Remove JepsenControl tag

* Add memory control e2e test

* Fix cmake for jemalloc

.clang-format

@@ -1,10 +1,10 @@
 ---
 Language:     Cpp
 BasedOnStyle: Google
-Standard:     "C++11"
+Standard:     "c++20"
 UseTab:       Never
 DerivePointerAlignment: false
 PointerAlignment: Right
-ColumnLimit : 80
+ColumnLimit : 120
 IncludeBlocks: Preserve
 ...

.githooks/pre-commit

@@ -15,7 +15,7 @@ exec 1>&2
 tmpdir=$(mktemp -d repo-XXXXXXXX)
 trap "rm -rf $tmpdir" EXIT INT
 
-modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp|lcp)$/p")
+modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp)$/p")
 for file in $modified_files; do
   echo "Checking $file..."
 
@@ -30,14 +30,6 @@ for file in $modified_files; do
   if [ $code -ne 0 ]; then
     break
   fi
-
-  echo "Running clang-tidy..."
-  $project_folder/tools/git-clang-tidy $tmpdir/$file
-  code=$?
-
-  if [ $code -ne 0 ]; then
-   break
-  fi
 done;
 
 return $code

.github/workflows/diff.yaml

@@ -4,7 +4,8 @@ on:
   push:
     paths-ignore:
       - 'docs/**'
-      - '*.md'
+      - '**/*.md'
+      - '.clang-*'
 
 jobs:
   community_build:
@@ -41,13 +42,29 @@ jobs:
 
           # Run unit tests.
           cd build
-          ctest -R memgraph__unit --output-on-failure
+          ctest -R memgraph__unit --output-on-failure -j$THREADS
 
       - name: Run stress test
         run: |
           cd tests/stress
           ./continuous_integration
 
+      - name: Create community DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Create community DEB package.
+          cd build
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save community DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community DEB package"
+          path: build/output/memgraph*.deb
+
   coverage_build:
     name: "Coverage build"
     runs-on: [self-hosted, General, Linux, X64, Debian10]
@@ -82,7 +99,7 @@ jobs:
 
           # Run unit tests.
           cd build
-          ctest -R memgraph__unit --output-on-failure
+          ctest -R memgraph__unit --output-on-failure -j$THREADS
 
       - name: Compute code coverage
         run: |
@@ -273,6 +290,23 @@ jobs:
             tests/gql_behave/gql_behave_status.csv
             tests/gql_behave/gql_behave_status.html
 
+      - name: Run e2e replication tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path replication/workloads.yaml
+
+      - name: Run e2e memory control tests
+        run: |
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path memory/workloads.yaml
+
       - name: Run stress test (plain)
         run: |
           cd tests/stress
@@ -288,3 +322,59 @@ jobs:
           cd tests/stress
           source ve3/bin/activate
           python3 durability --num-steps 5
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Create enterprise DEB package.
+          cd build
+          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
+
+  release_jepsen_test:
+    name: "Release Jepsen Test"
+    runs-on: [self-hosted, Linux, X64, Debian10, HP-DL360G6-v2-3]
+    #continue-on-error: true
+    env:
+      THREADS: 24
+
+    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-v2/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

.github/workflows/release_centos8.yaml

@@ -1,11 +1,14 @@
-name: Release CentOS
+name: Release CentOS 8
 
-on: [workflow_dispatch]
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
 
 jobs:
   community_build:
     name: "Community build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
     timeout-minutes: 960
@@ -69,7 +72,7 @@ jobs:
 
   coverage_build:
     name: "Coverage build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
 
@@ -124,7 +127,7 @@ jobs:
 
   debug_build:
     name: "Debug build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
 
@@ -198,7 +201,7 @@ jobs:
 
   release_build:
     name: "Release build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
     timeout-minutes: 960
@@ -280,6 +283,23 @@ jobs:
             tests/gql_behave/gql_behave_status.csv
             tests/gql_behave/gql_behave_status.html
 
+      - name: Run e2e replication tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path replication/workloads.yaml
+
+      - name: Run e2e memory control tests
+        run: |
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path memory/workloads.yaml
+
       - name: Run stress test (plain)
         run: |
           cd tests/stress

.github/workflows/release_debian10.yaml

@@ -0,0 +1,366 @@
+name: Release Debian10
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  community_build:
+    name: "Community build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    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 community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Create community DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Create community DEB package.
+          cd build
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save community DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Run stress test (plain)
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Run stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+  coverage_build:
+    name: "Coverage build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build coverage binaries.
+          cd build
+          cmake -DTEST_COVERAGE=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Compute code coverage.
+          cd tools/github
+          ./coverage_convert
+
+          # Package code coverage.
+          cd generated
+          tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
+
+      - name: Save code coverage
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/generated/code_coverage.tar.gz
+
+  debug_build:
+    name: "Debug build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+
+    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 debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Run leftover CTest tests (all except unit and benchmark tests).
+          cd build
+          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+
+      - 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: $name"
+            if [ -x prepare.sh ]; then
+              ./prepare.sh
+            fi
+            if [ -x runner.py ]; then
+              ./runner.py
+            elif [ -x runner.sh ]; then
+              ./runner.sh
+            fi
+            echo
+            popd >/dev/null
+          done
+
+      - name: Run cppcheck and clang-format
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/cppcheck_and_clang_format.txt
+
+  release_build:
+    name: "Release build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Create enterprise DEB package.
+          cd build
+          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: Run micro benchmark tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v2/activate
+
+          # Run micro benchmark tests.
+          cd build
+          # The `eval` benchmark needs a large stack limit.
+          ulimit -s 262144
+          ctest -R memgraph__benchmark -V
+
+      - name: Run macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Run parallel macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QueryParallelSuite MemgraphRunner \
+            --groups aggregation_parallel create_parallel bfs_parallel \
+            --num-database-workers 9 --num-clients-workers 30 \
+            --no-strict
+
+      - 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 e2e replication tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path replication/workloads.yaml
+
+      - name: Run e2e memory control tests
+        run: |
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path memory/workloads.yaml
+
+      - 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 stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+      - name: Run durability test (plain)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 5
+
+      - name: Run durability test (large)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 20
+
+  release_jepsen_test:
+    name: "Release Jepsen Test"
+    runs-on: [self-hosted, Linux, X64, Debian10, JepsenControl]
+    env:
+      THREADS: 24
+    timeout-minutes: 60
+
+    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-v2/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binary.
+          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

.github/workflows/release_ubuntu2004.yaml

@@ -1,4 +1,4 @@
-name: Release
+name: Release Ubuntu20.04
 
 on:
   workflow_dispatch:
@@ -8,7 +8,7 @@ on:
 jobs:
   community_build:
     name: "Community build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
     timeout-minutes: 960
@@ -71,7 +71,7 @@ jobs:
 
   coverage_build:
     name: "Coverage build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
 
@@ -126,7 +126,7 @@ jobs:
 
   debug_build:
     name: "Debug build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
 
@@ -200,7 +200,7 @@ jobs:
 
   release_build:
     name: "Release build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
     timeout-minutes: 960
@@ -281,6 +281,23 @@ jobs:
             tests/gql_behave/gql_behave_status.csv
             tests/gql_behave/gql_behave_status.html
 
+      - name: Run e2e replication tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path replication/workloads.yaml
+
+      - name: Run e2e memory control tests
+        run: |
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-path memory/workloads.yaml
+
       - name: Run stress test (plain)
         run: |
           cd tests/stress

.github/workflows/test_all_workers.yaml

@@ -1,116 +0,0 @@
-name: Test All Workers
-
-on: [workflow_dispatch]
-
-jobs:
-  HP-DL360G6-1:
-    name: "HP-DL360G6-1"
-    runs-on: [HP-DL360G6-1]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-2:
-    name: "HP-DL360G6-2"
-    runs-on: [HP-DL360G6-2]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-3:
-    name: "HP-DL360G6-3"
-    runs-on: [HP-DL360G6-3]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-
-  HP-DL360G6-v2-1:
-    name: "HP-DL360G6-v2-1"
-    runs-on: [HP-DL360G6-v2-1]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-2:
-    name: "HP-DL360G6-v2-2"
-    runs-on: [HP-DL360G6-v2-2]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-3:
-    name: "HP-DL360G6-v2-3"
-    runs-on: [HP-DL360G6-v2-3]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-4:
-    name: "HP-DL360G6-v2-4"
-    runs-on: [HP-DL360G6-v2-4]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-5:
-    name: "HP-DL360G6-v2-5"
-    runs-on: [HP-DL360G6-v2-5]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-6:
-    name: "HP-DL360G6-v2-6"
-    runs-on: [HP-DL360G6-v2-6]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-7:
-    name: "HP-DL360G6-v2-7"
-    runs-on: [HP-DL360G6-v2-7]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system

CHANGELOG.md

@@ -1,5 +1,68 @@
 # Change Log
 
+## Future
+
+### Breaking Changes
+
+* Changed `MEMORY LIMIT num (KB|MB)` clause in the procedure calls to `PROCEDURE MEMORY LIMIT num (KB|MB)`.
+  The functionality is still the same.
+
+### Major Feature and Improvements
+
+* Added replication to community version.
+* Add support for multiple query modules directories at the same time.
+  You can now define multiple, comma-separated paths to directories from
+  which the modules will be loaded using the `--query-modules-directory` flag.
+* Added support for programatically reading in data from CSV files through the
+  `LOAD CSV` clause. We support CSV files with and without a header, the
+  supported dialect being Excel.
+* Added a new flag `--memory-limit` which enables the user to set the maximum total amount of memory
+  memgraph can allocate during its runtime.
+* Added `FREE MEMORY` query which tries to free unusued memory chunks in different parts of storage.
+* Added the memory limit and amount of currently allocated bytes in the result of `SHOW STORAGE INFO` query.
+* Added `QUERY MEMORY LIMIT num (KB|MB)` to Cypher queries which allows you to limit memory allocation for
+  the entire query. It can be added only at the end of the entire Cypher query.
+
+### Bug Fixes
+
+* Fixed garbage collector by correctly marking the oldest current timestamp
+  after the database was recovered using the durability files.
+* Fixed reloading of the modules with changed result names.
+
+## v1.3.0
+
+### Breaking Changes
+
+* Added extra information in durability files to support replication, making it
+  incompatible with the durability files generated by older versions of
+  Memgraph. Even though the replication is an Enterprise feature, the files are
+  compatible with the Community version.
+
+### Major Features and Improvements
+
+* Added support for data replication across a cluster of Memgraph instances.
+  Supported instance types are MAIN and REPLICA. Supported replication modes
+  are SYNC (all SYNC REPLICAS have to receive data before the MAIN can commit
+  the transaction), ASYNC (MAIN doesn't care if data is replicated), SYNC WITH
+  TIMEOUT (MAIN will wait for REPLICAS within the given timeout period, after
+  timout, replication isn't aborted but the replication demotes the REPLICA to
+  the ASYNC mode).
+* Added support for query type deduction. Possible query types are `r` (read),
+  `w` (write), `rw` (read-write). The query type is returned as a part of the
+  summary.
+* Improved logging capabilities by introducing granular logging levels. Added
+  new flag, `--log-level`, which specifies the minimum log level that will be
+  printed. E.g., it's possible to print incoming queries or Bolt server states.
+* Added ability to lock the storage data directory by executing the `LOCK DATA
+  DIRECTORY;` query which delays the deletion of the files contained in the
+  data directory. The data directory can be unlocked again by executing the
+  `UNLOCK DATA DIRECTORY;` query.
+
+### Bug Fixes and Other Changes
+
+* Added cleanup of query executions if not in an explicit transaction.
+* Fix RPC dangling reference.
+
 ## v1.2.0
 
 ### Breaking Changes

CMakeLists.txt

@@ -35,6 +35,9 @@ else()
   message(FATAL_ERROR "Couldn't find clang and/or clang++!")
 endif()
 
+option(BUILD_FOR_DOCKER "Build Memgraph binary for docker." OFF)
+message(STATUS "BUILD_FOR_DOCKER: ${BUILD_FOR_DOCKER}")
+
 # -----------------------------------------------------------------------------
 
 project(memgraph)
@@ -67,28 +70,52 @@ set(get_version_script "${CMAKE_SOURCE_DIR}/release/get_version.py")
 # Get version that should be used in the binary.
 execute_process(
     OUTPUT_VARIABLE MEMGRAPH_VERSION
+    RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
     COMMAND "${get_version_script}" ${get_version_enterprise}
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_RESULT AND NOT MEMGRAPH_VERSION_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph version.")
+else()
+    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}" ${get_version_enterprise}
                 --variant deb
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_DEB_RESULT AND NOT MEMGRAPH_VERSION_DEB_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph DEB version.")
+else()
+    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}" ${get_version_enterprise}
                 --variant rpm
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_RPM_RESULT AND NOT MEMGRAPH_VERSION_RPM_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph RPM version.")
+else()
+    MESSAGE(STATUS "Memgraph RPM version: ${MEMGRAPH_VERSION_RPM}")
+endif()
 
 # We want the above variables to be updated each time something is committed to
 # the repository. That is why we include a dependency on the current git HEAD
@@ -289,6 +316,8 @@ if (UBSAN)
   # Make sure llvm-symbolizer binary is in path
 endif()
 
+set(MG_PYTHON_VERSION "" CACHE STRING "Specify the exact python version used by the query modules")
+
 # Add subprojects
 include_directories(src)
 add_subdirectory(src)

README.md

@@ -6,34 +6,8 @@ data structures, multi-version concurrency control and asynchronous IO.
 
 ## Development Documentation
 
-* [Quick Start](docs/dev/quick-start.md)
-* [Workflow](docs/dev/workflow.md)
-* [Storage](docs/dev/storage/v2/contents.md)
-* [Query Engine](docs/dev/query/contents.md)
-* [Communication](docs/dev/communication/contents.md)
-* [Lisp C++ Preprocessor (LCP)](docs/dev/lcp.md)
-
-## Feature Specifications
-
-Each prominent Memgraph feature requires a feature specification. The purpose
-of the feature specification is to have a base for discussing all aspects of
-the feature. Elements of feature specifications should be:
-
-* High-level context.
-* Interface.
-* User stories. Usage from the end-user perspective. In the case of a library,
-  that should be cases on how to use the programming interface. In the case of
-a shell script, that should be cases on how to use flags.
-* Discussion about concurrency, memory management, error management.
-* Any other essential functional or non-functional requirements.
-* Test and benchmark strategy.
-* Possible future changes/improvements/extensions.
-* Security concerns.
-* Additional and/or optional implementation details.
-
-It's crucial to keep feature spec up-to-date with the implementation. Take a
-look at the list of [feature specifications](docs/feature_spec/contents.md) to
-learn more about powerful Memgraph features.
+Please continue in
+[Notion](https://www.notion.so/memgraph/memgraph-0428591638604c8385550e214ea9f3e6).
 
 ## User Documentation
 

config/flags.yaml

@@ -39,6 +39,10 @@ modifications:
     value: "/var/log/memgraph/memgraph.log"
     override: true
 
+  - name: "log_level"
+    value: "WARNING"
+    override: true
+
   - name: "bolt_num_workers"
     value: ""
     override: false
@@ -79,15 +83,13 @@ modifications:
     value: "/usr/lib/memgraph/auth_module/example.py"
     override: false
 
+  - name: "memory_limit"
+    value: "0"
+    override: true 
+
 undocumented:
   - "flag_file"
-  - "log_file_mode"
-  - "log_link_basename"
-  - "log_prefix"
-  - "max_log_size"
-  - "min_log_level"
+  - "also_log_to_stderr"
   - "help"
   - "help_xml"
-  - "stderr_threshold"
-  - "stop_logging_if_full_disk"
   - "version"

docs/dev/code-review.md

@@ -1,269 +0,0 @@
-# Code Review Guidelines
-
-This chapter describes some of the things you should be on the lookout when
-reviewing someone else's code.
-
-## Exceptions
-
-Although the Google C++ Style Guide forbids exceptions, we do allow them in
-our codebase. As a reviewer you should watch out for the following.
-
-The documentation of throwing functions needs to be in-sync with the
-implementation. This must be enforced recursively. I.e. if a function A now
-throws a new exception, and the function B uses A, then B needs to handle that
-exception or have its documentation updated and so on. Naturally, the same
-applies when an exception is removed.
-
-Transitive callers of the function which throws a new exception must be OK
-with that. This ties into the previous point. You need to check that all users
-of the new exception either handle it correctly or propagate it.
-
-Exceptions should not escape out of class destructors, because that will
-terminate the program. The code should be changed so that such cases are not
-possible.
-
-Exceptions being thrown in class constructors. Although this is well defined
-in C++, it usually implies that a constructor is doing too much work and the
-class construction & initialization should be redesigned. Usual approaches are
-using the (Static) Factory Method pattern or having some sort of an
-initialization method that needs to be called after the construction is done.
-Prefer the Factory Method.
-
-Don't forget that STL functions may also throw!
-
-## Pointers & References
-
-In cases when some code passes a pointer or reference, or if a code stores a
-pointer or reference you should take a careful look at the following.
-
-  * Lifetime of the pointed to value (this includes both ownership and
-    multithreaded access).
-  * In case of a class, check validity of destructor and move/copy
-    constructors.
-  * Is the pointed to value mutated, if not it should be `const` (`const Type
-    *` or `const Type &`).
-
-## Allocators & Memory Resources
-
-With the introduction of polymorphic allocators (C++17 `<memory_resource>` and
-our `utils/memory.hpp`) we get a more convenient type signatures for
-containers so as to keep the outward facing API nice. This convenience comes
-at a cost of less static checks on the type level due to type erasure.
-
-For example:
-
-    std::pmr::vector<int> first_vec(std::pmr::null_memory_resource());
-    std::pmr::vector<int> second_vec(std::pmr::new_delete_resource());
-
-    second_vec = first_vec  // What happens here?
-
-    // Or with our implementation
-    utils::MonotonicBufferResource monotonic_memory(1024);
-    std::vector<int, utils::Allocator<int>> first_vec(&monotonic_memory);
-    std::vector<int, utils::Allocator<int>> second_vec(utils::NewDeleteResource());
-
-    second_vec = first_vec  // What happens here?
-
-In the above, both `first_vec` and `second_vec` have the same type, but have
-*different* allocators! This can lead to ambiguity when moving or copying
-elements between them.
-
-You need to watch out for the following.
-
-  * Swapping can lead to undefined behaviour if the allocators are not equal.
-  * Is the move construction done with the right allocator.
-  * Is the move assignment done correctly, also it may throw an exception.
-  * Is the copy construction done with the right allocator.
-  * Is the copy assignment done correctly.
-  * Using `auto` makes allocator propagation rules rather ambiguous.
-
-## Classes & Object Oriented Programming
-
-A common mistake is to use classes, inheritance and "OOP" when it's not
-needed. This sections shows examples of encountered cases.
-
-### Classes without (Meaningful) Members
-
-    class MyCoolClass {
-     public:
-      int BeCool(int a, int b) { return a + b; }
-
-      void SaySomethingCool() { std::cout << "Hello!"; }
-    };
-
-The above class has no members (i.e. state) which affect the behaviour of
-methods. This class should need not exist, it can be easily replaced with a
-more modular (and shorter) design -- top level functions.
-
-    int BeCool(int a, int b) { return a + b; }
-
-    void SaySomethingCool() { std::cout << "Hello!"; }
-
-### Classes with a Single Public Method
-
-    clas MyAwesomeClass {
-     public:
-      MyAwesomeClass(int state) : state_(state) {}
-
-      int GetAwesome() { return GetAwesomeImpl() + 1; }
-
-     private:
-      int state_;
-
-      int GetAwesomeImpl() { return state_; }
-    };
-
-The above class has a `state_` and even a private method, but there's only one
-public method -- `GetAwesome`.
-
-You should check "Does the stored state have any meaningful influence on the
-public method?", similarly to the previous point.
-
-In the above case it doesn't, and the class should be replaced with a public
-function in `.hpp` while the private method should become a private function
-in `.cpp` (static or in anonymous namespace).
-
-    // hpp
-    int GetAwesome(int state);
-
-    // cpp
-    namespace {
-      int GetAwesomeImpl(int state) { return state; }
-    }
-    int GetAwesome(int state) { return GetAwesomeImpl(state) + 1; }
-
-A counterexample is when the state is meaningful.
-
-    class Counter {
-     public:
-      Counter(int state) : state_(state) {}
-
-      int Get() { return state_++; }
-
-     private:
-      int state_;
-    };
-
-But even that could be replaced with a closure.
-
-    auto MakeCounter(int state) {
-      return [state]() mutable { return state++; };
-    }
-
-### Private Methods
-
-Instead of private methods, top level functions should be preferred. The
-reasoning is completely explained in "Effective C++" Item 23 by Scott Meyers.
-In our codebase, even improvements to compilation times can be noticed if
-private methods in interface (`.hpp`) files are replaced with top level
-functions in implementation (`.cpp`) files.
-
-### Inheritance
-
-The rule is simple -- if there are no virtual methods (but maybe destructor),
-then the class should be marked as `final` and never inherited.
-
-If there are virtual methods (i.e. class is meant to be inherited), make sure
-that either a public virtual destructor or a protected non-virtual destructor
-exist. See "Effective C++" Item 7 by Scott Meyers. Also take a look at
-"Effective C++" Items 32---39 by Scott Meyers.
-
-An example of how inheritance with no virtual methods is replaced with
-composition.
-
-    class MyBase {
-     public:
-      virtual ~MyBase() {}
-
-      void DoSomethingBase() { ... }
-    };
-
-    class MyDerived final : public MyBase {
-     public:
-      void DoSomethingNew() { ... DoSomethingBase(); ... }
-    };
-
-With composition, the above becomes.
-
-    class MyBase final {
-     public:
-      void DoSomethingBase() { ... }
-    };
-
-    class MyDerived final {
-      MyBase base_;
-
-     public:
-      void DoSomethingNew() { ... base_.DoSomethingBase(); ... }
-    };
-
-The composition approach is preferred as it encapsulates the fact that
-`MyBase` is used for the implementation and users only interact with the
-public interface of `MyDerived`. Additionally, you can easily replace `MyBase
-base_;` with a C++ PIMPL idiom (`std::unique_ptr<MyBase> base_;`) to make the
-code more modular with regards to compilation.
-
-More advanced C++ users will recognize that the encapsulation feature of the
-non-PIMPL composition can be replaced with private inheritance.
-
-    class MyDerived final : private MyBase {
-     public:
-      void DoSomethingNew() { ... MyBase::DoSomethingBase(); ... }
-    };
-
-One of the common "counterexample" is the ability to store objects of
-different type in a container or pass them to a function. Unfortunately, this
-is not that good of a design. For example.
-
-    class MyBase {
-      ... // No virtual methods (but the destructor)
-    };
-
-    class MyFirstClass final : public MyBase { ...  };
-
-    class MySecondClass final : public MyBase { ... };
-
-    std::vector<std::unique_ptr<MyBase>> first_and_second_classes;
-    first_and_second_classes.push_back(std::make_unique<MyFirstClass>());
-    first_and_second_classes.push_back(std::make_unique<MySecondClass>());
-
-    void FunctionOnFirstOrSecond(const MyBase &first_or_second, ...) { ... }
-
-With C++17, the containers for different types should be implemented with
-`std::variant`, and as before the functions can be templated.
-
-    class MyFirstClass final { ... };
-
-    class MySecondClass final { ... };
-
-    std::vector<std::variant<MyFirstClass, MySecondClass>> first_and_second_classes;
-    // Notice no heap allocation, since we don't store a pointer
-    first_and_second_classes.emplace_back(MyFirstClass());
-    first_and_second_classes.emplace_back(MySecondClass());
-
-    // You can also use `std::variant` here instead of template
-    template <class TFirstOrSecond>
-    void FunctionOnFirstOrSecond(const TFirstOrSecond &first_or_second, ...) { ... }
-
-Naturally, if the base class has meaningful virtual methods (i.e. other than
-destructor) it maybe is OK to use inheritance but also consider alternatives.
-See "Effective C++" Items 32---39 by Scott Meyers.
-
-### Multiple Inheritance
-
-Multiple inheritance should not be used unless all base classes are pure
-interface classes. This decision is inherited from [Google C++ Style
-Guide](https://google.github.io/styleguide/cppguide.html#Inheritance). For
-example on how to design with and around multiple inheritance refer to
-"Effective C++" Item 40 by Scott Meyers.
-
-Naturally, if there *really* is no better design, then multiple inheritance is
-allowed. An example of this can be found in our codebase when inheriting
-Visitor classes (though even that could be replaced with `std::variant` for
-example).
-
-## Code Format & Style
-
-If something doesn't conform to our code formatting and style, just refer the
-author to either [C++ Style](cpp-code-conventions.md) or [Other Code
-Conventions](other-code-conventions.md).

docs/dev/communication/contents.md

@@ -1,5 +0,0 @@
-# Communication
-
-## Bolt
-
-Memgraph implements [Bolt communication protocol](https://7687.org/).

docs/dev/cpp-code-conventions.md

@@ -1,350 +0,0 @@
-# C++ Code Conventions
-
-This chapter describes code conventions which should be followed when writing
-C++ code.
-
-## Code Style
-
-Memgraph uses the
-[Google Style Guide for C++](https://google.github.io/styleguide/cppguide.html)
-in most of its code.  You should follow them whenever writing new code.
-Besides following the style guide, take a look at
-[Code Review Guidelines](code-review.md) for common design issues and pitfalls
-with C++ as well as [Required Reading](required-reading.md).
-
-### Often Overlooked Style Conventions
-
-#### Pointers & References
-
-References provide a shorter syntax for accessing members and better declare
-the intent that a pointer *should* not be `nullptr`. They do not prevent
-accessing a `nullptr` and obfuscate the client/calling code because the
-reference argument is passed just like a value. Errors with such code have
-been very difficult to debug. Therefore, pointers are always used. They will
-not prevent bugs but will make some of them more obvious when reading code.
-
-The only time a reference can be used is if it is `const`. Note that this
-kind of reference is not allowed if it is stored somewhere, i.e. in a class.
-You should use a pointer to `const` then. The primary reason being is that
-references obscure the semantics of moving an object, thus making bugs with
-references pointing to invalid memory harder to track down.
-
-Example of this can be seen while capturing member variables by reference
-inside a lambda.
-Let's define a class that has two members, where one of those members is a
-lambda that captures the other member by reference.
-
-```cpp
-struct S {
-  std::function<void()> foo;
-  int bar;
-
-  S() : foo([&]() { std::cout << bar; })
-  {}
-};
-```
-What would happend if we move an instance of this object? Our lambda
-reference capture will point to the same location as before, i.e. it
-will point to the **old** memory location of `bar`. This means we have
-a dangling reference in our code!
-There are multiple ways to avoid this. The simple solutions would be
-capturing by value or disabling move constructors/assignments.
-Still, if we capture by reference an object that is not a member
-of the struct containing the lambda, we can still have a dangling
-reference if we move that object somewhere in our code and there is
-nothing we can do to prevent that.
-So, be careful with lambda catptures, and remember that references are
-still a pointer under the hood!
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Reference_Arguments)
-
-#### Constructors & RAII
-
-RAII (Resource Acquisition is Initialization) is a nice mechanism for managing
-resources. It is especially useful when exceptions are used, such as in our
-code. Unfortunately, they do have 2 major downsides.
-
-  * Only exceptions can be used for to signal failure.
-  * Calls to virtual methods are not resolved as expected.
-
-For those reasons the style guide recommends minimal work that cannot fail.
-Using virtual methods or doing a lot more should be delegated to some form of
-`Init` method, possibly coupled with static factory methods. Similar rules
-apply to destructors, which are not allowed to even throw exceptions.
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Doing_Work_in_Constructors)
-
-#### Constructors and member variables
-
-One of the most powerful tools in C++ is the move semantics. We won't go into
-detail how it works, but you should know how to utilize it as much as
-possible. In our example we will define a small `struct` called `S` which
-contains only a single member, `text` of type `std::string`.
-```cpp
-struct S {
-  std::string text;
-};
-```
-We want to define a constructor that takes a `std::string`, and saves its
-value in `text`. This is a common situation, where the constructor takes
-a value, and saves it in the object to be constructed.
-
-Our first implementation would look like this:
-```cpp
-S(const std::string &s) : text(s) {}
-```
-
-This is a valid solution but with one downside - we always copy. If we
-construct an object like this:
-```cpp
-S s("some text");
-```
-we would create a temporary `std::string` object and then copy it to our member
-variable.
-
-Of course, we know what to do now - we will capture temporary variables using
-`&&` and move it into our `text` variable.
-```cpp
-S(std::string &&s) : text(std::move(s)) {}
-```
-
-Now let's add an extra member variable of type `std::vector<int>` called
-`words`.  Our constructors accept 2 values now - `std::vector<int>` and
-`std::string`. Those arguments could be passed by value, by reference, or
-as rvalues. To cover all the cases we need to define a dedicated constructor
-for each case.
-Fortunately, there are two simpler options, the first one is writing a
-templated constructor:
-```cpp
-template<typename T1, typename T2>
-S(T1 &&s, T2 &&v) : text(std::forward<T1>(s), words(std::forward<T2>(v) {}
-```
-But don't forget to define `requires` clause so you don't accept any type. This
-solution is optimal but really hard to read AND write. The second solution is
-something you should ALWAYS prefer in these simple cases where we only store
-one of the arguments:
-```cpp
-S(std::string s, std::vector<int> v) : text(std::move(s)), words(std::move(v)) {}
-```
-This way we have an almost optimal solution. The only extra operation we have is
-the extra move when we send an `lvalue`. We would copy the value to the `s`, and
-then move it to the `text` variable. Before, we would copy directly to `text`.
-Also, you should ALWAYS write const-correct code, meaning `s` and `v` cannot be
-`const` as it's not correct here. Why is that? You CANNOT move a const object!
-It would just degrade to copying the object. I would say that this is a small
-price to pay for a much cleaner and more maintainable code.
-
-### Additional Style Conventions
-
-Old code may have broken Google C++ Style accidentally, but the new code
-should adhere to it as close as possible. We do have some exceptions
-to Google style as well as additions for unspecified conventions.
-
-#### Using C++ Exceptions
-
-Unlike Google, we do not forbid using exceptions.
-
-But, you should be very careful when using them and introducing new ones. They
-are indeed handy, but cause problems with understanding the control flow since
-exceptions are another form of `goto`. It also becomes very hard to determine
-that the program is in correct state after the stack is unwound and the thrown
-exception handled. Other than those issues, throwing exceptions in destructors
-will terminate the program. The same will happen if a thread doesn't handle an
-exception even though it is not the main thread.
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Exceptions)
-
-In general, when introducing a new exception, either via `throw` statement or
-calling a function which throws, you must examine all transitive callers and
-update their implementation and/or documentation.
-
-#### Assertions
-
-We use `CHECK` and `DCHECK` macros from glog library. You are encouraged to
-use them as often as possible to both document and validate various pre and
-post conditions of a function.
-
-`CHECK` remains even in release build and should be preferred over it's cousin
-`DCHECK` which only exists in debug builds. The primary reason is that you
-want to trigger assertions in release builds in case the tests didn't
-completely validate all code paths. It is better to fail fast and crash the
-program, than to leave it in undefined state and potentially corrupt end
-user's work. In cases when profiling shows that `CHECK` is causing visible
-slowdown you should switch to `DCHECK`.
-
-#### Template Parameter Naming
-
-Template parameter names should start with capital letter 'T' followed by a
-short descriptive name. For example:
-
-```cpp
-template <typename TKey, typename TValue>
-class KeyValueStore
-```
-
-## Code Formatting
-
-You should install `clang-format` and run it on code you change or add. The
-root of Memgraph's project contains the `.clang-format` file, which specifies
-how formatting should behave. Running `clang-format -style=file` in the
-project's root will read the file and behave as expected. For ease of use, you
-should integrate formatting with your favourite editor.
-
-The code formatting isn't enforced, because sometimes manual formatting may
-produce better results. Though, running `clang-format` is strongly encouraged.
-
-## Documentation
-
-Besides following the comment guidelines from [Google Style
-Guide](https://google.github.io/styleguide/cppguide.html#Comments), your
-documentation of the public API should be
-[Doxygen](https://github.com/doxygen/doxygen) compatible. For private parts of
-the code or for comments accompanying the implementation, you are free to
-break doxygen compatibility. In both cases, you should write your
-documentation as full sentences, correctly written in English.
-
-## Doxygen
-
-To start a Doxygen compatible documentation string, you should open your
-comment with either a JavaDoc style block comment (`/**`) or a line comment
-containing 3 slashes (`///`). Take a look at the 2 examples below.
-
-### Block Comment
-
-```cpp
-/**
- * One sentence, brief description.
- *
- * Long form description.
- */
-```
-
-### Line Comment
-
-```cpp
-/// One sentence, brief description.
-///
-/// Long form description.
-```
-
-If you only have a brief description, you may collapse the documentation into
-a single line.
-
-### Block Comment
-
-```cpp
-/** Brief description. */
-```
-
-### Line Comment
-
-```cpp
-/// Brief description.
-```
-
-Whichever style you choose, keep it consistent across the whole file.
-
-Doxygen supports various commands in comments, such as `@file` and `@param`.
-These help Doxygen to render specified things differently or to track them for
-cross referencing. If you want to learn more, take a look at these two links:
-
-  * http://www.stack.nl/~dimitri/doxygen/manual/docblocks.html
-  * http://www.stack.nl/~dimitri/doxygen/manual/commands.html
-
-## Examples
-
-Below are a few examples of documentation from the codebase.
-
-### Function
-
-```cpp
-/**
- * Removes whitespace characters from the start and from the end of a string.
- *
- * @param s String that is going to be trimmed.
- *
- * @return Trimmed string.
- */
-inline std::string Trim(const std::string &s);
-```
-
-### Class
-
-```cpp
-/** Base class for logical operators.
- *
- *  Each operator describes an operation, which is to be performed on the
- *  database. Operators are iterated over using a @c Cursor. Various operators
- *  can serve as inputs to others and thus a sequence of operations is formed.
- */
-class LogicalOperator
-    : public ::utils::Visitable<HierarchicalLogicalOperatorVisitor> {
- public:
-  /** Constructs a @c Cursor which is used to run this operator.
-   *
-   *  @param GraphDbAccessor Used to perform operations on the database.
-   */
-  virtual std::unique_ptr<Cursor> MakeCursor(GraphDbAccessor &db) const = 0;
-
-  /** Return @c Symbol vector where the results will be stored.
-   *
-   *  Currently, outputs symbols are only generated in @c Produce operator.
-   *  @c Skip, @c Limit and @c OrderBy propagate the symbols from @c Produce (if
-   *  it exists as input operator). In the future, we may want this method to
-   *  return the symbols that will be set in this operator.
-   *
-   *  @param SymbolTable used to find symbols for expressions.
-   *  @return std::vector<Symbol> used for results.
-   */
-  virtual std::vector<Symbol> OutputSymbols(const SymbolTable &) const {
-    return std::vector<Symbol>();
-  }
-
-  virtual ~LogicalOperator() {}
-};
-```
-
-### File Header
-
-```cpp
-/// @file visitor.hpp
-///
-/// This file contains the generic implementation of visitor pattern.
-///
-/// There are 2 approaches to the pattern:
-///
-///   * classic visitor pattern using @c Accept and @c Visit methods, and
-///   * hierarchical visitor which also uses @c PreVisit and @c PostVisit
-///   methods.
-///
-/// Classic Visitor
-/// ===============
-///
-/// Explanation on the classic visitor pattern can be found from many
-/// sources, but here is the link to hopefully most easily accessible
-/// information: https://en.wikipedia.org/wiki/Visitor_pattern
-///
-/// The idea behind the generic implementation of classic visitor pattern is to
-/// allow returning any type via @c Accept and @c Visit methods. Traversing the
-/// class hierarchy is relegated to the visitor classes. Therefore, visitor
-/// should call @c Accept on children when visiting their parents. To implement
-/// such a visitor refer to @c Visitor and @c Visitable classes.
-///
-/// Hierarchical Visitor
-/// ====================
-///
-/// Unlike the classic visitor, the intent of this design is to allow the
-/// visited structure itself to control the traversal. This way the internal
-/// children structure of classes can remain private. On the other hand,
-/// visitors may want to differentiate visiting composite types from leaf types.
-/// Composite types are those which contain visitable children, unlike the leaf
-/// nodes. Differentiation is accomplished by providing @c PreVisit and @c
-/// PostVisit methods, which should be called inside @c Accept of composite
-/// types. Regular @c Visit is only called inside @c Accept of leaf types.
-/// To implement such a visitor refer to @c CompositeVisitor, @c LeafVisitor and
-/// @c Visitable classes.
-///
-/// Implementation of hierarchical visiting is modelled after:
-/// http://wiki.c2.com/?HierarchicalVisitorPattern
-```
-

docs/dev/other-code-conventions.md

@@ -1,15 +0,0 @@
-# Other Code Conventions
-
-While we are mainly programming in C++, we do use other programming languages
-when appropriate. This chapter describes conventions for such code.
-
-## Python
-
-Code written in Python should adhere to
-[PEP 8](https://www.python.org/dev/peps/pep-0008/). You should run `flake8` on
-your code to automatically check compliance.
-
-## Common Lisp
-
-Code written in Common Lisp should adhere to
-[Google Common Lisp Style](https://google.github.io/styleguide/lispguide.xml).

