.cpp)
find_package(Boost REQUIRED)
add_library(mg-query-v2 STATIC ${mg_query_v2_sources})
add_dependencies(mg-query-v2 generate_lcp_query_v2)
target_include_directories(mg-query-v2 PUBLIC ${CMAKE_SOURCE_DIR}/include)
target_include_directories(mg-query-v2 PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/bindings)
target_link_libraries(mg-query-v2 dl cppitertools Boost::headers)
target_link_libraries(mg-query-v2 mg-integrations-pulsar mg-integrations-kafka mg-storage-v3 mg-license mg-utils mg-kvstore mg-memory)
target_link_libraries(mg-query-v2 mg-integrations-pulsar mg-integrations-kafka mg-storage-v3 mg-license mg-utils mg-kvstore mg-memory mg-coordinator)
target_link_libraries(mg-query-v2 mg-expr)
if(NOT "${MG_PYTHON_PATH}" STREQUAL "")
set(Python3_ROOT_DIR "${MG_PYTHON_PATH}")
@@ -60,45 +47,3 @@ else()
endif()
target_link_libraries(mg-query-v2 Python3::Python)
# Generate Antlr openCypher parser
set(opencypher_frontend ${CMAKE_CURRENT_SOURCE_DIR}/frontend/opencypher)
set(opencypher_generated ${opencypher_frontend}/generated)
set(opencypher_lexer_grammar ${opencypher_frontend}/grammar/MemgraphCypherLexer.g4)
set(opencypher_parser_grammar ${opencypher_frontend}/grammar/MemgraphCypher.g4)
set(antlr_opencypher_generated_src
${opencypher_generated}/MemgraphCypherLexer.cpp
${opencypher_generated}/MemgraphCypher.cpp
${opencypher_generated}/MemgraphCypherBaseVisitor.cpp
${opencypher_generated}/MemgraphCypherVisitor.cpp
)
set(antlr_opencypher_generated_include
${opencypher_generated}/MemgraphCypherLexer.h
${opencypher_generated}/MemgraphCypher.h
${opencypher_generated}/MemgraphCypherBaseVisitor.h
${opencypher_generated}/MemgraphCypherVisitor.h
)
add_custom_command(
OUTPUT ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include}
COMMAND ${CMAKE_COMMAND} -E make_directory ${opencypher_generated}
COMMAND
java -jar ${CMAKE_SOURCE_DIR}/libs/antlr-4.10.1-complete.jar
-Dlanguage=Cpp -visitor -package antlropencypher
-o ${opencypher_generated}
${opencypher_lexer_grammar} ${opencypher_parser_grammar}
WORKING_DIRECTORY "${CMAKE_BINARY_DIR}"
DEPENDS
${opencypher_lexer_grammar} ${opencypher_parser_grammar}
${opencypher_frontend}/grammar/CypherLexer.g4
${opencypher_frontend}/grammar/Cypher.g4)
add_custom_target(generate_opencypher_parser_v2
DEPENDS ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include})
add_library(antlr_opencypher_parser_lib_v2 STATIC ${antlr_opencypher_generated_src})
add_dependencies(antlr_opencypher_parser_lib_v2 generate_opencypher_parser_v2)
target_link_libraries(antlr_opencypher_parser_lib_v2 antlr4)
target_link_libraries(mg-query-v2 antlr_opencypher_parser_lib_v2)

View File

@@ -0,0 +1,96 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/accessors.hpp"
#include "query/v2/requests.hpp"
#include "query/v2/shard_request_manager.hpp"
#include "storage/v3/id_types.hpp"
namespace memgraph::query::v2::accessors {
EdgeAccessor::EdgeAccessor(Edge edge, const msgs::ShardRequestManagerInterface *manager)
: edge(std::move(edge)), manager_(manager) {}
EdgeTypeId EdgeAccessor::EdgeType() const { return edge.type.id; }
const std::vector<std::pair<PropertyId, Value>> &EdgeAccessor::Properties() const { return edge.properties; }
Value EdgeAccessor::GetProperty(const std::string &prop_name) const {
auto prop_id = manager_->NameToProperty(prop_name);
auto it = std::find_if(edge.properties.begin(), edge.properties.end(), [&](auto &pr) { return prop_id == pr.first; });
if (it == edge.properties.end()) {
return {};
}
return it->second;
}
const Edge &EdgeAccessor::GetEdge() const { return edge; }
bool EdgeAccessor::IsCycle() const { return edge.src == edge.dst; };
VertexAccessor EdgeAccessor::To() const {
return VertexAccessor(Vertex{edge.dst}, std::vector<std::pair<PropertyId, msgs::Value>>{}, manager_);
}
VertexAccessor EdgeAccessor::From() const {
return VertexAccessor(Vertex{edge.src}, std::vector<std::pair<PropertyId, msgs::Value>>{}, manager_);
}
VertexAccessor::VertexAccessor(Vertex v, std::vector<std::pair<PropertyId, Value>> props,
const msgs::ShardRequestManagerInterface *manager)
: vertex(std::move(v)), properties(std::move(props)), manager_(manager) {}
VertexAccessor::VertexAccessor(Vertex v, std::map<PropertyId, Value> &&props,
const msgs::ShardRequestManagerInterface *manager)
: vertex(std::move(v)), manager_(manager) {
properties.reserve(props.size());
for (auto &[id, value] : props) {
properties.emplace_back(std::make_pair(id, std::move(value)));
}
}
VertexAccessor::VertexAccessor(Vertex v, const std::map<PropertyId, Value> &props,
const msgs::ShardRequestManagerInterface *manager)
: vertex(std::move(v)), manager_(manager) {
properties.reserve(props.size());
for (const auto &[id, value] : props) {
properties.emplace_back(std::make_pair(id, value));
}
}
Label VertexAccessor::PrimaryLabel() const { return vertex.id.first; }
const msgs::VertexId &VertexAccessor::Id() const { return vertex.id; }
std::vector<Label> VertexAccessor::Labels() const { return vertex.labels; }
bool VertexAccessor::HasLabel(Label &label) const {
return std::find_if(vertex.labels.begin(), vertex.labels.end(),
[label](const auto &l) { return l.id == label.id; }) != vertex.labels.end();
}
const std::vector<std::pair<PropertyId, Value>> &VertexAccessor::Properties() const { return properties; }
Value VertexAccessor::GetProperty(PropertyId prop_id) const {
auto it = std::find_if(properties.begin(), properties.end(), [&](auto &pr) { return prop_id == pr.first; });
if (it == properties.end()) {
return {};
}
return it->second;
}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
Value VertexAccessor::GetProperty(const std::string &prop_name) const {
return GetProperty(manager_->NameToProperty(prop_name));
}
msgs::Vertex VertexAccessor::GetVertex() const { return vertex; }
} // namespace memgraph::query::v2::accessors

203
src/query/v2/accessors.hpp Normal file
View File

@@ -0,0 +1,203 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <map>
#include <optional>
#include <utility>
#include <vector>
#include "query/exceptions.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/view.hpp"
#include "utils/bound.hpp"
#include "utils/exceptions.hpp"
#include "utils/memory.hpp"
#include "utils/memory_tracker.hpp"
namespace memgraph::msgs {
class ShardRequestManagerInterface;
} // namespace memgraph::msgs
namespace memgraph::query::v2::accessors {
using Value = memgraph::msgs::Value;
using Edge = memgraph::msgs::Edge;
using Vertex = memgraph::msgs::Vertex;
using Label = memgraph::msgs::Label;
using PropertyId = memgraph::msgs::PropertyId;
using EdgeTypeId = memgraph::msgs::EdgeTypeId;
class VertexAccessor;
class EdgeAccessor final {
public:
explicit EdgeAccessor(Edge edge, const msgs::ShardRequestManagerInterface *manager);
[[nodiscard]] EdgeTypeId EdgeType() const;
[[nodiscard]] const std::vector<std::pair<PropertyId, Value>> &Properties() const;
[[nodiscard]] Value GetProperty(const std::string &prop_name) const;
[[nodiscard]] const Edge &GetEdge() const;
[[nodiscard]] bool IsCycle() const;
// Dummy function
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
[[nodiscard]] size_t CypherId() const { return 10; }
// bool HasSrcAccessor const { return src == nullptr; }
// bool HasDstAccessor const { return dst == nullptr; }
[[nodiscard]] VertexAccessor To() const;
[[nodiscard]] VertexAccessor From() const;
friend bool operator==(const EdgeAccessor &lhs, const EdgeAccessor &rhs) { return lhs.edge == rhs.edge; }
friend bool operator!=(const EdgeAccessor &lhs, const EdgeAccessor &rhs) { return !(lhs == rhs); }
private:
Edge edge;
const msgs::ShardRequestManagerInterface *manager_;
};
class VertexAccessor final {
public:
using PropertyId = msgs::PropertyId;
using Label = msgs::Label;
using VertexId = msgs::VertexId;
VertexAccessor(Vertex v, std::vector<std::pair<PropertyId, Value>> props,
const msgs::ShardRequestManagerInterface *manager);
VertexAccessor(Vertex v, std::map<PropertyId, Value> &&props, const msgs::ShardRequestManagerInterface *manager);
VertexAccessor(Vertex v, const std::map<PropertyId, Value> &props, const msgs::ShardRequestManagerInterface *manager);
[[nodiscard]] Label PrimaryLabel() const;
[[nodiscard]] const msgs::VertexId &Id() const;
[[nodiscard]] std::vector<Label> Labels() const;
[[nodiscard]] bool HasLabel(Label &label) const;
[[nodiscard]] const std::vector<std::pair<PropertyId, Value>> &Properties() const;
[[nodiscard]] Value GetProperty(PropertyId prop_id) const;
[[nodiscard]] Value GetProperty(const std::string &prop_name) const;
[[nodiscard]] msgs::Vertex GetVertex() const;
// Dummy function
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
[[nodiscard]] size_t CypherId() const { return 10; }
// auto InEdges(storage::View view, const std::vector<storage::EdgeTypeId> &edge_types) const
// -> storage::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
// auto maybe_edges = impl_.InEdges(view, edge_types);
// if (maybe_edges.HasError()) return maybe_edges.GetError();
// return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
// }
//
// auto InEdges(storage::View view) const { return InEdges(view, {}); }
//
// auto InEdges(storage::View view, const std::vector<storage::EdgeTypeId> &edge_types, const VertexAccessor &dest)
// const
// -> storage::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
// auto maybe_edges = impl_.InEdges(view, edge_types, &dest.impl_);
// if (maybe_edges.HasError()) return maybe_edges.GetError();
// return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
// }
//
// auto OutEdges(storage::View view, const std::vector<storage::EdgeTypeId> &edge_types) const
// -> storage::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
// auto maybe_edges = impl_.OutEdges(view, edge_types);
// if (maybe_edges.HasError()) return maybe_edges.GetError();
// return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
// }
//
// auto OutEdges(storage::View view) const { return OutEdges(view, {}); }
//
// auto OutEdges(storage::View view, const std::vector<storage::EdgeTypeId> &edge_types,
// const VertexAccessor &dest) const
// -> storage::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
// auto maybe_edges = impl_.OutEdges(view, edge_types, &dest.impl_);
// if (maybe_edges.HasError()) return maybe_edges.GetError();
// return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
// }
// storage::Result<size_t> InDegree(storage::View view) const { return impl_.InDegree(view); }
//
// storage::Result<size_t> OutDegree(storage::View view) const { return impl_.OutDegree(view); }
//
friend bool operator==(const VertexAccessor &lhs, const VertexAccessor &rhs) {
return lhs.vertex == rhs.vertex && lhs.properties == rhs.properties;
}
friend bool operator!=(const VertexAccessor &lhs, const VertexAccessor &rhs) { return !(lhs == rhs); }
private:
Vertex vertex;
std::vector<std::pair<PropertyId, Value>> properties;
const msgs::ShardRequestManagerInterface *manager_;
};
// inline VertexAccessor EdgeAccessor::To() const { return VertexAccessor(impl_.ToVertex()); }
// inline VertexAccessor EdgeAccessor::From() const { return VertexAccessor(impl_.FromVertex()); }
// Highly mocked interface. Won't work if used.
class Path {
public:
// Empty for now
explicit Path(const VertexAccessor & /*vertex*/, utils::MemoryResource *memory = utils::NewDeleteResource())
: mem(memory) {}
template <typename... TOthers>
explicit Path(const VertexAccessor &vertex, const TOthers &...others) {}
template <typename... TOthers>
Path(std::allocator_arg_t /*unused*/, utils::MemoryResource *memory, const VertexAccessor &vertex,
const TOthers &...others) {}
Path(const Path & /*other*/) {}
Path(const Path & /*other*/, utils::MemoryResource *memory) : mem(memory) {}
Path(Path && /*other*/) noexcept {}
Path(Path && /*other*/, utils::MemoryResource *memory) : mem(memory) {}
Path &operator=(const Path &path) {
if (this == &path) {
return *this;
}
return *this;
}
Path &operator=(Path &&path) noexcept {
if (this == &path) {
return *this;
}
return *this;
}
~Path() {}
friend bool operator==(const Path & /*lhs*/, const Path & /*rhs*/) { return true; };
utils::MemoryResource *GetMemoryResource() { return mem; }
private:
utils::MemoryResource *mem = utils::NewDeleteResource();
};
} // namespace memgraph::query::v2::accessors