docs/dev/query/.gitignore

@@ -1 +0,0 @@
-html/

docs/dev/query/contents.md

@@ -1,34 +0,0 @@
-# Query Parsing, Planning and Execution
-
-This part of the documentation deals with query execution.
-
-Memgraph currently supports only query interpretation. Each new query is
-parsed, analysed and translated into a sequence of operations which are then
-executed on the main database storage. Query execution is organized into the
-following phases:
-
-  1.  [Lexical Analysis (Tokenization)](parsing.md)
-  2.  [Syntactic Analysis (Parsing)](parsing.md)
-  3.  [Semantic Analysis and Symbol Generation](semantic.md)
-  4.  [Logical Planning](planning.md)
-  5.  [Logical Plan Execution](execution.md)
-
-The main entry point is `Interpreter::operator()`, which takes a query text
-string and produces a `Results` object. To instantiate the object,
-`Interpreter` needs to perform the above steps from 1 to 4. If any of the
-steps fail, a `QueryException` is thrown. The complete `LogicalPlan` is
-wrapped into a `CachedPlan` and stored for reuse. This way we can skip the
-whole process of analysing a query if it appears to be the same as before.
-
-When we have valid plan, the client code can invoke `Results::PullAll` with a
-stream object. The `Results` instance will then execute the plan and fill the
-stream with the obtained results.
-
-Since we want to optionally run Memgraph as a distributed database, we have
-hooks for creating a different plan of logical operators.
-`DistributedInterpreter` inherits from `Interpreter` and overrides
-`MakeLogicalPlan` method. This method needs to return a concrete instance of
-`LogicalPlan`, and in case of distributed database that will be
-`DistributedLogicalPlan`.
-
-![Intepreter Class Diagram](interpreter-class.png)

docs/dev/query/execution.md

@@ -1,373 +0,0 @@
-# Logical Plan Execution
-
-We implement classical iterator style operators. Logical operators define
-operations on database. They encapsulate the following info: what the input is
-(another `LogicalOperator`), what to do with the data, and how to do it.
-
-Currently logical operators can have zero or more input operations, and thus a
-`LogicalOperator` tree is formed. Most `LogicalOperator` types have only one
-input, so we are mostly working with chains instead of full fledged trees.
-You can find information on each operator in `src/query/plan/operator.lcp`.
-
-## Cursor
-
-Logical operators do not perform database work themselves. Instead they create
-`Cursor` objects that do the actual work, based on the info in the operator.
-Cursors expose a `Pull` method that gets called by the cursor's consumer. The
-consumer keeps pulling as long as the `Pull` returns `true` (indicating it
-successfully performed some work and might be eligible for another `Pull`).
-Most cursors will call the `Pull` function of their input provided cursor, so
-typically a cursor chain is created that is analogue to the logical operator
-chain it's created from.
-
-## Frame
-
-The `Frame` object contains all the data of the current `Pull` chain. It
-serves for communicating data between cursors.
-
-For example, in a `MATCH (n) RETURN n` query the `ScanAllCursor` places a
-vertex on the `Frame` for each `Pull`. It places it on the place reserved for
-the `n` symbol. Then the `ProduceCursor` can take that same value from the
-`Frame` because it knows the appropriate symbol. `Frame` positions are indexed
-by `Symbol` objects.
-
-## ExpressionEvaluator
-
-Expressions results are not placed on the `Frame` since they do not need to be
-communicated between different `Cursors`. Instead, expressions are evaluated
-using an instance of `ExpressionEvaluator`. Since generally speaking an
-expression can be defined by a tree of subexpressions, the
-`ExpressionEvaluator` is implemented as a tree visitor. There is a performance
-sub-optimality here because a stack is used to communicate intermediary
-expression results between elements of the tree. This is one of the reasons
-why it's planned to use `Frame` for intermediary expression results as well.
-The other reason is that it might facilitate compilation later on.
-
-## Cypher Execution Semantics
-
-Cypher query execution has *mostly* well-defined semantics. Some are
-explicitly defined by openCypher and its TCK, while others are implicitly
-defined by Neo4j's implementation of Cypher that we want to be generally
-compatible with.
-
-These semantics can in short be described as follows: a Cypher query consists
-of multiple clauses some of which modify it. Generally, every clause in the
-query, when reading it left to right, operates on a consistent state of the
-property graph, untouched by subsequent clauses. This means that a `MATCH`
-clause in the beginning operates on a graph-state in which modifications by
-the subsequent `SET` are not visible.
-
-The stated semantics feel very natural to the end-user, and Neo seems to
-implement them well. For Memgraph the situation is complex because
-`LogicalOperator` execution (through a `Cursor`) happens one `Pull` at a time
-(generally meaning all the query clauses get executed for every top-level
-`Pull`). This is not inherently consistent with Cypher semantics because a
-`SET` clause can modify data, and the `MATCH` clause that precedes it might
-see the modification in a subsequent `Pull`. Also, the `RETURN` clause might
-want to stream results to the user before all `SET` clauses have been
-executed, so the user might see some intermediate graph state. There are many
-edge-cases that Memgraph does its best to avoid to stay true to Cypher
-semantics, while at the same time using a high-performance streaming approach.
-The edge-cases are enumerated in this document along with the implementation
-details they imply.
-
-## Implementation Peculiarities
-
-### Once
-
-An operator that does nothing but whose `Cursor::Pull` returns `true` on the
-first `Pull` and `false` on subsequent ones. This operator is used when
-another operator has an optional input, because in Cypher a clause will
-typically execute once for every input from the preceding clauses, or just
-once if there was no preceding input. For example, consider the `CREATE`
-clause. In the query `CREATE (n)` only one node is created, while in the query
-`MATCH (n) CREATE (m)` a node is created for each existing node. Thus in our
-`CreateNode` logical operator the input is either a `ScanAll` operator, or a
-`Once` operator.
-
-### storage::View
-
-In the previous section, [Cypher Execution
-Semantics](#cypher-execution-semantics), we mentioned how the preceding
-clauses should not see changes made in subsequent ones. For that reason, some
-operators take a `storage::View` enum value. This value determines which state of
-the graph an operator sees.
-
-Consider the query `MATCH (n)--(m) WHERE n.x = 0 SET m.x = 1`. Naive streaming
-could match a vertex `n` on the given criteria, expand to `m`, update it's
-property, and in the next iteration consider the vertex previously matched to
-`m` and skip it because it's newly set property value does not qualify. This
-is not how Cypher works. To handle this issue properly, Memgraph designed the
-`VertexAccessor` class that tracks two versions of data: one that was visible
-before the current transaction+command, and the optional other that was
-created in the current transaction+command. The `MATCH` clause will be planned
-as `ScanAll` and `Expand` operations using `storage::View::OLD` value. This
-will ensure modifications performed in the same query do not affect it. The
-same applies to edges and the `EdgeAccessor` class.
-
-### Existing Record Detection
-
-It's possible that a pattern element has already been declared in the same
-pattern, or a preceding pattern. For example `MATCH (n)--(m), (n)--(l)` or a
-cycle-detection match `MATCH (n)-->(n) RETURN n`. Implementation-wise,
-existing record detection just checks that the expanded record is equal to the
-one already on the frame.
-
-### Why Not Use Separate Expansion Ops for Edges and Vertices?
-
-Expanding an edge and a vertex in separate ops is not feasible when matching a
-cycle in bi-directional expansions. Consider the query `MATCH (n)--(n) RETURN
-n`. Let's try to expand first the edge in one op, and vertex in the next. The
-vertex expansion consumes the edge expansion input. It takes the expanded edge
-from the frame. It needs to detect a cycle by comparing the vertex existing on
-the frame with one of the edge vertices (`from` or `to`). But which one? It
-doesn't know, and can't ensure correct cycle detection.
-
-### Data Visibility During and After SET
-
-In Cypher, setting values always works on the latest version of data (from
-preceding or current clause). That means that within a `SET` clause all the
-changes from previous clauses must be visible, as well as changes done by the
-current `SET` clause. Also, if there is a clause after `SET` it must see *all*
-the changes performed by the preceding `SET`. Both these things are best
-illustrated with the following queries executed on an empty database:
-
-    CREATE (n:A {x:0})-[:EdgeType]->(m:B {x:0})
-    MATCH (n)--(m) SET m.x = n.x + 1 RETURN labels(n), n.x, labels(m), m.x
-
-This returns:
-
-+---------+---+---------+---+
-|labels(n)|n.x|labels(m)|m.x|
-+:=======:+:=:+:=======:+:=:+
-|[A]      |2  |[B]      |1  |
-+---------+---+---------+---+
-|[B]      |1  |[A]      |2  |
-+---------+---+---------+---+
-
-The obtained result implies the following operations:
-
-  1. In the first iteration set the value of the `B.x` to 1
-  2. In the second iteration the we observe `B.x` with the value of 1 and set
-     `A.x` to 2
-  3. In `RETURN` we see all the changes made in both iterations
-
-To implement the desired behavior Memgraph utilizes two techniques. First is
-the already mentioned tracking of two versions of data in vertex accessors.
-Using this approach ensures that the second iteration in the example query
-sees the data modification performed by the preceding iteration. The second
-technique is the `Accumulate` operation that accumulates all the iterations
-from the preceding logical op before passing them to the next logical op. In
-the example query, `Accumulate` ensures that the results returned to the user
-reflect changes performed in all iterations of the query (naive streaming
-could stream results at the end of first iteration producing inconsistent
-results). Note that `Accumulate` is demanding regarding memory and slows down
-query execution. For that reason it should be used only when necessary, for
-example it does not have to be used in a query that has `MATCH` and `SET` but
-no `RETURN`.
-
-### Neo4j Inconsistency on Multiple SET Clauses
-
-Considering the preceding example it could be expected that when a query has
-multiple `SET` clauses all the changes from those preceding one are visible.
-This is not the case in Neo4j's implementation. Consider the following queries
-executed on an empty database:
-
-    CREATE (n:A {x:0})-[:EdgeType]->(m:B {x:0})
-    MATCH (n)--(m) SET n.x = n.x + 1 SET m.x = m.x * 2
-    RETURN labels(n), n.x, labels(m), m.x
-
-This returns:
-
-+---------+---+---------+---+
-|labels(n)|n.x|labels(m)|m.x|
-+:=======:+:=:+:=======:+:=:+
-|[A]      |2  |[B]      |1  |
-+---------+---+---------+---+
-|[B]      |1  |[A]      |2  |
-+---------+---+---------+---+
-
-If all the iterations of the first `SET` clause were executed before executing
-the second, all the resulting values would be 2. This not being the case, we
-conclude that Neo4j does not use a barrier-like mechanism between `SET`
-clauses.  It is Memgraph's current vision that this is inconsistent and we
-plan to reduce Neo4j compliance in favour of operation consistency.
-
-### Double Deletion
-
-It's possible to match the same graph element multiple times in a single query
-and delete it. Neo supports this, and so do we. The relevant implementation
-detail is in the `GraphDbAccessor` class, where the record deletion functions
-reside, and not in the logical plan execution. It comes down to checking if a
-record has already been deleted in the current transaction+command and not
-attempting to do it again (results in a crash).
-
-### Set + Delete Edge-case
-
-It's legal for a query to combine `SET` and `DELETE` clauses. Consider the
-following queries executed on an empty database:
-
-
-    CREATE ()-[:T]->()
-    MATCH (n)--(m) SET n.x = 42 DETACH DELETE m
-
-Due to the `MATCH` being undirected the second pull will attempt to set data
-on a deleted vertex. This is not a legal operation in Memgraph storage
-implementation. For that reason the logical operator for `SET` must check if
-the record it's trying to set something on has been deleted by the current
-transaction+command. If so, the modification is not executed.
-
-### Deletion Accumulation
-
-Sometimes it's necessary to accumulate deletions of all the matches before
-attempting to execute them. Consider this the following. Start with an empty
-database and execute queries:
-
-    CREATE ()-[:T]->()-[:T]->()
-    MATCH (a)-[r1]-(b)-[r2]-(c) DELETE r1, b, c
-
-Note that the `DELETE` clause attempts to delete node `c`, but it does not
-detach it by deleting edge `r2`. However, due to undirected edge in the
-`MATCH`, both edges get pulled and deleted.
-
-Currently Memgraph does not support this behavior, Neo does. There are a few
-ways that we could do this.
-
- * Accumulate on deletion (that sucks because we have to keep track of
-   everything that gets returned after the deletion).
- * Maybe we could stream through the deletion op, but defer actual deletion
-   until plan-execution end.
- * Ignore this because it's very edgy (this is the currently selected option).
-
-### Aggregation Without Input
-
-It is necessary to define what aggregation ops return when they receive no
-input. Following is a table that shows what Neo4j's Cypher implementation and
-SQL produce.
-
-
-+-------------+------------------------+---------------------+---------------------+------------------+
-|    \<OP\>   | 1. Cypher, no group-by | 2. Cypher, group-by | 3. SQL, no group-by | 4. SQL, group-by |
-+=============+:======================:+:===================:+:===================:+:================:+
-| Count(\*)   | 0                      | \<NO\_ROWS>         | 0                   | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Count(prop) | 0                      | \<NO\_ROWS>         | 0                   | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Sum         | 0                      | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Avg         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Min         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Max         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Collect     | []                     | \<NO\_ROWS>         | N/A                 | N/A              |
-+-------------+------------------------+---------------------+---------------------+------------------+
-
-Where:
-
-    1. `MATCH (n) RETURN <OP>(n.prop)`
-    2. `MATCH (n) RETURN <OP>(n.prop), (n.prop2)`
-    3. `SELECT <OP>(prop) FROM Table`
-    4. `SELECT <OP>(prop), prop2 FROM Table GROUP BY prop2`
-
-Neo's Cypher implementation diverges from SQL only when performing `SUM`.
-Memgraph implements SQL-like behavior. It is considered that `SUM` of
-arbitrary elements should not be implicitly 0, especially in a property graph
-without a strict schema (the property in question can contain values of
-arbitrary types, or no values at all).
-
-### OrderBy
-
-The `OrderBy` logical operator sorts the results in the desired order. It
-occurs in Cypher as part of a `WITH` or `RETURN` clause. Both the concept and
-the implementation are straightforward. It's necessary for the logical op to
-`Pull` everything from its input so it can be sorted. It's not necessary to
-keep the whole `Frame` state of each input, it is sufficient to keep a list of
-`TypedValues` on which the results will be sorted, and another list of values
-that need to be remembered and recreated on the `Frame` when yielding.
-
-The sorting itself is made to reflect that of Neo's implementation which comes
-down to these points.
-
-  * `Null` comes last (as if it's greater than anything).
-  * Primitive types compare naturally, with no implicit casting except from
-    `int` to `double`.
-  * Complex types are not comparable.
-  * Every unsupported comparison results in an exception that gets propagated
-    to the end user.
-
-### Limit in Write Queries
-
-`Limit` can be used as part of a write query, in which case it will *not*
-reduce the amount of performed updates. For example, consider a database that
-has 10 vertices. The query `MATCH (n) SET n.x = 1 RETURN n LIMIT 3` will
-result in all vertices having their property value changed, while returning
-only the first to the client. This makes sense from the implementation
-standpoint, because `Accumulate` is planned after `SetProperty` but before
-`Produce` and `Limit` operations. Note that this behavior can be
-non-deterministic in some queries, since it relies on the order of iteration
-over nodes which is undefined when not explicitly specified.
-
-### Merge
-
-`MERGE` in Cypher attempts to match a pattern. If it already exists, it does
-nothing and subsequent clauses like `RETURN` can use the matched pattern
-elements. If the pattern can't match to any data, it creates it. For detailed
-information see Neo4j's [merge
-documentation.](https://neo4j.com/docs/developer-manual/current/cypher/clauses/merge/)
-
-An important thing about `MERGE` is visibility of modified data. `MERGE` takes
-an input (typically a `MATCH`) and has two additional *phases*: the merging
-part, and the subsequent set parts (`ON MATCH SET` and `ON CREATE SET`).
-Analysis of Neo4j's behavior indicates that each of these three phases (input,
-merge, set) does not see changes to the graph state done by subsequent phase.
-The input phase does not see data created by the merge phase, nor the set
-phase. This is consistent with what seems like the general Cypher philosophy
-that query clause effects aren't visible in the preceding clauses.
-
-We define the `Merge` logical operator as a *routing* operator that uses three
-logical operator branches.
-
-  1. The input from a preceding clause.
-
-     For example in `MATCH (n), (m) MERGE (n)-[:T]-(m)`. This input is
-     optional because `MERGE` is allowed to be the first clause in a query.
-
-  2. The `merge_match` branch.
-
-     This logical operator branch is `Pull`-ed from until exhausted for each
-     successful `Pull` from the input branch.
-
-  3. The `merge_create` branch.
-
-     This branch is `Pull`ed when the `merge_match` branch does not match
-     anything (no successful `Pull`s) for an input `Pull`. It is `Pull`ed only
-     once in such a situation, since only one creation needs to occur for a
-     failed match.
-
-The `ON MATCH SET` and `ON CREATE SET` parts of the `MERGE` clause are
-included in the `merge_match` and `merge_create` branches respectively. They
-are placed on the end of their branches so that they execute only when those
-branches succeed.
-
-Memgraph strives to be consistent with Neo in its `MERGE` implementation,
-while at the same time keeping performance as good as possible. Consistency
-with Neo w.r.t. graph state visibility is not trivial. Documentation for
-`Expand` and `Set` describe how Memgraph keeps track of both the updated
-version of an edge/vertex and the old one, as it was before the current
-transaction+command. This technique is also used in `Merge`. The input
-phase/branch of `Merge` always looks at the old data. The merge phase needs to
-see the new data so it doesn't create more data then necessary.
-
-For example, consider the query.
-
-    MATCH (p:Person) MERGE (c:City {name: p.lives_in})
-
-This query needs to create a city node only once for each unique `p.lives_in`.
-Finally the set phase of a `MERGE` clause should not affect the merge phase.
-To achieve this the `merge_match` branch of the `Merge` operator should see
-the latest created nodes, but filter them on their old state (if those nodes
-were not created by the `create_branch`).  Implementation-wise that means that
-`ScanAll` and `Expand` operators in the `merge_branch` need to look at the new
-graph state, while `Filter` operators the old, if available.

docs/dev/query/interpreter-class.dot

@@ -1,23 +0,0 @@
-digraph interpreter {
-  node [fontname="dejavusansmono"]
-  edge [fontname="dejavusansmono"]
-  node [shape=record]
-  edge [dir=back,arrowtail=empty,arrowsize=1.5]
-  Interpreter [label="{\N|+ operator(query : string, ...) : Results\l|
-                      # MakeLogicalPlan(...) : LogicalPlan\l|
-                      - plan_cache_ : Map(QueryHash, CachedPlan)\l}"]
-  Interpreter -> DistributedInterpreter
-  Results [label="{\N|+ PullAll(stream) : void\l|- plan_ : CachedPlan\l}"]
-  Interpreter -> Results
-    [dir=forward,style=dashed,arrowhead=open,label="<<create>>"]
-  CachedPlan -> Results
-    [dir=forward,arrowhead=odiamond,taillabel="1",headlabel="*"]
-  Interpreter -> CachedPlan [arrowtail=diamond,taillabel="1",headlabel="*"]
-  CachedPlan -> LogicalPlan [arrowtail=diamond]
-  LogicalPlan [label="{\N|+ GetRoot() : LogicalOperator
-                      \l+ GetCost() : double\l}"]
-  LogicalPlan -> SingleNodeLogicalPlan [style=dashed]
-  LogicalPlan -> DistributedLogicalPlan [style=dashed]
-  DistributedInterpreter -> DistributedLogicalPlan
-    [dir=forward,style=dashed,arrowhead=open,label="<<create>>"]
-}

docs/dev/query/parsing.md

@@ -1,62 +0,0 @@
-# Lexical and Syntactic Analysis
-
-## Antlr
-
-We use Antlr for lexical and syntax analysis of Cypher queries. Antrl uses
-grammar file `Cypher.g4` downloaded from http://www.opencypher.org to generate
-the parser and the visitor for the Cypher parse tree. Even though the provided
-grammar is not very pleasant to work with we decided not to do any drastic
-changes to it so that our transition to newly published versions of
-`Cypher.g4` would be easier. Nevertheless, we had to fix some bugs and add
-features, so our version is not completely the same.
-
-In addition to using `Cypher.g4`, we have `MemgraphCypher.g4`. This grammar
-file defines Memgraph specific extensions to the original grammar. Most
-notable example is the inclusion of syntax for handling authorization. At the
-moment, some extensions are also found in `Cypher.g4`. For example, the syntax
-for using a lambda function in relationship patterns. These extensions should
-be moved out of `Cypher.g4`, so that it remains as close to the original
-grammar as possible. Additionally, having `MemgraphCypher.g4` may not be
-enough if we wish to split the functionality for community and enterprise
-editions of Memgraph.
-
-## Abstract Syntax Tree (AST)
-
-Since Antlr generated visitor and the official openCypher grammar are not very
-practical to use, we translate the Antlr's AST to our own AST. Currently there
-are ~40 types of nodes in our AST. Their definitions can be found in
-`src/query/frontend/ast/ast.lcp`.
-
-Major groups of types can be found under the following base types.
-
-  * `Expression` --- types corresponding to Cypher expressions.
-  * `Clause` --- types corresponding to Cypher clauses.
-  * `PatternAtom` --- node or edge related information.
-  * `Query` --- different kinds of queries, allows extending the language with
-    Memgraph specific query syntax.
-
-Memory management of created AST nodes is done with `AstStorage`. Each type
-must be created by invoking `AstStorage::Create` method. This way all of the
-pointers to nodes and their children are raw pointers. The only owner of
-allocated memory is the `AstStorage`. When the storage goes out of scope, the
-pointers become invalid. It may be more natural to handle tree ownership via
-`unique_ptr`, i.e. each node owns its children. But there are some benefits to
-having a custom storage and allocation scheme.
-
-The primary reason we opted for not using `unique_ptr` is the requirement of
-Antlr's base visitor class that the resulting values must by copyable. The
-result is wrapped in `antlr::Any` so that the derived visitor classes may
-return any type they wish when visiting Antlr's AST. Unfortunately,
-`antlr::Any` does not work with non-copyable types.
-
-Another benefit of having `AstStorage` is that we can easily add a different
-allocation scheme for AST nodes. The interface of node creation would not
-change.
-
-### AST Translation
-
-The translation process is done via `CypherMainVisitor` class, which is
-derived from Antlr generated visitor. Besides instancing our AST types, a
-minimal number of syntactic checks are done on a query. These checks handle
-the cases which were valid in original openCypher grammar, but may be invalid
-when combined with other syntax elements.

docs/dev/query/planning.md

@@ -1,526 +0,0 @@
-# Logical Planning
-
-After the semantic analysis and symbol generation, the AST is converted to a
-tree of logical operators. This conversion is called *planning* and the tree
-of logical operators is called a *plan*. The whole planning process is done in
-the following steps.
-
-  1. [AST Preprocessing](#ast-preprocessing)
-
-     The first step is to preprocess the AST by collecting
-     information on filters, divide the query into parts, normalize patterns
-     in `MATCH` clauses, etc.
-
-  2. [Logical Operator Planning](#logical-operator-planning)
-
-     After the preprocess step, the planning can be done via 2 planners:
-     `VariableStartPlanner` and `RuleBasedPlanner`. The first planner will
-     generate multiple plans where each plan has different starting points for
-     searching the patterns in `MATCH` clauses. The second planner produces a
-     single plan by mapping the query parts as they are to logical operators.
-
-  3. [Logical Plan Postprocessing](#logical-plan-postprocessing)
-
-     In this stage, we perform various transformations on the generated logical
-     plan. Here we want to optimize the operations in order to improve
-     performance during the execution. Naturally, transformations need to
-     preserve the semantic behaviour of the original plan.
-
-  4. [Cost Estimation](#cost-estimation)
-
-     After the generation, the execution cost of each plan is estimated. This
-     estimation is used to select the best plan which will be executed.
-
-The implementation can be found in the `query/plan` directory, with the public
-entry point being `query/plan/planner.hpp`.
-
-## AST Preprocessing
-
-Each openCypher query consists of at least 1 **single query**. Multiple single
-queries are chained together using a **query combinator**. Currently, there is
-only one combinator, `UNION`. The preprocessing step starts in the
-`CollectQueryParts` function. This function will take a look at each single
-query and divide it into parts. Each part is separated with `RETURN` and
-`WITH` clauses. For example:
-
-    MATCH (n) CREATE (m) WITH m MATCH (l)-[]-(m) RETURN l
-    |                          |                        |
-    |------- part 1 -----------+-------- part 2 --------|
-    |                                                   |
-    |-------------------- single query -----------------|
-
-Each part is created by collecting all `MATCH` clauses and *normalizing* their
-patterns. Pattern normalization is the process of converting an arbitrarily
-long pattern chain of nodes and edges into a list of triplets `(start node,
-edge, end node)`. The triplets should preserve the semantics of the match. For
-example:
-
-    MATCH (a)-[p]-(b)-[q]-(c)-[r]-(d)
-
-is equivalent to:
-
-    MATCH (a)-[p]-(b), (b)-[q]-(c), (c)-[r]-(d)
-
-With this representation, it becomes easier to reorder the triplets and choose
-different strategies for pattern matching.
-
-In addition to normalizing patterns, all of the filter expressions in patterns
-and inside of the `WHERE` clause (of the accompanying `MATCH`) are extracted
-and stored separately. During the extraction, symbols used in the filter
-expression are collected. This allows for planning filters in a valid order,
-as the matching for triplets is being done. Another important benefit of
-having extra information on filters, is to recognize when a database index
-could be used.
-
-After each `MATCH` is processed, they are all grouped, so that even the whole
-`MATCH` clauses may be reordered. The important thing is to remember which
-symbols were used to name edges in each `MATCH`. With those symbols we can
-plan for *cyphermorphism*, i.e. ensure different edges in the search pattern
-of a single `MATCH` map to different edges in the graph. This preserves the
-semantic of the query, even though we may have reordered the matching. The
-same steps are done for `OPTIONAL MATCH`.
-
-Another clause which needs processing is `MERGE`. Here we normalize the
-pattern, since the `MERGE` is a bit like `MATCH` and `CREATE` in one.
-
-All the other clauses are left as is.
-
-In the end, each query part consists of:
-
-  * processed and grouped `MATCH` clauses;
-  * processed and grouped `OPTIONAL MATCH` clauses;
-  * processed `MERGE` matching pattern and
-  * unchanged remaining clauses.
-
-The last stored clause is guaranteed to be either `WITH` or `RETURN`.
-
-## Logical Operator Planning
-
-### Variable Start Planner
-
-The `VariableStartPlanner` generates multiple plans for a single query. Each
-plan is generated by selecting a different starting point for pattern
-matching.
-
-The algorithm works as follows.
-
-  1. For each query part:
-     1. For each node in triplets of collected `MATCH` clauses:
-        i. Add the node to a set of `expanded` nodes
-        ii. Select a triplet `(start node, edge, end node)` whose `start node` is
-            in the `expanded` set
-        iii. If no triplet was selected, choose a new starting node that isn't in
-             `expanded` and continue expanding
-        iv. Repeat steps ii. -- iii. until all triplets have been selected
-            and store that as a variation of the `MATCH` clauses
-     2. Do step 1.1. for `OPTIONAL MATCH` and `MERGE` clauses
-     3. Take all combinations of the generated `MATCH`, `OPTIONAL MATCH` and
-        `MERGE` and store them as variations of the query part.
-  2. For each combination of query part variations:
-     1. Generate a plan using the rule based planner
-
-###  Rule Based Planner
-
-The `RuleBasedPlanner` generates a single plan for a single query. A plan is
-generated by following hardcoded rules for producing logical operators. The
-following sections are an overview on how each openCypher clause is converted
-to a `LogicalOperator`.
-
-####  MATCH
-
-`MATCH` clause is used to specify which patterns need to be searched for in
-the database. These patterns are normalized in the preprocess step to be
-represented as triplets `(start node, edge, end node)`. When there is no edge,
-then the triplet is reduced only to the `start node`. Generating the operators
-is done by looping over these triplets.
-
-##### Searching for Nodes
-
-The simplest search is finding standalone nodes. For example, `MATCH (n)`
-will find all the nodes in the graph. This is accomplished by generating a
-`ScanAll` operator and forwarding the node symbol which should store the
-results. In this case, all the nodes will be referenced by `n`.
-
-Multiple nodes can be specified in a single match, e.g. `MATCH (n), (m)`.
-Planning is done by repeating the same steps for each sub pattern (separated
-by a comma). In this case, we would get 2 `ScanAll` operators chained one
-after the other. An optimization can be obtained if the node in the pattern is
-already searched for. In `MATCH (n), (n)` we can drop the second `ScanAll`
-operator since we have already generated it for the first node.
-
-##### Searching for Relationships
-
-A more advanced search includes finding nodes with relationships. For example,
-`MATCH (n)-[r]-(m)` should find every pair of connected nodes in the database.
-This means, that if a single node has multiple connections, it will be
-repeated for each combination of pairs. The generation of operators starts
-from the first node in the pattern. If we are referencing a new starting node,
-we need to generate a `ScanAll` which finds all the nodes and stores them
-into `n`. Then, we generate an `Expand` operator which reads the `n` and
-traverses all the edges of that node. The edge is stored into `r`, while the
-destination node is stored in `m`.
-
-Matching multiple relationships proceeds similarly, by repeating the same
-steps. The only difference is that we need to ensure different edges in the
-search pattern, map to different edges in the graph. This means that after each
-`Expand` operator, we need to generate an `EdgeUniquenessFilter`. We provide
-this operator with a list of symbols for the previously matched edges and the
-symbol for the current edge.
-
-For example.
-
-    MATCH (n)-[r1]-(m)-[r2]-(l)
-
-The above is preprocessed into
-
-    MATCH (n)-[r1]-(m), (m)-[r2]-(l)
-
-Then we look at each triplet in order and perform the described steps. This
-way, we would generate:
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) >
-        EdgeUniquenessFilter ([r1], r2)
-
-Note that we don't need to make `EdgeUniquenessFilter` after the first
-`Expand`, since there are no edges to compare to. This filtering needs to work
-across multiple pattern, but inside a *single* `MATCH` clause.
-
-Let's take a look at the following.
-
-    MATCH (n)-[r1]-(m), (m)-[r2]-(l)
-
-We would also generate the exact same operators.
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) >
-        EdgeUniquenessFilter ([r1], r2)
-
-On the other hand,
-
-    MATCH (n)-[r1]-(m) MATCH (m)-[r2]-(l)-[r3]-(i)
-
-would reset the uniqueness filtering at the start of the second match. This
-would mean that we output the following:
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) > Expand (l, r3, i) >
-        EdgeUniquenessFilter ([r2], r3)
-
-There is a difference in how we handle edge uniqueness compared to Neo4j.
-Neo4j does not allow searching for a single edge multiple times, but we've
-decided to support that.
-
-For example, the user can say the following.
-
-    MATCH (n)-[r]-(m)-[r]-l
-
-We would ensure that both `r` variables match to the same edge. In our
-terminology, we call this the *edge cycle*. For the above example, we would
-generate this plan.
-
-    ScanAll (n) > Expand (n, r, m) > Expand (m, r, l)
-
-We do not put an `EdgeUniquenessFilter` operator between 2 `Expand`
-operators and we tell the 2nd `Expand` that it is an edge cycle. This, 2nd
-`Expand` will ensure we have matched both the same edges.
-
-##### Filtering
-
-To narrow the search down, the patterns in `MATCH` can have filtered labels
-and properties. A more general filtering is done using the accompanying
-`WHERE` clause. During the preprocess step, all filters are collected and
-extracted into expressions. Additional information on which symbols are used
-is also stored. This way, each time we generate a `ScanAll` or `Expand`, we
-look at all the filters to see if any of them can be used. I.e. if the symbols
-they use have been bound by a newly produced operator. If a filter expression
-can be used, we immediately add a `Filter` operator with that expression.
-
-For example.
-
-    MATCH (n)-[r]-(m :label) WHERE n.prop = 42
-
-We would produce:
-
-    ScanAll (n) > Filter (n.prop) > Expand (n, r, m) > Filter (m :label)
-
-This means that the same plan is generated for the query:
-
-    MATCH (n {prop: 42})-[r]-(m :label)
-
-#### OPTIONAL
-
-If a `MATCH` clause is preceded by `OPTIONAL`, then we need to generate a plan
-such that we produce results even if we fail to match anything. This is
-accomplished by generating an `Optional` operator, which takes 2 operator
-trees:
-
-  * input operation and
-  * optional operation.
-
-The input is the operation we generated for the part of the query before
-`OPTIONAL MATCH`. For the optional operation, we simply generate the `OPTIONAL
-MATCH` part just like we would for regular `MATCH`. In addition to operations,
-we need to send the symbols which are set during optional matching to the
-`Optional` operator. The operator will reset values of those symbols to
-`null`, when the optional part fails to match.
-
-#### RETURN & WITH
-
-`RETURN` and `WITH` clauses are very similar to each other. The only
-difference is that `WITH` separates parts of the query and can be paired with
-`WHERE` clause.
-
-The common part is generating operators for the body of the clause. Separation
-of query parts is mostly done in semantic analysis, which checks that only the
-symbols exposed through `WITH` are visible in the query parts after the
-clause. The minor part is done in planning.
-
-##### Named Results
-
-Both clauses contain multiple named expressions (`expr AS name`) which are
-used to generate `Produce` operator.
-
-##### Aggregations
-
-If an expression contains an aggregation operator (`sum`, `avg`, ...) we need
-to plan the `Aggregate` operator as input to `Produce`. This case is more
-complex, because aggregation in openCypher can perform implicit grouping of
-results used for aggregation.
-
-For example, `WITH/RETURN sum(n.x) AS s, n.y AS group` will implicitly group
-by `n.y` expression.
-
-Another, obscure grouping can be achieved with `RETURN sum(n.a) + n.b AS s`.
-Here, the `n.b` will be used for grouping, even though both the `sum` and
-`n.b` are in the same named expression.
-
-Therefore, we need to collect all expressions which do not contain
-aggregations and use them for grouping. You may have noticed that in the last
-example `sum` is actually a sub-expression of `+`. `Aggregate` operator does
-not see that (nor it should), so the responsibility of evaluating that falls
-on `Produce`. One way is for `Aggregate` to store results of grouping
-expressions on the frame in addition to aggregation results. Unfortunately,
-this would require rewiring named expressions in `Produce` to reference
-already evaluated expressions. In the current implementation, we opted for
-`Aggregate` to store only aggregation results on the frame, while `Produce`
-will re-evaluate all the other (grouping) expressions. To handle that, symbols
-which are used in expressions are passed to `Aggregate`, so that they can be
-remembered. `Produce` will read those symbols from the frame and use it to
-re-evaluate the needed expressions.
-
-##### Accumulation
-
-After we have `Produce` and potentially `Aggregate`, we need to handle a
-special case when the part of the query before `RETURN` or `WITH` performs
-updates. For that, we want to run that part of the query fully, so that we get
-the latest results. This is accomplished by adding `Accumulate` operator as
-input to `Aggregate` or `Produce` (if there is no aggregation). Accumulation
-will store all the values for all the used symbols inside `RETURN` and `WITH`,
-so that they can be used in the operator which follows. This way, only parts
-of the frame are copied, instead of the whole frame. Here is a minor
-difference between planning `WITH`, compared to `RETURN`. Since `WITH` can
-separate writing from reading, we need to advance the transaction command.
-This enables the later, read parts of the query to obtain the newest changes.
-This is supported by passing `advance_command` flag to `Accumulate` operator.
-
-In the simplest case, common to both clauses, we have `Accumulate > Aggregate
-> Produce` operators, where `Accumulate` and `Aggregate` may be left out.
-
-##### Ordering
-
-Planning `ORDER BY` is simple enough. Since it may see new symbols (filled in
-`Produce`), we add the `OrderBy` operator at the end. The operator will change
-the order of produced results, so we pass it the ordering expressions and the
-output symbols of named expressions.
-
-##### Filtering
-
-A final difference in `WITH`, is when it contains a `WHERE` clause. For that,
-we simply generate the `Filter` operator, appended after `Produce` or
-`OrderBy` (depending which operator is last).
-
-##### Skipping and Limiting
-
-If we have `SKIP` or `LIMIT`, we generate `Skip` or `Limit` operators,
-respectively. These operators are put at the end of the clause.
-
-This placement may have some unexpected behaviour when combined with
-operations that update the graph. For example.
-
-    MATCH (n) SET n.x = n.x + 1 RETURN n LIMIT 1
-
-The above query may be interpreted as if the `SET` will be done only once.
-Since this is a write query, we need to accumulate results, so the part before
-`RETURN` will execute completely. The accumulated results will be yielded up
-to the given limit, and the user would get only the first `n` that was
-updated.  This may confuse the user because in reality, every node in the
-database had been updated.
-
-Note that `Skip` always comes before `Limit`. In the current implementation,
-they are generated directly one after the other.
-
-#### CREATE
-
-`CREATE` clause is used to create nodes and edges (relationships).
-
-For multiple `CREATE` clauses or multiple creation patterns in a single
-clause, we perform the same, following steps.
-
-##### Creating a Single Node
-
-A node is created by simply specifying a node pattern.
-
-For example `CREATE (n :label {property: "value"}), ()` would create 2 nodes.
-The 1st one would be created with a label and a property. This node could be
-referenced later in the query, by using the variable `n`. The 2nd node cannot
-be referenced and it would be created without any labels nor properties. For
-node creation, we generate a `CreateNode` operator and pass it all the details
-of node creation: variable symbol, labels and properties. In the mentioned
-example, we would have `CreateNode > CreateNode`.
-
-##### Creating a Relationship
-
-To create a relationship, the `CREATE` clause must contain a pattern with a
-directed edge. Compared to creating a single node, this case is a bit more
-complicated, because either side of the edge may not exist. By exist, we mean
-that the endpoint is a variable which already references a node.
-
-For example, `MATCH (n) CREATE (n)-[r]->(m)` would create an edge `r` and a
-node `m` for each matched node `n`. If we focus on the `CREATE` part, we
-generate `CreateExpand (n, r, m)` where `n` already exists (refers to matched
-node) and `m` would be newly created along with edge `r`. If we had only
-`CREATE (n)-[r]->(m)`, then we would need to create both nodes of the edge
-`r`. This is done by generating `CreateNode (n) > CreateExpand(n, r, m)`. The
-final case is when both endpoints refer to an existing node. For example, when
-adding a node with a cyclical connection `CREATE (n)-[r]->(n)`. In this case,
-we would generate `CreateNode (n) > CreateExpand (n, r, n)`. We would tell
-`CreateExpand` to only create the edge `r` between the already created `n`.
-
-#### MERGE
-
-Although the merge operation is complex, planning turns out to be relatively
-simple. The pattern inside the `MERGE` clause is used for both matching and
-creating. Therefore, we create 2 operator trees, one for each action.
-
-For example.
-
-    MERGE (n)-[r:r]-(m)
-
-We would generate a single `Merge` operator which has the following.
-
-  * No input operation (since it is not preceded by any other clause).
-
-  * On match operation
-
-    `ScanAll (n) > Expand (n, r, m) > Filter (r)`
-
-  * On create operation
-
-    `CreateNode (n) > CreateExpand (n, r, m)`
-
-In cases when `MERGE` contains `ON MATCH` and `ON CREATE` parts, we simply
-append their operations to the respective operator trees.
-
-Observe the following example.
-
-    MERGE (n)-[r:r]-(m) ON MATCH SET n.x = 42 ON CREATE SET m :label
-
-The `Merge` would be generated with the following.
-
-  * No input operation (again, since there is no clause preceding it).
-
-  * On match operation
-
-    `ScanAll (n) > Expand (n, r, m) > Filter (r) > SetProperty (n.x, 42)`
-
-  * On create operation
-
-    `CreateNode (n) > CreateExpand (n, r, m) > SetLabels (n, :label)`
-
-When we have preceding clauses, we simply put their operator as input to
-`Merge`.
-
-    MATCH (n) MERGE (n)-[r:r]-(m)
-
-The above would be generated as
-
-    ScanAll (n) > Merge (on_match_operation, on_create_operation)
-
-Here we need to be careful to recognize which symbols are already declared.
-But, since the `on_match_operation` uses the same algorithm for generating a
-`Match`, that problem is handled there. The same should hold for
-`on_create_operation`, which uses the process of generating a `Create`. So,
-finally for this example, the `Merge` would have:
-
-  * Input operation
-
-    `ScanAll (n)`
-
-  * On match operation
-
-    `Expand (n, r, m) > Filter (r)`
-
-    Note that `ScanAll` is not needed since we get the nodes from input.
-
-  * On create operation
-
-    `CreateExpand (n, r, m)`
-
-    Note that `CreateNode` is dropped, since we want to expand the existing one.
-
-## Logical Plan Postprocessing
-
-Postprocessing of a logical plan is done by rewriting the original plan into
-a more efficient one while preserving the original semantic of operations.
-The rewriters are found in `query/plan/rewrite` directory, and currently we
-only have one -- `IndexLookupRewriter`.
-
-### IndexLookupRewriter
-
-The job of this rewriter is to merge `Filter` and `ScanAll` operations into
-equivalent `ScanAllBy<Index>` operations. In almost all cases using indexed
-lookup will be faster than regular lookup, so `IndexLookupRewriter` simply
-does the transformations whenever possible. The simplest case being the
-following, assuming we have an index over `id`.
-
-  * Original Plan
-
-    `ScanAll (n) > Filter (id(n) == 42) > Produce (n)`
-
-  * Rewritten Plan
-
-    `ScanAllById (n, id=42) > Produce (n)`
-
-Naturally, there are some cases we need to be careful about.
-
-  1. Operators with Multiple Branches
-
-     Here we may not carry `Filter` operations outside of the operator into
-     its branches, so the branches are rewritten as stand alone plans with a
-     branch new `IndexLookupRewriter`. Some of the operators with multiple
-     branches are `Merge`, `Optional`, `Cartesian` and `Union`.
-
-  2. Expand Operators
-
-     Expand operations aren't that tricky to handle, but they have a special
-     case where we want to use an indexed lookup of the destination so that the
-     expansion is performed between known nodes. This decision may depend on
-     various parameters which may need further tweaking as we encounter more
-     use-cases of Cypher queries.
-
-## Cost Estimation
-
-Cost estimation is the final step of processing a logical plan. The
-implementation can be found in `query/plan/cost_estimator.hpp`. We give each
-operator a cost based on the estimated cardinality of results of that operator
-and on the preset coefficient of the runtime performance of that operator.
-
-This scheme is rather simple and works quite well, but there are couple of
-improvements we may want to do at some point.
-
-  * Track more information about the stored graph and use that to improve the
-    estimates.
-  * Do a quick, partial run of the plan and tweak the estimation based on how
-    much each operator produced results. This may require us having some kind
-    of representative subset of the stored graph.
-  * Write micro benchmarks for each operator and based on the results create
-    sensible preset coefficients. This would replace the current coefficients
-    which are just assumptions on how each operator implementation performs.