View File

@@ -11,10 +11,6 @@
#pragma once
#include <functional>
#include <memory>
#include "query/v2/bindings/bindings.hpp"
namespace memgraph::query::v2::procedure {
class CypherType;
using CypherTypePtr = std::unique_ptr<CypherType, std::function<void(CypherType *)>>;
} // namespace memgraph::query::v2::procedure
#include "expr/ast/ast_visitor.hpp"

View File

@@ -0,0 +1,19 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#ifdef MG_AST_INCLUDE_PATH
#error You are probably trying to include files from expr from both the storage and query engines! You will have a rough time kid!
#endif
#define MG_AST_INCLUDE_PATH "query/v2/frontend/ast/ast.hpp" // NOLINT(cppcoreguidelines-macro-usage)
#define MG_INJECTED_NAMESPACE_NAME memgraph::query::v2 // NOLINT(cppcoreguidelines-macro-usage)

View File

@@ -10,10 +10,11 @@
// licenses/APL.txt.
#pragma once
#include <cstdint>
namespace memgraph::storage::v3::replication {
enum class ReplicationMode : std::uint8_t { SYNC, ASYNC };
#include "query/v2/bindings/bindings.hpp"
enum class ReplicaState : std::uint8_t { READY, REPLICATING, RECOVERY, INVALID };
} // namespace memgraph::storage::v3::replication
#include "expr/ast/cypher_main_visitor.hpp"
namespace memgraph::query::v2 {
using CypherMainVisitor = memgraph::expr::CypherMainVisitor;
} // namespace memgraph::query::v2

View File

@@ -0,0 +1,49 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/interpret/eval.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/context.hpp"
#include "query/v2/conversions.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/conversions.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/view.hpp"
namespace memgraph::msgs {
class ShardRequestManagerInterface;
} // namespace memgraph::msgs
namespace memgraph::query::v2 {
inline const auto lam = [](const auto &val) { return ValueToTypedValue(val); };
namespace detail {
class Callable {
public:
auto operator()(const memgraph::storage::v3::PropertyValue &val) const {
return memgraph::storage::v3::PropertyToTypedValue<TypedValue>(val);
};
auto operator()(const msgs::Value &val, memgraph::msgs::ShardRequestManagerInterface *manager) const {
return ValueToTypedValue(val, manager);
};
};
} // namespace detail
using ExpressionEvaluator = memgraph::expr::ExpressionEvaluator<
TypedValue, memgraph::query::v2::EvaluationContext, memgraph::msgs::ShardRequestManagerInterface, storage::v3::View,
storage::v3::LabelId, msgs::Value, detail::Callable, memgraph::storage::v3::Error, memgraph::expr::QueryEngineTag>;
} // namespace memgraph::query::v2

View File

@@ -0,0 +1,21 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "expr/interpret/frame.hpp"
namespace memgraph::query::v2 {
using Frame = memgraph::expr::Frame<TypedValue>;
} // namespace memgraph::query::v2

View File

@@ -11,13 +11,9 @@
#pragma once
#include <iostream>
#include "query/v2/bindings/bindings.hpp"
#include "query/v2/frontend/ast/ast.hpp"
#include "expr/ast/pretty_print.hpp"
namespace memgraph::query::v2 {
void PrintExpression(Expression *expr, std::ostream *out);
void PrintExpression(NamedExpression *expr, std::ostream *out);
} // namespace memgraph::query::v2

View File

@@ -0,0 +1,20 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol.hpp"
namespace memgraph::query::v2 {
using Symbol = memgraph::expr::Symbol;
} // namespace memgraph::query::v2

View File

@@ -0,0 +1,16 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol_generator.hpp"

View File

@@ -0,0 +1,20 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol_table.hpp"
namespace memgraph::query::v2 {
using SymbolTable = memgraph::expr::SymbolTable;
} // namespace memgraph::query::v2

View File

@@ -0,0 +1,19 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "expr/typed_value.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/path.hpp"
namespace memgraph::expr {
namespace v2 = memgraph::query::v2;
template class TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor, v2::accessors::Path>;
} // namespace memgraph::expr

View File

@@ -0,0 +1,27 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/typed_value.hpp"
#include "query/v2/accessors.hpp"
namespace memgraph::expr {
namespace v2 = memgraph::query::v2;
extern template class memgraph::expr::TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor,
v2::accessors::Path>;
} // namespace memgraph::expr
namespace memgraph::query::v2 {
using TypedValue =
memgraph::expr::TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor, v2::accessors::Path>;
} // namespace memgraph::query::v2

View File

@@ -18,15 +18,17 @@
#include <string_view>
#include <type_traits>
#include "query/v2/bindings/symbol.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/frontend/semantic/symbol.hpp"
#include "query/v2/typed_value.hpp"
#include "query/v2/path.hpp"
#include "storage/v3/conversions.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/schema_validator.hpp"
#include "storage/v3/shard_operation_result.hpp"
#include "storage/v3/view.hpp"
#include "utils/exceptions.hpp"
#include "utils/logging.hpp"
@@ -86,39 +88,17 @@ concept AccessorWithSetProperty = requires(T accessor, const storage::v3::Proper
{ accessor.SetProperty(key, new_value) } -> std::same_as<storage::v3::Result<storage::v3::PropertyValue>>;
};
inline void HandleSchemaViolation(const storage::v3::SchemaViolation &schema_violation, const DbAccessor &dba) {
switch (schema_violation.status) {
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_HAS_NO_PRIMARY_PROPERTY: {
throw SchemaViolationException(
fmt::format("Primary key {} not defined on label :{}",
storage::v3::SchemaTypeToString(schema_violation.violated_schema_property->type),
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::NO_SCHEMA_DEFINED_FOR_LABEL: {
throw SchemaViolationException(
fmt::format("Label :{} is not a primary label", dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_PROPERTY_WRONG_TYPE: {
throw SchemaViolationException(
fmt::format("Wrong type of property {} in schema :{}, should be of type {}",
*schema_violation.violated_property_value, dba.LabelToName(schema_violation.label),
storage::v3::SchemaTypeToString(schema_violation.violated_schema_property->type)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_UPDATE_PRIMARY_KEY: {
throw SchemaViolationException(fmt::format("Updating of primary key {} on schema :{} not supported",
*schema_violation.violated_property_value,
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_MODIFY_PRIMARY_LABEL: {
throw SchemaViolationException(fmt::format("Cannot add or remove label :{} since it is a primary label",
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_SECONDARY_LABEL_IS_PRIMARY: {
throw SchemaViolationException(
fmt::format("Cannot create vertex with secondary label :{}", dba.LabelToName(schema_violation.label)));
}
}
}
template <typename T>
concept AccessorWithSetPropertyAndValidate = requires(T accessor, const storage::v3::PropertyId key,
const storage::v3::PropertyValue new_value) {
{
accessor.SetPropertyAndValidate(key, new_value)
} -> std::same_as<storage::v3::ShardOperationResult<storage::v3::PropertyValue>>;
};
template <typename TRecordAccessor>
concept RecordAccessor =
AccessorWithSetProperty<TRecordAccessor> || AccessorWithSetPropertyAndValidate<TRecordAccessor>;
inline void HandleErrorOnPropertyUpdate(const storage::v3::Error error) {
switch (error) {
@@ -130,37 +110,9 @@ inline void HandleErrorOnPropertyUpdate(const storage::v3::Error error) {
throw QueryRuntimeException("Can't set property because properties on edges are disabled.");
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::NONEXISTENT_OBJECT:
throw QueryRuntimeException("Unexpected error when setting a property.");
}
}
case storage::v3::Error::VERTEX_ALREADY_INSERTED:
/// Set a property `value` mapped with given `key` on a `record`.
///
/// @throw QueryRuntimeException if value cannot be set as a property value
template <AccessorWithSetProperty T>
storage::v3::PropertyValue PropsSetChecked(T *record, const DbAccessor &dba, const storage::v3::PropertyId &key,
const TypedValue &value) {
try {
if constexpr (std::is_same_v<T, VertexAccessor>) {
const auto maybe_old_value = record->SetPropertyAndValidate(key, storage::v3::PropertyValue(value));
if (maybe_old_value.HasError()) {
std::visit(utils::Overloaded{[](const storage::v3::Error error) { HandleErrorOnPropertyUpdate(error); },
[&dba](const storage::v3::SchemaViolation &schema_violation) {
HandleSchemaViolation(schema_violation, dba);
}},
maybe_old_value.GetError());
}
return std::move(*maybe_old_value);
} else {
// No validation on edge properties
const auto maybe_old_value = record->SetProperty(key, storage::v3::PropertyValue(value));
if (maybe_old_value.HasError()) {
HandleErrorOnPropertyUpdate(maybe_old_value.GetError());
}
return std::move(*maybe_old_value);
}
} catch (const TypedValueException &) {
throw QueryRuntimeException("'{}' cannot be used as a property value.", value.type());
throw QueryRuntimeException("Unexpected error when setting a property.");
}
}

View File

@@ -13,16 +13,35 @@
#include <type_traits>
#include "io/local_transport/local_transport.hpp"
#include "query/v2/bindings/symbol_table.hpp"
#include "query/v2/common.hpp"
#include "query/v2/frontend/semantic/symbol_table.hpp"
#include "query/v2/metadata.hpp"
#include "query/v2/parameters.hpp"
#include "query/v2/plan/profile.hpp"
#include "query/v2/trigger.hpp"
//#include "query/v2/trigger.hpp"
#include "query/v2/shard_request_manager.hpp"
#include "utils/async_timer.hpp"
namespace memgraph::query::v2 {
// Used to store range of ids that are available
// Used for edge id assignment
class IdAllocator {
public:
IdAllocator() = default;
IdAllocator(uint64_t low, uint64_t high) : current_edge_id_{low}, max_id_{high} {};
uint64_t AllocateId() {
MG_ASSERT(current_edge_id_ < max_id_, "Current Edge Id went above max id");
return current_edge_id_++;
}
private:
uint64_t current_edge_id_;
uint64_t max_id_;
};
struct EvaluationContext {
/// Memory for allocations during evaluation of a *single* Pull call.
///
@@ -41,21 +60,28 @@ struct EvaluationContext {
mutable std::unordered_map<std::string, int64_t> counters;
};
inline std::vector<storage::v3::PropertyId> NamesToProperties(const std::vector<std::string> &property_names,
DbAccessor *dba) {
inline std::vector<storage::v3::PropertyId> NamesToProperties(
const std::vector<std::string> &property_names, msgs::ShardRequestManagerInterface *shard_request_manager) {
std::vector<storage::v3::PropertyId> properties;
// TODO Fix by using reference
properties.reserve(property_names.size());
for (const auto &name : property_names) {
properties.push_back(dba->NameToProperty(name));
if (shard_request_manager != nullptr) {
for (const auto &name : property_names) {
properties.push_back(shard_request_manager->NameToProperty(name));
}
}
return properties;
}
inline std::vector<storage::v3::LabelId> NamesToLabels(const std::vector<std::string> &label_names, DbAccessor *dba) {
inline std::vector<storage::v3::LabelId> NamesToLabels(const std::vector<std::string> &label_names,
msgs::ShardRequestManagerInterface *shard_request_manager) {
std::vector<storage::v3::LabelId> labels;
labels.reserve(label_names.size());
for (const auto &name : label_names) {
labels.push_back(dba->NameToLabel(name));
// TODO Fix by using reference
if (shard_request_manager != nullptr) {
for (const auto &name : label_names) {
labels.push_back(shard_request_manager->NameToLabel(name));
}
}
return labels;
}
@@ -70,8 +96,9 @@ struct ExecutionContext {
plan::ProfilingStats stats;
plan::ProfilingStats *stats_root{nullptr};
ExecutionStats execution_stats;
TriggerContextCollector *trigger_context_collector{nullptr};
utils::AsyncTimer timer;
msgs::ShardRequestManagerInterface *shard_request_manager{nullptr};
IdAllocator *edge_ids_alloc;
};
static_assert(std::is_move_assignable_v<ExecutionContext>, "ExecutionContext must be move assignable!");

View File

@@ -0,0 +1,103 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "bindings/typed_value.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/requests.hpp"
#include "query/v2/shard_request_manager.hpp"
namespace memgraph::query::v2 {
inline TypedValue ValueToTypedValue(const msgs::Value &value, msgs::ShardRequestManagerInterface *manager) {
using Value = msgs::Value;
switch (value.type) {
case Value::Type::Null:
return {};
case Value::Type::Bool:
return TypedValue(value.bool_v);
case Value::Type::Int64:
return TypedValue(value.int_v);
case Value::Type::Double:
return TypedValue(value.double_v);
case Value::Type::String:
return TypedValue(value.string_v);
case Value::Type::List: {
const auto &lst = value.list_v;
std::vector<TypedValue> dst;
dst.reserve(lst.size());
for (const auto &elem : lst) {
dst.push_back(ValueToTypedValue(elem, manager));
}
return TypedValue(std::move(dst));
}
case Value::Type::Map: {
const auto &value_map = value.map_v;
std::map<std::string, TypedValue> dst;
for (const auto &[key, val] : value_map) {
dst[key] = ValueToTypedValue(val, manager);
}
return TypedValue(std::move(dst));
}
case Value::Type::Vertex:
return TypedValue(accessors::VertexAccessor(
value.vertex_v, std::vector<std::pair<storage::v3::PropertyId, msgs::Value>>{}, manager));
case Value::Type::Edge:
return TypedValue(accessors::EdgeAccessor(value.edge_v, manager));
}
throw std::runtime_error("Incorrect type in conversion");
}
inline msgs::Value TypedValueToValue(const TypedValue &value) {
using Value = msgs::Value;
switch (value.type()) {
case TypedValue::Type::Null:
return {};
case TypedValue::Type::Bool:
return Value(value.ValueBool());
case TypedValue::Type::Int:
return Value(value.ValueInt());
case TypedValue::Type::Double:
return Value(value.ValueDouble());
case TypedValue::Type::String:
return Value(std::string(value.ValueString()));
case TypedValue::Type::List: {
const auto &lst = value.ValueList();
std::vector<Value> dst;
dst.reserve(lst.size());
for (const auto &elem : lst) {
dst.push_back(TypedValueToValue(elem));
}
return Value(std::move(dst));
}
case TypedValue::Type::Map: {
const auto &value_map = value.ValueMap();
std::map<std::string, Value> dst;
for (const auto &[key, val] : value_map) {
dst[std::string(key)] = TypedValueToValue(val);
}
return Value(std::move(dst));
}
case TypedValue::Type::Vertex:
return Value(value.ValueVertex().GetVertex());
case TypedValue::Type::Edge:
return Value(value.ValueEdge().GetEdge());
case TypedValue::Type::Path:
case TypedValue::Type::LocalTime:
case TypedValue::Type::LocalDateTime:
case TypedValue::Type::Date:
case TypedValue::Type::Duration:
break;
}
throw std::runtime_error("Incorrect type in conversion");
}
} // namespace memgraph::query::v2

View File

@@ -10,6 +10,8 @@
// licenses/APL.txt.
#include "query/v2/cypher_query_interpreter.hpp"
#include "query/v2/bindings/symbol_generator.hpp"
#include "query/v2/shard_request_manager.hpp"
// NOLINTNEXTLINE (cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_HIDDEN_bool(query_cost_planner, true, "Use the cost-estimating query planner.");
@@ -46,7 +48,7 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
auto hash = stripped_query.hash();
auto accessor = cache->access();
auto it = accessor.find(hash);
std::unique_ptr<frontend::opencypher::Parser> parser;
std::unique_ptr<memgraph::frontend::opencypher::Parser<>> parser;
// Return a copy of both the AST storage and the query.
CachedQuery result;
@@ -63,11 +65,11 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
if (it == accessor.end()) {
try {
parser = std::make_unique<frontend::opencypher::Parser>(stripped_query.query());
parser = std::make_unique<memgraph::frontend::opencypher::Parser<>>(stripped_query.query());
} catch (const SyntaxException &e) {
// There is a syntax exception in the stripped query. Re-run the parser
// on the original query to get an appropriate error messsage.
parser = std::make_unique<frontend::opencypher::Parser>(query_string);
parser = std::make_unique<memgraph::frontend::opencypher::Parser<>>(query_string);
// If an exception was not thrown here, the stripper messed something
// up.
@@ -76,8 +78,8 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
// Convert the ANTLR4 parse tree into an AST.
AstStorage ast_storage;
frontend::ParsingContext context{true};
frontend::CypherMainVisitor visitor(context, &ast_storage);
expr::ParsingContext context{true};
memgraph::expr::CypherMainVisitor visitor(context, &ast_storage);
visitor.visit(parser->tree());
@@ -116,10 +118,10 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
}
std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery *query, const Parameters &parameters,
DbAccessor *db_accessor,
msgs::ShardRequestManagerInterface *shard_manager,
const std::vector<Identifier *> &predefined_identifiers) {
auto vertex_counts = plan::MakeVertexCountCache(db_accessor);
auto symbol_table = MakeSymbolTable(query, predefined_identifiers);
auto vertex_counts = plan::MakeVertexCountCache(shard_manager);
auto symbol_table = expr::MakeSymbolTable(query, predefined_identifiers);
auto planning_context = plan::MakePlanningContext(&ast_storage, &symbol_table, query, &vertex_counts);
auto [root, cost] = plan::MakeLogicalPlan(&planning_context, parameters, FLAGS_query_cost_planner);
return std::make_unique<SingleNodeLogicalPlan>(std::move(root), cost, std::move(ast_storage),
@@ -128,7 +130,7 @@ std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery
std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_storage, CypherQuery *query,
const Parameters &parameters, utils::SkipList<PlanCacheEntry> *plan_cache,
DbAccessor *db_accessor,
msgs::ShardRequestManagerInterface *shard_manager,
const std::vector<Identifier *> &predefined_identifiers) {
std::optional<utils::SkipList<PlanCacheEntry>::Accessor> plan_cache_access;
if (plan_cache) {
@@ -144,7 +146,7 @@ std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_stor
}
auto plan = std::make_shared<CachedPlan>(
MakeLogicalPlan(std::move(ast_storage), query, parameters, db_accessor, predefined_identifiers));
MakeLogicalPlan(std::move(ast_storage), query, parameters, shard_manager, predefined_identifiers));
if (plan_cache_access) {
plan_cache_access->insert({hash, plan});
}