docs/dev/query/semantic.md

@@ -1,134 +0,0 @@
-# Semantic Analysis and Symbol Generation
-
-In this phase, various semantic and variable type checks are performed.
-Additionally, we generate symbols which map AST nodes to stored values
-computed from evaluated expressions.
-
-## Symbol Generation
-
-Implementation can be found in `query/frontend/semantic/symbol_generator.cpp`.
-
-Symbols are generated for each AST node that represents data that needs to
-have storage. Currently, these are:
-
-  * `NamedExpression`
-  * `CypherUnion`
-  * `Identifier`
-  * `Aggregation`
-
-You may notice that the above AST nodes may not correspond to something named
-by a user. For example, `Aggregation` can be a part of larger expression and
-thus remain unnamed. The reason we still generate symbols is to have a uniform
-behaviour when executing a query as well as allow for caching the results of
-expression evaluation.
-
-AST nodes do not actually store a `Symbol` instance, instead they have a
-`int32_t` index identifying the symbol in the `SymbolTable` class. This is
-done to minimize the size of AST types as well as allow easier sharing of same
-symbols with multiple instances of AST nodes.
-
-The storage for evaluated data is represented by the `Frame` class. Each
-symbol determines a unique position in the frame. During interpretation,
-evaluation of expressions which have a symbol will either read or store values
-in the frame. For example, instance of an `Identifier` will use the symbol to
-find and read the value from `Frame`. On the other hand, `NamedExpression`
-will take the result of evaluating its own expression and store it in the
-`Frame`.
-
-When a symbol is created, context of creation is used to assign a type to that
-symbol. This type is used for simple type checking operations. For example,
-`MATCH (n)` will create a symbol for variable `n`. Since the `MATCH (n)`
-represents finding a vertex in the graph, we can set `Symbol::Type::Vertex`
-for that symbol. Later, for example in `MATCH ()-[n]-()` we see that variable
-`n` is used as an edge. Since we already have a symbol for that variable, we
-detect this type mismatch and raise a `SemanticException`.
-
-Basic rule of symbol generation, is that variables inside `MATCH`, `CREATE`,
-`MERGE`, `WITH ... AS` and `RETURN ... AS` clauses establish new symbols.
-
-### Symbols in Patterns
-
-Inside `MATCH`, symbols are created only if they didn't exist before. For
-example, patterns in `MATCH (n {a: 5})--(m {b: 5}) RETURN n, m` will create 2
-symbols: one for `n` and one for `m`. `RETURN` clause will, in turn, reference
-those symbols. Symbols established in a part of pattern are immediately bound
-and visible in later parts. For example, `MATCH (n)--(n)` will create a symbol
-for variable `n` for 1st `(n)`. That symbol is referenced in 2nd `(n)`. Note
-that the symbol is not bound inside 1st `(n)` itself. What this means is that,
-for example, `MATCH (n {a: n.b})` should raise an error, because `n` is not
-yet bound when encountering `n.b`. On the other hand,
-`MATCH (n)--(n {a: n.b})` is fine.
-
-The `CREATE` is similar to `MATCH`, but it *always* establishes symbols for
-variables which create graph elements. What this means is that, for example
-`MATCH (n) CREATE (n)` is not allowed. `CREATE` wants to create a new node,
-for which we already have a symbol. In such a case, we need to throw an error
-that the variable `n` is being redeclared. On the other hand `MATCH (n) CREATE
-(n)-[r :r]->(n)` is fine, because `CREATE` will only create the edge `r`,
-connecting the already existing node `n`. Remaining behaviour is the same as
-in `MATCH`. This means that we can simplify `CREATE` to be like `MATCH` with 2
-special cases.
-
-  1. Are we creating a node, i.e. `CREATE (n)`? If yes, then the symbol for
-     `n` must not have been created before. Otherwise, we reference the
-     existing symbol.
-  2. Are we creating an edge, i.e. we encounter a variable for an edge inside
-     `CREATE`? If yes, then that variable must not reference a symbol.
-
-The `MERGE` clause is treated the same as `CREATE` with regards to symbol
-generation. The only difference is that we allow bidirectional edges in the
-pattern. When creating such a pattern, the direction of the created edge is
-arbitrarily determined.
-
-### Symbols in WITH and RETURN
-
-In addition to patterns, new symbols are established in the `WITH` clause.
-This clause makes the new symbols visible *only* to the rest of the query.
-For example, `MATCH (old) WITH old AS new RETURN new, old` should raise an
-error that `old` is unbound inside `RETURN`.
-
-There is a special case with symbol visibility in `WHERE` and `ORDER BY`. They
-need to see both the old and the new symbols. Therefore `MATCH (old) RETURN
-old AS new ORDER BY old.prop` needs to work. On the other hand, if we perform
-aggregations inside `WITH` or `RETURN`, then the old symbols should not be
-visible neither in `WHERE` nor in `ORDER BY`. Since the aggregation has to go
-through all the results in order to generate the final value, it makes no
-sense to store old symbols and their values. A query like `MATCH (old) WITH
-SUM(old.prop) AS sum WHERE old.prop = 42 RETURN sum` needs to raise an error
-that `old` is unbound inside `WHERE`.
-
-For cases when `SKIP` and `LIMIT` appear, we disallow any identifiers from
-appearing in their expressions. Basically, `SKIP` and `LIMIT` can only be
-constant expressions[^1]. For example, `MATCH (old) RETURN old AS new SKIP
-new.prop` needs to raise that variables are not allowed in `SKIP`. It makes no
-sense to allow variables, since their values may vary on each iteration. On
-the other hand, we could support variables to constant expressions, but for
-simplicity we do not. For example, `MATCH (old) RETURN old, 2 AS limit_var
-LIMIT limit_var` would still throw an error.
-
-Finally, we generate symbols for names created in `RETURN` clause. These
-symbols are used for the final results of a query.
-
-NOTE: New symbols in `WITH` and `RETURN` should be unique. This means that
-`WITH a AS same, b AS same` is not allowed, neither is a construct like
-`RETURN 2, 2`
-
-### Symbols in Functions which Establish New Scope
-
-Symbols can also be created in some functions. These functions usually take an
-expression, bind a single variable and run the expression inside the newly
-established scope.
-
-The `all` function takes a list, creates a variable for list element and runs
-the predicate expression. For example:
-
-    MATCH (n) RETURN n, all(n IN n.prop_list WHERE n < 42)
-
-We create a new symbol for use inside `all`, this means that the `WHERE n <
-42` uses the `n` which takes values from a `n.prop_list` elements. The
-original `n` bound by `MATCH` is not visible inside the `all` function, but it
-is visible outside. Therefore, the `RETURN n` and `n.prop_list` reference the
-`n` from `MATCH`.
-
-[^1]: Constant expressions are expressions for which the result can be
-  computed at compile time.

docs/dev/quick-start.md

@@ -1,107 +0,0 @@
-# Quick Start
-
-A short chapter on downloading the Memgraph source, compiling and running.
-
-## Obtaining the Source Code
-
-Memgraph uses `git` for source version control. You will need to install `git`
-on your machine before you can download the source code.
-
-On Debian systems, you can do it inside a terminal with the following
-command:
-
-    apt install git
-
-After installing `git`, you are now ready to fetch your own copy of Memgraph
-source code. Run the following command:
-
-    git clone https://github.com/memgraph/memgraph.git
-
-The above will create a `memgraph` directory and put all source code there.
-
-## Compiling Memgraph
-
-With the source code, you are now ready to compile Memgraph. Well... Not
-quite. You'll need to download Memgraph's dependencies first.
-
-In your terminal, position yourself in the obtained memgraph directory.
-
-    cd memgraph
-
-### Installing Dependencies
-
-Dependencies that are required by the codebase should be checked by running the
-`init` script:
-
-    ./init
-
-If the script fails, dependencies installation scripts could be found under
-`environment/os/`. The directory contains dependencies management script for
-each supported operating system. E.g. if your system is **Debian 10**, run the
-following to install all required build packages:
-
-    ./environment/os/debian-10.sh install MEMGRAPH_BUILD_DEPS
-
-Once everything is installed, rerun the `init` script.
-
-Once the `init` script is successfully finished, issue the following commands:
-
-    mkdir -p build
-    ./libs/setup.sh
-
-### Compiling
-
-Memgraph is compiled using our own custom toolchain that can be obtained from
-the toolchain repository. You should read the `environment/README.txt` file
-in the repository and install the apropriate toolchain for your distribution.
-After you have installed the toolchain you should read the instructions for the
-toolchain in the toolchain install directory (`/opt/toolchain-vXYZ/README.md`)
-and install dependencies that are necessary to run the toolchain.
-
-When you want to compile Memgraph you should activate the toolchain using the
-prepared toolchain activation script that is also described in the toolchain
-`README`.
-
-NOTE: You **must** activate the toolchain every time you want to compile
-Memgraph!
-
-You should now activate the toolchain in your console.
-
-    source /opt/toolchain-vXYZ/activate
-
-With all of the dependencies installed and the build environment set-up, you
-need to configure the build system. To do that, execute the following:
-
-    cd build
-    cmake ..
-
-If everything went OK, you can now, finally, compile Memgraph.
-
-    make -j$(nproc)
-
-### Running
-
-After the compilation verify that Memgraph works:
-
-    ./memgraph --version
-
-To make extra sure, run the unit tests:
-
-    ctest -R unit -j$(nproc)
-
-## Problems
-
-If you have any trouble running the above commands, contact your nearest
-developer who successfully built Memgraph. Ask for help and insist on getting
-this document updated with correct steps!
-
-## Next Steps
-
-Familiarise yourself with our code conventions and guidelines:
-
-  * [C++ Code](cpp-code-conventions.md)
-  * [Other Code](other-code-conventions.md)
-  * [Code Review Guidelines](code-review.md)
-
-Take a look at the list of [required reading](required-reading.md) for
-brushing up on technical skills.

docs/dev/required-reading.md

@@ -1,129 +0,0 @@
-# Required Reading
-
-This chapter lists a few books that should be read by everyone working on
-Memgraph. Since Memgraph is developed primarily with C++, Python and Common
-Lisp, books are oriented around those languages. Of course, there are plenty
-of general books which will help you improve your technical skills (such as
-"The Pragmatic Programmer", "The Mythical Man-Month", etc.), but they are not
-listed here. This way the list should be kept short and the *required* part in
-"Required Reading" more easily honored.
-
-Some of these books you may find in our office, so feel free to pick them up.
-If any are missing and you would like a physical copy, don't be afraid to
-request the book for our office shelves.
-
-Besides reading, don't get stuck in a rut and be a
-[Blub Programmer](http://www.paulgraham.com/avg.html).
-
-## Effective C++ by Scott Meyers
-
-Required for C++ developers.
-
-The book is a must-read as it explains most common gotchas of using C++. After
-reading this book, you are good to write competent C++ which will pass code
-reviews easily.
-
-## Effective Modern C++ by Scott Meyers
-
-Required for C++ developers.
-
-This is a continuation of the previous book, it covers updates to C++ which
-came with C++11 and later. The book isn't as imperative as the previous one,
-but it will make you aware of modern features we are using in our codebase.
-
-## Practical Common Lisp by Peter Siebel
-
-Required for Common Lisp developers.
-
-Free: http://www.gigamonkeys.com/book/
-
-We use Common Lisp to generate C++ code and make our lives easier.
-Unfortunately, not many developers are familiar with the language. This book
-will make you familiar very quickly as it has tons of very practical
-exercises. E.g. implementing unit testing library, serialization library and
-bundling all that to create a mp3 music server.
-
-## Effective Python by Brett Slatkin
-
-(Almost) required reading for Python developers.
-
-Why the "almost"? Well, Python is relatively easy to pick up and you will
-probably learn all the gotchas during code review from someone more
-experienced. This makes the book less necessary for a newcomer to Memgraph,
-but the book is not advanced enough to delegate it to
-[Advanced Reading](#advanced-reading). The book is written in similar vein as
-the "Effective C++" ones and will make you familiar with nifty Python features
-that make everyone's lives easier.
-
-# Advanced Reading
-
-The books listed below are not required reading, but you may want to read them
-at some point when you feel comfortable enough.
-
-## Design Patterns by Gamma et. al.
-
-Recommended for C++ developers.
-
-This book is highly divisive because it introduced a culture centered around
-design patterns. The main issues is overuse of patterns which complicates the
-code. This has made many Java programs to serve as examples of highly
-complicated, "enterprise" code.
-
-Unfortunately, design patterns are pretty much missing
-language features. This is most evident in dynamic languages such as Python
-and Lisp, as demonstrated by
-[Peter Norvig](http://www.norvig.com/design-patterns/).
-
-Or as [Paul Graham](http://www.paulgraham.com/icad.html) put it:
-
-```
-This practice is not only common, but institutionalized. For example, in the
-OO world you hear a good deal about "patterns". I wonder if these patterns are
-not sometimes evidence of case (c), the human compiler, at work. When I see
-patterns in my programs, I consider it a sign of trouble. The shape of a
-program should reflect only the problem it needs to solve. Any other
-regularity in the code is a sign, to me at least, that I'm using abstractions
-that aren't powerful enough-- often that I'm generating by hand the expansions
-of some macro that I need to write
-```
-
-After presenting the book so negatively, why you should even read it then?
-Well, it is good to be aware of those design patterns and use them when
-appropriate. They can improve modularity and reuse of the code. You will also
-find examples of such patterns in our code, primarily Strategy and Visitor
-patterns. The book is also a good stepping stone to more advanced reading
-about software design.
-
-## Modern C++ Design by Andrei Alexandrescu
-
-Recommended for C++ developers.
-
-This book can be treated as a continuation of the previous "Design Patterns"
-book. It introduced "dark arts of template meta-programming" to the world.
-Many of the patterns are converted to use C++ templates which makes them even
-better for reuse. But, like the previous book, there are downsides if used too
-much. You should approach it with a critical eye and it will help you
-understand ideas that are used in some parts of our codebase.
-
-## Large Scale C++ Software Design by John Lakos
-
-Recommended for C++ developers.
-
-An old book, but well worth the read. Lakos presents a very pragmatic view of
-writing modular software and how it affects both development time as well as
-program runtime. Some things are outdated or controversial, but it will help
-you understand how the whole C++ process of working in a large team, compiling
-and linking affects development.
-
-## On Lisp by Paul Graham
-
-Recommended for Common Lisp developers.
-
-Free: http://www.paulgraham.com/onlisp.html
-
-An excellent continuation to "Practical Common Lisp". It starts of slow, as if
-introducing the language, but very quickly picks up speed. The main meat of
-the book are macros and their uses. From using macros to define cooperative
-concurrency to including Prolog as if it's part of Common Lisp. The book will
-help you understand more advanced macros that are occasionally used in our
-Lisp C++ Preprocessor (LCP).

docs/dev/storage/v1/accessors.md

@@ -1,110 +0,0 @@
-# DatabaseAccessor
-
-A `DatabaseAccessor` actually wraps a transactional access to database
-data, for a single transaction. In that sense the naming is bad. It
-encapsulates references to the database and the transaction object.
-
-It contains logic for working with database content (graph element
-data) in the context of a single transaction. All CRUD operations are
-performed within a single transaction (as Memgraph is a transactional
-database), and therefore iteration over data, finding a specific graph
-element etc are all functionalities of a `GraphDbAccessor`.
-
-In single-node Memgraph the database accessor also defined the lifetime
-of a transaction. Even though a `Transaction` object was owned by the
-transactional engine, it was `GraphDbAccessor`'s lifetime that object
-was bound to (the transaction was implicitly aborted in
-`GraphDbAccessor`'s destructor, if it was not explicitly ended before
-that).
-
-# RecordAccessor
-
-It is important to understand data organization and access in the
-storage layer. This discussion pertains to vertices and edges as graph
-elements that the end client works with.
-
-Memgraph uses MVCC (documented on it's own page). This means that for
-each graph element there could be different versions visible to
-different currently executing transactions. When we talk about a
-`Vertex` or `Edge` as a data structure we typically mean one of those
-versions. In code this semantic is implemented so that both those classes
-inherit `mvcc::Record`, which in turn inherits `mvcc::Version`.
-
-Handling MVCC and visibility is not in itself trivial. Next to that,
-there is other book-keeping to be performed when working with data. For
-that reason, Memgraph uses "accessors" to define an API of working with
-data in a safe way. Most of the code in Memgraph (for example the
-interpretation code) should work with accessors. There is a
-`RecordAccessor` as a base class for `VertexAccessor` and
-`EdgeAccessor`. Following is an enumeration of their purpose.
-
-### Data Access
-
-The client interacts with Memgraph using the Cypher query language. That
-language has certain semantics which imply that multiple versions of the
-data need to be visible during the execution of a single query. For
-example: expansion over the graph is always done over the graph state as
-it was at the beginning of the transaction.
-
-The `RecordAccessor` exposes functions to switch between the old and the new
-versions of the same graph element (intelligently named `SwitchOld` and
-`SwitchNew`) within a single transaction. In that way the client code
-(mostly the interpreter) can avoid dealing with the underlying MVCC
-version concepts.
-
-### Updates
-
-Data updates are also done through accessors. Meaning: there are methods
-on the accessors that modify data, the client code should almost never
-interact directly with `Vertex` or `Edge` objects.
-
-The accessor layer takes care of creating version in the MVCC layer and
-performing updates on appropriate versions.
-
-Next, for many kinds of updates it is necessary to update the relevant
-indexes. There are implicit indexes for vertex labels, as
-well as user-created indexes for (label, property) pairs. The accessor
-layer takes care of updating the indexes when these values are changed.
-
-Each update also triggers a log statement in the write-ahead log. This
-is also handled by the accessor layer.
-
-### Distributed
-
-In distributed Memgraph accessors also contain a lot of the remote graph
-element handling logic. More info on that is available in the
-documentation for distributed.
-
-### Deferred MVCC Data Lookup for Edges
-
-Vertices and edges are versioned using MVCC. This means that for each
-transaction an MVCC lookup needs to be done to determine which version
-is visible to that transaction. This tends to slow things down due to
-cache invalidations (version lists and versions are stored in arbitrary
-locations on the heap).
-
-However, for edges, only the properties are mutable. The edge endpoints
-and type are fixed once the edge is created. For that reason both edge
-endpoints and type are available in vertex data, so that when expanding
-it is not mandatory to do MVCC lookups of versioned, mutable data. This
-logic is implemented in `RecordAccessor` and `EdgeAccessor`.
-
-### Exposure
-
-The original idea and implementation of graph element accessors was that
-they'd prevent client code from ever interacting with raw `Vertex` or
-`Edge` data. This however turned out to be impractical when implementing
-distributed Memgraph and the raw data members have since been exposed
-(through getters to old and new version pointers). However, refrain from
-working with that data directly whenever possible! Always consider the
-accessors to be the first go-to for interacting with data, especially
-when in the context of a transaction.
-
-# Skiplist Accessor
-
-The term "accessor" is also used in the context of a skiplist. Every
-operation on a skiplist must be performed within on an
-accessor. The skiplist ensures that there will be no physical deletions
-of an object during the lifetime of an accessor. This mechanism is used
-to ensure deletion correctness in a highly concurrent container.
-We only mention that here to avoid confusion regarding terminology.

docs/dev/storage/v1/contents.md

@@ -1,6 +0,0 @@
-# Storage v1
-
-* [Accessors](accessors.md)
-* [Indexes](indexes.md)
-* [Property Storage](property-storage.md)
-* [Durability](durability.md)

docs/dev/storage/v1/durability.md

@@ -1,80 +0,0 @@
-# Durability
-
-## Write-ahead Logging
-
-Typically WAL denotes the process of writing a "log" of database
-operations (state changes) to persistent storage before committing the
-transaction, thus ensuring that the state can be recovered (in the case
-of a crash) for all the transactions which the database committed.
-
-The WAL is a fine-grained durability format. It's purpose is to store
-database changes fast. It's primary purpose is not to provide
-space-efficient storage, nor to support fast recovery. For that reason
-it's often used in combination with a different persistence mechanism
-(in Memgraph's case the "snapshot") that has complementary
-characteristics.
-
-### Guarantees
-
-Ensuring that the log is written before the transaction is committed can
-slow down the database. For that reason this guarantee is most often
-configurable in databases.
-
-Memgraph offers two options for the WAL. The default option, where the WAL is
-flushed to the disk periodically and transactions do not wait for this to
-complete, introduces the risk of database inconsistency because an operating
-system or hardware crash might lead to missing transactions in the WAL. Memgraph
-will handle this as if those transactions never happened. The second option,
-called synchronous commit, will instruct Memgraph to wait for the WAL to be
-flushed to the disk when a transactions completes and the transaction will wait
-for this to complete. This option can be turned on with the
-`--synchronous-commit` command line flag.
-
-### Format
-
-The WAL file contains a series of DB state changes called `StateDelta`s.
-Each of them describes what the state change is and in which transaction
-it happened. Also some kinds of meta-information needed to ensure proper
-state recovery are recorded (transaction beginnings and commits/abort).
-
-The following is guaranteed w.r.t. `StateDelta` ordering in
-a single WAL file:
-- For two ops in the same transaction, if op A happened before B in the
-  database, that ordering is preserved in the log.
-- Transaction begin/commit/abort messages also appear in exactly the
-  same order as they were executed in the transactional engine.
-
-### Recovery
-
-The database can recover from the WAL on startup. This works in
-conjunction with snapshot recovery. The database attempts to recover from
-the latest snapshot and then apply as much as possible from the WAL
-files. Only those transactions that were not recovered from the snapshot
-are recovered from the WAL, for speed efficiency. It is possible (but
-inefficient) to recover the database from WAL only, provided all the WAL
-files created from DB start are available. It is not possible to recover
-partial database state (i.e. from some suffix of WAL files, without the
-preceding snapshot).
-
-## Snapshots
-
-A "snapshot" is a record of the current database state stored in permanent
-storage. Note that the term "snapshot" is used also in the context of
-the transaction engine to denote a set of running transactions.
-
-A snapshot is written to the file by Memgraph periodically if so
-configured. The snapshot creation  process is done within a transaction created
-specifically for that purpose. The transaction is needed to ensure that
-the stored state is internally consistent.
-
-The database state can be recovered from the snapshot during startup, if
-so configured. This recovery works in conjunction with write-ahead log
-recovery.
-
-A single snapshot contains all the data needed to recover a database. In
-that sense snapshots are independent of each other and old snapshots can
-be deleted once the new ones are safely stored, if it is not necessary
-to revert the database to some older state.
-
-The exact format of the snapshot file is defined inline in the snapshot
-creation code.

docs/dev/storage/v1/indexes.md

@@ -1,116 +0,0 @@
-# Label Indexes
-
-These are unsorted indexes that contain all the vertices that have the label
-the indexes are for (one index per label). These kinds of indexes get
-automatically generated for each label used in the database.
-
-### Updating the Indexes
-
-Whenever something gets added to the record we update the index (add that
-record to index). We keep an index which might contain garbage (not relevant
-records, because the value got removed or something similar) but we will
-filter it out when querying the index. We do it like this because we don't
-have to do bookkeeping and deciding if we update the index on the end of the
-transaction (commit/abort phase), moreover current interpreter advances the
-command in transaction and as such assumes that the indexes now contain
-objects added in the previous command inside this transaction, so we need to
-update over the whole scope of transaction (whenever something is added to the
-record).
-
-### Index Entries Label
-
-These kinds of indexes are internally keeping track of pair (record, vlist).
-Why do we need to keep track of exactly those two things?
-
-Problems with two different approaches
-
-1) Keep track of just the record:
-
-  - We need the `VersionList` for creating an accessor (this in itself is a
-    deal-breaker).
-  - Semantically it makes sense. An edge/vertex maps bijectionally to a
-    `VersionList`.
-  - We might try to access some members of record while the record is being
-    modified from another thread.
-  - A vertex/edge could get updated, thus expiring the record in the index.
-    The newly created record should be present in the index, but it's not.
-    Without the `VersionList` we can't reach the newly created record.
-  - Probably there are even more reasons... It should be obvious by now that
-    we need the `VersionList` in the index.
-
-2) Keep track of just the version list:
-
-  - Removing from an index is a problem for two major reasons. First, if we
-    only have the `VersionList`, checking if it should be removed implies
-    checking all the reachable records, which is not thread-safe. Second,
-    there are issues with concurrent removal and insertion. The cleanup thread
-    could determine the vertex/edge should be removed from the index and
-    remove it, while in between those ops another thread attempts to insert
-    the `VersionList` into the index. The insertion does nothing because the
-    `VersionList` is already in, but it gets removed immediately after.
-
-Because of inability to keep track of just the record, or value, we need to
-keep track of both of them.  Resolution of problems mentioned above, in the
-same order, with (record, vlist) pair
-
-  - simple `vlist.find(current transaction)` will get us the newest visible
-    record
-  - we'll never try to access some record if it's still being written since we
-    will always operate on vlist.find returned record
-  - newest record will contain that label
-  - since we have (record, vlist) pair as the key in the index when we update
-    and delete in the same time we will never delete the same record, vlist
-    pair we are adding because the record, vlist pair we are deleting is
-    already superseded by a newer record and as such won't be inserted while
-    it's being deleted
-
-### Querying the Index
-
-We run through the index for the given label and do `vlist.find` operation for
-the current transaction, and check if the newest return record has that
-label. If it has it then we return it. By now you are probably wondering
-aren't we sometimes returning duplicate vlist entries? And you are wondering
-correctly, we would be returning them, but we are making sure that the entires
-in the index are sorted by their `vlist*` and as such we can filter consecutive
-duplicate `vlist*` to only return one of those while still being able to create
-an iterator to index.
-
-### Cleaning the Index
-
-Cleaning the index is not as straightforward as it seems as a lot of garbage
-can accumulate, but it's hard to know when exactly can we delete some (record,
-vlist) pair. First, let's assume that we are doing the cleaning process at
-some `transaction_id`, `id` such that there doesn't exist an active transaction
-with an id lower than `id`.
-
-We scan through the whole index and for each (record, vlist) pair we first
-check if it was deleted before the id (i.e. no transaction with an id >= `id`
-will ever again see that record), if it was deleted before we might naively
-say that it's safe to delete it, but, we must take into account that when some
-new record is created from this record (update operation), that record still
-contains the label but by deleting this record we won't be able to see that
-vlist because that new record won't add again to index because we didn't
-explicitly add that label again to it.
-
-Because of this we have to 'update' this index (record, vlist) pair. We have
-to update the record to now point to a newer record in vlist, the one that is
-not deleted yet. We can do that by querying the `version_list` for the last
-record inside (oldest it has — remember that `mvcc_gc` will re-link not
-visible records so the last record will be visible for the current GC id).
-When updating the record inside the index, it's not okay to just update the
-pointer and leave the index as it is, because with updating the `record*` we
-might change the relative order of entries inside the index. We first have to
-re-insert it with new `record*`, and then delete the old entry. And we need to
-do insertion before the remove operation! Otherwise it could happen that the
-vlist with a newer record with that label won't exist while some transaction
-is querying the index.
-
-Records which we added as a consequence of deleting older records will be
-eventually removed from the index if they don't contain label because if we
-see that the record is not deleted we try to check if that record still
-contains the label. We also need to be careful here because we can't check
-that while the record is being potentially updated by some transaction (race
-condition), so we need can check if records still contain label if it's
-creation id is smaller than our `id`, as that implies that the creating
-transaction either aborted or committed as our `id` is equal to the oldest
-active transaction in time of starting the GC.