View File

@@ -11,11 +11,11 @@
#pragma once
#include "parser/opencypher/parser.hpp"
#include "query/v2/bindings/cypher_main_visitor.hpp"
#include "query/v2/bindings/symbol_table.hpp"
#include "query/v2/config.hpp"
#include "query/v2/frontend/ast/cypher_main_visitor.hpp"
#include "query/v2/frontend/opencypher/parser.hpp"
#include "query/v2/frontend/semantic/required_privileges.hpp"
#include "query/v2/frontend/semantic/symbol_generator.hpp"
#include "query/v2/frontend/stripped.hpp"
#include "query/v2/plan/planner.hpp"
#include "utils/flag_validation.hpp"
@@ -132,7 +132,7 @@ class SingleNodeLogicalPlan final : public LogicalPlan {
};
std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery *query, const Parameters &parameters,
DbAccessor *db_accessor,
msgs::ShardRequestManagerInterface *shard_manager,
const std::vector<Identifier *> &predefined_identifiers);
/**
@@ -145,7 +145,7 @@ std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery
*/
std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_storage, CypherQuery *query,
const Parameters &parameters, utils::SkipList<PlanCacheEntry> *plan_cache,
DbAccessor *db_accessor,
msgs::ShardRequestManagerInterface *shard_manager,
const std::vector<Identifier *> &predefined_identifiers = {});
} // namespace memgraph::query::v2

View File

@@ -11,6 +11,7 @@
#pragma once
#include <cstdint>
#include <optional>
#include <vector>
@@ -19,8 +20,10 @@
#include "query/v2/exceptions.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/key_store.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/shard_operation_result.hpp"
///////////////////////////////////////////////////////////
// Our communication layer and query engine don't mix
@@ -109,15 +112,21 @@ class VertexAccessor final {
auto PrimaryLabel(storage::v3::View view) const { return impl_.PrimaryLabel(view); }
storage::v3::Result<bool> AddLabel(storage::v3::LabelId label) { return impl_.AddLabel(label); }
auto PrimaryKey(storage::v3::View view) const { return impl_.PrimaryKey(view); }
storage::v3::ResultSchema<bool> AddLabelAndValidate(storage::v3::LabelId label) {
storage::v3::ShardOperationResult<bool> AddLabel(storage::v3::LabelId label) {
return impl_.AddLabelAndValidate(label);
}
storage::v3::Result<bool> RemoveLabel(storage::v3::LabelId label) { return impl_.RemoveLabel(label); }
storage::v3::ShardOperationResult<bool> AddLabelAndValidate(storage::v3::LabelId label) {
return impl_.AddLabelAndValidate(label);
}
storage::v3::ResultSchema<bool> RemoveLabelAndValidate(storage::v3::LabelId label) {
storage::v3::ShardOperationResult<bool> RemoveLabel(storage::v3::LabelId label) {
return impl_.RemoveLabelAndValidate(label);
}
storage::v3::ShardOperationResult<bool> RemoveLabelAndValidate(storage::v3::LabelId label) {
return impl_.RemoveLabelAndValidate(label);
}
@@ -132,17 +141,17 @@ class VertexAccessor final {
return impl_.GetProperty(key, view);
}
storage::v3::Result<storage::v3::PropertyValue> SetProperty(storage::v3::PropertyId key,
const storage::v3::PropertyValue &value) {
return impl_.SetProperty(key, value);
storage::v3::ShardOperationResult<storage::v3::PropertyValue> SetProperty(storage::v3::PropertyId key,
const storage::v3::PropertyValue &value) {
return impl_.SetPropertyAndValidate(key, value);
}
storage::v3::ResultSchema<storage::v3::PropertyValue> SetPropertyAndValidate(
storage::v3::ShardOperationResult<storage::v3::PropertyValue> SetPropertyAndValidate(
storage::v3::PropertyId key, const storage::v3::PropertyValue &value) {
return impl_.SetPropertyAndValidate(key, value);
}
storage::v3::ResultSchema<storage::v3::PropertyValue> RemovePropertyAndValidate(storage::v3::PropertyId key) {
storage::v3::ShardOperationResult<storage::v3::PropertyValue> RemovePropertyAndValidate(storage::v3::PropertyId key) {
return SetPropertyAndValidate(key, storage::v3::PropertyValue{});
}
@@ -162,7 +171,8 @@ class VertexAccessor final {
auto InEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types,
const VertexAccessor &dest) const
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
auto maybe_edges = impl_.InEdges(view, edge_types, &dest.impl_);
const auto dest_id = dest.impl_.Id(view).GetValue();
auto maybe_edges = impl_.InEdges(view, edge_types, &dest_id);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
}
@@ -179,7 +189,8 @@ class VertexAccessor final {
auto OutEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types,
const VertexAccessor &dest) const
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
auto maybe_edges = impl_.OutEdges(view, edge_types, &dest.impl_);
const auto dest_id = dest.impl_.Id(view).GetValue();
auto maybe_edges = impl_.OutEdges(view, edge_types, &dest_id);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
}
@@ -188,9 +199,8 @@ class VertexAccessor final {
storage::v3::Result<size_t> OutDegree(storage::v3::View view) const { return impl_.OutDegree(view); }
int64_t CypherId() const { return impl_.Gid().AsInt(); }
storage::v3::Gid Gid() const noexcept { return impl_.Gid(); }
// TODO(jbajic) Fix Remove Gid
static int64_t CypherId() { return 1; }
bool operator==(const VertexAccessor &v) const noexcept {
static_assert(noexcept(impl_ == v.impl_));
@@ -200,198 +210,19 @@ class VertexAccessor final {
bool operator!=(const VertexAccessor &v) const noexcept { return !(*this == v); }
};
inline VertexAccessor EdgeAccessor::To() const { return VertexAccessor(impl_.ToVertex()); }
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wnull-dereference"
// NOLINTNEXTLINE(readability-convert-member-functions-to-static,clang-analyzer-core.NonNullParamChecker)
inline VertexAccessor EdgeAccessor::To() const { return *static_cast<VertexAccessor *>(nullptr); }
inline VertexAccessor EdgeAccessor::From() const { return VertexAccessor(impl_.FromVertex()); }
// NOLINTNEXTLINE(readability-convert-member-functions-to-static,clang-analyzer-core.NonNullParamChecker)
inline VertexAccessor EdgeAccessor::From() const { return *static_cast<VertexAccessor *>(nullptr); }
#pragma clang diagnostic pop
inline bool EdgeAccessor::IsCycle() const { return To() == From(); }
class DbAccessor final {
storage::v3::Storage::Accessor *accessor_;
class VerticesIterable final {
storage::v3::VerticesIterable iterable_;
public:
class Iterator final {
storage::v3::VerticesIterable::Iterator it_;
public:
explicit Iterator(storage::v3::VerticesIterable::Iterator it) : it_(it) {}
VertexAccessor operator*() const { return VertexAccessor(*it_); }
Iterator &operator++() {
++it_;
return *this;
}
bool operator==(const Iterator &other) const { return it_ == other.it_; }
bool operator!=(const Iterator &other) const { return !(other == *this); }
};
explicit VerticesIterable(storage::v3::VerticesIterable iterable) : iterable_(std::move(iterable)) {}
Iterator begin() { return Iterator(iterable_.begin()); }
Iterator end() { return Iterator(iterable_.end()); }
};
public:
explicit DbAccessor(storage::v3::Storage::Accessor *accessor) : accessor_(accessor) {}
std::optional<VertexAccessor> FindVertex(storage::v3::Gid gid, storage::v3::View view) {
auto maybe_vertex = accessor_->FindVertex(gid, view);
if (maybe_vertex) return VertexAccessor(*maybe_vertex);
return std::nullopt;
}
void FinalizeTransaction() { accessor_->FinalizeTransaction(); }
VerticesIterable Vertices(storage::v3::View view) { return VerticesIterable(accessor_->Vertices(view)); }
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label) {
return VerticesIterable(accessor_->Vertices(label, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property) {
return VerticesIterable(accessor_->Vertices(label, property, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property,
const storage::v3::PropertyValue &value) {
return VerticesIterable(accessor_->Vertices(label, property, value, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &lower,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &upper) {
return VerticesIterable(accessor_->Vertices(label, property, lower, upper, view));
}
// TODO Remove when query modules have been fixed
[[deprecated]] VertexAccessor InsertVertex() { return VertexAccessor(accessor_->CreateVertex()); }
storage::v3::ResultSchema<VertexAccessor> InsertVertexAndValidate(
const storage::v3::LabelId primary_label, const std::vector<storage::v3::LabelId> &labels,
const std::vector<std::pair<storage::v3::PropertyId, storage::v3::PropertyValue>> &properties) {
auto maybe_vertex_acc = accessor_->CreateVertexAndValidate(primary_label, labels, properties);
if (maybe_vertex_acc.HasError()) {
return {std::move(maybe_vertex_acc.GetError())};
}
return VertexAccessor{maybe_vertex_acc.GetValue()};
}
storage::v3::Result<EdgeAccessor> InsertEdge(VertexAccessor *from, VertexAccessor *to,
const storage::v3::EdgeTypeId &edge_type) {
auto maybe_edge = accessor_->CreateEdge(&from->impl_, &to->impl_, edge_type);
if (maybe_edge.HasError()) return storage::v3::Result<EdgeAccessor>(maybe_edge.GetError());
return EdgeAccessor(*maybe_edge);
}
storage::v3::Result<std::optional<EdgeAccessor>> RemoveEdge(EdgeAccessor *edge) {
auto res = accessor_->DeleteEdge(&edge->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<EdgeAccessor>{};
}
return std::make_optional<EdgeAccessor>(*value);
}
storage::v3::Result<std::optional<std::pair<VertexAccessor, std::vector<EdgeAccessor>>>> DetachRemoveVertex(
VertexAccessor *vertex_accessor) {
using ReturnType = std::pair<VertexAccessor, std::vector<EdgeAccessor>>;
auto res = accessor_->DetachDeleteVertex(&vertex_accessor->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<ReturnType>{};
}
const auto &[vertex, edges] = *value;
std::vector<EdgeAccessor> deleted_edges;
deleted_edges.reserve(edges.size());
std::transform(edges.begin(), edges.end(), std::back_inserter(deleted_edges),
[](const auto &deleted_edge) { return EdgeAccessor{deleted_edge}; });
return std::make_optional<ReturnType>(vertex, std::move(deleted_edges));
}
storage::v3::Result<std::optional<VertexAccessor>> RemoveVertex(VertexAccessor *vertex_accessor) {
auto res = accessor_->DeleteVertex(&vertex_accessor->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<VertexAccessor>{};
}
return {std::make_optional<VertexAccessor>(*value)};
}
storage::v3::PropertyId NameToProperty(const std::string_view name) { return accessor_->NameToProperty(name); }
storage::v3::LabelId NameToLabel(const std::string_view name) { return accessor_->NameToLabel(name); }
storage::v3::EdgeTypeId NameToEdgeType(const std::string_view name) { return accessor_->NameToEdgeType(name); }
const std::string &PropertyToName(storage::v3::PropertyId prop) const { return accessor_->PropertyToName(prop); }
const std::string &LabelToName(storage::v3::LabelId label) const { return accessor_->LabelToName(label); }
const std::string &EdgeTypeToName(storage::v3::EdgeTypeId type) const { return accessor_->EdgeTypeToName(type); }
void AdvanceCommand() { accessor_->AdvanceCommand(); }
utils::BasicResult<storage::v3::ConstraintViolation, void> Commit() { return accessor_->Commit(); }
void Abort() { accessor_->Abort(); }
bool LabelIndexExists(storage::v3::LabelId label) const { return accessor_->LabelIndexExists(label); }
bool LabelPropertyIndexExists(storage::v3::LabelId label, storage::v3::PropertyId prop) const {
return accessor_->LabelPropertyIndexExists(label, prop);
}
int64_t VerticesCount() const { return accessor_->ApproximateVertexCount(); }
int64_t VerticesCount(storage::v3::LabelId label) const { return accessor_->ApproximateVertexCount(label); }
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property) const {
return accessor_->ApproximateVertexCount(label, property);
}
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property,
const storage::v3::PropertyValue &value) const {
return accessor_->ApproximateVertexCount(label, property, value);
}
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &lower,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &upper) const {
return accessor_->ApproximateVertexCount(label, property, lower, upper);
}
storage::v3::IndicesInfo ListAllIndices() const { return accessor_->ListAllIndices(); }
storage::v3::ConstraintsInfo ListAllConstraints() const { return accessor_->ListAllConstraints(); }
const storage::v3::SchemaValidator &GetSchemaValidator() const { return accessor_->GetSchemaValidator(); }
storage::v3::SchemasInfo ListAllSchemas() const { return accessor_->ListAllSchemas(); }
};
} // namespace memgraph::query::v2