docs/dev/storage/v1/property-storage.md

@@ -1,131 +0,0 @@
-# Property Storage
-
-Although the reader is probably familiar with properties in *Memgraph*, let's
-briefly recap.
-
-Both vertices and edges can store an arbitrary number of properties. Properties
-are, in essence, ordered pairs of property names and property values. Each
-property name within a single graph element (edge/node) can store a single
-property value. Property names are represented as strings, while property values
-must be one of the following types:
-
- Type      | Description
------------|------------
- `Null`    | Denotes that the property has no value. This is the same as if the property does not exist.
- `String`  | A character string, i.e. text.
- `Boolean` | A boolean value, either `true` or `false`.
- `Integer` | An integer number.
- `Float`   | A floating-point number, i.e. a real number.
- `List`    | A list containing any number of property values of any supported type. It can be used to store multiple values under a single property name.
- `Map`     | A mapping of string keys to values of any supported type.
-
-Property values are modeled in a class conveniently called `PropertyValue`.
-
-## Mapping Between Property Names and Property Keys.
-
-Although users think of property names in terms of descriptive strings
-(e.g. "location" or "department"), *Memgraph* internally converts those names
-into property keys which are, essentially, unsigned 16-bit integers.
-
-Property keys are modelled by a not-so-conveniently named class called
-`Property` which can be found in `storage/types.hpp`. The actual conversion
-between property names and property keys is done within the `ConcurrentIdMapper`
-but the internals of that implementation are out of scope for understanding
-property storage.
-
-## PropertyValueStore
-
-Both `Edge` and `Vertex` objects contain an instance of `PropertyValueStore`
-object which is responsible for storing properties of a corresponding graph
-element.
-
-An interface of `PropertyValueStore` is as follows:
-
- Method    | Description
------------|------------
- `at`      | Returns the `PropertyValue` for a given `Property` (key).
- `set`     | Stores a given `PropertyValue` under a given `Property` (key).
- `erase`   | Deletes a given `Property` (key) alongside its corresponding `PropertyValue`.
- `clear`   | Clears the storage.
- `iterator`| Provides an extension of `std::input_iterator` that iterates over storage.
-
-## Storage Location
-
-By default, *Memgraph* is an in-memory database and all properties are therefore
-stored in working memory unless specified otherwise by the user. User has an
-option to specify via the command line which properties they wish to be stored
-on disk.
-
-Storage location of each property is encapsulated within a `Property` object
-which is ensured by the `ConcurrentIdMapper`. More precisely, the unsigned 16-bit
-property key has the following format:
-
-```
-|---location--|------id------|
-|-Memory|Disk-|-----2^15-----|
-```
-
-In other words, the most significant bit determines the location where the
-property will be stored.
-
-### In-memory Storage
-
-The underlying implementation of in-memory storage for the time being is
-`std::vector<std::pair<Property, PropertyValue>>`. Implementations of`at`, `set`
-and `erase` are linear in time. This implementation is arguably more efficient
-than `std::map` or `std::unordered_map` when the average number of properties of
-a record is relatively small (up to 10) which seems to be the case.
-
-### On-disk Storage
-
-#### KVStore
-
-Disk storage is modeled by an abstraction of key-value storage as implemented in
-`storage/kvstore.hpp'. An interface of this abstraction is as follows:
-
- Method         | Description
-----------------|------------
- `Put`          | Stores the given value under the given key.
- `Get`          | Obtains the given value stored under the given key.
- `Delete`       | Deletes a given (key, value) pair from storage..
- `DeletePrefix` | Deletes all (key, value) pairs where key begins with a given prefix.
- `Size`         | Returns the size of the storage or, optionally, the number of stored pairs that begin with a given prefix.
- `iterator`     | Provides an extension of `std::input_iterator` that iterates over storage.
-
-Keys and values in this context are of type `std::string`.
-
-The actual underlying implementation of this abstraction uses
-[RocksDB]{https://rocksdb.org} &mdash; a persistent key-value store for fast
-storage.
-
-It is worthy to note that the custom iterator implementation allows the user
-to iterate over a given prefix. Otherwise, the implementation follows familiar
-c++ constructs and can be used as follows:
-
-```
-KVStore storage = ...;
-for (auto it = storage.begin(); it != storage.end(); ++it) {}
-for (auto kv : storage) {}
-for (auto it = storage.begin("prefix"); it != storage.end("prefix"); ++it) {}
-```
-
-Note that it is not possible to scan over multiple prefixes. For instance, one
-might assume that you can scan over all keys that fall in a certain
-lexicographical range. Unfortunately, that is not the case and running the
-following code will result in an infinite loop with a touch of undefined
-behavior.
-
-```
-KVStore storage = ...;
-for (auto it = storage.begin("alpha"); it != storage.end("omega"); ++it) {}
-```
-
-#### Data Organization on Disk
-
-Each `PropertyValueStore` instance can access a static `KVStore` object that can
-store `(key, value)` pairs on disk. The key of each property on disk consists of
-two parts &mdash; a unique identifier (unsigned 64-bit integer) of the current
-record version (see mvcc docummentation for further clarification) and a
-property key as described above. The actual value of the property is serialized
-into a bytestring using bolt `BaseEncoder`. Similarly, deserialization is
-performed by bolt `Decoder`.

docs/dev/storage/v2/contents.md

@@ -1,3 +0,0 @@
-# Storage v2
-
-TODO(gitbuda): Write documentation.

docs/dev/workflow.md

@@ -1,166 +0,0 @@
-# Memgraph Workflow
-
-This chapter describes the usual workflow for working on Memgraph.
-
-## Git
-
-Memgraph uses [git](https://git-scm.com/) for source version control. If you
-obtained the source, you probably already have it installed. Before you can
-track new changes, you need to setup some basic information.
-
-First, tell git your name:
-
-    git config --global user.name "FirstName LastName"
-
-Then, set your Memgraph email:
-
-    git config --global user.email "my.email@memgraph.com"
-
-Finally, make git aware of your favourite editor:
-
-    git config --global core.editor "vim"
-
-## Github
-
-All of the code in Memgraph needs to go through code review before it can be
-accepted in the codebase. This is done through [Github](https://github.com/).
-You should already have it installed if you followed the steps in [Quick
-Start](quick-start.md).
-
-## Working on Your Feature Branch
-
-Git has a concept of source code **branches**. The `master` branch contains all
-of the changes which were reviewed and accepted in Memgraph's code base. The
-`master` branch is selected by default.
-
-### Creating a Branch
-
-When working on a new feature or fixing a bug, you should create a new branch
-out of the `master` branch. There are two branch types, **epic** and **task**
-branches. The epic branch is created when introducing a new feature or any work
-unit requiring more than one commit. More commits are required to split the
-work into chunks to be able to easier review code or find a bug (in each
-commit, there could be various problems, e.g., related to performance or
-concurrency issues, which are the hardest to track down). Each commit on the
-master or epic branch should be a compilable and well-documented set of
-changes. Task branches should be created when a smaller work unit has to be
-integrated into the codebase. The task branch could be branched out of the
-master or an epic branch. We manage epics and tasks on the project management
-tool called [Airtable](https://airtable.com/tblTUqycq8sHTTkBF). Each epic is
-prefixed by `Exyz-MG`, on the other hand, each task has `Tabcd-MG` prefix.
-Examples on how to create branches follow:
-
-```
-git checkout master
-git checkout -b T0025-MG-fix-a-problem
-...
-git checkout master
-git checkout -b E025-MG-huge-feature
-...
-git checkout E025-MG-huge-feature
-git checkout -b T0123-MG-add-feature-part
-```
-
-Note that a branch is created from the currently selected branch. So, if you
-wish to create another branch from `master` you need to switch to `master`
-first.
-
-### Making and Committing Changes
-
-When you have a branch for your new addition, you can now actually start
-implementing it. After some amount of time, you may have created new files,
-modified others and maybe even deleted unused files. You need to tell git to
-track those changes. This is accomplished with `git add` and `git rm`
-commands.
-
-    git add path-to-new-file path-to-modified-file
-    git rm path-to-deleted-file
-
-To check that everything is correctly tracked, you may use the `git status`
-command. It will also print the name of the currently selected branch.
-
-If everything seems OK, you should commit these changes to git.
-
-    git commit
-
-You will be presented with an editor where you need to type the commit
-message. Writing a good commit message is an art in itself. You should take a
-look at the links below. We try to follow these conventions as much as
-possible.
-
-  * [How to Write a Git Commit Message](http://chris.beams.io/posts/git-commit/)
-  * [A Note About Git Commit Messages](http://tbaggery.com/2008/04/19/a-note-about-git-commit-messages.html)
-  * [stopwritingramblingcommitmessages](http://stopwritingramblingcommitmessages.com/)
-
-### Sending Changes on a Review
-
-After finishing your work on your feature branch, you will want to send it on
-code review. This is done by pushing the branch to Github and creating a pull
-request. You can find all PRs
-[here](https://github.com/memgraph/memgraph/pulls).
-
-### Code Integration
-
-When working, you have to integrate some changes to your work or push your work
-to be available for others. To pull changes into a local `branch`, usually run
-the following:
-
-    git checkout {{branch}}
-    git pull origin {{branch}}
-
-To push your changes, usually run the following:
-
-    git checkout {{branch}}
-    git push origin {{branch}}
-
-Sometimes, things could get a little bit more complicated. Diagram below shows
-which git operation should be performed if a piece of code has to be integrated
-from one branch to another. Note, `main_branch` is the **master** branch in our
-case.
-
-```
-      |<---------------------------|
-      |       squash merge         |
-      |--------------------------->|
-      |          merge             |
-      |                            |
-      |<-----------|<--------------|
-      |   merge    | squash merge  |
-      |            |               |
-      |----------->|-------------->|
-      |   rebase   |     merge     |
-      |            | rebase --onto |
-      |            |               |
- main_branch  epic_branch     task_branch
-```
-
-There are a couple of cases:
-
-* If a code has to be integrated from a task branch to the main branch, use
-  **squash merge**. While you were working on a task, you probably committed a
-couple of cleanup commits that are not relevant to the main branch. In the
-other direction, while integrating the main branch to a task branch, the
-**regular merge** is ok because changes from the task branch will later be
-squash merged.
-
-* You should use **squash merge** when integrating changes from task to epic
-  branch (task might have irrelevant commits). On the other hand, you should
-use a **regular merge** when an epic is completed and has to be integrated into
-the main branch. Epic is a more significant piece of work, decoupled in
-compilable and testable commits. All these commits should be preserved to be
-able to find potential issues later on.
-
-* You should use **rebase** when integrating changes from main to an epic
-  branch. The epic branch has to be as clean as possible, avoid pure merge
-commits. Once you rebase epic on main, all commits on the epic branch will
-change the hashes. The implications are: 1) you have to force push your local
-branch to the origin, 2) if you made a task branch out of the epic branch, you
-would have to use **rebase --onto** (please refer to `git help rebase` for
-details). In simple cases, **regular merge** should be sufficient to integrate
-changes from epic to a task branch (that can even be done via GitHub web
-interface).
-
-During any code integration, you may get reports that some files have
-conflicting changes. If you need help resolving them, don't be afraid to ask
-around! After you've resolved them, mark them as done with `git add` command.
-You may then continue with `git {{action}} --continue`.

docs/feature_spec/contents.md

@@ -1,3 +0,0 @@
-# Feature Specifications
-
-* [Python Query Modules](python-query-modules.md)

docs/feature_spec/distributed.md

@@ -1,78 +0,0 @@
-# Distributed Memgraph specs
-This document describes reasnonings behind Memgraphs distributed concepts.
-
-## Distributed state machine
-Memgraphs distributed mode introduces two states of the cluster, recovering and
-working. The change between states shouldn't happen often, but when it happens
-it can take a while to make a transition from one to another.
-
-### Recovering
-This state is the default state for Memgraph when the cluster starts with
-recovery flags. If the recovery finishes successfully, the state changes to
-working. If recovery fails, the user will be presented with a message that
-explains what happened and what are the next steps.
-
-Another way to enter this state is failure. If the cluster encounters a failure,
-the master will enter the Recovering mode. This time, it will wait for all
-workers to respond with a message saying they are alive and well, and making
-sure they all have consistent state.
-
-### Working
-This state should be the default state of Memgraph most of the time. When in
-this state, Memgraph accepts connections from Bolt clients and allows query
-execution.
-
-If distributed execution fails for a transaction, that transaction, and all
-other active transactions will be aborted and the cluster will enter the
-Recovering state.
-
-## Durability
-One of the important concepts in distributed Memgraph is durability.
-
-### Cluster configuration
-When running Memgraph in distributed mode, the master will store cluster
-metadata in a persistent store. If fore some reason the cluster shuts down,
-recovering Memgraph from durability files shouldn't require any additional
-flags.
-
-### Database ID
-Each new and clean run of Memgraph should generate a new globally unique
-database id.  This id will associate all files that have persisted with this
-run. Adding the database id to snapshots, write-ahead logs and cluster metadata
-files ties them a specific Memgraph run, and it makes recovery easier to reason
-about.
-
-When recovering, the cluster won't generate a new id, but will reuse the one
-from the snapshot/wal that it was able to recover from.
-
-### Durability files
-Memgraph uses snapshots and write-ahead logs for durability.
-
-When Memgraph recovers it has to make sure all machines in the cluster recover
-to the same recovery point. This is done by finding a common snapshot and
-finding common transactions in per-machine available write-ahead logs.
-
-Since we can not be sure that each machine persisted durability files, we need
-to be able to negotiate a common recovery point in the cluster. Possible
-durability file failures could require to start the cluster from scratch,
-purging everything from storage and recovering from existing durability files.
-
-We need to ensure that we keep wal files containing information about
-transactions between all existing snapshots. This will provide better durability
-in the case of a random machine durability file failure, where the cluster can
-find a common recovery point that all machines in the cluster have.
-
-Also, we should suggest and make clear docs that anything less than two
-snapshots isn't considered safe for recovery.
-
-### Recovery
-The recovery happens in following steps:
-* Master enables worker registration.
-* Master recovers cluster metadata from the persisted storage.
-* Master waits all required workers to register.
-* Master broadcasts a recovery request to all workers.
-* Workers respond with with a set of possible recovery points.
-* Master finds a common recovery point for the whole cluster.
-* Master broadcasts a recovery request with the common recovery point.
-* Master waits for the cluster to recover.
-* After a successful cluster recovery, master can enter Working state.

docs/feature_spec/dynamic_graph_partitioning.md

@@ -1,75 +0,0 @@
-# Dynamic Graph Partitioning (abbr. DGP)
-
-## Implementation
-
-Take a look under `dev/memgraph/distributed/dynamic_graph_partitioning.md`.
-
-### Implemented parameters
-
---dynamic-graph-partitioner-enabled (If the dynamic graph partitioner should be
-  enabled.) type: bool default: false (start time)
---dgp-improvement-threshold (How much better should specific node score be
-  to consider a migration to another worker. This represents the minimal
-  difference between new score that the vertex will have when migrated
-  and the old one such that it's migrated.) type: int32 default: 10
-  (start time)
---dgp-max-batch-size (Maximal amount of vertices which should be migrated
-  in one dynamic graph partitioner step.) type: int32 default: 2000
-  (start time)
-
-## Planning
-
-### Design decisions
-
-* Each partitioning session has to be a new transaction.
-* When and how does an instance perform the moves?
-  * Periodically.
-  * Token sharing (round robin, exactly one instance at a time has an
-    opportunity to perform the moves).
-* On server-side serialization error (when DGP receives an error).
-  -> Quit partitioning and wait for the next turn.
-* On client-side serialization error (when end client receives an error).
-  -> The client should never receive an error because of any
-     internal operation.
-  -> For the first implementation, it's good enough to wait until data becomes
-     available again.
-  -> It would be nice to achieve that DGP has lower priority than end client
-     operations.
-
-### End-user parameters
-
-* --dynamic-graph-partitioner-enabled (execution time)
-* --dgp-improvement-threshold (execution time)
-* --dgp-max-batch-size (execution time)
-* --dgp-min-batch-size (execution time)
-  -> Minimum number of nodes that will be moved in each step.
-* --dgp-fitness-threshold (execution time)
-  -> Do not perform moves if partitioning is good enough.
-* --dgp-delta-turn-time (execution time)
-  -> Time between each turn.
-* --dgp-delta-step-time (execution time)
-  -> Time between each step.
-* --dgp-step-time (execution time)
-  -> Time limit per each step.
-
-### Testing
-
-The implementation has to provide good enough results in terms of:
-  * How good the partitioning is (numeric value), aka goodness.
-  * Workload execution time.
-  * Stress test correctness.
-
-Test cases:
-  * N not connected subgraphs
-    -> shuffle nodes to N instances
-    -> run partitioning
-    -> test perfect partitioning.
-  * N connected subgraph
-    -> shuffle nodes to N instance
-    -> run partitioning
-    -> test partitioning.
-  * Take realistic workload (Long Running, LDBC1, LDBC2, Card Fraud, BFS, WSP)
-    -> measure exec time
-    -> run partitioning
-    -> test partitioning
-    -> measure exec time (during and after partitioning).

docs/feature_spec/high_availability.md

@@ -1,275 +0,0 @@
-# High Availability (abbr. HA)
-
-## High Level Context
-
-High availability is a characteristic of a system which aims to ensure a
-certain level of operational performance for a higher-than-normal period.
-Although there are multiple ways to design highly available systems, Memgraph
-strives to achieve HA by elimination of single points of failure. In essence,
-this implies adding redundancy to the system so that a failure of a component
-does not imply the failure of the entire system. To ensure this, HA Memgraph
-implements the [Raft consensus algorithm](https://raft.github.io/).
-
-Correct implementation of the algorithm guarantees that the cluster will be
-fully functional (available) as long as any strong majority of the servers are
-operational and can communicate with each other and with clients. For example,
-clusters of three or four machines can tolerate the failure of a single server,
-clusters of five and six machines can tolerate the failure of any two servers,
-and so on. Therefore, we strongly recommend a setup of an odd-sized cluster.
-
-### Performance Implications
-
-Internally, Raft achieves high availability by keeping a consistent replicated
-log on each server within the cluster. Therefore, we must successfully replicate
-a transaction on the majority of servers within the cluster before we actually
-commit it and report the result back to the client. This operation represents
-a significant performance hit when compared with single node version of
-Memgraph.
-
-Luckily, the algorithm can be tweaked in a way which allows read-only
-transactions to perform significantly better than those which modify the
-database state. That being said, the performance of read-only operations
-is still not going to be on par with single node Memgraph.
-
-This section will be updated with exact numbers once we integrate HA with
-new storage.
-
-With the old storage, write throughput was almost five times lower than read
-throughput (~30000 reads per second vs ~6000 writes per second).
-
-## User Facing Setup
-
-### How to Setup HA Memgraph Cluster?
-
-First, the user needs to install `memgraph_ha` package on each machine
-in their cluster. HA Memgraph should be available as a Debian package,
-so its installation on each machine should be as simple as:
-
-```plaintext
-dpkg -i /path/to/memgraph_ha_<version>.deb
-```
-
-After successful installation of the `memgraph_ha` package, the user should
-finish its configuration before attempting to start the cluster.
-
-There are two main things that need to be configured on every node in order for
-the cluster to be able to run:
-
-1. The user has to edit the main configuration file and specify the unique node
-   ID to each server in the cluster
-2. The user has to create a file that describes all IP addresses of all servers
-   that will be used in the cluster
-
-The `memgraph_ha` binary loads all main configuration parameters from
-`/etc/memgraph/memgraph_ha.conf`. On each node of the cluster, the user should
-uncomment the `--server-id=0` parameter and change its value to the `server_id`
-of that node.
-
-The last step before starting the server is to create a `coordination`
-configuration file. That file is already present as an example in
-`/etc/memgraph/coordination.json.example` and you have to copy it to
-`/etc/memgraph/coordination.json` and edit it according to your cluster
-configuration. The file contains coordination info consisting of a list of
-`server_id`, `ip_address` and `rpc_port` lists. The assumed contents of the
-`coordination.json` file are:
-
-```plaintext
-[
-  [1, "192.168.0.1", 10000],
-  [2, "192.168.0.2", 10000],
-  [3, "192.168.0.3", 10000]
-]
-```
-Here, each line corresponds to coordination of one server. The first entry is
-that server's ID, the second is its IP address and the third is the RPC port it
-listens to. This port should not be confused with the port used for client
-interaction via the Bolt protocol.
-
-The `ip_address` entered for each `server_id` *must* match the exact IP address
-that belongs to that server and that will be used to communicate to other nodes
-in the cluster. The coordination configuration file *must* be identical on all
-nodes in the cluster.
-
-After the user has set the `server_id` on each node in
-`/etc/memgraph/memgraph_ha.conf` and provided the same
-`/etc/memgraph/coordination.json` file to each node in the cluster, they can
-start the Memgraph HA service by issuing the following command on each node in
-the cluster:
-
-```plaintext
-systemctl start memgraph_ha
-```
-
-### How to Configure Raft Parameters?
-
-All Raft configuration parameters can be controlled by modifying
-`/etc/memgraph/raft.json`.  The assumed contents of the `raft.json` file are:
-
-```plaintext
-{
-  "election_timeout_min": 750,
-  "election_timeout_max": 1000,
-  "heartbeat_interval": 100,
-  "replication_timeout": 20000,
-  "log_size_snapshot_threshold": 50000
-}
-```
-
-The meaning behind each entry is demystified in the following table:
-
-Flag                          | Description
-------------------------------|------------
-`election_timeout_min`        | Lower bound for the randomly sampled reelection timer given in milliseconds
-`election_timeout_max`        | Upper bound for the randomly sampled reelection timer given in milliseconds
-`heartbeat_interval`          | Time interval between consecutive heartbeats given in milliseconds
-`replication_timeout`         | Time interval allowed for data replication given in milliseconds
-`log_size_snapshot_threshold` | Allowed number of entries in Raft log before its compaction
-
-### How to Query HA Memgraph via Proxy?
-
-This chapter describes how to query HA Memgraph using our proxy server.
-Note that this is not intended to be a long-term solution. Instead, we will
-implement a proper Memgraph HA client which is capable of communicating with
-the HA cluster. Once our own client is implemented, it will no longer be
-possible to query HA Memgraph using other clients (such as neo4j client).
-
-The Bolt protocol that is exposed by each Memgraph HA node is an extended
-version of the standard Bolt protocol. In order to be able to communicate with
-the highly available cluster of Memgraph HA nodes, the client must have some
-logic implemented in itself so that it can communicate correctly with all nodes
-in the cluster. To facilitate a faster start with the HA cluster we will build
-the Memgraph HA proxy binary that communicates with all nodes in the HA cluster
-using the extended Bolt protocol and itself exposes a standard Bolt protocol to
-the user. All standard Bolt clients (libraries and custom systems) can
-communicate with the Memgraph HA proxy without any code modifications.
-
-The HA proxy should be deployed on each client machine that is used to
-communicate with the cluster. It can't be deployed on the Memgraph HA nodes!
-
-When using the Memgraph HA proxy, the communication flow is described in the
-following diagram:
-
-```plaintext
-Memgraph HA node 1 -----+
-                        |
-Memgraph HA node 2 -----+ Memgraph HA proxy <---> any standard Bolt client (C, Java, PHP, Python, etc.)
-                        |
-Memgraph HA node 3 -----+
-```
-
-To setup the Memgraph HA proxy the user should install the `memgraph_ha_proxy`
-package.
-
-After its successful installation, the user should enter all endpoints of the
-HA Memgraph cluster servers into the configuration before attempting to start
-the HA Memgraph proxy server.
-
-The HA Memgraph proxy server loads all of its configuration from
-`/etc/memgraph/memgraph_ha_proxy.conf`. Assuming that the cluster is set up
-like in the previous examples, the user should uncomment and enter the following
-value into the `--endpoints` parameter:
-
-```plaintext
---endpoints=192.168.0.1:7687,192.168.0.2:7687,192.168.0.3:7687
-```
-
-Note that the IP addresses used in the example match the individual cluster
-nodes IP addresses, but the ports used are the Bolt server ports exposed by
-each node (currently the default value of `7687`).
-
-The user can now start the proxy by using the following command:
-
-```plaintext
-systemctl start memgraph_ha_proxy
-```
-
-After the proxy has been started, the user can query the HA cluster by
-connecting to the HA Memgraph proxy IP address using their favorite Bolt
-client.
-
-## Integration with Memgraph
-
-The first thing that should be defined is a single instruction within the
-context of Raft (i.e. a single entry in a replicated log).
-These instructions should be completely deterministic when applied
-to the state machine. We have therefore decided that the appropriate level
-of abstraction within Memgraph corresponds to `Delta`s (data structures
-which describe a single change to the Memgraph state, used for durability
-in WAL). Moreover, a single instruction in a replicated log will consist of a
-batch of `Delta`s which correspond to a single transaction that's about
-to be **committed**.
-
-Apart from `Delta`s, there are certain operations within the storage called
-`StorageGlobalOperations` which do not conform to usual transactional workflow
-(e.g. Creating indices).  Since our storage engine implementation guarantees
-that at the moment of their execution no other transactions are active, we can
-safely replicate them as well. In other words, no additional logic needs to be
-implemented because of them.
-
-Therefore, we will introduce a new `RaftDelta` object which can be constructed
-both from storage `Delta` and `StorageGlobalOperation`. Instead of appending
-these to WAL (as we do in single node), we will start to replicate them across
-our cluster. Once we have replicated the corresponding Raft log entry on
-majority of the cluster, we are able to safely commit the transaction or execute
-a global operation. If for any reason the replication fails (leadership change,
-worker failures, etc.) the transaction will be aborted.
-
-In the follower mode, we need to be able to apply `RaftDelta`s we got from
-the leader when the protocol allows us to do so. In that case, we will use the
-same concepts from durability in storage v2, i.e., applying deltas maps
-completely to recovery from WAL in storage v2.
-
-## Test and Benchmark Strategy
-
-We have already implemented some integration and stress tests. These are:
-
-1. leader election -- Tests whether leader election works properly.
-2. basic test -- Tests basic leader election and log replication.
-3. term updates test -- Tests a specific corner case (which used to fail)
-                        regarding term updates.
-4. log compaction test -- Tests whether log compaction works properly.
-5. large log entries -- Tests whether we can successfully replicate relatively
-                        large log entries.
-6. index test -- Tests whether index creation works in HA.
-7. normal operation stress test -- Long running concurrent stress test under
-                                   normal conditions (no failures).
-8. read benchmark -- Measures read throughput in HA.
-9. write benchmark -- Measures write throughput in HA.
-
-At the moment, our main goal is to pass existing tests and have a stable version
-on our stress test. We should also implement a stress test which occasionally
-introduces different types of failures in our cluster (we did this kind of
-testing manually thus far). Passing these tests should convince us that we have
-a "stable enough" version which we can start pushing to our customers.
-
-Additional (proper) testing should probably involve some ideas from
-[here](https://jepsen.io/analyses/dgraph-1-0-2)
-
-## Possible Future Changes/Improvements/Extensions
-
-There are two general directions in which we can alter HA Memgraph. The first
-direction assumes we are going to stick with the Raft protocol. In that case
-there are a few known ways to extend the basic algorithm in order to gain
-better performance or achieve extra functionality. In no particular order,
-these are:
-
-1. Improving read performance using leader leases [Section 6.4 from Raft thesis]
-2. Introducing cluster membership changes [Chapter 4 from Raft thesis]
-3. Introducing a [learner mode](https://etcd.io/docs/v3.3.12/learning/learner/).
-4. Consider different log compaction strategies [Chapter 5 from Raft thesis]
-5. Removing HA proxy and implementing our own HA Memgraph client.
-
-On the other hand, we might decide in the future to base our HA implementation
-on a completely different protocol which might even offer different guarantees.
-In that case we probably need to do a bit more of market research and weigh the
-trade-offs of different solutions.
-[This](https://www.postgresql.org/docs/9.5/different-replication-solutions.html)
-might be a good starting point.
-
-## Reading materials
-
-1. [Raft paper](https://raft.github.io/raft.pdf)
-2. [Raft thesis](https://github.com/ongardie/dissertation) (book.pdf)
-3. [Raft playground](https://raft.github.io/)
-4. [Leader Leases](https://blog.yugabyte.com/low-latency-reads-in-geo-distributed-sql-with-raft-leader-leases/)
-5. [Improving Raft ETH](https://pub.tik.ee.ethz.ch/students/2017-FS/SA-2017-80.pdf)

docs/feature_spec/kafka/opencypher.md

@@ -1,80 +0,0 @@
-# Kafka - openCypher clause
-
-One must be able to specify the following when importing data from Kafka:
-
-* Kafka URI
-* Kafka topic
-* Transform [script](transform.md) URI
-
-
-Minimum required syntax looks like:
-```opencypher
-CREATE STREAM stream_name AS LOAD DATA KAFKA 'URI'
-  WITH TOPIC 'topic'
-  WITH TRANSFORM 'URI';
-```
-
-
-The full openCypher clause for creating a stream is:
-```opencypher
-CREATE STREAM stream_name AS
-  LOAD DATA KAFKA 'URI'
-  WITH TOPIC 'topic'
-  WITH TRANSFORM 'URI'
-  [BATCH_INTERVAL milliseconds]
-  [BATCH_SIZE count]
-```
-The `CREATE STREAM` clause happens in a transaction.
-
-`WITH TOPIC` parameter specifies the Kafka topic from which we'll stream
-data.
-
-`WITH TRANSFORM` parameter should contain a URI of the transform script.
-
-`BATCH_INTERVAL` parameter defines the time interval in milliseconds
-which is the time between two successive stream importing operations.
-
-`BATCH_SIZE` parameter defines the count of Kafka messages that will be
-batched together before import.
-
-If both `BATCH_INTERVAL` and `BATCH_SIZE` parameters are given, the condition
-that is satisfied first will trigger the batched import.
-
-Default value for `BATCH_INTERVAL` is 100 milliseconds, and the default value
-for `BATCH_SIZE` is 10;
-
-The `DROP` clause deletes a stream:
-```opencypher
-DROP STREAM stream_name;
-```
-
-The `SHOW` clause enables you to see all configured streams:
-```opencypher
-SHOW STREAMS;
-```
-
-You can also start/stop streams with the `START` and `STOP` clauses:
-```opencypher
-START STREAM stream_name [LIMIT count BATCHES];
-STOP STREAM stream_name;
-```
-A stream needs to be stopped in order to start it and it needs to be started in
-order to stop it. Starting a started or stopping a stopped stream will not
-affect that stream.
-
-There are also convenience clauses to start and stop all streams:
-```opencypher
-START ALL STREAMS;
-STOP ALL STREAMS;
-```
-
-Before the actual import, you can also test the stream with the `TEST
-STREAM` clause:
-```opencypher
-TEST STREAM stream_name [LIMIT count BATCHES];
-```
-When a stream is tested, data extraction and transformation occurs, but no
-output is inserted in the graph.
-
-A stream needs to be stopped in order to test it. When the batch limit is
-omitted, `TEST STREAM` will run for only one batch by default.

docs/feature_spec/kafka/transform.md

@@ -1,34 +0,0 @@
-# Kafka - data transform
-
-The transform script is a user defined script written in Python.  The script
-should be aware of the data format in the Kafka message.
-
-Each Kafka message is byte length encoded, which means that the first eight
-bytes of each message contain the length of the message.
-
-A sample code for a streaming transform script could look like this:
-
-```python
-def create_vertex(vertex_id):
-  return ("CREATE (:Node {id: $id})", {"id": vertex_id})
-
-
-def create_edge(from_id, to_id):
-  return ("MATCH (n:Node {id: $from_id}), (m:Node {id: $to_id}) "\
-          "CREATE (n)-[:Edge]->(m)", {"from_id": from_id, "to_id": to_id})
-
-
-def stream(batch):
-    result = []
-    for item in batch:
-        message = item.decode('utf-8').strip().split()
-        if len(message) == 1:
-          result.append(create_vertex(message[0])))
-        else:
-          result.append(create_edge(message[0], message[1]))
-    return result
-
-```
-
-The script should output openCypher query strings based on the type of the
-records.

docs/feature_spec/python-query-modules.md

@@ -1,185 +0,0 @@
-# Python 3 Query Modules
-
-## Introduction
-
-Memgraph exposes a C API for writing the so called Query Modules. These
-modules contain definitions of procedures which can be invoked through the
-query language using the `CALL ... YIELD ...` syntax. This mechanism allows
-database users to extend Memgraph with their own algorithms and
-functionalities.
-
-Using a low level language like C can be quite cumbersome for writing modules,
-so it seems natural to add support for a higher level language on top of the
-existing C API.
-
-There are languages written exactly for this purpose of extending C with high
-level constructs, for example Lua and Guile. Instead of those, we have chosen
-Python 3 to be the first high level language we will support. The primary reason
-being that it's very popular, so more people should be able to write modules.
-Another benefit of Python which comes out of its popularity is the large
-ecosystem of libraries, especially graph algorithm related ones like NetworkX.
-Python does have significant performance and implementation downsides compared
-to Lua and Guile, but these are described in more detail later in this
-document.
-
-## Python 3 API Overview
-
-The Python 3 API should be as user friendly as possible as well as look
-Pythonic. This implies that some functions from the C API will not map to the
-exact same functions. The most obvious case for a Pythonic approach is
-registering procedures of a query module. Let's take a look at the C example
-and its transformation to Python.
-
-```c
-static void procedure(const struct mgp_list *args,
-                      const struct mgp_graph *graph, struct mgp_result *result,
-                      struct mgp_memory *memory);
-
-int mgp_init_module(struct mgp_module *module, struct mgp_memory *memory) {
-  struct mgp_proc *proc =
-      mgp_module_add_read_procedure(module, "procedure", procedure);
-  if (!proc) return 1;
-  if (!mgp_proc_add_arg(proc, "required_arg",
-                        mgp_type_nullable(mgp_type_any())))
-    return 1;
-  struct mgp_value *null_value = mgp_value_make_null(memory);
-  if (!mgp_proc_add_opt_arg(proc, "optional_arg",
-                            mgp_type_nullable(mgp_type_any()), null_value)) {
-    mgp_value_destroy(null_value);
-    return 1;
-  }
-  mgp_value_destroy(null_value);
-  if (!mgp_proc_add_result(proc, "result", mgp_type_string())) return 1;
-  if (!mgp_proc_add_result(proc, "args",
-                           mgp_type_list(mgp_type_nullable(mgp_type_any()))))
-    return 1;
-  return 0;
-}
-```
-
-In Python things should be a lot simpler.
-
-```Python
-# mgp.read_proc obtains the procedure name via __name__ attribute of a function.
-@mgp.read_proc(# Arguments passed to multiple mgp_proc_add_arg calls
-               (('required_arg', mgp.Nullable(mgp.Any)), ('optional_arg', mgp.Nullable(mgp.Any), None)),
-               # Result fields passed to multiple mgp_proc_add_result calls
-               (('result', str), ('args', mgp.List(mgp.Nullable(mgp.Any)))))
-def procedure(args, graph, result, memory):
-    pass
-```
-
-Here we have replaced `mgp_module_*` and `mgp_proc_*` C API with a much
-simpler decorator function in Python -- `mgp.read_proc`. The types of
-arguments and result fields can both be our types as well as Python builtin
-types which can map to supported `mgp_value` types. The expected builtin types
-we ought to support are: `bool`, `str`, `int`, `float` and `map`. While the
-rest of the types are provided via our Python API. Optionally, we can add
-convenience support for `object` type which would map to
-`mgp.Nullable(mgp.Any)` and `list` which would map to
-`mgp.List(mgp.Nullable(mgp.Any))`. Also, it makes sense to take a look if we
-can leverage Python's `typing` module here.
-
-Another Pythonic change is to remove `mgp_value` C API from Python altogether.
-This means that the arguments a Python procedure receives are not `mgp_value`
-instances but rather `PyObject` instances. In other words, our implementation
-would immediately marshal `mgp_value` to corresponding type in Python.
-Obviously we would need to provide our own Python types for non-builtin
-things like `mgp.Vertex` (equivalent to `mgp_vertex`) and other.
-
-Continuing from our example above, let's say the procedure was invoked through
-Cypher using the following query.
-
-    MATCH (n) CALL py_module.procedure(42, n) YIELD *;
-
-The Python procedure could then do the following and complete without throwing
-neither the AssertionError nor the ValueError.
-
-```Python
-def procedure(args, graph, result, memory):
-    assert isinstance(args, list)
-    # Unpacking throws ValueError if args does not contain exactly 2 values.
-    required_arg, optional_arg = args
-    assert isintance(required_arg, int)
-    assert isinstance(optional_arg, mgp.Vertex)
-```
-
-The rest of the C API should naturally map to either top level functions or
-class methods as appropriate.
-
-## Loading Python Query Modules
-
-Our current mechanism for loading the modules is to look for `.so` files in
-the directory specified by `--query-modules` flag. This is done when Memgraph
-is started. We can extend this mechanism to look for `.py` files in addition
-to `.so` files in the same directory and import them in the embedded Python
-interpreter. The only issue is embedding the interpreter in Memgraph.  There
-are multiple choices:
-
-  1. Building Memgraph and statically linking to Python.
-  2. Building Memgraph and dynamically linking to Python, and distributing
-     Python with Memgraph's installation.
-  3. Building Memgraph and dynamically linking to Python, but without
-     distributing the Python library.
-  4. Building Memgraph and optionally loading Python library by trying to
-     `dlopen` it.
-
-The first two options are only viable if the Python license allows, and this
-will need further investigation.
-
-The third option adds Python as an installation dependency for Memgraph, and
-without it Memgraph will not run. This is problematic for users which cannot
-or do not want to install Python 3.
-
-The fourth option avoids all of the issues present in the first 3 options, but
-comes at a higher implementation cost. We would need to try to `dlopen` the
-Python library and setup function pointers. If we succeed we would import
-`.py` files from the `--query-modules` directory. On the other hand, if the
-user does not have Python, `dlopen` would fail and Memgraph would run without
-Python support.
-
-After live discussion, we've decided to go with option 3. This way we don't
-have to worry about mismatching Python versions we support and what the users
-expect. Also, we should target Python 3.5 as that should be common between
-Debian and CentOS for which we ship installation packages.
-
-## Performance and Implementation Problems
-
-As previously mentioned, embedding Python introduces usability issues compared
-to other embeddable languages.
-
-The first, major issue is Global Interpreter Lock (GIL). Initializing Python
-will start a single global interpreter and running multiple threads will
-require acquiring GIL. In practice, this means that when multiple users run a
-procedure written in Python in parallel the execution will not actually be
-parallel. Python's interpreter will jump between executing one user's
-procedure and the other's. This can be quite an issue for long running
-procedures when multiple users are querying Memgraph. The solution for this
-issue is Python's API for sub-interpreters. Unfortunately, the support for
-them is rather poor and the API contains a lot of critical bugs when we tried
-to use them. For the time being, we will have to accept GIL and its downsides.
-Perhaps in the future we will gain more knowledge on how we could reduce the
-acquire rate of GIL or the sub-interpreter API will get improved.
-
-Another major issue is memory allocation. Python's C API does not have support
-for setting up a temporary allocator during execution of a single function.
-It only has support for setting up a global heap allocator. This obviously
-impacts our control of memory during a query procedure invocation. Besides
-potential performance penalty, a procedure could allocate much more memory
-than we would actually allow for execution of a single query. This means that
-options controlling the memory limit during query execution are useless. On
-the bright side, Python does use block style allocators and reference
-counting, so the performance penalty and global memory usage should not be
-that terrible.
-
-The final issue that isn't as major as the ones above is the global state of
-the interpreter. In practice this means that any registered procedure and
-imported module has access to any other procedure and module. This may pollute
-the namespace for other users, but it should not be much of a problem because
-Python always has things under a module scope. The other, slightly bigger
-downside is that a malicious user could use this knowledge to modify other
-modules and procedures. This seems like a major issue, but if we take the
-bigger picture into consideration, we already have a security issue in general
-by invoking `dlopen` on `.so` and potentially running arbitrary code. This was
-the trade off we chose to allow users to extend Memgraph. It's up to the users
-to write sane extensions and protect their servers from access.

docs/feature_spec/tensorflow_op/technicalities.md

@@ -1,61 +0,0 @@
-# Tensorflow Op - Technicalities
-
-The final result should be a shared object (".so") file that can be
-dynamically loaded by the Tensorflow runtime in order to directly
-access the bolt client.
-
-## About Tensorflow
-
-Tensorflow is usually used with Python such that the Python code is used
-to define a directed acyclic computation graph. Basically no computation
-is done in Python. Instead, values from Python are copied into the graph
-structure as constants to be used by other Ops. The directed acyclic graph
-naturally ends up with two sets of border nodes, one for inputs, one for
-outputs. These are sometimes called "feeds".
-
-Following the Python definition of the graph, during training, the entire
-data processing graph/pipeline is called from Python as a single expression.
-This leads to lazy evaluation since the called result has already been
-defined for a while.
-
-Tensorflow internally works with tensors, i.e. n-dimensional arrays. That
-means all of its inputs need to be matrices as well as its outputs. While
-it is possible to feed data directly from Python's numpy matrices straight
-into Tensorflow, this is less desirable than using the Tensorflow data API
-(which defines data input and processing as a Tensorflow graph) because:
-
-  1. The data API is written in C++ and entirely avoids Python and as such
-  is faster
-  2. The data API, unlike Python is available in "Tensorflow serving". The
-  default way to serve Tensorflow models in production.
-
-Once the entire input pipeline is defined via the tf.data API, its input
-is basically a list of node IDs the model is supposed to work with. The
-model, through the data API knows how to connect to Memgraph and execute
-openCypher queries in order to get the remaining data it needs.
-(For example features of neighbouring nodes.)
-
-## The Interface
-
-I think it's best you read the official guide...  
-<https://www.tensorflow.org/extend/adding_an_op>  
-And especially the addition that specifies how data ops are special  
-<https://www.tensorflow.org/extend/new_data_formats>  
-
-## Compiling the TF Op
-
-There are two options for compiling a custom op.  
-One of them involves pulling the TF source, adding your code to it and
-compiling via bazel.  
-This is probably awkward to do for us and would
-significantly slow down compilation.  
-
-The other method involves installing Tensorflow as a Python package and
-pulling the required headers from for example:  
-`/usr/local/lib/python3.6/site-packages/tensorflow/include`  
-We can then compile our Op with our regular build system.
-
-This is practical since we can copy the required headers to our repo.
-If necessary, we can have several versions of the headers to build several
-versions of our Op for every TF version which we want to support.
-(But this is unlikely to be required as the API should be stable).

docs/feature_spec/tensorflow_op/usage_example.md

@@ -1,142 +0,0 @@
-# Example for Using the Bolt Client Tensorflow Op
-
-## Dynamic Loading
-
-``` python3
-import tensorflow as tf
-
-mg_ops = tf.load_op_library('/usr/bin/memgraph/tensorflow_ops.so')
-```
-
-## Basic Usage
-
-``` python3
-dataset = mg_ops.OpenCypherDataset(
-            # This is probably unfortunate as the username and password
-            # get hardcoded into the graph, but for the simple case it's fine
-            "hostname:7687", auth=("user", "pass"),
-
-            # Our query
-            '''
-            MATCH (n:Train) RETURN n.id, n.features
-            ''',
-
-            # Cast return values to these types
-            (tf.string, tf.float32))
-
-# Some Tensorflow data api boilerplate
-iterator = dataset.make_one_shot_iterator()
-next_element = iterator.get_next()
-
-# Up to now we have only defined our computation graph which basically
-# just connects to Memgraph
-# `next_element` is not really data but a handle to a node in the Tensorflow
-# graph, which we can and do evaluate
-# It is a Tensorflow tensor with shape=(None, 2)
-# and dtype=(tf.string, tf.float)
-# shape `None` means the shape of the tensor is unknown at definition time
-# and is dynamic and will only be known once the tensor has been evaluated
-
-with tf.Session() as sess:
-    node_ids = sess.run(next_element)
-    # `node_ids` contains IDs and features of all the nodes 
-    # in the graph with the label "Train"
-    # It is a numpy.ndarray with a shape ($n_matching_nodes, 2)
-```
-
-## Memgraph Client as a Generic Tensorflow Op
-
-Other than the Tensorflow Data Op, we'll want to support a generic Tensorflow
-Op which can be put anywhere in the Tensorflow computation Graph. It takes in
-an arbitrary tensor and produces a tensor. This would be used in the GraphSage
-algorithm to fetch the lowest level features into Tensorflow
-
-```python3
-requested_ids = np.array([1, 2, 3])
-ids_placeholder = tf.placeholder(tf.int32)
-
-model = mg_ops.OpenCypher()
-    "hostname:7687", auth=("user", "pass"),
-    """
-    UNWIND $node_ids as nid
-    MATCH (n:Train {id: nid})
-    RETURN n.features
-    """,
-
-    # What to call the input tensor as an openCypher parameter
-    parameter_name="node_ids",
-
-    # Type of our resulting tensor
-    dtype=(tf.float32)
-)
-
-features = model(ids_placeholder)
-
-with tf.Session() as sess:
-    result = sess.run(features,
-                    feed_dict={ids_placeholder: requested_ids})
-```
-
-This is probably easier to implement than the Data Op, so it might be a good
-idea to start with.
-
-## Production Usage
-
-During training, in the GraphSage algorithm at least, Memgraph is at the
-beginning and at the end of the Tensorflow computation graph.  
-At the beginning, the Data Op provides the node IDs which are fed into the
-generic Tensorflow Op to find their neighbours and their neighbours and
-their features.
-
-Production usage differs in that we don't use the Data Op. The Data Op is
-effectively cut off and the initial input is fed by Tensorflow serving,
-with the data found in the request.
-
-For example a JSON request to classify a node might look like:
-
-`POST http://host:port/v1/models/GraphSage/versions/v1:classify`
-
-With the contents:
-
-```json
-{
-    "examples": [
-        {"node_id": 1},
-        {"node_id": 2}
-    ],
-}
-```
-
-Every element of the "examples" list is an example to be computed. Each is
-represented by a dict with keys matching names of feeds in the Tensorflow
-graph and values being the values we want fed in for each example
-
-The REST API then replies in kind with the classification result in JSON
-
-Note about adding our custom Op to Tensorflow serving.  
-Our Ops .so can be added into the Bazel build to link with Tensorflow serving
-or it can be dynamically loaded by starting Tensorflow serving with a flag
-`--custom_op_paths`
-
-## Considerations
-
-There might be issues here that the url to connect to Memgraph is
-hardcoded into the op and would thus be wrong when moved to production,
-requiring some type of a hack to make work. We probably want to solve
-this by having the client op take in another tf.Variable as an input
-which would contain a connection url and username/password.  
-We have to research whether this makes it easy enough to move to
-production, as the connection string variable is still a part of the
-graph, but maybe easier to replace.  
-
-It is probably the best idea to utilize openCypher parameters to make
-our queries flexible. The exact API as to how to declare the parameters
-in Python is open to discussion.
-
-The Data Op might not even be necessary to implement as it is not
-key for production use. It can be replaced in training mode with
-feed dicts and either
-
- 1. Getting the initial list of nodes via a Python Bolt client
- 2. Creating a separate Tensorflow computation graph that gets all the
- relevant node IDs into Python

docs/presentation/latex-template/README.md

@@ -1,22 +0,0 @@
-# Memgraph LaTeX Beamer Template
-
-This folder contains all of the needed files for creating a presentation with
-Memgraph styling. You should use this style for any public presentations.
-
-Feel free to improve it according to style guidelines and raise issues if you
-find any.
-
-## Usage
-
-Copy the contents of this folder (excluding this README file) to where you
-want to write your own presentation. After copying, you can start editing the
-`template.tex` with your content.
-
-To compile the presentation to a PDF, run `latexmk -pdf -xelatex`. Some
-directives require XeLaTeX, so you need to pass `-xelatex` as the final option
-of `latexmk`. You may also need to install some packages if the compilation
-complains about missing packages.
-
-To clean up the generated files, use `latexmk -C`. This will also delete the
-generated PDF. If you wish to remove generated files except the PDF, use
-`latexmk -c`.

docs/presentation/latex-template/mg-beamer.cls

@@ -1,82 +0,0 @@
-\NeedsTeXFormat{LaTeX2e}
-\ProvidesClass{mg-beamer}[2018/03/26 Memgraph Beamer]
-
-\DeclareOption*{\PassOptionsToClass{\CurrentOption}{beamer}}
-
-\ProcessOptions \relax
-
-\LoadClass{beamer}
-
-\usetheme{Pittsburgh}
-
-% Memgraph color palette
-\definecolor{mg-purple}{HTML}{720096}
-\definecolor{mg-red}{HTML}{DD2222}
-\definecolor{mg-orange}{HTML}{FB6E00}
-\definecolor{mg-yellow}{HTML}{FFC500}
-\definecolor{mg-gray}{HTML}{857F87}
-\definecolor{mg-black}{HTML}{231F20}
-
-\RequirePackage{fontspec}
-% Title fonts
-\setbeamerfont{frametitle}{family={\fontspec[Path = ./mg-style/fonts/]{EncodeSansSemiCondensed-Regular.ttf}}}
-\setbeamerfont{title}{family={\fontspec[Path = ./mg-style/fonts/]{EncodeSansSemiCondensed-Regular.ttf}}}
-% Body font
-\RequirePackage[sfdefault,light]{roboto}
-% Roboto is pretty bad for monospace font. We will find a replacement.
-% \setmonofont{RobotoMono-Regular.ttf}[Path = ./mg-style/fonts/]
-
-% Title slide styles
-% \setbeamerfont{frametitle}{size=\huge}
-% \setbeamerfont{title}{size=\huge}
-% \setbeamerfont{date}{size=\tiny}
-
-% Other typography styles
-\setbeamertemplate{frametitle}[default][center]
-\setbeamercolor{frametitle}{fg=mg-black}
-\setbeamercolor{title}{fg=mg-black}
-\setbeamercolor{section in toc}{fg=mg-black}
-\setbeamercolor{local structure}{fg=mg-orange}
-\setbeamercolor{alert text}{fg=mg-red}
-
-% Commands
-\newcommand{\mgalert}[1]{{\usebeamercolor[fg]{alert text}#1}}
-\newcommand{\titleframe}{\frame[plain]{\titlepage}}
-\newcommand{\mgtexttt}[1]{{\textcolor{mg-gray}{\texttt{#1}}}}
-
-% Title slide background
-\RequirePackage{tikz,calc}
-% Use title-slide-169 if aspect ration is 16:9
-\pgfdeclareimage[interpolate=true,width=\paperwidth,height=\paperheight]{logo}{mg-style/title-slide-169}
-\setbeamertemplate{background}{
-  \begin{tikzpicture}
-  \useasboundingbox (0,0) rectangle (\the\paperwidth,\the\paperheight);
-    \pgftext[at=\pgfpoint{0}{0},left,base]{\pgfuseimage{logo}};
-  \ifnum\thepage>1\relax
-  \useasboundingbox (0,0) rectangle (\the\paperwidth,\the\paperheight);
-      \fill[white, opacity=1](0,\the\paperheight)--(\the\paperwidth,\the\paperheight)--(\the\paperwidth,0)--(0,0)--(0,\the\paperheight);
-  \fi
-  \end{tikzpicture}
-}
-
-% Footline content
-\setbeamertemplate{navigation symbols}{}%remove navigation symbols
- \setbeamertemplate{footline}{
-  \begin{beamercolorbox}[ht=1.6cm,wd=\paperwidth]{footlinecolor}
-    \vspace{0.1cm}
-    \hfill
-    \begin{minipage}[c]{3cm}
-      \begin{center}
-       \includegraphics[height=0.8cm]{mg-style/memgraph-logo.png}
-      \end{center}
-    \end{minipage}
-    \begin{minipage}[c]{7cm}
-         \insertshorttitle\ --- \insertsection
-    \end{minipage}
-    \begin{minipage}[c]{2cm}
-        \tiny{\insertframenumber{} of \inserttotalframenumber}
-    \end{minipage}
-   \end{beamercolorbox}
-}
-
-\endinput

docs/presentation/latex-template/template.tex

@@ -1,40 +0,0 @@
-% Set 16:9 aspect ratio
-\documentclass[aspectratio=169]{mg-beamer}
-% Default directive sets the regular 4:3 aspect ratio
-% \documentclass{mg-beamer}
-\mode<presentation>
-
-% requires xelatex
-\usepackage{ccicons}
-
-\title{Insert Presentation Title}
-\titlegraphic{\ccbyncnd}
-\author{Insert Name}
-
-% Institute doesn't look good in our current styling class.
-% \institute[Memgraph Ltd.]{\pgfimage[height=1.5cm]{mg-logo.png}}
-
-% Date is autogenerated on compilation, so no need to set it explicitly,
-% unless you wish to override it with a different date.
-% \date{March 23, 2018}
-
-\begin{document}
-
-\titleframe
-
-\section{Intro}
-
-\begin{frame}{Contents}
-  \tableofcontents
-\end{frame}
-
-\begin{frame}{Memgraph Markup Test}
-  \begin{itemize}
-    \item \mgtexttt{Prefer \\mgtexttt for monospace}
-    \item Replace this slide with your own
-    \item Add even more slides in different sections
-    \item Make sure you spellcheck your presentation
-  \end{itemize}
-\end{frame}
-
-\end{document}

environment/README.md

@@ -1,44 +1,4 @@
 # Memgraph Build and Run Environments
 
-## Toolchain Installation Procedure
-
-1) Download the toolchain for your operating system from one of the following
-   links (current active toolchain is `toolchain-v2`):
-
-* [CentOS 7](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-centos-7.tar.gz)
-* [CentOS 8](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-centos-8.tar.gz)
-* [Debian 9](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-debian-9.tar.gz)
-* [Debian 10](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-debian-10.tar.gz)
-* [Ubuntu 18.04](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-ubuntu-18.04.tar.gz)
-* [Ubuntu 20.04](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-ubuntu-20.04.tar.gz)
-
-2) Extract the toolchain with the following command:
-
-```bash
-tar xzvf {{toolchain-archive}}.tar.gz -C /opt
-```
-
-3) Check and install required toolchain runtime dependencies by executing
-   (e.g., on **Debian 10**):
-
-```bash
-./environment/os/debian-10.sh check TOOLCHAIN_RUN_DEPS
-./environment/os/debian-10.sh install TOOLCHAIN_RUN_DEPS
-```
-
-4) Activate the toolchain:
-
-```bash
-source /opt/toolchain-v2/activate
-```
-
-## Toolchain Upgrade Procedure
-
-1) Build a new toolchain for each supported OS (latest versions).
-2) If the new toolchain doesn't compile on some supported OS, the last
-   compilable toolchain has to be used instead. In other words, the project has
-   to compile on the oldest active toolchain as well. Suppose some
-   changes/improvements were added when migrating to the latest toolchain; in
-   that case, the maintainer has to ensure that the project still compiles on
-   previous toolchains (everything from `init` script to the actual code has to
-   work on all supported operating systems).
+Please continue in
+[Notion](https://www.notion.so/memgraph/Tools-05e0baafb78a49b386e0063b4833d23d).

environment/os/centos-7.sh

@@ -46,6 +46,7 @@ MEMGRAPH_BUILD_DEPS=(
     rpm-build rpmlint # for RPM package building
     doxygen graphviz # source documentation generators
     which mono-complete dotnet-sdk-3.1 golang nodejs zip unzip java-11-openjdk-devel # for driver tests
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"

environment/os/centos-8.sh

@@ -45,6 +45,7 @@ MEMGRAPH_BUILD_DEPS=(
     doxygen graphviz # source documentation generators
     which mono-complete dotnet-sdk-3.1 nodejs golang zip unzip java-11-openjdk-devel # for driver tests
     sbcl # for custom Lisp C++ preprocessing
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"
@@ -85,7 +86,7 @@ install() {
         echo "NOTE: export LANG=en_US.utf8"
     fi
     dnf install -y epel-release
-    dnf config-manager --set-enabled PowerTools # Required to install texinfo.
+    dnf config-manager --set-enabled powertools # Required to install texinfo.
     dnf update -y
     dnf install -y wget git python36 python3-pip
     for pkg in $1; do

environment/os/debian-10.sh

@@ -43,6 +43,7 @@ MEMGRAPH_BUILD_DEPS=(
     doxygen graphviz # source documentation generators
     mono-runtime mono-mcs zip unzip default-jdk-headless # for driver tests
     dotnet-sdk-3.1 golang nodejs npm
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"

environment/os/debian-9.sh

@@ -41,6 +41,7 @@ MEMGRAPH_BUILD_DEPS=(
     sbcl # for custom Lisp C++ preprocessing
     doxygen graphviz # source documentation generators
     mono-runtime mono-mcs nodejs zip unzip default-jdk-headless # for driver tests
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"

environment/os/ubuntu-18.04.sh

@@ -42,6 +42,7 @@ MEMGRAPH_BUILD_DEPS=(
     sbcl # custom Lisp C++ preprocessing
     doxygen graphviz # source documentation generators
     mono-runtime mono-mcs nodejs zip unzip default-jdk-headless # driver tests
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"

environment/os/ubuntu-20.04.sh

@@ -43,6 +43,7 @@ MEMGRAPH_BUILD_DEPS=(
     doxygen graphviz # source documentation generators
     mono-runtime mono-mcs zip unzip default-jdk-headless # for driver tests
     dotnet-sdk-3.1 golang nodejs npm
+    autoconf # for jemalloc code generation
 )
 list() {
     echo "$1"

environment/util.sh

@@ -43,3 +43,8 @@ check_all_dnf() {
         exit 1
     fi
 }
+install_all_apt() {
+    for pkg in $1; do
+        apt install -y "$pkg"
+    done
+}

init

@@ -80,7 +80,7 @@ echo \
   (ql:quickload '(:lcp :lcp/test) :silent t)
   " | sbcl --script
 
-# setup libs (download)
+# Setup libs (download).
 cd libs
 ./cleanup.sh
 ./setup.sh
@@ -95,6 +95,14 @@ setup_virtualenv tests/stress
 # setup integration/ldap dependencies
 setup_virtualenv tests/integration/ldap
 
+# Setup tests dependencies.
+# cd tests
+# ./setup.sh
+# cd ..
+# TODO(gitbuda): Remove setup_virtualenv, replace it with tests/ve3. Take care
+# of the build order because tests/setup.py builds pymgclient which depends on
+# mgclient which is build after this script by calling make.
+
 echo "Done installing dependencies for Memgraph"
 
 echo "Linking git hooks"

libs/.gitignore

@@ -4,3 +4,4 @@
 !cleanup.sh
 !CMakeLists.txt
 !__main.cpp
+!jemalloc.cmake

libs/CMakeLists.txt

@@ -1,11 +1,15 @@
 include(ExternalProject)
 
+include(GNUInstallDirs)
+
 include(ProcessorCount)
 ProcessorCount(NPROC)
 if (NPROC EQUAL 0)
   set(NPROC 1)
 endif()
 
+set(LIB_DIR ${CMAKE_CURRENT_SOURCE_DIR})
+
 # convenience functions
 function(import_header_library name include_dir)
   add_library(${name} INTERFACE IMPORTED GLOBAL)
@@ -102,7 +106,7 @@ import_external_library(benchmark STATIC
 
 # setup fmt format
 import_external_library(fmt STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/lib/libfmt.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/${CMAKE_INSTALL_LIBDIR}/libfmt.a
   ${CMAKE_CURRENT_SOURCE_DIR}/fmt/include
   # Skip testing.
   CMAKE_ARGS -DFMT_TEST=OFF)
@@ -149,24 +153,6 @@ import_external_library(gflags STATIC
              -DBUILD_gflags_nothreads_LIB=OFF
              -DGFLAGS_NO_FILENAMES=${GFLAGS_NO_FILENAMES})
 
-# Setup google logging after gflags (so that glog can use it).
-set(GLOG_DISABLE_OPTIONS "0")
-if ("${CMAKE_BUILD_TYPE}" MATCHES "^(R|r)(E|e)(L|l).+")
-  set(GLOG_DISABLE_OPTIONS "1")
-endif()
-
-# Setup google logging after gflags (so that glog can use it).
-import_external_library(glog STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/glog/lib/libglog.a
-  ${CMAKE_CURRENT_SOURCE_DIR}/glog/include
-  DEPENDS gflags-proj
-  CMAKE_ARGS -Dgflags_DIR=${CMAKE_CURRENT_SOURCE_DIR}/gflags/lib/cmake/gflags
-             -DBUILD_TESTING=OFF
-             -DGLOG_NO_FILENAMES=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_STACKTRACE=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_BUFFER_SETTINGS=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_TIME_PID_FILENAME=${GLOG_DISABLE_OPTIONS})
-
 # Setup cppitertools
 import_header_library(cppitertools ${CMAKE_CURRENT_SOURCE_DIR})
 
@@ -222,3 +208,11 @@ import_external_library(mgclient STATIC
              -DBUILD_TESTING=OFF)
 find_package(OpenSSL REQUIRED)
 target_link_libraries(mgclient INTERFACE ${OPENSSL_LIBRARIES})
+
+# Setup spdlog
+import_external_library(spdlog STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/spdlog/${CMAKE_INSTALL_LIBDIR}/libspdlog.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/spdlog/include
+  BUILD_COMMAND $(MAKE) spdlog)
+
+include(jemalloc.cmake)

libs/jemalloc.cmake

@@ -0,0 +1,55 @@
+set(JEMALLOC_DIR "${LIB_DIR}/jemalloc")
+
+set(JEMALLOC_SRCS
+    ${JEMALLOC_DIR}/src/arena.c
+    ${JEMALLOC_DIR}/src/background_thread.c
+    ${JEMALLOC_DIR}/src/base.c
+    ${JEMALLOC_DIR}/src/bin.c
+    ${JEMALLOC_DIR}/src/bitmap.c
+    ${JEMALLOC_DIR}/src/ckh.c
+    ${JEMALLOC_DIR}/src/ctl.c
+    ${JEMALLOC_DIR}/src/div.c
+    ${JEMALLOC_DIR}/src/extent.c
+    ${JEMALLOC_DIR}/src/extent_dss.c
+    ${JEMALLOC_DIR}/src/extent_mmap.c
+    ${JEMALLOC_DIR}/src/hash.c
+    ${JEMALLOC_DIR}/src/hook.c
+    ${JEMALLOC_DIR}/src/jemalloc.c
+    ${JEMALLOC_DIR}/src/large.c
+    ${JEMALLOC_DIR}/src/log.c
+    ${JEMALLOC_DIR}/src/malloc_io.c
+    ${JEMALLOC_DIR}/src/mutex.c
+    ${JEMALLOC_DIR}/src/mutex_pool.c
+    ${JEMALLOC_DIR}/src/nstime.c
+    ${JEMALLOC_DIR}/src/pages.c
+    ${JEMALLOC_DIR}/src/prng.c
+    ${JEMALLOC_DIR}/src/prof.c
+    ${JEMALLOC_DIR}/src/rtree.c
+    ${JEMALLOC_DIR}/src/sc.c
+    ${JEMALLOC_DIR}/src/stats.c
+    ${JEMALLOC_DIR}/src/sz.c
+    ${JEMALLOC_DIR}/src/tcache.c
+    ${JEMALLOC_DIR}/src/test_hooks.c
+    ${JEMALLOC_DIR}/src/ticker.c
+    ${JEMALLOC_DIR}/src/tsd.c
+    ${JEMALLOC_DIR}/src/witness.c
+    ${JEMALLOC_DIR}/src/safety_check.c
+)
+
+add_library(jemalloc ${JEMALLOC_SRCS})
+target_include_directories(jemalloc PUBLIC "${JEMALLOC_DIR}/include")
+
+find_package(Threads REQUIRED)
+target_link_libraries(jemalloc PUBLIC Threads::Threads)
+
+target_compile_definitions(jemalloc PRIVATE -DJEMALLOC_NO_PRIVATE_NAMESPACE)
+
+if (CMAKE_BUILD_TYPE STREQUAL "DEBUG")
+    target_compile_definitions(jemalloc PRIVATE -DJEMALLOC_DEBUG=1 -DJEMALLOC_PROF=1)
+endif()
+
+target_compile_options(jemalloc PRIVATE -Wno-redundant-decls)
+# for RTLD_NEXT
+target_compile_definitions(jemalloc PRIVATE _GNU_SOURCE)
+
+set_property(TARGET jemalloc APPEND PROPERTY INTERFACE_COMPILE_DEFINITIONS USE_JEMALLOC=1)

libs/setup.sh

@@ -59,10 +59,8 @@ cppitertools_ref="cb3635456bdb531121b82b4d2e3afc7ae1f56d47"
 clone https://github.com/ryanhaining/cppitertools.git cppitertools $cppitertools_ref
 
 # fmt
-fmt_tag="7fa8f8fa48b0903deab5bb42e6760477173ac485" # v3.0.1
-# Commit which fixes an issue when compiling with C++14 and higher.
-fmt_cxx14_fix="b9aaa507fc49680d037fd84c043f747a395bce04"
-clone https://github.com/fmtlib/fmt.git fmt $fmt_tag $fmt_cxx14_fix
+fmt_tag="7bdf0628b1276379886c7f6dda2cef2b3b374f0b" # (2020-11-25) 
+clone https://github.com/fmtlib/fmt.git fmt $fmt_tag
 
 # rapidcheck
 rapidcheck_tag="7bc7d302191a4f3d0bf005692677126136e02f60" # (2020-05-04)
@@ -76,10 +74,6 @@ clone https://github.com/google/benchmark.git benchmark $benchmark_tag
 googletest_tag="ec44c6c1675c25b9827aacd08c02433cccde7780" # v1.8.0
 clone https://github.com/google/googletest.git googletest $googletest_tag
 
-# google logging
-glog_tag="042a21657e79784226babab8b942f7bd0949635f" # custom version (v0.3.5+)
-clone https://github.com/memgraph/glog.git glog $glog_tag
-
 # google flags
 gflags_tag="b37ceb03a0e56c9f15ce80409438a555f8a67b7c" # custom version (May 6, 2017)
 clone https://github.com/memgraph/gflags.git gflags $gflags_tag
@@ -117,6 +111,32 @@ clone https://github.com/facebook/rocksdb.git rocksdb $rocksdb_tag
 sed -i 's/TARGETS ${ROCKSDB_SHARED_LIB}/TARGETS ${ROCKSDB_SHARED_LIB} OPTIONAL/' rocksdb/CMakeLists.txt
 
 # mgclient
-mgclient_tag="fe94b3631385ef5dbe40a3d8458860dbcc33e6ea" # May 27, 2019
+mgclient_tag="v1.2.0" # (2021-01-14)
 clone https://github.com/memgraph/mgclient.git mgclient $mgclient_tag
 sed -i 's/\${CMAKE_INSTALL_LIBDIR}/lib/' mgclient/src/CMakeLists.txt
+
+# pymgclient
+pymgclient_tag="4f85c179e56302d46a1e3e2cf43509db65f062b3" # (2021-01-15)
+clone https://github.com/memgraph/pymgclient.git pymgclient $pymgclient_tag
+
+spdlog_tag="46d418164dd4cd9822cf8ca62a116a3f71569241" # (2020-12-01)
+clone https://github.com/gabime/spdlog spdlog $spdlog_tag
+
+jemalloc_tag="ea6b3e973b477b8061e0076bb257dbd7f3faa756" # (2021-02-11)
+clone https://github.com/jemalloc/jemalloc.git jemalloc $jemalloc_tag
+pushd jemalloc
+# ThreadPool select job randomly, and there can be some threads that had been
+# performed some memory heavy task before and will be inactive for some time,
+# but until it will became active again, the memory will not be freed since by
+# default each thread has it's own arena, but there should be not more then
+# 4*CPU arenas (see opt.nareans description).
+#
+# By enabling percpu_arena number of arenas limited to number of CPUs and hence
+# this problem should go away.
+#
+# muzzy_decay_ms -- use MADV_FREE when available on newer Linuxes, to
+# avoid spurious latencies and additional work associated with
+# MADV_DONTNEED. See
+# https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
+./autogen.sh --with-malloc-conf="percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:10000"
+popd

query_modules/louvain/test/unit/CMakeLists.txt

@@ -17,7 +17,7 @@ function(add_unit_test test_cpp)
   # TODO: this is a temporary workaround the test build warnings
   target_compile_options(${target_name} PRIVATE -Wno-comment -Wno-sign-compare
                                                 -Wno-unused-variable)
-  target_link_libraries(${target_name} glog gflags gtest gtest_main Threads::Threads
+  target_link_libraries(${target_name} spdlog gflags gtest gtest_main Threads::Threads
                                        louvain-core louvain-test)
   # register test
   add_test(${target_name} ${exec_name})

query_modules/louvain/test/unit/graph.cpp

@@ -1,4 +1,3 @@
-#include <glog/logging.h>
 #include <gtest/gtest.h>
 
 #include "data_structures/graph.hpp"
@@ -10,8 +9,7 @@ bool CommunityCheck(const comdata::Graph &graph,
                     const std::vector<uint32_t> &c) {
   if (graph.Size() != c.size()) return false;
   for (uint32_t node_id = 0; node_id < graph.Size(); ++node_id)
-    if (graph.Community(node_id) != c[node_id])
-      return false;
+    if (graph.Community(node_id) != c[node_id]) return false;
   return true;
 }
 
@@ -20,8 +18,7 @@ bool DegreeCheck(const comdata::Graph &graph,
                  const std::vector<uint32_t> &deg) {
   if (graph.Size() != deg.size()) return false;
   for (uint32_t node_id = 0; node_id < graph.Size(); ++node_id)
-    if (graph.Degree(node_id) != deg[node_id])
-      return false;
+    if (graph.Degree(node_id) != deg[node_id]) return false;
   return true;
 }
 
@@ -127,10 +124,7 @@ TEST(Graph, Degrees) {
 
   // Chain
   // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 1},
-                     {1, 2, 1},
-                     {2, 3, 1},
-                     {3, 4, 1}});
+  graph = BuildGraph(5, {{0, 1, 1}, {1, 2, 1}, {2, 3, 1}, {3, 4, 1}});
   deg = {1, 2, 2, 2, 1};
   ASSERT_TRUE(DegreeCheck(graph, deg));
 
@@ -140,12 +134,8 @@ TEST(Graph, Degrees) {
   //   (1)   (2)
   //    |   /   \
   //   (4) (5)  (6)
-  graph = BuildGraph(7, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 4, 1},
-                     {2, 5, 1},
-                     {2, 6, 1}});
+  graph = BuildGraph(
+      7, {{0, 1, 1}, {0, 2, 1}, {0, 3, 1}, {1, 4, 1}, {2, 5, 1}, {2, 6, 1}});
   deg = {3, 2, 3, 1, 1, 1, 1};
   ASSERT_TRUE(DegreeCheck(graph, deg));
 
@@ -155,12 +145,12 @@ TEST(Graph, Degrees) {
   //  |  \ |  \
   // (2)--(3)-(4)
   graph = BuildGraph(5, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 3, 1},
-                     {1, 4, 1},
-                     {2, 3, 1},
-                     {3, 4, 1}});
+                         {0, 2, 1},
+                         {0, 3, 1},
+                         {1, 3, 1},
+                         {1, 4, 1},
+                         {2, 3, 1},
+                         {3, 4, 1}});
   deg = {3, 3, 2, 4, 2};
   ASSERT_TRUE(DegreeCheck(graph, deg));
 
@@ -170,15 +160,15 @@ TEST(Graph, Degrees) {
   //  |  \ |  \
   // (2*)--(3)-(4*)
   graph = BuildGraph(5, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 3, 1},
-                     {1, 4, 1},
-                     {2, 3, 1},
-                     {3, 4, 1},
-                     {1, 1, 1},
-                     {2, 2, 2},
-                     {4, 4, 4}});
+                         {0, 2, 1},
+                         {0, 3, 1},
+                         {1, 3, 1},
+                         {1, 4, 1},
+                         {2, 3, 1},
+                         {3, 4, 1},
+                         {1, 1, 1},
+                         {2, 2, 2},
+                         {4, 4, 4}});
   deg = {3, 4, 3, 4, 3};
   ASSERT_TRUE(DegreeCheck(graph, deg));
 
@@ -196,10 +186,7 @@ TEST(Graph, Weights) {
 
   // Chain
   // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {1, 2, 0.5},
-                     {2, 3, 2.3},
-                     {3, 4, 4.2}});
+  graph = BuildGraph(5, {{0, 1, 0.1}, {1, 2, 0.5}, {2, 3, 2.3}, {3, 4, 4.2}});
   inc_w = {0.1, 0.6, 2.8, 6.5, 4.2};
   ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
   ASSERT_NEAR(graph.TotalWeight(), 7.1, 1e-6);
@@ -211,11 +198,11 @@ TEST(Graph, Weights) {
   //    |   /   \
   //   (4) (5)  (6)
   graph = BuildGraph(7, {{0, 1, 1.3},
-                     {0, 2, 0.2},
-                     {0, 3, 1},
-                     {1, 4, 3.2},
-                     {2, 5, 4.2},
-                     {2, 6, 0.7}});
+                         {0, 2, 0.2},
+                         {0, 3, 1},
+                         {1, 4, 3.2},
+                         {2, 5, 4.2},
+                         {2, 6, 0.7}});
   inc_w = {2.5, 4.5, 5.1, 1, 3.2, 4.2, 0.7};
   ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
   EXPECT_NEAR(graph.TotalWeight(), 10.6, 1e-6);
@@ -226,12 +213,12 @@ TEST(Graph, Weights) {
   //  |  \ |  \
   // (2)--(3)-(4)
   graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7}});
+                         {0, 2, 0.2},
+                         {0, 3, 0.3},
+                         {1, 3, 0.4},
+                         {1, 4, 0.5},
+                         {2, 3, 0.6},
+                         {3, 4, 0.7}});
   inc_w = {0.6, 1, 0.8, 2, 1.2};
   ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
   EXPECT_NEAR(graph.TotalWeight(), 2.8, 1e-6);
@@ -242,15 +229,15 @@ TEST(Graph, Weights) {
   //  |  \ |  \
   // (2*)--(3)-(4*)
   graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7},
-                     {1, 1, 0.8},
-                     {2, 2, 0.9},
-                     {4, 4, 1}});
+                         {0, 2, 0.2},
+                         {0, 3, 0.3},
+                         {1, 3, 0.4},
+                         {1, 4, 0.5},
+                         {2, 3, 0.6},
+                         {3, 4, 0.7},
+                         {1, 1, 0.8},
+                         {2, 2, 0.9},
+                         {4, 4, 1}});
   inc_w = {0.6, 1.8, 1.7, 2, 2.2};
   ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
   EXPECT_NEAR(graph.TotalWeight(), 5.5, 1e-6);
@@ -267,10 +254,7 @@ TEST(Graph, Modularity) {
 