View File

@@ -13,7 +13,7 @@
#include <vector>
#include "query/v2/typed_value.hpp"
#include "query/v2/bindings/typed_value.hpp"
namespace memgraph::query::v2 {
struct DiscardValueResultStream final {

View File

@@ -1,541 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/dump.hpp"
#include <iomanip>
#include <limits>
#include <map>
#include <optional>
#include <ostream>
#include <utility>
#include <vector>
#include <fmt/format.h>
#include "query/v2/db_accessor.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/stream.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/storage.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
#include "utils/temporal.hpp"
namespace memgraph::query::v2 {
namespace {
// Property that is used to make a difference among vertices. It is added to
// property set of vertices to match edges and removed after the entire graph
// is built.
const char *kInternalPropertyId = "__mg_id__";
// Label that is attached to each vertex and is used for easier creation of
// index on internal property id.
const char *kInternalVertexLabel = "__mg_vertex__";
/// A helper function that escapes label, edge type and property names.
std::string EscapeName(const std::string_view value) {
std::string out;
out.reserve(value.size() + 2);
out.append(1, '`');
for (auto c : value) {
if (c == '`') {
out.append("``");
} else {
out.append(1, c);
}
}
out.append(1, '`');
return out;
}
void DumpPreciseDouble(std::ostream *os, double value) {
// A temporary stream is used to keep precision of the original output
// stream unchanged.
std::ostringstream temp_oss;
temp_oss << std::setprecision(std::numeric_limits<double>::max_digits10) << value;
*os << temp_oss.str();
}
namespace {
void DumpDate(std::ostream &os, const storage::v3::TemporalData &value) {
utils::Date date(value.microseconds);
os << "DATE(\"" << date << "\")";
}
void DumpLocalTime(std::ostream &os, const storage::v3::TemporalData &value) {
utils::LocalTime lt(value.microseconds);
os << "LOCALTIME(\"" << lt << "\")";
}
void DumpLocalDateTime(std::ostream &os, const storage::v3::TemporalData &value) {
utils::LocalDateTime ldt(value.microseconds);
os << "LOCALDATETIME(\"" << ldt << "\")";
}
void DumpDuration(std::ostream &os, const storage::v3::TemporalData &value) {
utils::Duration dur(value.microseconds);
os << "DURATION(\"" << dur << "\")";
}
void DumpTemporalData(std::ostream &os, const storage::v3::TemporalData &value) {
switch (value.type) {
case storage::v3::TemporalType::Date: {
DumpDate(os, value);
return;
}
case storage::v3::TemporalType::LocalTime: {
DumpLocalTime(os, value);
return;
}
case storage::v3::TemporalType::LocalDateTime: {
DumpLocalDateTime(os, value);
return;
}
case storage::v3::TemporalType::Duration: {
DumpDuration(os, value);
return;
}
}
}
} // namespace
void DumpPropertyValue(std::ostream *os, const storage::v3::PropertyValue &value) {
switch (value.type()) {
case storage::v3::PropertyValue::Type::Null:
*os << "Null";
return;
case storage::v3::PropertyValue::Type::Bool:
*os << (value.ValueBool() ? "true" : "false");
return;
case storage::v3::PropertyValue::Type::String:
*os << utils::Escape(value.ValueString());
return;
case storage::v3::PropertyValue::Type::Int:
*os << value.ValueInt();
return;
case storage::v3::PropertyValue::Type::Double:
DumpPreciseDouble(os, value.ValueDouble());
return;
case storage::v3::PropertyValue::Type::List: {
*os << "[";
const auto &list = value.ValueList();
utils::PrintIterable(*os, list, ", ", [](auto &os, const auto &item) { DumpPropertyValue(&os, item); });
*os << "]";
return;
}
case storage::v3::PropertyValue::Type::Map: {
*os << "{";
const auto &map = value.ValueMap();
utils::PrintIterable(*os, map, ", ", [](auto &os, const auto &kv) {
os << EscapeName(kv.first) << ": ";
DumpPropertyValue(&os, kv.second);
});
*os << "}";
return;
}
case storage::v3::PropertyValue::Type::TemporalData: {
DumpTemporalData(*os, value.ValueTemporalData());
return;
}
}
}
void DumpProperties(std::ostream *os, query::v2::DbAccessor *dba,
const std::map<storage::v3::PropertyId, storage::v3::PropertyValue> &store,
std::optional<int64_t> property_id = std::nullopt) {
*os << "{";
if (property_id) {
*os << kInternalPropertyId << ": " << *property_id;
if (store.size() > 0) *os << ", ";
}
utils::PrintIterable(*os, store, ", ", [&dba](auto &os, const auto &kv) {
os << EscapeName(dba->PropertyToName(kv.first)) << ": ";
DumpPropertyValue(&os, kv.second);
});
*os << "}";
}
void DumpVertex(std::ostream *os, query::v2::DbAccessor *dba, const query::v2::VertexAccessor &vertex) {
*os << "CREATE (";
*os << ":" << kInternalVertexLabel;
auto maybe_labels = vertex.Labels(storage::v3::View::OLD);
if (maybe_labels.HasError()) {
switch (maybe_labels.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get labels from a deleted node.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get labels from a node that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting labels.");
}
}
for (const auto &label : *maybe_labels) {
*os << ":" << EscapeName(dba->LabelToName(label));
}
*os << " ";
auto maybe_props = vertex.Properties(storage::v3::View::OLD);
if (maybe_props.HasError()) {
switch (maybe_props.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a node that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting properties.");
}
}
DumpProperties(os, dba, *maybe_props, vertex.CypherId());
*os << ");";
}
void DumpEdge(std::ostream *os, query::v2::DbAccessor *dba, const query::v2::EdgeAccessor &edge) {
*os << "MATCH ";
*os << "(u:" << kInternalVertexLabel << "), ";
*os << "(v:" << kInternalVertexLabel << ")";
*os << " WHERE ";
*os << "u." << kInternalPropertyId << " = " << edge.From().CypherId();
*os << " AND ";
*os << "v." << kInternalPropertyId << " = " << edge.To().CypherId() << " ";
*os << "CREATE (u)-[";
*os << ":" << EscapeName(dba->EdgeTypeToName(edge.EdgeType()));
auto maybe_props = edge.Properties(storage::v3::View::OLD);
if (maybe_props.HasError()) {
switch (maybe_props.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from an edge that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting properties.");
}
}
if (maybe_props->size() > 0) {
*os << " ";
DumpProperties(os, dba, *maybe_props);
}
*os << "]->(v);";
}
void DumpLabelIndex(std::ostream *os, query::v2::DbAccessor *dba, const storage::v3::LabelId label) {
*os << "CREATE INDEX ON :" << EscapeName(dba->LabelToName(label)) << ";";
}
void DumpLabelPropertyIndex(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
storage::v3::PropertyId property) {
*os << "CREATE INDEX ON :" << EscapeName(dba->LabelToName(label)) << "(" << EscapeName(dba->PropertyToName(property))
<< ");";
}
void DumpExistenceConstraint(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
storage::v3::PropertyId property) {
*os << "CREATE CONSTRAINT ON (u:" << EscapeName(dba->LabelToName(label)) << ") ASSERT EXISTS (u."
<< EscapeName(dba->PropertyToName(property)) << ");";
}
void DumpUniqueConstraint(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
const std::set<storage::v3::PropertyId> &properties) {
*os << "CREATE CONSTRAINT ON (u:" << EscapeName(dba->LabelToName(label)) << ") ASSERT ";
utils::PrintIterable(*os, properties, ", ", [&dba](auto &stream, const auto &property) {
stream << "u." << EscapeName(dba->PropertyToName(property));
});
*os << " IS UNIQUE;";
}
} // namespace
PullPlanDump::PullPlanDump(DbAccessor *dba)
: dba_(dba),
vertices_iterable_(dba->Vertices(storage::v3::View::OLD)),
pull_chunks_{// Dump all label indices
CreateLabelIndicesPullChunk(),
// Dump all label property indices
CreateLabelPropertyIndicesPullChunk(),
// Dump all existence constraints
CreateExistenceConstraintsPullChunk(),
// Dump all unique constraints
CreateUniqueConstraintsPullChunk(),
// Create internal index for faster edge creation
CreateInternalIndexPullChunk(),
// Dump all vertices
CreateVertexPullChunk(),
// Dump all edges
CreateEdgePullChunk(),
// Drop the internal index
CreateDropInternalIndexPullChunk(),
// Internal index cleanup
CreateInternalIndexCleanupPullChunk()} {}
bool PullPlanDump::Pull(AnyStream *stream, std::optional<int> n) {
// Iterate all functions that stream some results.
// Each function should return number of results it streamed after it
// finishes. If the function did not finish streaming all the results,
// std::nullopt should be returned because n results have already been sent.
while (current_chunk_index_ < pull_chunks_.size() && (!n || *n > 0)) {
const auto maybe_streamed_count = pull_chunks_[current_chunk_index_](stream, n);
if (!maybe_streamed_count) {
// n wasn't large enough to stream all the results from the current chunk
break;
}
if (n) {
// chunk finished streaming its results
// subtract number of results streamed in current pull
// so we know how many results we need to stream from future
// chunks.
*n -= *maybe_streamed_count;
}
++current_chunk_index_;
}
return current_chunk_index_ == pull_chunks_.size();
}
PullPlanDump::PullChunk PullPlanDump::CreateLabelIndicesPullChunk() {
// Dump all label indices
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of indices vectors
if (!indices_info_) {
indices_info_.emplace(dba_->ListAllIndices());
}
const auto &label = indices_info_->label;
size_t local_counter = 0;
while (global_index < label.size() && (!n || local_counter < *n)) {
std::ostringstream os;
DumpLabelIndex(&os, dba_, label[global_index]);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == label.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateLabelPropertyIndicesPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of indices vectors
if (!indices_info_) {
indices_info_.emplace(dba_->ListAllIndices());
}
const auto &label_property = indices_info_->label_property;
size_t local_counter = 0;
while (global_index < label_property.size() && (!n || local_counter < *n)) {
std::ostringstream os;
const auto &label_property_index = label_property[global_index];
DumpLabelPropertyIndex(&os, dba_, label_property_index.first, label_property_index.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == label_property.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateExistenceConstraintsPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of constraint vectors
if (!constraints_info_) {
constraints_info_.emplace(dba_->ListAllConstraints());
}
const auto &existence = constraints_info_->existence;
size_t local_counter = 0;
while (global_index < existence.size() && (!n || local_counter < *n)) {
const auto &constraint = existence[global_index];
std::ostringstream os;
DumpExistenceConstraint(&os, dba_, constraint.first, constraint.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == existence.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateUniqueConstraintsPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of constraint vectors
if (!constraints_info_) {
constraints_info_.emplace(dba_->ListAllConstraints());
}
const auto &unique = constraints_info_->unique;
size_t local_counter = 0;
while (global_index < unique.size() && (!n || local_counter < *n)) {
const auto &constraint = unique[global_index];
std::ostringstream os;
DumpUniqueConstraint(&os, dba_, constraint.first, constraint.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == unique.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateInternalIndexPullChunk() {
return [this](AnyStream *stream, std::optional<int>) mutable -> std::optional<size_t> {
if (vertices_iterable_.begin() != vertices_iterable_.end()) {
std::ostringstream os;
os << "CREATE INDEX ON :" << kInternalVertexLabel << "(" << kInternalPropertyId << ");";
stream->Result({TypedValue(os.str())});
internal_index_created_ = true;
return 1;
}
return 0;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateVertexPullChunk() {
return [this, maybe_current_iter = std::optional<VertexAccessorIterableIterator>{}](
AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the call of begin() function
// If multiple begins are called before an iteration,
// one iteration will make the rest of iterators be in undefined
// states.
if (!maybe_current_iter) {
maybe_current_iter.emplace(vertices_iterable_.begin());
}
auto &current_iter{*maybe_current_iter};
size_t local_counter = 0;
while (current_iter != vertices_iterable_.end() && (!n || local_counter < *n)) {
std::ostringstream os;
DumpVertex(&os, dba_, *current_iter);
stream->Result({TypedValue(os.str())});
++local_counter;
++current_iter;
}
if (current_iter == vertices_iterable_.end()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateEdgePullChunk() {
return [this, maybe_current_vertex_iter = std::optional<VertexAccessorIterableIterator>{},
// we need to save the iterable which contains list of accessor so
// our saved iterator is valid in the next run
maybe_edge_iterable = std::shared_ptr<EdgeAccessorIterable>{nullptr},
maybe_current_edge_iter = std::optional<EdgeAccessorIterableIterator>{}](
AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the call of begin() function
// If multiple begins are called before an iteration,
// one iteration will make the rest of iterators be in undefined
// states.
if (!maybe_current_vertex_iter) {
maybe_current_vertex_iter.emplace(vertices_iterable_.begin());
}
auto &current_vertex_iter{*maybe_current_vertex_iter};
size_t local_counter = 0U;
for (; current_vertex_iter != vertices_iterable_.end() && (!n || local_counter < *n); ++current_vertex_iter) {
const auto &vertex = *current_vertex_iter;
// If we have a saved iterable from a previous pull
// we need to use the same iterable
if (!maybe_edge_iterable) {
maybe_edge_iterable = std::make_shared<EdgeAccessorIterable>(vertex.OutEdges(storage::v3::View::OLD));
}
auto &maybe_edges = *maybe_edge_iterable;
MG_ASSERT(maybe_edges.HasValue(), "Invalid database state!");
auto current_edge_iter = maybe_current_edge_iter ? *maybe_current_edge_iter : maybe_edges->begin();
for (; current_edge_iter != maybe_edges->end() && (!n || local_counter < *n); ++current_edge_iter) {
std::ostringstream os;
DumpEdge(&os, dba_, *current_edge_iter);
stream->Result({TypedValue(os.str())});
++local_counter;
}
if (current_edge_iter != maybe_edges->end()) {
maybe_current_edge_iter.emplace(current_edge_iter);
return std::nullopt;
}
maybe_current_edge_iter = std::nullopt;
maybe_edge_iterable = nullptr;
}
if (current_vertex_iter == vertices_iterable_.end()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateDropInternalIndexPullChunk() {
return [this](AnyStream *stream, std::optional<int>) {
if (internal_index_created_) {
std::ostringstream os;
os << "DROP INDEX ON :" << kInternalVertexLabel << "(" << kInternalPropertyId << ");";
stream->Result({TypedValue(os.str())});
return 1;
}
return 0;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateInternalIndexCleanupPullChunk() {
return [this](AnyStream *stream, std::optional<int>) {
if (internal_index_created_) {
std::ostringstream os;
os << "MATCH (u) REMOVE u:" << kInternalVertexLabel << ", u." << kInternalPropertyId << ";";
stream->Result({TypedValue(os.str())});
return 1;
}
return 0;
};
}
void DumpDatabaseToCypherQueries(query::v2::DbAccessor *dba, AnyStream *stream) { PullPlanDump(dba).Pull(stream, {}); }
} // namespace memgraph::query::v2