   // Chain
   // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {1, 2, 0.5},
-                     {2, 3, 2.3},
-                     {3, 4, 4.2}});
+  graph = BuildGraph(5, {{0, 1, 0.1}, {1, 2, 0.5}, {2, 3, 2.3}, {3, 4, 4.2}});
   std::vector<uint32_t> c = {0, 1, 1, 2, 2};
   SetCommunities(&graph, c);
   EXPECT_NEAR(graph.Modularity(), 0.036798254314620096, 1e-6);
@@ -282,11 +266,11 @@ TEST(Graph, Modularity) {
   //    |   /   \
   //   (4) (5)  (6)
   graph = BuildGraph(7, {{0, 1, 1.3},
-                     {0, 2, 0.2},
-                     {0, 3, 1},
-                     {1, 4, 3.2},
-                     {2, 5, 4.2},
-                     {2, 6, 0.7}});
+                         {0, 2, 0.2},
+                         {0, 3, 1},
+                         {1, 4, 3.2},
+                         {2, 5, 4.2},
+                         {2, 6, 0.7}});
   c = {0, 0, 1, 0, 0, 1, 2};
   SetCommunities(&graph, c);
   EXPECT_NEAR(graph.Modularity(), 0.4424617301530794, 1e-6);
@@ -297,12 +281,12 @@ TEST(Graph, Modularity) {
   //  |  \ |  \
   // (2)--(3)-(4)
   graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7}});
+                         {0, 2, 0.2},
+                         {0, 3, 0.3},
+                         {1, 3, 0.4},
+                         {1, 4, 0.5},
+                         {2, 3, 0.6},
+                         {3, 4, 0.7}});
   c = {0, 1, 1, 1, 1};
   SetCommunities(&graph, c);
   EXPECT_NEAR(graph.Modularity(), -0.022959183673469507, 1e-6);
@@ -313,15 +297,15 @@ TEST(Graph, Modularity) {
   //  |  \ |  \
   // (2*)--(3)-(4*)
   graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7},
-                     {1, 1, 0.8},
-                     {2, 2, 0.9},
-                     {4, 4, 1}});
+                         {0, 2, 0.2},
+                         {0, 3, 0.3},
+                         {1, 3, 0.4},
+                         {1, 4, 0.5},
+                         {2, 3, 0.6},
+                         {3, 4, 0.7},
+                         {1, 1, 0.8},
+                         {2, 2, 0.9},
+                         {4, 4, 1}});
   c = {0, 0, 0, 0, 1};
   SetCommunities(&graph, c);
   EXPECT_NEAR(graph.Modularity(), 0.188842975206611, 1e-6);

release/README.md

@@ -1,43 +1,4 @@
-# Memgraph Release Packaging
+# Memgraph Release
 
-Various tools and packaging configuration files should be put under this
-directory. Common files for all packages can be kept in the root of this
-directory, for example `memgraph.service`. If the common stuff should be
-grouped, it should be in a subdirectory. `examples` directory is one such
-case. Packaging specific stuff must have its own directory.
-
-Currently we support distributing Memgraph binary through the following
-packages.
-
-  * Debian package
-  * RPM package
-  * Docker image
-  * ArchLinux package
-
-## Release process
-
-While releasing an official version of Memgraph, there are two possible
-scenarios:
-  * First release in new major.minor series
-  * Patch release in existing major.minor series
-
-To release a new major.minor release of Memgraph you should execute the
-following steps:
-  1. Merge all PRs that must be in the new release
-  2. Document all changes in `CHANGELOG.md` and merge them
-  3. From the `master` branch, create a branch named `release/X.Y` and push it
-     to `origin`
-  4. Create the release packages triggering a `Release {{Operating System}}`
-     workflow using branch `release/X.Y` on Github Actions
-  5. Enjoy
-
-To release a new patch release in an existing major.minor series you should
-execute the following steps:
-  1. Checkout to the `release/X.Y` branch
-  2. Cherry-pick all landed commits that should be included in the patch version
-  3. Document all changes in `CHANGELOG.md` and commit them
-  4. Edit the root `CMakeLists.txt` and set `MEMGRAPH_OVERRIDE_VERSION` to
-     `X.Y.patch` and commit the change
-  5. Create the release packages triggering a `Release {{Operating System}}`
-     workflow using branch `release/X.Y` on Github Actions
-  6. Enjoy
+Please continue in
+[Notion](https://www.notion.so/memgraph/Release-621733518c82456ebc119d2a025b5dd3).

release/get_version.py

@@ -3,6 +3,7 @@ import argparse
 import re
 import subprocess
 import sys
+import os
 
 
 # This script is used to determine the current version of Memgraph. The script
@@ -161,8 +162,17 @@ parser.add_argument(
 parser.add_argument(
     "--variant", choices=("binary", "deb", "rpm"), default="binary",
     help="which variant of the version string should be generated")
+parser.add_argument(
+    "--memgraph-root-dir", help="The root directory of the checked out "
+    "Memgraph repository.", default=".")
 args = parser.parse_args()
 
+if not os.path.isdir(args.memgraph_root_dir):
+    raise Exception("The root directory ({}) is not a valid directory".format(
+        args.memgraph_root_dir))
+
+os.chdir(args.memgraph_root_dir)
+
 offering = "enterprise" if args.enterprise else "community"
 
 # Check whether the version was manually supplied.
@@ -173,6 +183,20 @@ if args.version:
                          suffix=args.suffix), end="")
     sys.exit(0)
 
+# Within CI, after the regular checkout, master is sometimes (e.g. in the case
+# of an epic or task branch) NOT created as a local branch. cpack depends on
+# variables generated by calling this script during the cmake phase. This
+# script needs master to be the local branch. `git fetch origin master:master`
+# is creating the local master branch without checking it out. Does nothing if
+# master is already there.
+try:
+    current_branch = get_output("git", "rev-parse", "--abbrev-ref", "HEAD")
+    if current_branch != "master":
+        get_output("git", "fetch", "origin", "master:master")
+except Exception:
+    print("Fatal error while ensuring local master branch.")
+    sys.exit(1)
+
 # Get current commit hashes.
 current_hash = get_output("git", "rev-parse", "HEAD")
 current_hash_short = get_output("git", "rev-parse", "--short", "HEAD")

release/logrotate_community.conf

@@ -1,13 +1,2 @@
 # logrotate configuration for Memgraph Community
 # see "man logrotate" for details
-
-/var/log/memgraph/memgraph.log {
-    # rotate log files weekly
-    weekly
-    # keep 5 weeks worth of backlog
-    rotate 5
-    # send SIGUSR1 to notify memgraph to recreate logfile
-    postrotate
-        /usr/bin/killall -s SIGUSR1 memgraph
-    endscript
-}

release/logrotate_enterprise.conf

@@ -1,17 +1,6 @@
 # logrotate configuration for Memgraph Enterprise
 # see "man logrotate" for details
 
-/var/log/memgraph/memgraph.log {
-    # rotate log files weekly
-    weekly
-    # keep 5 weeks worth of backlog
-    rotate 5
-    # send SIGUSR1 to notify memgraph to recreate logfile
-    postrotate
-        /usr/bin/killall -s SIGUSR1 memgraph
-    endscript
-}
-
 /var/lib/memgraph/durability/audit/audit.log {
     # rotate log files daily
     daily

release/rpm/community/memgraph.spec.in

@@ -30,6 +30,7 @@ BuildRequires: systemd
 # This is needed to prevent Python compilation errors when building the RPM
 # package
 # https://github.com/scylladb/scylla/issues/2235
+%if 0%{?rhel} < 8
 %global __os_install_post    \
     /usr/lib/rpm/redhat/brp-compress \
     %{!?__debug_package:\
@@ -39,6 +40,16 @@ BuildRequires: systemd
     /usr/lib/rpm/redhat/brp-strip-static-archive %{__strip} \
     %{!?__jar_repack:/usr/lib/rpm/redhat/brp-java-repack-jars} \
 %{nil}
+%else
+%global __os_install_post    \
+    /usr/lib/rpm/brp-compress \
+    %{!?__debug_package:\
+    /usr/lib/rpm/brp-strip %{__strip} \
+    /usr/lib/rpm/brp-strip-comment-note %{__strip} %{__objdump} \
+    } \
+    /usr/lib/rpm/brp-strip-static-archive %{__strip} \
+%{nil}
+%endif
 
 %define _rpmdir %_topdir/RPMS
 %define _srcrpmdir %_topdir/SRPMS

release/rpm/enterprise/memgraph.spec.in

@@ -30,6 +30,7 @@ BuildRequires: systemd
 # This is needed to prevent Python compilation errors when building the RPM
 # package
 # https://github.com/scylladb/scylla/issues/2235
+%if 0%{?rhel} < 8
 %global __os_install_post    \
     /usr/lib/rpm/redhat/brp-compress \
     %{!?__debug_package:\
@@ -39,6 +40,16 @@ BuildRequires: systemd
     /usr/lib/rpm/redhat/brp-strip-static-archive %{__strip} \
     %{!?__jar_repack:/usr/lib/rpm/redhat/brp-java-repack-jars} \
 %{nil}
+%else
+%global __os_install_post    \
+    /usr/lib/rpm/brp-compress \
+    %{!?__debug_package:\
+    /usr/lib/rpm/brp-strip %{__strip} \
+    /usr/lib/rpm/brp-strip-comment-note %{__strip} %{__objdump} \
+    } \
+    /usr/lib/rpm/brp-strip-static-archive %{__strip} \
+%{nil}
+%endif
 
 %define _rpmdir %_topdir/RPMS
 %define _srcrpmdir %_topdir/SRPMS

src/CMakeLists.txt

@@ -10,11 +10,11 @@ add_subdirectory(telemetry)
 add_subdirectory(communication)
 add_subdirectory(storage/v2)
 add_subdirectory(query)
+add_subdirectory(slk)
+add_subdirectory(rpc)
 if (MG_ENTERPRISE)
   add_subdirectory(audit)
   add_subdirectory(auth)
-  add_subdirectory(slk)
-  add_subdirectory(rpc)
 endif()
 
 string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
@@ -37,17 +37,17 @@ if (MG_ENTERPRISE)
       glue/auth.cpp)
 endif()
 
-set(MG_SINGLE_NODE_V2_LIBS stdc++fs Threads::Threads
-    telemetry_lib mg-query mg-communication)
+set(mg_single_node_v2_libs stdc++fs Threads::Threads
+    telemetry_lib mg-query mg-communication mg-new-delete mg-utils)
 if (MG_ENTERPRISE)
   # These are enterprise subsystems
-  set(MG_SINGLE_NODE_V2_LIBS ${MG_SINGLE_NODE_V2_LIBS} mg-auth mg-audit)
+  set(mg_single_node_v2_libs ${mg_single_node_v2_libs} mg-auth mg-audit)
 endif()
 
 # memgraph main executable
 add_executable(memgraph ${mg_single_node_v2_sources})
 target_include_directories(memgraph PUBLIC ${CMAKE_SOURCE_DIR}/include)
-target_link_libraries(memgraph ${MG_SINGLE_NODE_V2_LIBS})
+target_link_libraries(memgraph ${mg_single_node_v2_libs})
 # NOTE: `include/mg_procedure.syms` describes a pattern match for symbols which
 # should be dynamically exported, so that `dlopen` can correctly link the
 # symbols in custom procedure module libraries.

src/audit/CMakeLists.txt

@@ -1,5 +1,5 @@
 set(audit_src_files log.cpp)
 
 add_library(mg-audit STATIC ${audit_src_files})
-target_link_libraries(mg-audit json glog gflags fmt)
+target_link_libraries(mg-audit json gflags fmt)
 target_link_libraries(mg-audit mg-utils mg-storage-v2)

src/audit/log.cpp

@@ -3,9 +3,9 @@
 #include <chrono>
 
 #include <fmt/format.h>
-#include <glog/logging.h>
 #include <json/json.hpp>
 
+#include "utils/logging.hpp"
 #include "utils/string.hpp"
 
 namespace audit {
@@ -38,8 +38,7 @@ inline nlohmann::json PropertyValueToJson(const storage::PropertyValue &pv) {
     case storage::PropertyValue::Type::Map: {
       ret = nlohmann::json::object();
       for (const auto &item : pv.ValueMap()) {
-        ret.push_back(nlohmann::json::object_t::value_type(
-            item.first, PropertyValueToJson(item.second)));
+        ret.push_back(nlohmann::json::object_t::value_type(item.first, PropertyValueToJson(item.second)));
       }
       break;
     }
@@ -47,15 +46,14 @@ inline nlohmann::json PropertyValueToJson(const storage::PropertyValue &pv) {
   return ret;
 }
 
-Log::Log(const std::filesystem::path &storage_directory, int32_t buffer_size,
-         int32_t buffer_flush_interval_millis)
+Log::Log(const std::filesystem::path &storage_directory, int32_t buffer_size, int32_t buffer_flush_interval_millis)
     : storage_directory_(storage_directory),
       buffer_size_(buffer_size),
       buffer_flush_interval_millis_(buffer_flush_interval_millis),
       started_(false) {}
 
 void Log::Start() {
-  CHECK(!started_) << "Trying to start an already started audit log!";
+  MG_ASSERT(!started_, "Trying to start an already started audit log!");
 
   utils::EnsureDirOrDie(storage_directory_);
 
@@ -63,9 +61,7 @@ void Log::Start() {
   started_ = true;
 
   ReopenLog();
-  scheduler_.Run("Audit",
-                 std::chrono::milliseconds(buffer_flush_interval_millis_),
-                 [&] { Flush(); });
+  scheduler_.Run("Audit", std::chrono::milliseconds(buffer_flush_interval_millis_), [&] { Flush(); });
 }
 
 Log::~Log() {
@@ -78,13 +74,12 @@ Log::~Log() {
   Flush();
 }
 
-void Log::Record(const std::string &address, const std::string &username,
-                 const std::string &query,
+void Log::Record(const std::string &address, const std::string &username, const std::string &query,
                  const storage::PropertyValue &params) {
   if (!started_.load(std::memory_order_relaxed)) return;
-  auto timestamp = std::chrono::duration_cast<std::chrono::microseconds>(
-                       std::chrono::system_clock::now().time_since_epoch())
-                       .count();
+  auto timestamp =
+      std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::system_clock::now().time_since_epoch())
+          .count();
   buffer_->emplace(Item{timestamp, address, username, query, params});
 }
 
@@ -92,8 +87,7 @@ void Log::ReopenLog() {
   if (!started_.load(std::memory_order_relaxed)) return;
   std::lock_guard<std::mutex> guard(lock_);
   if (log_.IsOpen()) log_.Close();
-  log_.Open(storage_directory_ / "audit.log",
-            utils::OutputFile::Mode::APPEND_TO_EXISTING);
+  log_.Open(storage_directory_ / "audit.log", utils::OutputFile::Mode::APPEND_TO_EXISTING);
 }
 
 void Log::Flush() {
@@ -101,11 +95,9 @@ void Log::Flush() {
   for (uint64_t i = 0; i < buffer_size_; ++i) {
     auto item = buffer_->pop();
     if (!item) break;
-    log_.Write(
-        fmt::format("{}.{:06d},{},{},{},{}\n", item->timestamp / 1000000,
-                    item->timestamp % 1000000, item->address, item->username,
-                    utils::Escape(item->query),
-                    utils::Escape(PropertyValueToJson(item->params).dump())));
+    log_.Write(fmt::format("{}.{:06d},{},{},{},{}\n", item->timestamp / 1000000, item->timestamp % 1000000,
+                           item->address, item->username, utils::Escape(item->query),
+                           utils::Escape(PropertyValueToJson(item->params).dump())));
   }
   log_.Sync();
 }

src/audit/log.hpp

@@ -27,8 +27,7 @@ class Log {
   };
 
  public:
-  Log(const std::filesystem::path &storage_directory, int32_t buffer_size,
-      int32_t buffer_flush_interval_millis);
+  Log(const std::filesystem::path &storage_directory, int32_t buffer_size, int32_t buffer_flush_interval_millis);
 
   ~Log();
 
@@ -43,8 +42,8 @@ class Log {
   void Start();
 
   /// Adds an entry to the audit log. Thread-safe.
-  void Record(const std::string &address, const std::string &username,
-              const std::string &query, const storage::PropertyValue &params);
+  void Record(const std::string &address, const std::string &username, const std::string &query,
+              const storage::PropertyValue &params);
 
   /// Reopens the log file. Used for log file rotation. Thread-safe.
   void ReopenLog();

src/auth/CMakeLists.txt

@@ -7,7 +7,7 @@ set(auth_src_files
 find_package(Seccomp REQUIRED)
 
 add_library(mg-auth STATIC ${auth_src_files})
-target_link_libraries(mg-auth json libbcrypt glog gflags fmt)
+target_link_libraries(mg-auth json libbcrypt gflags fmt)
 target_link_libraries(mg-auth mg-utils mg-kvstore)
 
 target_link_libraries(mg-auth ${Seccomp_LIBRARIES})

src/auth/auth.cpp

@@ -6,32 +6,26 @@
 #include <utility>
 
 #include <fmt/format.h>
-#include <glog/logging.h>
 
 #include "auth/exceptions.hpp"
 #include "utils/flag_validation.hpp"
+#include "utils/logging.hpp"
 #include "utils/string.hpp"
 
-DEFINE_VALIDATED_string(
-    auth_module_executable, "",
-    "Absolute path to the auth module executable that should be used.", {
-      if (value.empty()) return true;
-      // Check the file status, following symlinks.
-      auto status = std::filesystem::status(value);
-      if (!std::filesystem::is_regular_file(status)) {
-        std::cerr << "The auth module path doesn't exist or isn't a file!"
-                  << std::endl;
-        return false;
-      }
-      return true;
-    });
-DEFINE_bool(auth_module_create_missing_user, true,
-            "Set to false to disable creation of missing users.");
-DEFINE_bool(auth_module_create_missing_role, true,
-            "Set to false to disable creation of missing roles.");
-DEFINE_bool(
-    auth_module_manage_roles, true,
-    "Set to false to disable management of roles through the auth module.");
+DEFINE_VALIDATED_string(auth_module_executable, "", "Absolute path to the auth module executable that should be used.",
+                        {
+                          if (value.empty()) return true;
+                          // Check the file status, following symlinks.
+                          auto status = std::filesystem::status(value);
+                          if (!std::filesystem::is_regular_file(status)) {
+                            std::cerr << "The auth module path doesn't exist or isn't a file!" << std::endl;
+                            return false;
+                          }
+                          return true;
+                        });
+DEFINE_bool(auth_module_create_missing_user, true, "Set to false to disable creation of missing users.");
+DEFINE_bool(auth_module_create_missing_role, true, "Set to false to disable creation of missing roles.");
+DEFINE_bool(auth_module_manage_roles, true, "Set to false to disable management of roles through the auth module.");
 DEFINE_VALIDATED_int32(auth_module_timeout_ms, 10000,
                        "Timeout (in milliseconds) used when waiting for a "
                        "response from the auth module.",
@@ -60,11 +54,9 @@ const std::string kLinkPrefix = "link:";
  * key="link:<username>", value="<rolename>"
  */
 
-Auth::Auth(const std::string &storage_directory)
-    : storage_(storage_directory), module_(FLAGS_auth_module_executable) {}
+Auth::Auth(const std::string &storage_directory) : storage_(storage_directory), module_(FLAGS_auth_module_executable) {}
 
-std::optional<User> Auth::Authenticate(const std::string &username,
-                                       const std::string &password) {
+std::optional<User> Auth::Authenticate(const std::string &username, const std::string &password) {
   if (module_.IsUsed()) {
     nlohmann::json params = nlohmann::json::object();
     params["username"] = username;
@@ -73,8 +65,7 @@ std::optional<User> Auth::Authenticate(const std::string &username,
     auto ret = module_.Call(params, FLAGS_auth_module_timeout_ms);
 
     // Verify response integrity.
-    if (!ret.is_object() || ret.find("authenticated") == ret.end() ||
-        ret.find("role") == ret.end()) {
+    if (!ret.is_object() || ret.find("authenticated") == ret.end() || ret.find("role") == ret.end()) {
       return std::nullopt;
     }
     const auto &ret_authenticated = ret.at("authenticated");
@@ -94,15 +85,17 @@ std::optional<User> Auth::Authenticate(const std::string &username,
       if (FLAGS_auth_module_create_missing_user) {
         user = AddUser(username, password);
         if (!user) {
-          LOG(WARNING) << "Couldn't authenticate user '" << username
-                       << "' using the auth module because the user already "
-                          "exists as a role!";
+          spdlog::warn(
+              "Couldn't authenticate user '{}' using the auth module because "
+              "the user already exists as a role!",
+              username);
           return std::nullopt;
         }
       } else {
-        LOG(WARNING)
-            << "Couldn't authenticate user '" << username
-            << "' using the auth module because the user doesn't exist!";
+        spdlog::warn(
+            "Couldn't authenticate user '{}' using the auth module because the "
+            "user doesn't exist!",
+            username);
         return std::nullopt;
       }
     } else {
@@ -115,17 +108,18 @@ std::optional<User> Auth::Authenticate(const std::string &username,
           if (FLAGS_auth_module_create_missing_role) {
             role = AddRole(rolename);
             if (!role) {
-              LOG(WARNING)
-                  << "Couldn't authenticate user '" << username
-                  << "' using the auth module because the user's role '"
-                  << rolename << "' already exists as a user!";
+              spdlog::warn(
+                  "Couldn't authenticate user '{}' using the auth module "
+                  "because the user's role '{}' already exists as a user!",
+                  username, rolename);
               return std::nullopt;
             }
             SaveRole(*role);
           } else {
-            LOG(WARNING) << "Couldn't authenticate user '" << username
-                         << "' using the auth module because the user's role '"
-                         << rolename << "' doesn't exist!";
+            spdlog::warn(
+                "Couldn't authenticate user '{}' using the auth module because "
+                "the user's role '{}' doesn't exist!",
+                username, rolename);
             return std::nullopt;
           }
         }
@@ -138,8 +132,14 @@ std::optional<User> Auth::Authenticate(const std::string &username,
     return user;
   } else {
     auto user = GetUser(username);
-    if (!user) return std::nullopt;
-    if (!user->CheckPassword(password)) return std::nullopt;
+    if (!user) {
+      spdlog::warn("Couldn't authenticate user '{}' because the user doesn't exist", username);
+      return std::nullopt;
+    }
+    if (!user->CheckPassword(password)) {
+      spdlog::warn("Couldn't authenticate user '{}'", username);
+      return std::nullopt;
+    }
     return user;
   }
 }
@@ -171,21 +171,18 @@ std::optional<User> Auth::GetUser(const std::string &username_orig) {
 void Auth::SaveUser(const User &user) {
   bool success = false;
   if (user.role()) {
-    success = storage_.PutMultiple(
-        {{kUserPrefix + user.username(), user.Serialize().dump()},
-         {kLinkPrefix + user.username(), user.role()->rolename()}});
+    success = storage_.PutMultiple({{kUserPrefix + user.username(), user.Serialize().dump()},
+                                    {kLinkPrefix + user.username(), user.role()->rolename()}});
   } else {
-    success = storage_.PutAndDeleteMultiple(
-        {{kUserPrefix + user.username(), user.Serialize().dump()}},
-        {kLinkPrefix + user.username()});
+    success = storage_.PutAndDeleteMultiple({{kUserPrefix + user.username(), user.Serialize().dump()}},
+                                            {kLinkPrefix + user.username()});
   }
   if (!success) {
     throw AuthException("Couldn't save user '{}'!", user.username());
   }
 }
 
-std::optional<User> Auth::AddUser(const std::string &username,
-                                  const std::optional<std::string> &password) {
+std::optional<User> Auth::AddUser(const std::string &username, const std::optional<std::string> &password) {
   auto existing_user = GetUser(username);
   if (existing_user) return std::nullopt;
   auto existing_role = GetRole(username);
@@ -199,8 +196,7 @@ std::optional<User> Auth::AddUser(const std::string &username,
 bool Auth::RemoveUser(const std::string &username_orig) {
   auto username = utils::ToLowerCase(username_orig);
   if (!storage_.Get(kUserPrefix + username)) return false;
-  std::vector<std::string> keys(
-      {kLinkPrefix + username, kUserPrefix + username});
+  std::vector<std::string> keys({kLinkPrefix + username, kUserPrefix + username});
   if (!storage_.DeleteMultiple(keys)) {
     throw AuthException("Couldn't remove user '{}'!", username);
   }
@@ -209,8 +205,7 @@ bool Auth::RemoveUser(const std::string &username_orig) {
 
 std::vector<auth::User> Auth::AllUsers() {
   std::vector<auth::User> ret;
-  for (auto it = storage_.begin(kUserPrefix); it != storage_.end(kUserPrefix);
-       ++it) {
+  for (auto it = storage_.begin(kUserPrefix); it != storage_.end(kUserPrefix); ++it) {
     auto username = it->first.substr(kUserPrefix.size());
     if (username != utils::ToLowerCase(username)) continue;
     auto user = GetUser(username);
@@ -221,9 +216,7 @@ std::vector<auth::User> Auth::AllUsers() {
   return ret;
 }
 
-bool Auth::HasUsers() {
-  return storage_.begin(kUserPrefix) != storage_.end(kUserPrefix);
-}
+bool Auth::HasUsers() { return storage_.begin(kUserPrefix) != storage_.end(kUserPrefix); }
 
 std::optional<Role> Auth::GetRole(const std::string &rolename_orig) {
   auto rolename = utils::ToLowerCase(rolename_orig);
@@ -260,8 +253,7 @@ bool Auth::RemoveRole(const std::string &rolename_orig) {
   auto rolename = utils::ToLowerCase(rolename_orig);
   if (!storage_.Get(kRolePrefix + rolename)) return false;
   std::vector<std::string> keys;
-  for (auto it = storage_.begin(kLinkPrefix); it != storage_.end(kLinkPrefix);
-       ++it) {
+  for (auto it = storage_.begin(kLinkPrefix); it != storage_.end(kLinkPrefix); ++it) {
     if (utils::ToLowerCase(it->second) == rolename) {
       keys.push_back(it->first);
     }
@@ -275,8 +267,7 @@ bool Auth::RemoveRole(const std::string &rolename_orig) {
 
 std::vector<auth::Role> Auth::AllRoles() {
   std::vector<auth::Role> ret;
-  for (auto it = storage_.begin(kRolePrefix); it != storage_.end(kRolePrefix);
-       ++it) {
+  for (auto it = storage_.begin(kRolePrefix); it != storage_.end(kRolePrefix); ++it) {
     auto rolename = it->first.substr(kRolePrefix.size());
     if (rolename != utils::ToLowerCase(rolename)) continue;
     auto role = GetRole(rolename);
@@ -289,12 +280,10 @@ std::vector<auth::Role> Auth::AllRoles() {
   return ret;
 }
 
-std::vector<auth::User> Auth::AllUsersForRole(
-    const std::string &rolename_orig) {
+std::vector<auth::User> Auth::AllUsersForRole(const std::string &rolename_orig) {
   auto rolename = utils::ToLowerCase(rolename_orig);
   std::vector<auth::User> ret;
-  for (auto it = storage_.begin(kLinkPrefix); it != storage_.end(kLinkPrefix);
-       ++it) {
+  for (auto it = storage_.begin(kLinkPrefix); it != storage_.end(kLinkPrefix); ++it) {
     auto username = it->first.substr(kLinkPrefix.size());
     if (username != utils::ToLowerCase(username)) continue;
     if (it->second != utils::ToLowerCase(it->second)) continue;

src/auth/auth.hpp

@@ -32,8 +32,7 @@ class Auth final {
    * @return a user when the username and password match, nullopt otherwise
    * @throw AuthException if unable to authenticate for whatever reason.
    */
-  std::optional<User> Authenticate(const std::string &username,
-                                   const std::string &password);
+  std::optional<User> Authenticate(const std::string &username, const std::string &password);
 
   /**
    * Gets a user from the storage.
@@ -63,9 +62,7 @@ class Auth final {
    * @return a user when the user is created, nullopt if the user exists
    * @throw AuthException if unable to save the user.
    */
-  std::optional<User> AddUser(
-      const std::string &username,
-      const std::optional<std::string> &password = std::nullopt);
+  std::optional<User> AddUser(const std::string &username, const std::optional<std::string> &password = std::nullopt);
 
   /**
    * Removes a user from the storage.

src/auth/models.cpp

@@ -9,8 +9,7 @@
 #include "utils/cast.hpp"
 #include "utils/string.hpp"
 
-DEFINE_bool(auth_password_permit_null, true,
-            "Set to false to disable null passwords.");
+DEFINE_bool(auth_password_permit_null, true, "Set to false to disable null passwords.");
 
 DEFINE_string(auth_password_strength_regex, ".+",
               "The regular expression that should be used to match the entire "
@@ -40,6 +39,14 @@ std::string PermissionToString(Permission permission) {
       return "CONSTRAINT";
     case Permission::DUMP:
       return "DUMP";
+    case Permission::REPLICATION:
+      return "REPLICATION";
+    case Permission::LOCK_PATH:
+      return "LOCK_PATH";
+    case Permission::READ_FILE:
+      return "READ_FILE";
+    case Permission::FREE_MEMORY:
+      return "FREE_MEMORY";
     case Permission::AUTH:
       return "AUTH";
   }
@@ -125,8 +132,7 @@ Permissions Permissions::Deserialize(const nlohmann::json &data) {
   if (!data.is_object()) {
     throw AuthException("Couldn't load permissions data!");
   }
-  if (!data["grants"].is_number_unsigned() ||
-      !data["denies"].is_number_unsigned()) {
+  if (!data["grants"].is_number_unsigned() || !data["denies"].is_number_unsigned()) {
     throw AuthException("Couldn't load permissions data!");
   }
   return {data["grants"], data["denies"]};
@@ -139,12 +145,9 @@ bool operator==(const Permissions &first, const Permissions &second) {
   return first.grants() == second.grants() && first.denies() == second.denies();
 }
 
-bool operator!=(const Permissions &first, const Permissions &second) {
-  return !(first == second);
-}
+bool operator!=(const Permissions &first, const Permissions &second) { return !(first == second); }
 
-Role::Role(const std::string &rolename)
-    : rolename_(utils::ToLowerCase(rolename)) {}
+Role::Role(const std::string &rolename) : rolename_(utils::ToLowerCase(rolename)) {}
 
 Role::Role(const std::string &rolename, const Permissions &permissions)
     : rolename_(utils::ToLowerCase(rolename)), permissions_(permissions) {}
@@ -172,18 +175,13 @@ Role Role::Deserialize(const nlohmann::json &data) {
 }
 
 bool operator==(const Role &first, const Role &second) {
-  return first.rolename_ == second.rolename_ &&
-         first.permissions_ == second.permissions_;
+  return first.rolename_ == second.rolename_ && first.permissions_ == second.permissions_;
 }
 
-User::User(const std::string &username)
-    : username_(utils::ToLowerCase(username)) {}
+User::User(const std::string &username) : username_(utils::ToLowerCase(username)) {}
 
-User::User(const std::string &username, const std::string &password_hash,
-           const Permissions &permissions)
-    : username_(utils::ToLowerCase(username)),
-      password_hash_(password_hash),
-      permissions_(permissions) {}
+User::User(const std::string &username, const std::string &password_hash, const Permissions &permissions)
+    : username_(utils::ToLowerCase(username)), password_hash_(password_hash), permissions_(permissions) {}
 
 bool User::CheckPassword(const std::string &password) {
   if (password_hash_ == "") return true;
@@ -240,8 +238,7 @@ User User::Deserialize(const nlohmann::json &data) {
   if (!data.is_object()) {
     throw AuthException("Couldn't load user data!");
   }
-  if (!data["username"].is_string() || !data["password_hash"].is_string() ||
-      !data["permissions"].is_object()) {
+  if (!data["username"].is_string() || !data["password_hash"].is_string() || !data["permissions"].is_object()) {
     throw AuthException("Couldn't load user data!");
   }
   auto permissions = Permissions::Deserialize(data["permissions"]);
@@ -249,9 +246,7 @@ User User::Deserialize(const nlohmann::json &data) {
 }
 
 bool operator==(const User &first, const User &second) {
-  return first.username_ == second.username_ &&
-         first.password_hash_ == second.password_hash_ &&
-         first.permissions_ == second.permissions_ &&
-         first.role_ == second.role_;
+  return first.username_ == second.username_ && first.password_hash_ == second.password_hash_ &&
+         first.permissions_ == second.permissions_ && first.role_ == second.role_;
 }
 }  // namespace auth

src/auth/models.hpp

@@ -9,26 +9,32 @@ namespace auth {
 
 // These permissions must have values that are applicable for usage in a
 // bitmask.
+// clang-format off
 enum class Permission : uint64_t {
-  MATCH = 0x00000001,
-  CREATE = 0x00000002,
-  MERGE = 0x00000004,
-  DELETE = 0x00000008,
-  SET = 0x00000010,
-  REMOVE = 0x00000020,
-  INDEX = 0x00000040,
-  STATS = 0x00000080,
-  CONSTRAINT = 0x00000100,
-  DUMP = 0x00000200,
-  AUTH = 0x00010000,
+  MATCH       = 1,
+  CREATE      = 1U << 1U,
+  MERGE       = 1U << 2U,
+  DELETE      = 1U << 3U,
+  SET         = 1U << 4U,
+  REMOVE      = 1U << 5U,
+  INDEX       = 1U << 6U,
+  STATS       = 1U << 7U,
+  CONSTRAINT  = 1U << 8U,
+  DUMP        = 1U << 9U,
+  REPLICATION = 1U << 10U,
+  LOCK_PATH   = 1U << 11U,
+  READ_FILE   = 1U << 12U,
+  FREE_MEMORY = 1U << 13U,
+  AUTH        = 1U << 16U
 };
+// clang-format on
 
 // Constant list of all available permissions.
-const std::vector<Permission> kPermissionsAll = {
-    Permission::MATCH,  Permission::CREATE, Permission::MERGE,
-    Permission::DELETE, Permission::SET,    Permission::REMOVE,
-    Permission::INDEX,  Permission::STATS,  Permission::CONSTRAINT,
-    Permission::DUMP,   Permission::AUTH};
+const std::vector<Permission> kPermissionsAll = {Permission::MATCH,     Permission::CREATE,    Permission::MERGE,
+                                                 Permission::DELETE,    Permission::SET,       Permission::REMOVE,
+                                                 Permission::INDEX,     Permission::STATS,     Permission::CONSTRAINT,
+                                                 Permission::DUMP,      Permission::AUTH,      Permission::REPLICATION,
+                                                 Permission::LOCK_PATH, Permission::READ_FILE, Permission::FREE_MEMORY};
 
 // Function that converts a permission to its string representation.
 std::string PermissionToString(Permission permission);
@@ -105,15 +111,13 @@ class User final {
  public:
   User(const std::string &username);
 
-  User(const std::string &username, const std::string &password_hash,
-       const Permissions &permissions);
+  User(const std::string &username, const std::string &password_hash, const Permissions &permissions);
 
   /// @throw AuthException if unable to verify the password.
   bool CheckPassword(const std::string &password);
 