View File

@@ -1,66 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <ostream>
#include "query/v2/db_accessor.hpp"
#include "query/v2/stream.hpp"
#include "storage/v3/storage.hpp"
namespace memgraph::query::v2 {
void DumpDatabaseToCypherQueries(query::v2::DbAccessor *dba, AnyStream *stream);
struct PullPlanDump {
explicit PullPlanDump(query::v2::DbAccessor *dba);
/// Pull the dump results lazily
/// @return true if all results were returned, false otherwise
bool Pull(AnyStream *stream, std::optional<int> n);
private:
query::v2::DbAccessor *dba_ = nullptr;
std::optional<storage::v3::IndicesInfo> indices_info_ = std::nullopt;
std::optional<storage::v3::ConstraintsInfo> constraints_info_ = std::nullopt;
using VertexAccessorIterable = decltype(std::declval<query::v2::DbAccessor>().Vertices(storage::v3::View::OLD));
using VertexAccessorIterableIterator = decltype(std::declval<VertexAccessorIterable>().begin());
using EdgeAccessorIterable = decltype(std::declval<VertexAccessor>().OutEdges(storage::v3::View::OLD));
using EdgeAccessorIterableIterator = decltype(std::declval<EdgeAccessorIterable>().GetValue().begin());
VertexAccessorIterable vertices_iterable_;
bool internal_index_created_ = false;
size_t current_chunk_index_ = 0;
using PullChunk = std::function<std::optional<size_t>(AnyStream *stream, std::optional<int> n)>;
// We define every part of the dump query in a self contained function.
// Each functions is responsible of keeping track of its execution status.
// If a function did finish its execution, it should return number of results
// it streamed so we know how many rows should be pulled from the next
// function, otherwise std::nullopt is returned.
std::vector<PullChunk> pull_chunks_;
PullChunk CreateLabelIndicesPullChunk();
PullChunk CreateLabelPropertyIndicesPullChunk();
PullChunk CreateExistenceConstraintsPullChunk();
PullChunk CreateUniqueConstraintsPullChunk();
PullChunk CreateInternalIndexPullChunk();
PullChunk CreateVertexPullChunk();
PullChunk CreateEdgePullChunk();
PullChunk CreateDropInternalIndexPullChunk();
PullChunk CreateInternalIndexCleanupPullChunk();
};
} // namespace memgraph::query::v2

View File

@@ -17,11 +17,13 @@
#include <variant>
#include <vector>
#include "query/v2/frontend/ast/ast_visitor.hpp"
#include "query/v2/frontend/semantic/symbol.hpp"
#include "query/v2/bindings/ast_visitor.hpp"
#include "common/types.hpp"
#include "query/v2/bindings/symbol.hpp"
#include "query/v2/interpret/awesome_memgraph_functions.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/property_value.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/path.hpp"
#include "utils/typeinfo.hpp"
cpp<#
@@ -630,7 +632,7 @@ cpp<#
(:clone))
(lcp:define-class primitive-literal (base-literal)
((value "::storage::v3::PropertyValue" :scope :public)
((value "TypedValue" :scope :public)
(token-position :int32_t :scope :public :initval -1
:documentation "This field contains token position of literal used to create PrimitiveLiteral object. If PrimitiveLiteral object is not created from query, leave its value at -1."))
(:public