   /// @throw AuthException if unable to set the password.
-  void UpdatePassword(
-      const std::optional<std::string> &password = std::nullopt);
+  void UpdatePassword(const std::optional<std::string> &password = std::nullopt);
 
   void SetRole(const Role &role);
 

src/auth/module.cpp

@@ -24,7 +24,8 @@
 
 #include <fmt/format.h>
 #include <gflags/gflags.h>
-#include <glog/logging.h>
+
+#include "utils/logging.hpp"
 
 namespace {
 
@@ -85,54 +86,22 @@ class CharPP final {
 ////////////////////////////////////
 
 const std::vector<int> kSeccompSyscallsBlacklist = {
-    SCMP_SYS(mknod),
-    SCMP_SYS(mount),
-    SCMP_SYS(setuid),
-    SCMP_SYS(stime),
-    SCMP_SYS(ptrace),
-    SCMP_SYS(setgid),
-    SCMP_SYS(acct),
-    SCMP_SYS(umount),
-    SCMP_SYS(setpgid),
-    SCMP_SYS(chroot),
-    SCMP_SYS(setreuid),
-    SCMP_SYS(setregid),
-    SCMP_SYS(sethostname),
-    SCMP_SYS(settimeofday),
-    SCMP_SYS(setgroups),
-    SCMP_SYS(swapon),
-    SCMP_SYS(reboot),
-    SCMP_SYS(setpriority),
-    SCMP_SYS(ioperm),
-    SCMP_SYS(syslog),
-    SCMP_SYS(iopl),
-    SCMP_SYS(vhangup),
-    SCMP_SYS(vm86old),
-    SCMP_SYS(swapoff),
-    SCMP_SYS(setdomainname),
-    SCMP_SYS(adjtimex),
-    SCMP_SYS(init_module),
-    SCMP_SYS(delete_module),
-    SCMP_SYS(setfsuid),
-    SCMP_SYS(setfsgid),
-    SCMP_SYS(setresuid),
-    SCMP_SYS(vm86),
-    SCMP_SYS(setresgid),
-    SCMP_SYS(capset),
-    SCMP_SYS(setreuid),
-    SCMP_SYS(setregid),
-    SCMP_SYS(setgroups),
-    SCMP_SYS(setresuid),
-    SCMP_SYS(setresgid),
-    SCMP_SYS(setuid),
-    SCMP_SYS(setgid),
-    SCMP_SYS(setfsuid),
-    SCMP_SYS(setfsgid),
-    SCMP_SYS(pivot_root),
-    SCMP_SYS(sched_setaffinity),
-    SCMP_SYS(clock_settime),
-    SCMP_SYS(kexec_load),
-    SCMP_SYS(mknodat),
+    SCMP_SYS(mknod),         SCMP_SYS(mount),        SCMP_SYS(setuid),
+    SCMP_SYS(stime),         SCMP_SYS(ptrace),       SCMP_SYS(setgid),
+    SCMP_SYS(acct),          SCMP_SYS(umount),       SCMP_SYS(setpgid),
+    SCMP_SYS(chroot),        SCMP_SYS(setreuid),     SCMP_SYS(setregid),
+    SCMP_SYS(sethostname),   SCMP_SYS(settimeofday), SCMP_SYS(setgroups),
+    SCMP_SYS(swapon),        SCMP_SYS(reboot),       SCMP_SYS(setpriority),
+    SCMP_SYS(ioperm),        SCMP_SYS(syslog),       SCMP_SYS(iopl),
+    SCMP_SYS(vhangup),       SCMP_SYS(vm86old),      SCMP_SYS(swapoff),
+    SCMP_SYS(setdomainname), SCMP_SYS(adjtimex),     SCMP_SYS(init_module),
+    SCMP_SYS(delete_module), SCMP_SYS(setfsuid),     SCMP_SYS(setfsgid),
+    SCMP_SYS(setresuid),     SCMP_SYS(vm86),         SCMP_SYS(setresgid),
+    SCMP_SYS(capset),        SCMP_SYS(setreuid),     SCMP_SYS(setregid),
+    SCMP_SYS(setgroups),     SCMP_SYS(setresuid),    SCMP_SYS(setresgid),
+    SCMP_SYS(setuid),        SCMP_SYS(setgid),       SCMP_SYS(setfsuid),
+    SCMP_SYS(setfsgid),      SCMP_SYS(pivot_root),   SCMP_SYS(sched_setaffinity),
+    SCMP_SYS(clock_settime), SCMP_SYS(kexec_load),   SCMP_SYS(mknodat),
     SCMP_SYS(unshare),
 #ifdef SYS_seccomp
     SCMP_SYS(seccomp),
@@ -181,24 +150,20 @@ int Target(void *arg) {
   // Redirect `stdin` to `/dev/null`.
   int fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
   if (fd == -1) {
-    std::cerr
-        << "Couldn't open \"/dev/null\" for auth module stdin because of: "
-        << strerror(errno) << " (" << errno << ")!" << std::endl;
+    std::cerr << "Couldn't open \"/dev/null\" for auth module stdin because of: " << strerror(errno) << " (" << errno
+              << ")!" << std::endl;
     return EXIT_FAILURE;
   }
   if (dup2(fd, STDIN_FILENO) != STDIN_FILENO) {
-    std::cerr
-        << "Couldn't attach \"/dev/null\" to auth module stdin because of: "
-        << strerror(errno) << " (" << errno << ")!" << std::endl;
+    std::cerr << "Couldn't attach \"/dev/null\" to auth module stdin because of: " << strerror(errno) << " (" << errno
+              << ")!" << std::endl;
     return EXIT_FAILURE;
   }
 
   // Change the current directory to the module directory.
   if (chdir(ta->module_executable_path.parent_path().c_str()) != 0) {
-    std::cerr << "Couldn't change directory to "
-              << ta->module_executable_path.parent_path()
-              << " for auth module stdin because of: " << strerror(errno)
-              << " (" << errno << ")!" << std::endl;
+    std::cerr << "Couldn't change directory to " << ta->module_executable_path.parent_path()
+              << " for auth module stdin because of: " << strerror(errno) << " (" << errno << ")!" << std::endl;
     return EXIT_FAILURE;
   }
 
@@ -213,8 +178,7 @@ int Target(void *arg) {
   }
 
   // Connect the communication input pipe.
-  if (dup2(ta->pipe_to_module, kCommunicationToModuleFd) !=
-      kCommunicationToModuleFd) {
+  if (dup2(ta->pipe_to_module, kCommunicationToModuleFd) != kCommunicationToModuleFd) {
     std::cerr << "Couldn't attach communication to module pipe to auth module "
                  "because of: "
               << strerror(errno) << " (" << errno << ")!" << std::endl;
@@ -222,8 +186,7 @@ int Target(void *arg) {
   }
 
   // Connect the communication output pipe.
-  if (dup2(ta->pipe_from_module, kCommunicationFromModuleFd) !=
-      kCommunicationFromModuleFd) {
+  if (dup2(ta->pipe_from_module, kCommunicationFromModuleFd) != kCommunicationFromModuleFd) {
     std::cerr << "Couldn't attach communication from module pipe to auth "
                  "module because of: "
               << strerror(errno) << " (" << errno << ")!" << std::endl;
@@ -245,8 +208,8 @@ int Target(void *arg) {
   sigemptyset(&action.sa_mask);
   action.sa_flags = 0;
   if (sigaction(SIGINT, &action, nullptr) != 0) {
-    std::cerr << "Couldn't ignore SIGINT for auth module because of: "
-              << strerror(errno) << " (" << errno << ")!" << std::endl;
+    std::cerr << "Couldn't ignore SIGINT for auth module because of: " << strerror(errno) << " (" << errno << ")!"
+              << std::endl;
     return EXIT_FAILURE;
   }
 
@@ -260,8 +223,7 @@ int Target(void *arg) {
 
   // If the `execve` call succeeded then the process will exit from that call
   // and won't reach this piece of code ever.
-  std::cerr << "Couldn't start auth module because of: " << strerror(errno)
-            << " (" << errno << ")!" << std::endl;
+  std::cerr << "Couldn't start auth module because of: " << strerror(errno) << " (" << errno << ")!" << std::endl;
 
   return EXIT_FAILURE;
 }
@@ -361,13 +323,15 @@ bool Module::Startup() {
 
   // Setup communication pipes.
   if (pipe2(pipe_to_module_, O_CLOEXEC) != 0) {
-    LOG(ERROR) << "Couldn't create communication pipe from the database to "
-                  "the auth module!";
+    spdlog::error(
+        "Couldn't create communication pipe from the database to "
+        "the auth module!");
     return false;
   }
   if (pipe2(pipe_from_module_, O_CLOEXEC) != 0) {
-    LOG(ERROR) << "Couldn't create communication pipe from the auth module to "
-                  "the database!";
+    spdlog::error(
+        "Couldn't create communication pipe from the auth module to "
+        "the database!");
     close(pipe_to_module_[kPipeReadEnd]);
     close(pipe_to_module_[kPipeWriteEnd]);
     return false;
@@ -384,7 +348,7 @@ bool Module::Startup() {
   // Create the process.
   pid_ = clone(Target, stack_top, CLONE_VFORK, target_arguments_.get());
   if (pid_ == -1) {
-    LOG(ERROR) << "Couldn't start the auth module process!";
+    spdlog::error("Couldn't start the auth module process!");
     close(pipe_to_module_[kPipeReadEnd]);
     close(pipe_to_module_[kPipeWriteEnd]);
     close(pipe_from_module_[kPipeReadEnd]);
@@ -394,7 +358,7 @@ bool Module::Startup() {
 
   // Check whether the process is still running.
   if (waitpid(pid_, &status_, WNOHANG | WUNTRACED) != 0) {
-    LOG(ERROR) << "The auth module process couldn't be started!";
+    spdlog::error("The auth module process couldn't be started!");
     return false;
   }
 
@@ -405,8 +369,7 @@ bool Module::Startup() {
   return true;
 }
 
-nlohmann::json Module::Call(const nlohmann::json &params,
-                            int timeout_millisec) {
+nlohmann::json Module::Call(const nlohmann::json &params, int timeout_millisec) {
   std::lock_guard<std::mutex> guard(lock_);
 
   if (!params.is_object()) return {};
@@ -416,18 +379,18 @@ nlohmann::json Module::Call(const nlohmann::json &params,
 
   // Put the request to the module process.
   if (!PutData(pipe_to_module_[kPipeWriteEnd], params, timeout_millisec)) {
-    LOG(ERROR) << "Couldn't send data to the auth module process!";
+    spdlog::error("Couldn't send data to the auth module process!");
     return {};
   }
 
   // Get the response from the module process.
   auto ret = GetData(pipe_from_module_[kPipeReadEnd], timeout_millisec);
   if (ret.is_null()) {
-    LOG(ERROR) << "Couldn't receive data from the auth module process!";
+    spdlog::error("Couldn't receive data from the auth module process!");
     return {};
   }
   if (!ret.is_object()) {
-    LOG(ERROR) << "Data received from the auth module is of wrong type!";
+    spdlog::error("Data received from the auth module is of wrong type!");
     return {};
   }
   return ret;
@@ -441,7 +404,7 @@ void Module::Shutdown() {
   // Try to terminate the process gracefully in `kTerminateTimeoutSec`.
   std::this_thread::sleep_for(std::chrono::milliseconds(100));
   for (int i = 0; i < kTerminateTimeoutSec * 10; ++i) {
-    LOG(INFO) << "Terminating the auth module process with pid " << pid_;
+    spdlog::info("Terminating the auth module process with pid {}", pid_);
     kill(pid_, SIGTERM);
     std::this_thread::sleep_for(std::chrono::milliseconds(100));
     int ret = waitpid(pid_, &status_, WNOHANG | WUNTRACED);
@@ -452,7 +415,7 @@ void Module::Shutdown() {
 
   // If the process is still alive, kill it and wait for it to die.
   if (waitpid(pid_, &status_, WNOHANG | WUNTRACED) == 0) {
-    LOG(WARNING) << "Killing the auth module process with pid " << pid_;
+    spdlog::warn("Killing the auth module process with pid {}", pid_);
     kill(pid_, SIGKILL);
     waitpid(pid_, &status_, 0);
   }

src/communication/CMakeLists.txt

@@ -7,7 +7,7 @@ set(communication_src_files
     init.cpp)
 
 add_library(mg-communication STATIC ${communication_src_files})
-target_link_libraries(mg-communication Threads::Threads mg-utils mg-io fmt glog gflags)
+target_link_libraries(mg-communication Threads::Threads mg-utils mg-io fmt gflags)
 
 find_package(OpenSSL REQUIRED)
 target_link_libraries(mg-communication ${OPENSSL_LIBRARIES})

src/communication/bolt/client.hpp

@@ -1,7 +1,5 @@
 #pragma once
 
-#include <glog/logging.h>
-
 #include "communication/bolt/v1/decoder/chunked_decoder_buffer.hpp"
 #include "communication/bolt/v1/decoder/decoder.hpp"
 #include "communication/bolt/v1/encoder/chunked_encoder_buffer.hpp"
@@ -10,6 +8,7 @@
 #include "communication/context.hpp"
 #include "io/network/endpoint.hpp"
 #include "utils/exceptions.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -23,7 +22,7 @@ class ClientQueryException : public utils::BasicException {
   ClientQueryException() : utils::BasicException("Couldn't execute query!") {}
 
   template <class... Args>
-  ClientQueryException(const std::string &code, Args &&... args)
+  ClientQueryException(const std::string &code, Args &&...args)
       : utils::BasicException(std::forward<Args>(args)...), code_(code) {}
 
   const std::string &code() const { return code_; }
@@ -44,16 +43,14 @@ class ClientFatalException : public utils::BasicException {
 // only handle the `ClientFatalException`.
 class ServerCommunicationException : public ClientFatalException {
  public:
-  ServerCommunicationException()
-      : ClientFatalException("Couldn't communicate with the server!") {}
+  ServerCommunicationException() : ClientFatalException("Couldn't communicate with the server!") {}
 };
 
 // Internal exception used whenever a malformed data error occurs. You should
 // only handle the `ClientFatalException`.
 class ServerMalformedDataException : public ClientFatalException {
  public:
-  ServerMalformedDataException()
-      : ClientFatalException("The server sent malformed data!") {}
+  ServerMalformedDataException() : ClientFatalException("The server sent malformed data!") {}
 };
 
 /// Structure that is used to return results from an executed query.
@@ -80,54 +77,50 @@ class Client final {
   /// connection is set-up, multiple queries may be executed through a single
   /// established connection.
   /// @throws ClientFatalException when we couldn't connect to the server
-  void Connect(const io::network::Endpoint &endpoint,
-               const std::string &username, const std::string &password,
+  void Connect(const io::network::Endpoint &endpoint, const std::string &username, const std::string &password,
                const std::string &client_name = "memgraph-bolt") {
     if (!client_.Connect(endpoint)) {
       throw ClientFatalException("Couldn't connect to {}!", endpoint);
     }
 
     if (!client_.Write(kPreamble, sizeof(kPreamble), true)) {
-      DLOG(ERROR) << "Couldn't send preamble!";
+      SPDLOG_ERROR("Couldn't send preamble!");
       throw ServerCommunicationException();
     }
     for (int i = 0; i < 4; ++i) {
       if (!client_.Write(kProtocol, sizeof(kProtocol), i != 3)) {
-        DLOG(ERROR) << "Couldn't send protocol version!";
+        SPDLOG_ERROR("Couldn't send protocol version!");
         throw ServerCommunicationException();
       }
     }
 
     if (!client_.Read(sizeof(kProtocol))) {
-      DLOG(ERROR) << "Couldn't get negotiated protocol version!";
+      SPDLOG_ERROR("Couldn't get negotiated protocol version!");
       throw ServerCommunicationException();
     }
     if (memcmp(kProtocol, client_.GetData(), sizeof(kProtocol)) != 0) {
-      DLOG(ERROR) << "Server negotiated unsupported protocol version!";
-      throw ClientFatalException(
-          "The server negotiated an usupported protocol version!");
+      SPDLOG_ERROR("Server negotiated unsupported protocol version!");
+      throw ClientFatalException("The server negotiated an usupported protocol version!");
     }
     client_.ShiftData(sizeof(kProtocol));
 
-    if (!encoder_.MessageInit(client_name, {{"scheme", "basic"},
-                                            {"principal", username},
-                                            {"credentials", password}})) {
-      DLOG(ERROR) << "Couldn't send init message!";
+    if (!encoder_.MessageInit(client_name, {{"scheme", "basic"}, {"principal", username}, {"credentials", password}})) {
+      SPDLOG_ERROR("Couldn't send init message!");
       throw ServerCommunicationException();
     }
 
     Signature signature;
     Value metadata;
     if (!ReadMessage(&signature, &metadata)) {
-      DLOG(ERROR) << "Couldn't read init message response!";
+      SPDLOG_ERROR("Couldn't read init message response!");
       throw ServerCommunicationException();
     }
     if (signature != Signature::Success) {
-      DLOG(ERROR) << "Handshake failed!";
+      SPDLOG_ERROR("Handshake failed!");
       throw ClientFatalException("Handshake with the server failed!");
     }
 
-    DLOG(INFO) << "Metadata of init message response: " << metadata;
+    SPDLOG_INFO("Metadata of init message response: {}", metadata);
   }
 
   /// Function used to execute queries against the server. Before you can
@@ -136,20 +129,17 @@ class Client final {
   ///                              executing the query (eg. mistyped query,
   ///                              etc.)
   /// @throws ClientFatalException when we couldn't communicate with the server
-  QueryData Execute(const std::string &query,
-                    const std::map<std::string, Value> &parameters) {
+  QueryData Execute(const std::string &query, const std::map<std::string, Value> &parameters) {
     if (!client_.IsConnected()) {
-      throw ClientFatalException(
-          "You must first connect to the server before using the client!");
+      throw ClientFatalException("You must first connect to the server before using the client!");
     }
 
-    DLOG(INFO) << "Sending run message with statement: '" << query
-               << "'; parameters: " << parameters;
+    SPDLOG_INFO("Sending run message with statement: '{}'; parameters: {}", query, parameters);
 
     encoder_.MessageRun(query, parameters);
     encoder_.MessagePullAll();
 
-    DLOG(INFO) << "Reading run message response";
+    SPDLOG_INFO("Reading run message response");
     Signature signature;
     Value fields;
     if (!ReadMessage(&signature, &fields)) {
@@ -166,8 +156,7 @@ class Client final {
       if (it != tmp.end()) {
         auto it_code = tmp.find("code");
         if (it_code != tmp.end()) {
-          throw ClientQueryException(it_code->second.ValueString(),
-                                     it->second.ValueString());
+          throw ClientQueryException(it_code->second.ValueString(), it->second.ValueString());
         } else {
           throw ClientQueryException("", it->second.ValueString());
         }
@@ -177,7 +166,7 @@ class Client final {
       throw ServerMalformedDataException();
     }
 
-    DLOG(INFO) << "Reading pull_all message response";
+    SPDLOG_INFO("Reading pull_all message response");
     Marker marker;
     Value metadata;
     std::vector<std::vector<Value>> records;
@@ -210,8 +199,7 @@ class Client final {
         if (it != tmp.end()) {
           auto it_code = tmp.find("code");
           if (it_code != tmp.end()) {
-            throw ClientQueryException(it_code->second.ValueString(),
-                                       it->second.ValueString());
+            throw ClientQueryException(it_code->second.ValueString(), it->second.ValueString());
           } else {
             throw ClientQueryException("", it->second.ValueString());
           }
@@ -309,15 +297,11 @@ class Client final {
   communication::ClientOutputStream output_stream_{client_};
 
   // decoder objects
-  ChunkedDecoderBuffer<communication::ClientInputStream> decoder_buffer_{
-      input_stream_};
-  Decoder<ChunkedDecoderBuffer<communication::ClientInputStream>> decoder_{
-      decoder_buffer_};
+  ChunkedDecoderBuffer<communication::ClientInputStream> decoder_buffer_{input_stream_};
+  Decoder<ChunkedDecoderBuffer<communication::ClientInputStream>> decoder_{decoder_buffer_};
 
   // encoder objects
-  ChunkedEncoderBuffer<communication::ClientOutputStream> encoder_buffer_{
-      output_stream_};
-  ClientEncoder<ChunkedEncoderBuffer<communication::ClientOutputStream>>
-      encoder_{encoder_buffer_};
+  ChunkedEncoderBuffer<communication::ClientOutputStream> encoder_buffer_{output_stream_};
+  ClientEncoder<ChunkedEncoderBuffer<communication::ClientOutputStream>> encoder_{encoder_buffer_};
 };
 }  // namespace communication::bolt

src/communication/bolt/ha_client.hpp

@@ -1,181 +0,0 @@
-#pragma once
-
-#include <chrono>
-#include <memory>
-#include <thread>
-#include <vector>
-
-#include <glog/logging.h>
-
-#include "communication/bolt/client.hpp"
-
-namespace communication::bolt {
-
-/// HA Bolt client.
-/// It has methods used to execute queries against a cluster of servers. It
-/// supports both SSL and plaintext connections.
-class HAClient final {
- public:
-  HAClient(const std::vector<io::network::Endpoint> &endpoints,
-           communication::ClientContext *context, const std::string &username,
-           const std::string &password, uint64_t num_retries,
-           const std::chrono::milliseconds &retry_delay,
-           const std::string &client_name = "memgraph-bolt")
-      : endpoints_(endpoints),
-        context_(context),
-        username_(username),
-        password_(password),
-        num_retries_(num_retries),
-        retry_delay_(retry_delay),
-        client_name_(client_name) {
-    if (endpoints.size() < 3) {
-      throw ClientFatalException(
-          "You should specify at least three server endpoints to connect to!");
-    }
-    // Create all clients.
-    for (size_t i = 0; i < endpoints.size(); ++i) {
-      clients_.push_back(std::make_unique<Client>(context_));
-    }
-  }
-
-  HAClient(const HAClient &) = delete;
-  HAClient(HAClient &&) = delete;
-  HAClient &operator=(const HAClient &) = delete;
-  HAClient &operator=(HAClient &&) = delete;
-
-  /// Function used to execute queries against the leader server.
-  /// @throws ClientQueryException when there is some transient error while
-  ///                              executing the query (eg. mistyped query,
-  ///                              etc.)
-  /// @throws ClientFatalException when we couldn't communicate with the leader
-  ///                              server even after `num_retries` tries
-  QueryData Execute(const std::string &query,
-                    const std::map<std::string, Value> &parameters) {
-    for (int i = 0; i < num_retries_; ++i) {
-      // Try to find a leader.
-      if (!leader_) {
-        for (int j = 0; j < num_retries_; ++j) {
-          if (!(i == 0 && j == 0)) {
-            std::this_thread::sleep_for(
-                std::chrono::milliseconds(retry_delay_));
-          }
-          try {
-            FindLeader();
-            break;
-          } catch (const ClientFatalException &e) {
-            continue;
-          }
-        }
-        if (!leader_) {
-          throw ClientFatalException("Couldn't find leader after {} tries!",
-                                     num_retries_);
-        }
-      }
-      // Try to execute the query.
-      try {
-        return leader_->Execute(query, parameters);
-      } catch (const utils::BasicException &e) {
-        // Check if this is a cluster failure or a Raft failure.
-        auto qe = dynamic_cast<const ClientQueryException *>(&e);
-        if (dynamic_cast<const ClientFatalException *>(&e) ||
-            (qe && qe->code() == "Memgraph.DatabaseError.Raft.Error")) {
-          // We need to look for a new leader.
-          leader_ = nullptr;
-          continue;
-        }
-        // If it isn't just forward the exception to the client.
-        throw;
-      }
-    }
-    throw ClientFatalException("Couldn't execute query after {} tries!",
-                               num_retries_);
-  }
-
-  /// Function that returns the current leader ID.
-  ///
-  /// @throws ClientFatalException when we couldn't find the leader server even
-  ///                              after `num_retries` tries
-  uint64_t GetLeaderId() {
-    Execute("SHOW RAFT INFO", {});
-    return leader_id_;
-  }
-
- private:
-  void FindLeader() {
-    // Reconnect clients that aren't available
-    bool connected = false;
-    for (size_t i = 0; i < clients_.size(); ++i) {
-      const auto &ep = endpoints_[i];
-      const auto &client = clients_[i];
-      try {
-        client->Execute("SHOW RAFT INFO", {});
-        connected = true;
-        continue;
-      } catch (const ClientQueryException &e) {
-        continue;
-      } catch (const ClientFatalException &e) {
-        client->Close();
-        try {
-          client->Connect(ep, username_, password_, client_name_);
-          connected = true;
-        } catch (const utils::BasicException &) {
-          // Suppress any exceptions.
-        }
-      }
-    }
-    if (!connected) {
-      throw ClientFatalException("Couldn't connect to any server!");
-    }
-
-    // Determine which server is the leader
-    leader_ = nullptr;
-    uint64_t leader_id = 0;
-    int64_t leader_term = -1;
-    for (uint64_t i = 0; i < clients_.size(); ++i) {
-      auto &client = clients_[i];
-      try {
-        auto ret = client->Execute("SHOW RAFT INFO", {});
-        int64_t term_id = -1;
-        bool is_leader = false;
-        for (const auto &rec : ret.records) {
-          if (rec.size() != 2) continue;
-          if (!rec[0].IsString()) continue;
-          const auto &key = rec[0].ValueString();
-          if (key == "term_id") {
-            if (!rec[1].IsInt()) continue;
-            term_id = rec[1].ValueInt();
-          } else if (key == "is_leader") {
-            if (!rec[1].IsBool()) continue;
-            is_leader = rec[1].ValueBool();
-          } else {
-            continue;
-          }
-        }
-        if (is_leader && term_id > leader_term) {
-          leader_term = term_id;
-          leader_id = i + 1;
-          leader_ = client.get();
-        }
-      } catch (const utils::BasicException &) {
-        continue;
-      }
-    }
-    leader_id_ = leader_id;
-    if (!leader_) {
-      throw ClientFatalException("Couldn't find leader server!");
-    }
-  }
-
-  std::vector<io::network::Endpoint> endpoints_;
-  communication::ClientContext *context_;
-  std::string username_;
-  std::string password_;
-  uint64_t num_retries_;
-  std::chrono::milliseconds retry_delay_;
-  std::string client_name_;
-
-  uint64_t leader_id_ = 0;
-  Client *leader_ = nullptr;
-  std::vector<std::unique_ptr<Client>> clients_;
-};
-}  // namespace communication::bolt

src/communication/bolt/v1/codes.hpp

@@ -78,12 +78,8 @@ enum class Marker : uint8_t {
 };
 
 static constexpr uint8_t MarkerString = 0, MarkerList = 1, MarkerMap = 2;
-static constexpr Marker MarkerTiny[3] = {Marker::TinyString, Marker::TinyList,
-                                         Marker::TinyMap};
-static constexpr Marker Marker8[3] = {Marker::String8, Marker::List8,
-                                      Marker::Map8};
-static constexpr Marker Marker16[3] = {Marker::String16, Marker::List16,
-                                       Marker::Map16};
-static constexpr Marker Marker32[3] = {Marker::String32, Marker::List32,
-                                       Marker::Map32};
+static constexpr Marker MarkerTiny[3] = {Marker::TinyString, Marker::TinyList, Marker::TinyMap};
+static constexpr Marker Marker8[3] = {Marker::String8, Marker::List8, Marker::Map8};
+static constexpr Marker Marker16[3] = {Marker::String16, Marker::List16, Marker::Map16};
+static constexpr Marker Marker32[3] = {Marker::String32, Marker::List32, Marker::Map32};
 }  // namespace communication::bolt

src/communication/bolt/v1/decoder/chunked_decoder_buffer.hpp

@@ -6,7 +6,6 @@
 #include <vector>
 
 #include <fmt/format.h>
-#include <glog/logging.h>
 
 #include "communication/bolt/v1/constants.hpp"
 
@@ -41,9 +40,7 @@ enum class ChunkState : uint8_t {
 template <typename TBuffer>
 class ChunkedDecoderBuffer {
  public:
-  ChunkedDecoderBuffer(TBuffer &buffer) : buffer_(buffer) {
-    data_.reserve(kChunkMaxDataSize);
-  }
+  ChunkedDecoderBuffer(TBuffer &buffer) : buffer_(buffer) { data_.reserve(kChunkMaxDataSize); }
 
   /**
    * Reads data from the internal buffer.

src/communication/bolt/v1/decoder/decoder.hpp

@@ -2,12 +2,11 @@
 
 #include <string>
 
-#include <glog/logging.h>
-
 #include "communication/bolt/v1/codes.hpp"
 #include "communication/bolt/v1/value.hpp"
 #include "utils/cast.hpp"
 #include "utils/endian.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -153,14 +152,13 @@ class Decoder {
 
  private:
   bool ReadNull(const Marker &marker, Value *data) {
-    DCHECK(marker == Marker::Null) << "Received invalid marker!";
+    DMG_ASSERT(marker == Marker::Null, "Received invalid marker!");
     *data = Value();
     return true;
   }
 
   bool ReadBool(const Marker &marker, Value *data) {
-    DCHECK(marker == Marker::False || marker == Marker::True)
-        << "Received invalid marker!";
+    DMG_ASSERT(marker == Marker::False || marker == Marker::True, "Received invalid marker!");
     if (marker == Marker::False) {
       *data = Value(false);
     } else {
@@ -208,7 +206,7 @@ class Decoder {
   bool ReadDouble(const Marker marker, Value *data) {
     uint64_t value;
     double ret;
-    DCHECK(marker == Marker::Float64) << "Received invalid marker!";
+    DMG_ASSERT(marker == Marker::Float64, "Received invalid marker!");
     if (!buffer_.Read(reinterpret_cast<uint8_t *>(&value), sizeof(value))) {
       return false;
     }
@@ -264,14 +262,14 @@ class Decoder {
     // `buffer_.Read(data->ValueString().data())`.
     if (size < kMaxStackBuffer) {
       if (!buffer_.Read(buffer, size)) {
-        DLOG(WARNING) << "[ReadString] Missing data!";
+        SPDLOG_WARN("[ReadString] Missing data!");
         return false;
       }
       *data = Value(std::string(reinterpret_cast<char *>(buffer), size));
     } else {
       std::unique_ptr<uint8_t[]> ret(new uint8_t[size]);
       if (!buffer_.Read(ret.get(), size)) {
-        DLOG(WARNING) << "[ReadString] Missing data!";
+        SPDLOG_WARN("[ReadString] Missing data!");
         return false;
       }
       *data = Value(std::string(reinterpret_cast<char *>(ret.get()), size));

src/communication/bolt/v1/encoder/base_encoder.hpp

@@ -7,8 +7,7 @@
 #include "utils/cast.hpp"
 #include "utils/endian.hpp"
 
-static_assert(std::is_same_v<std::uint8_t, char> ||
-                  std::is_same_v<std::uint8_t, unsigned char>,
+static_assert(std::is_same_v<std::uint8_t, char> || std::is_same_v<std::uint8_t, unsigned char>,
               "communication::bolt::Encoder requires uint8_t to be "
               "implemented as char or unsigned char.");
 
@@ -29,9 +28,7 @@ class BaseEncoder {
 
   void WriteRAW(const uint8_t *data, uint64_t len) { buffer_.Write(data, len); }
 
-  void WriteRAW(const char *data, uint64_t len) {
-    WriteRAW((const uint8_t *)data, len);
-  }
+  void WriteRAW(const char *data, uint64_t len) { WriteRAW((const uint8_t *)data, len); }
 
   void WriteRAW(const uint8_t data) { WriteRAW(&data, 1); }
 
@@ -126,8 +123,7 @@ class BaseEncoder {
 
   void WriteEdge(const Edge &edge, bool unbound = false) {
     WriteRAW(utils::UnderlyingCast(Marker::TinyStruct) + (unbound ? 3 : 5));
-    WriteRAW(utils::UnderlyingCast(unbound ? Signature::UnboundRelationship
-                                           : Signature::Relationship));
+    WriteRAW(utils::UnderlyingCast(unbound ? Signature::UnboundRelationship : Signature::Relationship));
 
     WriteInt(edge.id.AsInt());
     if (!unbound) {

src/communication/bolt/v1/encoder/chunked_encoder_buffer.hpp

@@ -5,8 +5,6 @@
 #include <memory>
 #include <vector>
 
-#include <glog/logging.h>
-
 #include "communication/bolt/v1/constants.hpp"
 
 namespace communication::bolt {
@@ -39,8 +37,7 @@ namespace communication::bolt {
 template <class TOutputStream>
 class ChunkedEncoderBuffer {
  public:
-  ChunkedEncoderBuffer(TOutputStream &output_stream)
-      : output_stream_(output_stream) {}
+  ChunkedEncoderBuffer(TOutputStream &output_stream) : output_stream_(output_stream) {}
 
   /**
    * Writes n values into the buffer. If n is bigger than whole chunk size
@@ -55,12 +52,10 @@ class ChunkedEncoderBuffer {
     while (n > 0) {
       // Define the number of bytes which will be copied into the chunk because
       // the internal storage is a fixed length array.
-      size_t size =
-          n < kChunkMaxDataSize - have_ ? n : kChunkMaxDataSize - have_;
+      size_t size = n < kChunkMaxDataSize - have_ ? n : kChunkMaxDataSize - have_;
 
       // Copy `size` values to the chunk array.
-      std::memcpy(chunk_.data() + kChunkHeaderSize + have_, values + written,
-                  size);
+      std::memcpy(chunk_.data() + kChunkHeaderSize + have_, values + written, size);
 
       // Update positions. The position pointer and incoming size have to be
       // updated because all incoming values have to be processed.
@@ -89,8 +84,7 @@ class ChunkedEncoderBuffer {
     chunk_[1] = have_ & 0xFF;
 
     // Write the data to the stream.
-    auto ret = output_stream_.Write(chunk_.data(), kChunkHeaderSize + have_,
-                                    have_more);
+    auto ret = output_stream_.Write(chunk_.data(), kChunkHeaderSize + have_, have_more);
 
     // Cleanup.
     Clear();

src/communication/bolt/v1/encoder/client_encoder.hpp

@@ -38,8 +38,7 @@ class ClientEncoder : private BaseEncoder<Buffer> {
    * @returns true if the data was successfully sent to the client
    *          when flushing, false otherwise
    */
-  bool MessageInit(const std::string client_name,
-                   const std::map<std::string, Value> &auth_token) {
+  bool MessageInit(const std::string client_name, const std::map<std::string, Value> &auth_token) {
     WriteRAW(utils::UnderlyingCast(Marker::TinyStruct2));
     WriteRAW(utils::UnderlyingCast(Signature::Init));
     WriteString(client_name);
@@ -65,9 +64,7 @@ class ClientEncoder : private BaseEncoder<Buffer> {
    * @returns true if the data was successfully sent to the client
    *          when flushing, false otherwise
    */
-  bool MessageRun(const std::string &statement,
-                  const std::map<std::string, Value> &parameters,
-                  bool have_more = true) {
+  bool MessageRun(const std::string &statement, const std::map<std::string, Value> &parameters, bool have_more = true) {
     WriteRAW(utils::UnderlyingCast(Marker::TinyStruct2));
     WriteRAW(utils::UnderlyingCast(Signature::Run));
     WriteString(statement);

src/communication/bolt/v1/exceptions.hpp

@@ -50,13 +50,10 @@ class VerboseError : public utils::BasicException {
   };
 
   template <class... Args>
-  VerboseError(Classification classification, const std::string &category,
-               const std::string &title, const std::string &format,
-               Args &&... args)
+  VerboseError(Classification classification, const std::string &category, const std::string &title,
+               const std::string &format, Args &&...args)
       : BasicException(format, std::forward<Args>(args)...),
-        code_(fmt::format("Memgraph.{}.{}.{}",
-                          ClassificationToString(classification), category,
-                          title)) {}
+        code_(fmt::format("Memgraph.{}.{}.{}", ClassificationToString(classification), category, title)) {}
 
   const std::string &code() const noexcept { return code_; }
 

src/communication/bolt/v1/session.hpp

@@ -3,8 +3,6 @@
 #include <optional>
 #include <thread>
 
-#include "glog/logging.h"
-
 #include "communication/bolt/v1/constants.hpp"
 #include "communication/bolt/v1/decoder/chunked_decoder_buffer.hpp"
 #include "communication/bolt/v1/decoder/decoder.hpp"
@@ -16,6 +14,7 @@
 #include "communication/bolt/v1/states/handshake.hpp"
 #include "communication/bolt/v1/states/init.hpp"
 #include "utils/exceptions.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -63,9 +62,7 @@ class Session {
    * @param q If set, defines from which query to pull the results,
    * otherwise the last query is used.
    */
-  virtual std::map<std::string, Value> Pull(TEncoder *encoder,
-                                            std::optional<int> n,
-                                            std::optional<int> qid) = 0;
+  virtual std::map<std::string, Value> Pull(TEncoder *encoder, std::optional<int> n, std::optional<int> qid) = 0;
 
   /**
    * Discard results of the processed query.
@@ -75,8 +72,7 @@ class Session {
    * @param q If set, defines from which query to discard the results,
    * otherwise the last query is used.
    */
-  virtual std::map<std::string, Value> Discard(std::optional<int> n,
-                                               std::optional<int> qid) = 0;
+  virtual std::map<std::string, Value> Discard(std::optional<int> n, std::optional<int> qid) = 0;
 
   virtual void BeginTransaction() = 0;
   virtual void CommitTransaction() = 0;
@@ -86,8 +82,7 @@ class Session {
   virtual void Abort() = 0;
 
   /** Return `true` if the user was successfully authenticated. */
-  virtual bool Authenticate(const std::string &username,
-                            const std::string &password) = 0;
+  virtual bool Authenticate(const std::string &username, const std::string &password) = 0;
 