File diff suppressed because it is too large Load Diff

View File

@@ -1,921 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <string>
#include <unordered_set>
#include <utility>
#include <antlr4-runtime.h>
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/frontend/opencypher/generated/MemgraphCypherBaseVisitor.h"
#include "utils/exceptions.hpp"
#include "utils/logging.hpp"
namespace memgraph::query::v2::frontend {
using antlropencypher::MemgraphCypher;
struct ParsingContext {
bool is_query_cached = false;
};
class CypherMainVisitor : public antlropencypher::MemgraphCypherBaseVisitor {
public:
explicit CypherMainVisitor(ParsingContext context, AstStorage *storage) : context_(context), storage_(storage) {}
private:
Expression *CreateBinaryOperatorByToken(size_t token, Expression *e1, Expression *e2) {
switch (token) {
case MemgraphCypher::OR:
return storage_->Create<OrOperator>(e1, e2);
case MemgraphCypher::XOR:
return storage_->Create<XorOperator>(e1, e2);
case MemgraphCypher::AND:
return storage_->Create<AndOperator>(e1, e2);
case MemgraphCypher::PLUS:
return storage_->Create<AdditionOperator>(e1, e2);
case MemgraphCypher::MINUS:
return storage_->Create<SubtractionOperator>(e1, e2);
case MemgraphCypher::ASTERISK:
return storage_->Create<MultiplicationOperator>(e1, e2);
case MemgraphCypher::SLASH:
return storage_->Create<DivisionOperator>(e1, e2);
case MemgraphCypher::PERCENT:
return storage_->Create<ModOperator>(e1, e2);
case MemgraphCypher::EQ:
return storage_->Create<EqualOperator>(e1, e2);
case MemgraphCypher::NEQ1:
case MemgraphCypher::NEQ2:
return storage_->Create<NotEqualOperator>(e1, e2);
case MemgraphCypher::LT:
return storage_->Create<LessOperator>(e1, e2);
case MemgraphCypher::GT:
return storage_->Create<GreaterOperator>(e1, e2);
case MemgraphCypher::LTE:
return storage_->Create<LessEqualOperator>(e1, e2);
case MemgraphCypher::GTE:
return storage_->Create<GreaterEqualOperator>(e1, e2);
default:
throw utils::NotYetImplemented("binary operator");
}
}
Expression *CreateUnaryOperatorByToken(size_t token, Expression *e) {
switch (token) {
case MemgraphCypher::NOT:
return storage_->Create<NotOperator>(e);
case MemgraphCypher::PLUS:
return storage_->Create<UnaryPlusOperator>(e);
case MemgraphCypher::MINUS:
return storage_->Create<UnaryMinusOperator>(e);
default:
throw utils::NotYetImplemented("unary operator");
}
}
auto ExtractOperators(std::vector<antlr4::tree::ParseTree *> &all_children,
const std::vector<size_t> &allowed_operators) {
std::vector<size_t> operators;
for (auto *child : all_children) {
antlr4::tree::TerminalNode *operator_node = nullptr;
if ((operator_node = dynamic_cast<antlr4::tree::TerminalNode *>(child))) {
if (std::find(allowed_operators.begin(), allowed_operators.end(), operator_node->getSymbol()->getType()) !=
allowed_operators.end()) {
operators.push_back(operator_node->getSymbol()->getType());
}
}
}
return operators;
}
/**
* Convert opencypher's n-ary production to ast binary operators.
*
* @param _expressions Subexpressions of child for which we construct ast
* operators, for example expression6 if we want to create ast nodes for
* expression7.
*/
template <typename TExpression>
Expression *LeftAssociativeOperatorExpression(std::vector<TExpression *> _expressions,
std::vector<antlr4::tree::ParseTree *> all_children,
const std::vector<size_t> &allowed_operators) {
DMG_ASSERT(_expressions.size(), "can't happen");
std::vector<Expression *> expressions;
auto operators = ExtractOperators(all_children, allowed_operators);
for (auto *expression : _expressions) {
expressions.push_back(std::any_cast<Expression *>(expression->accept(this)));
}
Expression *first_operand = expressions[0];
for (int i = 1; i < (int)expressions.size(); ++i) {
first_operand = CreateBinaryOperatorByToken(operators[i - 1], first_operand, expressions[i]);
}
return first_operand;
}
template <typename TExpression>
Expression *PrefixUnaryOperator(TExpression *_expression, std::vector<antlr4::tree::ParseTree *> all_children,
const std::vector<size_t> &allowed_operators) {
DMG_ASSERT(_expression, "can't happen");
auto operators = ExtractOperators(all_children, allowed_operators);
Expression *expression = std::any_cast<Expression *>(_expression->accept(this));
for (int i = (int)operators.size() - 1; i >= 0; --i) {
expression = CreateUnaryOperatorByToken(operators[i], expression);
}
return expression;
}
/**
* @return CypherQuery*
*/
antlrcpp::Any visitCypherQuery(MemgraphCypher::CypherQueryContext *ctx) override;
/**
* @return IndexQuery*
*/
antlrcpp::Any visitIndexQuery(MemgraphCypher::IndexQueryContext *ctx) override;
/**
* @return ExplainQuery*
*/
antlrcpp::Any visitExplainQuery(MemgraphCypher::ExplainQueryContext *ctx) override;
/**
* @return ProfileQuery*
*/
antlrcpp::Any visitProfileQuery(MemgraphCypher::ProfileQueryContext *ctx) override;
/**
* @return InfoQuery*
*/
antlrcpp::Any visitInfoQuery(MemgraphCypher::InfoQueryContext *ctx) override;
/**
* @return Constraint
*/
antlrcpp::Any visitConstraint(MemgraphCypher::ConstraintContext *ctx) override;
/**
* @return ConstraintQuery*
*/
antlrcpp::Any visitConstraintQuery(MemgraphCypher::ConstraintQueryContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitAuthQuery(MemgraphCypher::AuthQueryContext *ctx) override;
/**
* @return DumpQuery*
*/
antlrcpp::Any visitDumpQuery(MemgraphCypher::DumpQueryContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitReplicationQuery(MemgraphCypher::ReplicationQueryContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitSetReplicationRole(MemgraphCypher::SetReplicationRoleContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitShowReplicationRole(MemgraphCypher::ShowReplicationRoleContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitRegisterReplica(MemgraphCypher::RegisterReplicaContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitDropReplica(MemgraphCypher::DropReplicaContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitShowReplicas(MemgraphCypher::ShowReplicasContext *ctx) override;
/**
* @return LockPathQuery*
*/
antlrcpp::Any visitLockPathQuery(MemgraphCypher::LockPathQueryContext *ctx) override;
/**
* @return LoadCsvQuery*
*/
antlrcpp::Any visitLoadCsv(MemgraphCypher::LoadCsvContext *ctx) override;
/**
* @return FreeMemoryQuery*
*/
antlrcpp::Any visitFreeMemoryQuery(MemgraphCypher::FreeMemoryQueryContext *ctx) override;
/**
* @return TriggerQuery*
*/
antlrcpp::Any visitTriggerQuery(MemgraphCypher::TriggerQueryContext *ctx) override;
/**
* @return CreateTrigger*
*/
antlrcpp::Any visitCreateTrigger(MemgraphCypher::CreateTriggerContext *ctx) override;
/**
* @return DropTrigger*
*/
antlrcpp::Any visitDropTrigger(MemgraphCypher::DropTriggerContext *ctx) override;
/**
* @return ShowTriggers*
*/
antlrcpp::Any visitShowTriggers(MemgraphCypher::ShowTriggersContext *ctx) override;
/**
* @return IsolationLevelQuery*
*/
antlrcpp::Any visitIsolationLevelQuery(MemgraphCypher::IsolationLevelQueryContext *ctx) override;
/**
* @return CreateSnapshotQuery*
*/
antlrcpp::Any visitCreateSnapshotQuery(MemgraphCypher::CreateSnapshotQueryContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStreamQuery(MemgraphCypher::StreamQueryContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCreateStream(MemgraphCypher::CreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitConfigKeyValuePair(MemgraphCypher::ConfigKeyValuePairContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitConfigMap(MemgraphCypher::ConfigMapContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitKafkaCreateStream(MemgraphCypher::KafkaCreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitKafkaCreateStreamConfig(MemgraphCypher::KafkaCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitPulsarCreateStreamConfig(MemgraphCypher::PulsarCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitPulsarCreateStream(MemgraphCypher::PulsarCreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCommonCreateStreamConfig(MemgraphCypher::CommonCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitDropStream(MemgraphCypher::DropStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStartStream(MemgraphCypher::StartStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStartAllStreams(MemgraphCypher::StartAllStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStopStream(MemgraphCypher::StopStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStopAllStreams(MemgraphCypher::StopAllStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitShowStreams(MemgraphCypher::ShowStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCheckStream(MemgraphCypher::CheckStreamContext *ctx) override;
/**
* @return SettingQuery*
*/
antlrcpp::Any visitSettingQuery(MemgraphCypher::SettingQueryContext *ctx) override;
/**
* @return SetSetting*
*/
antlrcpp::Any visitSetSetting(MemgraphCypher::SetSettingContext *ctx) override;
/**
* @return ShowSetting*
*/
antlrcpp::Any visitShowSetting(MemgraphCypher::ShowSettingContext *ctx) override;
/**
* @return ShowSettings*
*/
antlrcpp::Any visitShowSettings(MemgraphCypher::ShowSettingsContext *ctx) override;
/**
* @return VersionQuery*
*/
antlrcpp::Any visitVersionQuery(MemgraphCypher::VersionQueryContext *ctx) override;
/**
* @return CypherUnion*
*/
antlrcpp::Any visitCypherUnion(MemgraphCypher::CypherUnionContext *ctx) override;
/**
* @return SingleQuery*
*/
antlrcpp::Any visitSingleQuery(MemgraphCypher::SingleQueryContext *ctx) override;
/**
* @return Clause* or vector<Clause*>!!!
*/
antlrcpp::Any visitClause(MemgraphCypher::ClauseContext *ctx) override;
/**
* @return Match*
*/
antlrcpp::Any visitCypherMatch(MemgraphCypher::CypherMatchContext *ctx) override;
/**
* @return Create*
*/
antlrcpp::Any visitCreate(MemgraphCypher::CreateContext *ctx) override;
/**
* @return CallProcedure*
*/
antlrcpp::Any visitCallProcedure(MemgraphCypher::CallProcedureContext *ctx) override;
/**
* @return std::string
*/
antlrcpp::Any visitUserOrRoleName(MemgraphCypher::UserOrRoleNameContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitCreateRole(MemgraphCypher::CreateRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDropRole(MemgraphCypher::DropRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowRoles(MemgraphCypher::ShowRolesContext *ctx) override;
/**
* @return IndexQuery*
*/
antlrcpp::Any visitCreateIndex(MemgraphCypher::CreateIndexContext *ctx) override;
/**
* @return DropIndex*
*/
antlrcpp::Any visitDropIndex(MemgraphCypher::DropIndexContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitCreateUser(MemgraphCypher::CreateUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitSetPassword(MemgraphCypher::SetPasswordContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDropUser(MemgraphCypher::DropUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowUsers(MemgraphCypher::ShowUsersContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitSetRole(MemgraphCypher::SetRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitClearRole(MemgraphCypher::ClearRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitGrantPrivilege(MemgraphCypher::GrantPrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDenyPrivilege(MemgraphCypher::DenyPrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitRevokePrivilege(MemgraphCypher::RevokePrivilegeContext *ctx) override;
/**
* @return AuthQuery::Privilege
*/
antlrcpp::Any visitPrivilege(MemgraphCypher::PrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowPrivileges(MemgraphCypher::ShowPrivilegesContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowRoleForUser(MemgraphCypher::ShowRoleForUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowUsersForRole(MemgraphCypher::ShowUsersForRoleContext *ctx) override;
/**
* @return Return*
*/
antlrcpp::Any visitCypherReturn(MemgraphCypher::CypherReturnContext *ctx) override;
/**
* @return Return*
*/
antlrcpp::Any visitReturnBody(MemgraphCypher::ReturnBodyContext *ctx) override;
/**
* @return pair<bool, vector<NamedExpression*>> first member is true if
* asterisk was found in return
* expressions.
*/
antlrcpp::Any visitReturnItems(MemgraphCypher::ReturnItemsContext *ctx) override;
/**
* @return vector<NamedExpression*>
*/
antlrcpp::Any visitReturnItem(MemgraphCypher::ReturnItemContext *ctx) override;
/**
* @return vector<SortItem>
*/
antlrcpp::Any visitOrder(MemgraphCypher::OrderContext *ctx) override;
/**
* @return SortItem
*/
antlrcpp::Any visitSortItem(MemgraphCypher::SortItemContext *ctx) override;
/**
* @return NodeAtom*
*/
antlrcpp::Any visitNodePattern(MemgraphCypher::NodePatternContext *ctx) override;
/**
* @return vector<LabelIx>
*/
antlrcpp::Any visitNodeLabels(MemgraphCypher::NodeLabelsContext *ctx) override;
/**
* @return unordered_map<PropertyIx, Expression*>
*/
antlrcpp::Any visitProperties(MemgraphCypher::PropertiesContext *ctx) override;
/**
* @return map<std::string, Expression*>
*/
antlrcpp::Any visitMapLiteral(MemgraphCypher::MapLiteralContext *ctx) override;
/**
* @return vector<Expression*>
*/
antlrcpp::Any visitListLiteral(MemgraphCypher::ListLiteralContext *ctx) override;
/**
* @return PropertyIx
*/
antlrcpp::Any visitPropertyKeyName(MemgraphCypher::PropertyKeyNameContext *ctx) override;
/**
* @return string
*/
antlrcpp::Any visitSymbolicName(MemgraphCypher::SymbolicNameContext *ctx) override;
/**
* @return vector<Pattern*>
*/
antlrcpp::Any visitPattern(MemgraphCypher::PatternContext *ctx) override;
/**
* @return Pattern*
*/
antlrcpp::Any visitPatternPart(MemgraphCypher::PatternPartContext *ctx) override;
/**
* @return Pattern*
*/
antlrcpp::Any visitPatternElement(MemgraphCypher::PatternElementContext *ctx) override;
/**
* @return vector<pair<EdgeAtom*, NodeAtom*>>
*/
antlrcpp::Any visitPatternElementChain(MemgraphCypher::PatternElementChainContext *ctx) override;
/**
*@return EdgeAtom*
*/
antlrcpp::Any visitRelationshipPattern(MemgraphCypher::RelationshipPatternContext *ctx) override;
/**
* This should never be called. Everything is done directly in
* visitRelationshipPattern.
*/
antlrcpp::Any visitRelationshipDetail(MemgraphCypher::RelationshipDetailContext *ctx) override;
/**
* This should never be called. Everything is done directly in
* visitRelationshipPattern.
*/
antlrcpp::Any visitRelationshipLambda(MemgraphCypher::RelationshipLambdaContext *ctx) override;
/**
* @return vector<EdgeTypeIx>
*/
antlrcpp::Any visitRelationshipTypes(MemgraphCypher::RelationshipTypesContext *ctx) override;
/**
* @return std::tuple<EdgeAtom::Type, int64_t, int64_t>.
*/
antlrcpp::Any visitVariableExpansion(MemgraphCypher::VariableExpansionContext *ctx) override;
/**
* Top level expression, does nothing.
*
* @return Expression*
*/
antlrcpp::Any visitExpression(MemgraphCypher::ExpressionContext *ctx) override;
/**
* OR.
*
* @return Expression*
*/
antlrcpp::Any visitExpression12(MemgraphCypher::Expression12Context *ctx) override;
/**
* XOR.
*
* @return Expression*
*/
antlrcpp::Any visitExpression11(MemgraphCypher::Expression11Context *ctx) override;
/**
* AND.
*
* @return Expression*
*/
antlrcpp::Any visitExpression10(MemgraphCypher::Expression10Context *ctx) override;
/**
* NOT.
*
* @return Expression*
*/
antlrcpp::Any visitExpression9(MemgraphCypher::Expression9Context *ctx) override;
/**
* Comparisons.
*
* @return Expression*
*/
antlrcpp::Any visitExpression8(MemgraphCypher::Expression8Context *ctx) override;
/**
* Never call this. Everything related to generating code for comparison
* operators should be done in visitExpression8.
*/
antlrcpp::Any visitPartialComparisonExpression(MemgraphCypher::PartialComparisonExpressionContext *ctx) override;
/**
* Addition and subtraction.
*
* @return Expression*
*/
antlrcpp::Any visitExpression7(MemgraphCypher::Expression7Context *ctx) override;
/**
* Multiplication, division, modding.
*
* @return Expression*
*/
antlrcpp::Any visitExpression6(MemgraphCypher::Expression6Context *ctx) override;
/**
* Power.
*
* @return Expression*
*/
antlrcpp::Any visitExpression5(MemgraphCypher::Expression5Context *ctx) override;
/**
* Unary minus and plus.
*
* @return Expression*
*/
antlrcpp::Any visitExpression4(MemgraphCypher::Expression4Context *ctx) override;
/**
* IS NULL, IS NOT NULL, STARTS WITH, END WITH, =~, ...
*
* @return Expression*
*/
antlrcpp::Any visitExpression3a(MemgraphCypher::Expression3aContext *ctx) override;
/**
* Does nothing, everything is done in visitExpression3a.
*
* @return Expression*
*/
antlrcpp::Any visitStringAndNullOperators(MemgraphCypher::StringAndNullOperatorsContext *ctx) override;
/**
* List indexing and slicing.
*
* @return Expression*
*/
antlrcpp::Any visitExpression3b(MemgraphCypher::Expression3bContext *ctx) override;
/**
* Does nothing, everything is done in visitExpression3b.
*/
antlrcpp::Any visitListIndexingOrSlicing(MemgraphCypher::ListIndexingOrSlicingContext *ctx) override;
/**
* Node labels test.
*
* @return Expression*
*/
antlrcpp::Any visitExpression2a(MemgraphCypher::Expression2aContext *ctx) override;
/**
* Property lookup.
*
* @return Expression*
*/
antlrcpp::Any visitExpression2b(MemgraphCypher::Expression2bContext *ctx) override;
/**
* Literals, params, list comprehension...
*
* @return Expression*
*/
antlrcpp::Any visitAtom(MemgraphCypher::AtomContext *ctx) override;
/**
* @return ParameterLookup*
*/
antlrcpp::Any visitParameter(MemgraphCypher::ParameterContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitParenthesizedExpression(MemgraphCypher::ParenthesizedExpressionContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitFunctionInvocation(MemgraphCypher::FunctionInvocationContext *ctx) override;
/**
* @return string - uppercased
*/
antlrcpp::Any visitFunctionName(MemgraphCypher::FunctionNameContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitLiteral(MemgraphCypher::LiteralContext *ctx) override;
/**
* Convert escaped string from a query to unescaped utf8 string.
*
* @return string
*/
antlrcpp::Any visitStringLiteral(const std::string &escaped);
/**
* @return bool
*/
antlrcpp::Any visitBooleanLiteral(MemgraphCypher::BooleanLiteralContext *ctx) override;
/**
* @return TypedValue with either double or int
*/
antlrcpp::Any visitNumberLiteral(MemgraphCypher::NumberLiteralContext *ctx) override;
/**
* @return int64_t
*/
antlrcpp::Any visitIntegerLiteral(MemgraphCypher::IntegerLiteralContext *ctx) override;
/**
* @return double
*/
antlrcpp::Any visitDoubleLiteral(MemgraphCypher::DoubleLiteralContext *ctx) override;
/**
* @return Delete*
*/
antlrcpp::Any visitCypherDelete(MemgraphCypher::CypherDeleteContext *ctx) override;
/**
* @return Where*
*/
antlrcpp::Any visitWhere(MemgraphCypher::WhereContext *ctx) override;
/**
* return vector<Clause*>
*/
antlrcpp::Any visitSet(MemgraphCypher::SetContext *ctx) override;
/**
* @return Clause*
*/
antlrcpp::Any visitSetItem(MemgraphCypher::SetItemContext *ctx) override;
/**
* return vector<Clause*>
*/
antlrcpp::Any visitRemove(MemgraphCypher::RemoveContext *ctx) override;
/**
* @return Clause*
*/
antlrcpp::Any visitRemoveItem(MemgraphCypher::RemoveItemContext *ctx) override;
/**
* @return PropertyLookup*
*/
antlrcpp::Any visitPropertyExpression(MemgraphCypher::PropertyExpressionContext *ctx) override;
/**
* @return IfOperator*
*/
antlrcpp::Any visitCaseExpression(MemgraphCypher::CaseExpressionContext *ctx) override;
/**
* Never call this. Ast generation for this production is done in
* @c visitCaseExpression.
*/
antlrcpp::Any visitCaseAlternatives(MemgraphCypher::CaseAlternativesContext *ctx) override;
/**
* @return With*
*/
antlrcpp::Any visitWith(MemgraphCypher::WithContext *ctx) override;
/**
* @return Merge*
*/
antlrcpp::Any visitMerge(MemgraphCypher::MergeContext *ctx) override;
/**
* @return Unwind*
*/
antlrcpp::Any visitUnwind(MemgraphCypher::UnwindContext *ctx) override;
/**
* Never call this. Ast generation for these expressions should be done by
* explicitly visiting the members of @c FilterExpressionContext.
*/
antlrcpp::Any visitFilterExpression(MemgraphCypher::FilterExpressionContext *) override;
/**
* @return Foreach*
*/
antlrcpp::Any visitForeach(MemgraphCypher::ForeachContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitPropertyType(MemgraphCypher::PropertyTypeContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitSchemaPropertyMap(MemgraphCypher::SchemaPropertyMapContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitSchemaQuery(MemgraphCypher::SchemaQueryContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitShowSchema(MemgraphCypher::ShowSchemaContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitShowSchemas(MemgraphCypher::ShowSchemasContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitCreateSchema(MemgraphCypher::CreateSchemaContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitDropSchema(MemgraphCypher::DropSchemaContext *ctx) override;
public:
Query *query() { return query_; }
const static std::string kAnonPrefix;
struct QueryInfo {
bool is_cacheable{true};
bool has_load_csv{false};
};
const auto &GetQueryInfo() const { return query_info_; }
private:
LabelIx AddLabel(const std::string &name);
PropertyIx AddProperty(const std::string &name);
EdgeTypeIx AddEdgeType(const std::string &name);
ParsingContext context_;
AstStorage *storage_;
std::unordered_map<uint8_t, std::variant<Expression *, std::string, std::vector<std::string>,
std::unordered_map<Expression *, Expression *>>>
memory_;
// Set of identifiers from queries.
std::unordered_set<std::string> users_identifiers;
// Identifiers that user didn't name.
std::vector<Identifier **> anonymous_identifiers;
Query *query_ = nullptr;
// All return items which are not variables must be aliased in with.
// We use this variable in visitReturnItem to check if we are in with or
// return.
bool in_with_ = false;
QueryInfo query_info_;
};
} // namespace memgraph::query::v2::frontend

Some files were not shown because too many files have changed in this diff Show More