   /** Return the name of the server that should be used for the Bolt INIT
    * message. */
@@ -105,8 +100,7 @@ class Session {
 
       // Receive the handshake.
       if (input_stream_.size() < kHandshakeSize) {
-        DLOG(WARNING) << fmt::format("Received partial handshake of size {}",
-                                     input_stream_.size());
+        spdlog::trace("Received partial handshake of size {}", input_stream_.size());
         return;
       }
       state_ = StateHandshakeRun(*this);

src/communication/bolt/v1/state.hpp

@@ -44,4 +44,4 @@ enum class State : uint8_t {
    */
   Close
 };
-}
+}  // namespace communication::bolt

src/communication/bolt/v1/states/error.hpp

@@ -1,13 +1,13 @@
 #pragma once
 
 #include <fmt/format.h>
-#include <glog/logging.h>
 
 #include "communication/bolt/v1/codes.hpp"
 #include "communication/bolt/v1/state.hpp"
 #include "communication/bolt/v1/value.hpp"
 #include "utils/cast.hpp"
 #include "utils/likely.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -22,29 +22,27 @@ State StateErrorRun(TSession &session, State state) {
   Marker marker;
   Signature signature;
   if (!session.decoder_.ReadMessageHeader(&signature, &marker)) {
-    DLOG(WARNING) << "Missing header data!";
+    spdlog::trace("Missing header data!");
     return State::Close;
   }
 
-  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 &&
-               session.version_.minor == 1)) {
-    DLOG(INFO) << "Received NOOP message";
+  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 && session.version_.minor == 1)) {
+    spdlog::trace("Received NOOP message");
     return state;
   }
 
   // Clear the data buffer if it has any leftover data.
   session.encoder_buffer_.Clear();
 
-  if ((session.version_.major == 1 && signature == Signature::AckFailure) ||
-      signature == Signature::Reset) {
+  if ((session.version_.major == 1 && signature == Signature::AckFailure) || signature == Signature::Reset) {
     if (signature == Signature::AckFailure) {
-      DLOG(INFO) << "AckFailure received";
+      spdlog::trace("AckFailure received");
     } else {
-      DLOG(INFO) << "Reset received";
+      spdlog::trace("Reset received");
     }
 
     if (!session.encoder_.MessageSuccess()) {
-      DLOG(WARNING) << "Couldn't send success message!";
+      spdlog::trace("Couldn't send success message!");
       return State::Close;
     }
 
@@ -54,7 +52,7 @@ State StateErrorRun(TSession &session, State state) {
     }
 
     // We got AckFailure get back to right state.
-    CHECK(state == State::Error) << "Shouldn't happen";
+    MG_ASSERT(state == State::Error, "Shouldn't happen");
     return State::Idle;
   } else {
     uint8_t value = utils::UnderlyingCast(marker);
@@ -62,8 +60,7 @@ State StateErrorRun(TSession &session, State state) {
     // All bolt client messages have less than 15 parameters so if we receive
     // anything than a TinyStruct it's an error.
     if ((value & 0xF0) != utils::UnderlyingCast(Marker::TinyStruct)) {
-      DLOG(WARNING) << fmt::format(
-          "Expected TinyStruct marker, but received 0x{:02X}!", value);
+      spdlog::trace("Expected TinyStruct marker, but received 0x{:02X}!", value);
       return State::Close;
     }
 
@@ -72,15 +69,14 @@ State StateErrorRun(TSession &session, State state) {
     Value dv;
     for (int i = 0; i < value; ++i) {
       if (!session.decoder_.ReadValue(&dv)) {
-        DLOG(WARNING) << fmt::format("Couldn't clean up parameter {} / {}!", i,
-                                     value);
+        spdlog::trace("Couldn't clean up parameter {} / {}!", i, value);
         return State::Close;
       }
     }
 
     // Ignore this message.
     if (!session.encoder_.MessageIgnored()) {
-      DLOG(WARNING) << "Couldn't send ignored message!";
+      spdlog::trace("Couldn't send ignored message!");
       return State::Close;
     }
 

src/communication/bolt/v1/states/executing.hpp

@@ -4,8 +4,6 @@
 #include <new>
 #include <string>
 
-#include <glog/logging.h>
-
 #include "communication/bolt/v1/codes.hpp"
 #include "communication/bolt/v1/constants.hpp"
 #include "communication/bolt/v1/exceptions.hpp"
@@ -13,12 +11,12 @@
 #include "communication/bolt/v1/value.hpp"
 #include "communication/exceptions.hpp"
 #include "utils/likely.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
 // TODO (mferencevic): revise these error messages
-inline std::pair<std::string, std::string> ExceptionToErrorMessage(
-    const std::exception &e) {
+inline std::pair<std::string, std::string> ExceptionToErrorMessage(const std::exception &e) {
   if (auto *verbose = dynamic_cast<const VerboseError *>(&e)) {
     return {verbose->code(), verbose->what()};
   }
@@ -50,13 +48,12 @@ inline std::pair<std::string, std::string> ExceptionToErrorMessage(
   if (dynamic_cast<const std::bad_alloc *>(&e)) {
     // std::bad_alloc was thrown, God knows in which state is database ->
     // terminate.
-    LOG(FATAL) << "Memgraph is out of memory";
+    LOG_FATAL("Memgraph is out of memory");
   }
   // All exceptions used in memgraph are derived from BasicException. Since
   // we caught some other exception we don't know what is going on. Return
   // DatabaseError, log real message and return generic string.
-  LOG(ERROR) << "Unknown exception occurred during query execution "
-             << e.what();
+  spdlog::error("Unknown exception occurred during query execution {}", e.what());
   return {"Memgraph.DatabaseError.MemgraphError.MemgraphError",
           "An unknown exception occurred, this is unexpected. Real message "
           "should be in database logs."};
@@ -64,16 +61,15 @@ inline std::pair<std::string, std::string> ExceptionToErrorMessage(
 
 template <typename TSession>
 inline State HandleFailure(TSession &session, const std::exception &e) {
-  DLOG(WARNING) << fmt::format("Error message: {}", e.what());
+  spdlog::trace("Error message: {}", e.what());
   if (const auto *p = dynamic_cast<const utils::StacktraceException *>(&e)) {
-    DLOG(WARNING) << fmt::format("Error trace: {}", p->trace());
+    spdlog::trace("Error trace: {}", p->trace());
   }
   session.encoder_buffer_.Clear();
   auto code_message = ExceptionToErrorMessage(e);
-  bool fail_sent = session.encoder_.MessageFailure(
-      {{"code", code_message.first}, {"message", code_message.second}});
+  bool fail_sent = session.encoder_.MessageFailure({{"code", code_message.first}, {"message", code_message.second}});
   if (!fail_sent) {
-    DLOG(WARNING) << "Couldn't send failure message!";
+    spdlog::trace("Couldn't send failure message!");
     return State::Close;
   }
   return State::Error;
@@ -81,33 +77,29 @@ inline State HandleFailure(TSession &session, const std::exception &e) {
 
 template <typename TSession>
 State HandleRun(TSession &session, State state, Marker marker) {
-  const std::map<std::string, Value> kEmptyFields = {
-      {"fields", std::vector<Value>{}}};
+  const std::map<std::string, Value> kEmptyFields = {{"fields", std::vector<Value>{}}};
 
-  const auto expected_marker =
-      session.version_.major == 1 ? Marker::TinyStruct2 : Marker::TinyStruct3;
+  const auto expected_marker = session.version_.major == 1 ? Marker::TinyStruct2 : Marker::TinyStruct3;
   if (marker != expected_marker) {
-    DLOG(WARNING) << fmt::format(
-        "Expected {} marker, but received 0x{:02X}!",
-        session.version_.major == 1 ? "TinyStruct2" : "TinyStruct3",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected {} marker, but received 0x{:02X}!",
+                  session.version_.major == 1 ? "TinyStruct2" : "TinyStruct3", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
   Value query, params, extra;
   if (!session.decoder_.ReadValue(&query, Value::Type::String)) {
-    DLOG(WARNING) << "Couldn't read query string!";
+    spdlog::trace("Couldn't read query string!");
     return State::Close;
   }
 
   if (!session.decoder_.ReadValue(&params, Value::Type::Map)) {
-    DLOG(WARNING) << "Couldn't read parameters!";
+    spdlog::trace("Couldn't read parameters!");
     return State::Close;
   }
 
   if (session.version_.major == 4) {
     if (!session.decoder_.ReadValue(&extra, Value::Type::Map)) {
-      DLOG(WARNING) << "Couldn't read extra field!";
+      spdlog::trace("Couldn't read extra field!");
     }
   }
 
@@ -115,19 +107,17 @@ State HandleRun(TSession &session, State state, Marker marker) {
     // Client could potentially recover if we move to error state, but there is
     // no legitimate situation in which well working client would end up in this
     // situation.
-    DLOG(WARNING) << "Unexpected RUN command!";
+    spdlog::trace("Unexpected RUN command!");
     return State::Close;
   }
 
-  DCHECK(!session.encoder_buffer_.HasData())
-      << "There should be no data to write in this state";
+  DMG_ASSERT(!session.encoder_buffer_.HasData(), "There should be no data to write in this state");
 
-  DLOG(INFO) << fmt::format("[Run] '{}'", query.ValueString());
+  spdlog::debug("[Run] '{}'", query.ValueString());
 
   try {
     // Interpret can throw.
-    auto [header, qid] =
-        session.Interpret(query.ValueString(), params.ValueMap());
+    auto [header, qid] = session.Interpret(query.ValueString(), params.ValueMap());
     // Convert std::string to Value
     std::vector<Value> vec;
     std::map<std::string, Value> data;
@@ -136,7 +126,7 @@ State HandleRun(TSession &session, State state, Marker marker) {
     data.emplace("fields", std::move(vec));
     // Send the header.
     if (!session.encoder_.MessageSuccess(data)) {
-      DLOG(WARNING) << "Couldn't send query header!";
+      spdlog::trace("Couldn't send query header!");
       return State::Close;
     }
     return State::Result;
@@ -148,21 +138,18 @@ State HandleRun(TSession &session, State state, Marker marker) {
 namespace detail {
 template <bool is_pull, typename TSession>
 State HandlePullDiscard(TSession &session, State state, Marker marker) {
-  const auto expected_marker =
-      session.version_.major == 1 ? Marker::TinyStruct : Marker::TinyStruct1;
+  const auto expected_marker = session.version_.major == 1 ? Marker::TinyStruct : Marker::TinyStruct1;
   if (marker != expected_marker) {
-    DLOG(WARNING) << fmt::format(
-        "Expected {} marker, but received 0x{:02X}!",
-        session.version_.major == 1 ? "TinyStruct" : "TinyStruct1",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected {} marker, but received 0x{:02X}!",
+                  session.version_.major == 1 ? "TinyStruct" : "TinyStruct1", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
   if (state != State::Result) {
     if constexpr (is_pull) {
-      DLOG(WARNING) << "Unexpected PULL!";
+      spdlog::trace("Unexpected PULL!");
     } else {
-      DLOG(WARNING) << "Unexpected DISCARD!";
+      spdlog::trace("Unexpected DISCARD!");
     }
     // Same as `unexpected RUN` case.
     return State::Close;
@@ -175,19 +162,17 @@ State HandlePullDiscard(TSession &session, State state, Marker marker) {
     if (session.version_.major == 4) {
       Value extra;
       if (!session.decoder_.ReadValue(&extra, Value::Type::Map)) {
-        DLOG(WARNING) << "Couldn't read extra field!";
+        spdlog::trace("Couldn't read extra field!");
       }
       const auto &extra_map = extra.ValueMap();
       if (extra_map.count("n")) {
-        if (const auto n_value = extra_map.at("n").ValueInt();
-            n_value != kPullAll) {
+        if (const auto n_value = extra_map.at("n").ValueInt(); n_value != kPullAll) {
           n = n_value;
         }
       }
 
       if (extra_map.count("qid")) {
-        if (const auto qid_value = extra_map.at("qid").ValueInt();
-            qid_value != kPullLast) {
+        if (const auto qid_value = extra_map.at("qid").ValueInt(); qid_value != kPullLast) {
           qid = qid_value;
         }
       }
@@ -202,7 +187,7 @@ State HandlePullDiscard(TSession &session, State state, Marker marker) {
     }
 
     if (!session.encoder_.MessageSuccess(summary)) {
-      DLOG(WARNING) << "Couldn't send query summary!";
+      spdlog::trace("Couldn't send query summary!");
       return State::Close;
     }
 
@@ -239,9 +224,7 @@ State HandleReset(Session &session, State, Marker marker) {
   // now this command only resets the session to a clean state. It
   // does not IGNORE running and pending commands as it should.
   if (marker != Marker::TinyStruct) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct marker, but received 0x{:02X}!",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected TinyStruct marker, but received 0x{:02X}!", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
@@ -249,7 +232,7 @@ State HandleReset(Session &session, State, Marker marker) {
   session.encoder_buffer_.Clear();
 
   if (!session.encoder_.MessageSuccess()) {
-    DLOG(WARNING) << "Couldn't send success message!";
+    spdlog::trace("Couldn't send success message!");
     return State::Close;
   }
 
@@ -261,33 +244,30 @@ State HandleReset(Session &session, State, Marker marker) {
 template <typename Session>
 State HandleBegin(Session &session, State state, Marker marker) {
   if (session.version_.major == 1) {
-    DLOG(WARNING) << "BEGIN messsage not supported in Bolt v1!";
+    spdlog::trace("BEGIN messsage not supported in Bolt v1!");
     return State::Close;
   }
 
   if (marker != Marker::TinyStruct1) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct1 marker, but received 0x{:02x}!",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected TinyStruct1 marker, but received 0x{:02x}!", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
   Value extra;
   if (!session.decoder_.ReadValue(&extra, Value::Type::Map)) {
-    DLOG(WARNING) << "Couldn't read extra fields!";
+    spdlog::trace("Couldn't read extra fields!");
     return State::Close;
   }
 
   if (state != State::Idle) {
-    DLOG(WARNING) << "Unexpected BEGIN command!";
+    spdlog::trace("Unexpected BEGIN command!");
     return State::Close;
   }
 
-  DCHECK(!session.encoder_buffer_.HasData())
-      << "There should be no data to write in this state";
+  DMG_ASSERT(!session.encoder_buffer_.HasData(), "There should be no data to write in this state");
 
   if (!session.encoder_.MessageSuccess({})) {
-    DLOG(WARNING) << "Couldn't send success message!";
+    spdlog::trace("Couldn't send success message!");
     return State::Close;
   }
 
@@ -303,28 +283,25 @@ State HandleBegin(Session &session, State state, Marker marker) {
 template <typename Session>
 State HandleCommit(Session &session, State state, Marker marker) {
   if (session.version_.major == 1) {
-    DLOG(WARNING) << "COMMIT messsage not supported in Bolt v1!";
+    spdlog::trace("COMMIT messsage not supported in Bolt v1!");
     return State::Close;
   }
 
   if (marker != Marker::TinyStruct) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct marker, but received 0x{:02x}!",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected TinyStruct marker, but received 0x{:02x}!", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
   if (state != State::Idle) {
-    DLOG(WARNING) << "Unexpected COMMIT command!";
+    spdlog::trace("Unexpected COMMIT command!");
     return State::Close;
   }
 
-  DCHECK(!session.encoder_buffer_.HasData())
-      << "There should be no data to write in this state";
+  DMG_ASSERT(!session.encoder_buffer_.HasData(), "There should be no data to write in this state");
 
   try {
     if (!session.encoder_.MessageSuccess({})) {
-      DLOG(WARNING) << "Couldn't send success message!";
+      spdlog::trace("Couldn't send success message!");
       return State::Close;
     }
     session.CommitTransaction();
@@ -337,28 +314,25 @@ State HandleCommit(Session &session, State state, Marker marker) {
 template <typename Session>
 State HandleRollback(Session &session, State state, Marker marker) {
   if (session.version_.major == 1) {
-    DLOG(WARNING) << "ROLLBACK messsage not supported in Bolt v1!";
+    spdlog::trace("ROLLBACK messsage not supported in Bolt v1!");
     return State::Close;
   }
 
   if (marker != Marker::TinyStruct) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct marker, but received 0x{:02x}!",
-        utils::UnderlyingCast(marker));
+    spdlog::trace("Expected TinyStruct marker, but received 0x{:02x}!", utils::UnderlyingCast(marker));
     return State::Close;
   }
 
   if (state != State::Idle) {
-    DLOG(WARNING) << "Unexpected ROLLBACK command!";
+    spdlog::trace("Unexpected ROLLBACK command!");
     return State::Close;
   }
 
-  DCHECK(!session.encoder_buffer_.HasData())
-      << "There should be no data to write in this state";
+  DMG_ASSERT(!session.encoder_buffer_.HasData(), "There should be no data to write in this state");
 
   try {
     if (!session.encoder_.MessageSuccess({})) {
-      DLOG(WARNING) << "Couldn't send success message!";
+      spdlog::trace("Couldn't send success message!");
       return State::Close;
     }
     session.RollbackTransaction();
@@ -379,13 +353,12 @@ State StateExecutingRun(Session &session, State state) {
   Marker marker;
   Signature signature;
   if (!session.decoder_.ReadMessageHeader(&signature, &marker)) {
-    DLOG(WARNING) << "Missing header data!";
+    spdlog::trace("Missing header data!");
     return State::Close;
   }
 
-  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 &&
-               session.version_.minor == 1)) {
-    DLOG(INFO) << "Received NOOP message";
+  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 && session.version_.minor == 1)) {
+    spdlog::trace("Received NOOP message");
     return state;
   }
 
@@ -406,8 +379,7 @@ State StateExecutingRun(Session &session, State state) {
   } else if (signature == Signature::Goodbye && session.version_.major != 1) {
     throw SessionClosedException("Closing connection.");
   } else {
-    DLOG(WARNING) << fmt::format("Unrecognized signature received (0x{:02X})!",
-                                 utils::UnderlyingCast(signature));
+    spdlog::trace("Unrecognized signature received (0x{:02X})!", utils::UnderlyingCast(signature));
     return State::Close;
   }
 }

src/communication/bolt/v1/states/handshake.hpp

@@ -1,13 +1,12 @@
 #pragma once
 
-#include <glog/logging.h>
-
 #include <fmt/format.h>
 
 #include "communication/bolt/v1/codes.hpp"
 #include "communication/bolt/v1/constants.hpp"
 #include "communication/bolt/v1/state.hpp"
 #include "utils/likely.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -18,15 +17,13 @@ namespace communication::bolt {
  */
 template <typename TSession>
 State StateHandshakeRun(TSession &session) {
-  auto precmp =
-      std::memcmp(session.input_stream_.data(), kPreamble, sizeof(kPreamble));
+  auto precmp = std::memcmp(session.input_stream_.data(), kPreamble, sizeof(kPreamble));
   if (UNLIKELY(precmp != 0)) {
-    DLOG(WARNING) << "Received a wrong preamble!";
+    spdlog::trace("Received a wrong preamble!");
     return State::Close;
   }
 
-  DCHECK(session.input_stream_.size() >= kHandshakeSize)
-      << "Wrong size of the handshake data!";
+  DMG_ASSERT(session.input_stream_.size() >= kHandshakeSize, "Wrong size of the handshake data!");
 
   auto dataPosition = session.input_stream_.data() + sizeof(kPreamble);
 
@@ -53,17 +50,16 @@ State StateHandshakeRun(TSession &session) {
   session.version_.minor = protocol[2];
   session.version_.major = protocol[3];
   if (!session.version_.major) {
-    DLOG(WARNING) << "Server doesn't support any of the requested versions!";
+    spdlog::trace("Server doesn't support any of the requested versions!");
     return State::Close;
   }
 
   if (!session.output_stream_.Write(protocol, sizeof(protocol))) {
-    DLOG(WARNING) << "Couldn't write handshake response!";
+    spdlog::trace("Couldn't write handshake response!");
     return State::Close;
   }
 
-  DLOG(INFO) << fmt::format("Using version {}.{} of protocol",
-                            session.version_.major, session.version_.minor);
+  spdlog::info("Using version {}.{} of protocol", session.version_.major, session.version_.minor);
 
   // Delete data from the input stream. It is guaranteed that there will more
   // than, or equal to 20 bytes (kHandshakeSize) in the buffer.

src/communication/bolt/v1/states/init.hpp

@@ -1,13 +1,13 @@
 #pragma once
 
 #include <fmt/format.h>
-#include <glog/logging.h>
 
 #include "communication/bolt/v1/codes.hpp"
 #include "communication/bolt/v1/state.hpp"
 #include "communication/bolt/v1/value.hpp"
 #include "communication/exceptions.hpp"
 #include "utils/likely.hpp"
+#include "utils/logging.hpp"
 
 namespace communication::bolt {
 
@@ -15,30 +15,28 @@ namespace detail {
 template <typename TSession>
 std::optional<Value> StateInitRunV1(TSession &session, const Marker marker) {
   if (UNLIKELY(marker != Marker::TinyStruct2)) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct2 marker, but received 0x{:02X}!",
-        utils::UnderlyingCast(marker));
-    DLOG(WARNING) << "The client sent malformed data, but we are continuing "
-                     "because the official Neo4j Java driver sends malformed "
-                     "data. D'oh!";
+    spdlog::trace("Expected TinyStruct2 marker, but received 0x{:02X}!", utils::UnderlyingCast(marker));
+    spdlog::trace(
+        "The client sent malformed data, but we are continuing "
+        "because the official Neo4j Java driver sends malformed "
+        "data. D'oh!");
     // TODO: this should be uncommented when the Neo4j Java driver is fixed
     // return State::Close;
   }
 
   Value client_name;
   if (!session.decoder_.ReadValue(&client_name, Value::Type::String)) {
-    DLOG(WARNING) << "Couldn't read client name!";
+    spdlog::trace("Couldn't read client name!");
     return std::nullopt;
   }
 
   Value metadata;
   if (!session.decoder_.ReadValue(&metadata, Value::Type::Map)) {
-    DLOG(WARNING) << "Couldn't read metadata!";
+    spdlog::trace("Couldn't read metadata!");
     return std::nullopt;
   }
 
-  LOG(INFO) << fmt::format("Client connected '{}'", client_name.ValueString())
-            << std::endl;
+  spdlog::info("Client connected '{}'", client_name.ValueString());
 
   return metadata;
 }
@@ -46,31 +44,28 @@ std::optional<Value> StateInitRunV1(TSession &session, const Marker marker) {
 template <typename TSession>
 std::optional<Value> StateInitRunV4(TSession &session, const Marker marker) {
   if (UNLIKELY(marker != Marker::TinyStruct1)) {
-    DLOG(WARNING) << fmt::format(
-        "Expected TinyStruct1 marker, but received 0x{:02X}!",
-        utils::UnderlyingCast(marker));
-    DLOG(WARNING) << "The client sent malformed data, but we are continuing "
-                     "because the official Neo4j Java driver sends malformed "
-                     "data. D'oh!";
+    spdlog::trace("Expected TinyStruct1 marker, but received 0x{:02X}!", utils::UnderlyingCast(marker));
+    spdlog::trace(
+        "The client sent malformed data, but we are continuing "
+        "because the official Neo4j Java driver sends malformed "
+        "data. D'oh!");
     // TODO: this should be uncommented when the Neo4j Java driver is fixed
     // return State::Close;
   }
 
   Value metadata;
   if (!session.decoder_.ReadValue(&metadata, Value::Type::Map)) {
-    DLOG(WARNING) << "Couldn't read metadata!";
+    spdlog::trace("Couldn't read metadata!");
     return std::nullopt;
   }
 
   const auto &data = metadata.ValueMap();
   if (!data.count("user_agent")) {
-    LOG(WARNING) << "The client didn't supply the user agent!";
+    spdlog::warn("The client didn't supply the user agent!");
     return std::nullopt;
   }
 
-  LOG(INFO) << fmt::format("Client connected '{}'",
-                           data.at("user_agent").ValueString())
-            << std::endl;
+  spdlog::info("Client connected '{}'", data.at("user_agent").ValueString());
 
   return metadata;
 }
@@ -83,32 +78,27 @@ std::optional<Value> StateInitRunV4(TSession &session, const Marker marker) {
  */
 template <typename Session>
 State StateInitRun(Session &session) {
-  DCHECK(!session.encoder_buffer_.HasData())
-      << "There should be no data to write in this state";
+  DMG_ASSERT(!session.encoder_buffer_.HasData(), "There should be no data to write in this state");
 
   Marker marker;
   Signature signature;
   if (!session.decoder_.ReadMessageHeader(&signature, &marker)) {
-    DLOG(WARNING) << "Missing header data!";
+    spdlog::trace("Missing header data!");
     return State::Close;
   }
 
-  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 &&
-               session.version_.minor == 1)) {
-    DLOG(INFO) << "Received NOOP message";
+  if (UNLIKELY(signature == Signature::Noop && session.version_.major == 4 && session.version_.minor == 1)) {
+    SPDLOG_DEBUG("Received NOOP message");
     return State::Init;
   }
 
   if (UNLIKELY(signature != Signature::Init)) {
-    DLOG(WARNING) << fmt::format(
-        "Expected Init signature, but received 0x{:02X}!",
-        utils::UnderlyingCast(signature));
+    spdlog::trace("Expected Init signature, but received 0x{:02X}!", utils::UnderlyingCast(signature));
     return State::Close;
   }
 
-  auto maybeMetadata = session.version_.major == 1
-                           ? detail::StateInitRunV1(session, marker)
-                           : detail::StateInitRunV4(session, marker);
+  auto maybeMetadata =
+      session.version_.major == 1 ? detail::StateInitRunV1(session, marker) : detail::StateInitRunV4(session, marker);
 
   if (!maybeMetadata) {
     return State::Close;
@@ -119,28 +109,26 @@ State StateInitRun(Session &session) {
   std::string password;
   auto &data = maybeMetadata->ValueMap();
   if (!data.count("scheme")) {
-    LOG(WARNING) << "The client didn't supply authentication information!";
+    spdlog::warn("The client didn't supply authentication information!");
     return State::Close;
   }
   if (data["scheme"].ValueString() == "basic") {
     if (!data.count("principal") || !data.count("credentials")) {
-      LOG(WARNING) << "The client didn't supply authentication information!";
+      spdlog::warn("The client didn't supply authentication information!");
       return State::Close;
     }
     username = data["principal"].ValueString();
     password = data["credentials"].ValueString();
   } else if (data["scheme"].ValueString() != "none") {
-    LOG(WARNING) << "Unsupported authentication scheme: "
-                 << data["scheme"].ValueString();
+    spdlog::warn("Unsupported authentication scheme: {}", data["scheme"].ValueString());
     return State::Close;
   }
 
   // Authenticate the user.
   if (!session.Authenticate(username, password)) {
     if (!session.encoder_.MessageFailure(
-            {{"code", "Memgraph.ClientError.Security.Unauthenticated"},
-             {"message", "Authentication failure"}})) {
-      DLOG(WARNING) << "Couldn't send failure message to the client!";
+            {{"code", "Memgraph.ClientError.Security.Unauthenticated"}, {"message", "Authentication failure"}})) {
+      spdlog::trace("Couldn't send failure message to the client!");
     }
     // Throw an exception to indicate to the network stack that the session
     // should be closed and cleaned up.
@@ -160,7 +148,7 @@ State StateInitRun(Session &session) {
     }
     success_sent = session.encoder_.MessageSuccess(metadata);
     if (!success_sent) {
-      DLOG(WARNING) << "Couldn't send success message to the client!";
+      spdlog::trace("Couldn't send success message to the client!");
       return State::Close;
     }
   }

src/communication/bolt/v1/value.cpp

@@ -198,8 +198,7 @@ Value &Value::operator=(Value &&other) noexcept {
         new (&edge_v) Edge(std::move(other.edge_v));
         break;
       case Type::UnboundedEdge:
-        new (&unbounded_edge_v)
-            UnboundedEdge(std::move(other.unbounded_edge_v));
+        new (&unbounded_edge_v) UnboundedEdge(std::move(other.unbounded_edge_v));
         break;
       case Type::Path:
         new (&path_v) Path(std::move(other.path_v));
@@ -258,17 +257,14 @@ std::ostream &operator<<(std::ostream &os, const Vertex &vertex) {
   if (vertex.labels.size() > 0) {
     os << ":";
   }
-  utils::PrintIterable(os, vertex.labels, ":",
-                       [&](auto &stream, auto label) { stream << label; });
+  utils::PrintIterable(os, vertex.labels, ":", [&](auto &stream, auto label) { stream << label; });
   if (vertex.labels.size() > 0 && vertex.properties.size() > 0) {
     os << " ";
   }
   if (vertex.properties.size() > 0) {
     os << "{";
     utils::PrintIterable(os, vertex.properties, ", ",
-                         [&](auto &stream, const auto &pair) {
-                           stream << pair.first << ": " << pair.second;
-                         });
+                         [&](auto &stream, const auto &pair) { stream << pair.first << ": " << pair.second; });
     os << "}";
   }
   return os << ")";
@@ -279,9 +275,7 @@ std::ostream &operator<<(std::ostream &os, const Edge &edge) {
   if (edge.properties.size() > 0) {
     os << " {";
     utils::PrintIterable(os, edge.properties, ", ",
-                         [&](auto &stream, const auto &pair) {
-                           stream << pair.first << ": " << pair.second;
-                         });
+                         [&](auto &stream, const auto &pair) { stream << pair.first << ": " << pair.second; });
     os << "}";
   }
   return os << "]";
@@ -292,9 +286,7 @@ std::ostream &operator<<(std::ostream &os, const UnboundedEdge &edge) {
   if (edge.properties.size() > 0) {
     os << " {";
     utils::PrintIterable(os, edge.properties, ", ",
-                         [&](auto &stream, const auto &pair) {
-                           stream << pair.first << ": " << pair.second;
-                         });
+                         [&](auto &stream, const auto &pair) { stream << pair.first << ": " << pair.second; });
     os << "}";
   }
   return os << "]";
@@ -339,9 +331,7 @@ std::ostream &operator<<(std::ostream &os, const Value &value) {
     case Value::Type::Map:
       os << "{";
       utils::PrintIterable(os, value.ValueMap(), ", ",
-                           [](auto &stream, const auto &pair) {
-                             stream << pair.first << ": " << pair.second;
-                           });
+                           [](auto &stream, const auto &pair) { stream << pair.first << ": " << pair.second; });
       return os << "}";
     case Value::Type::Vertex:
       return os << value.ValueVertex();

src/communication/bolt/v1/value.hpp

@@ -33,9 +33,7 @@ class Id {
   int64_t id_;
 };
 
-inline bool operator==(const Id &id1, const Id &id2) {
-  return id1.AsInt() == id2.AsInt();
-}
+inline bool operator==(const Id &id1, const Id &id2) { return id1.AsInt() == id2.AsInt(); }
 
 inline bool operator!=(const Id &id1, const Id &id2) { return !(id1 == id2); }
 
@@ -84,13 +82,10 @@ struct Path {
     // into the collection and puts that index into `indices`. A multiplier is
     // added to switch between positive and negative indices (that define edge
     // direction).
-    auto add_element = [this](auto &collection, const auto &element,
-                              int multiplier, int offset) {
+    auto add_element = [this](auto &collection, const auto &element, int multiplier, int offset) {
       auto found =
-          std::find_if(collection.begin(), collection.end(),
-                       [&](const auto &e) { return e.id == element.id; });
-      indices.emplace_back(multiplier *
-                           (std::distance(collection.begin(), found) + offset));
+          std::find_if(collection.begin(), collection.end(), [&](const auto &e) { return e.id == element.id; });
+      indices.emplace_back(multiplier * (std::distance(collection.begin(), found) + offset));
       if (found == collection.end()) collection.push_back(element);
     };
 
@@ -125,19 +120,7 @@ class Value {
   Value() : type_(Type::Null) {}
 
   /** Types that can be stored in a Value. */
-  enum class Type : unsigned {
-    Null,
-    Bool,
-    Int,
-    Double,
-    String,
-    List,
-    Map,
-    Vertex,
-    Edge,
-    UnboundedEdge,
-    Path
-  };
+  enum class Type : unsigned { Null, Bool, Int, Double, String, List, Map, Vertex, Edge, UnboundedEdge, Path };
 
   // constructors for primitive types
   Value(bool value) : type_(Type::Bool) { bool_v = value; }
@@ -146,47 +129,29 @@ class Value {
   Value(double value) : type_(Type::Double) { double_v = value; }
 
   // constructors for non-primitive types
-  Value(const std::string &value) : type_(Type::String) {
-    new (&string_v) std::string(value);
-  }
+  Value(const std::string &value) : type_(Type::String) { new (&string_v) std::string(value); }
   Value(const char *value) : Value(std::string(value)) {}
-  Value(const std::vector<Value> &value) : type_(Type::List) {
-    new (&list_v) std::vector<Value>(value);
-  }
+  Value(const std::vector<Value> &value) : type_(Type::List) { new (&list_v) std::vector<Value>(value); }
   Value(const std::map<std::string, Value> &value) : type_(Type::Map) {
     new (&map_v) std::map<std::string, Value>(value);
   }
-  Value(const Vertex &value) : type_(Type::Vertex) {
-    new (&vertex_v) Vertex(value);
-  }
+  Value(const Vertex &value) : type_(Type::Vertex) { new (&vertex_v) Vertex(value); }
   Value(const Edge &value) : type_(Type::Edge) { new (&edge_v) Edge(value); }
-  Value(const UnboundedEdge &value) : type_(Type::UnboundedEdge) {
-    new (&unbounded_edge_v) UnboundedEdge(value);
-  }
+  Value(const UnboundedEdge &value) : type_(Type::UnboundedEdge) { new (&unbounded_edge_v) UnboundedEdge(value); }
   Value(const Path &value) : type_(Type::Path) { new (&path_v) Path(value); }
 
   // move constructors for non-primitive values
-  Value(std::string &&value) noexcept : type_(Type::String) {
-    new (&string_v) std::string(std::move(value));
-  }
-  Value(std::vector<Value> &&value) noexcept : type_(Type::List) {
-    new (&list_v) std::vector<Value>(std::move(value));
-  }
+  Value(std::string &&value) noexcept : type_(Type::String) { new (&string_v) std::string(std::move(value)); }
+  Value(std::vector<Value> &&value) noexcept : type_(Type::List) { new (&list_v) std::vector<Value>(std::move(value)); }
   Value(std::map<std::string, Value> &&value) noexcept : type_(Type::Map) {
     new (&map_v) std::map<std::string, Value>(std::move(value));
   }
-  Value(Vertex &&value) noexcept : type_(Type::Vertex) {
-    new (&vertex_v) Vertex(std::move(value));
-  }
-  Value(Edge &&value) noexcept : type_(Type::Edge) {
-    new (&edge_v) Edge(std::move(value));
-  }
+  Value(Vertex &&value) noexcept : type_(Type::Vertex) { new (&vertex_v) Vertex(std::move(value)); }
+  Value(Edge &&value) noexcept : type_(Type::Edge) { new (&edge_v) Edge(std::move(value)); }
   Value(UnboundedEdge &&value) noexcept : type_(Type::UnboundedEdge) {
     new (&unbounded_edge_v) UnboundedEdge(std::move(value));
   }
-  Value(Path &&value) noexcept : type_(Type::Path) {
-    new (&path_v) Path(std::move(value));
-  }
+  Value(Path &&value) noexcept : type_(Type::Path) { new (&path_v) Path(std::move(value)); }
 
   Value &operator=(const Value &other);
   Value &operator=(Value &&other) noexcept;

src/communication/buffer.cpp

@@ -1,11 +1,10 @@
-#include "glog/logging.h"
-
 #include "communication/buffer.hpp"
 
+#include "utils/logging.hpp"
+
 namespace communication {
 
-Buffer::Buffer()
-    : data_(kBufferInitialSize, 0), read_end_(this), write_end_(this) {}
+Buffer::Buffer() : data_(kBufferInitialSize, 0), read_end_(this), write_end_(this) {}
 
 Buffer::ReadEnd::ReadEnd(Buffer *buffer) : buffer_(buffer) {}
 
@@ -21,9 +20,7 @@ void Buffer::ReadEnd::Clear() { buffer_->Clear(); }
 
 Buffer::WriteEnd::WriteEnd(Buffer *buffer) : buffer_(buffer) {}
 
-io::network::StreamBuffer Buffer::WriteEnd::Allocate() {
-  return buffer_->Allocate();
-}
+io::network::StreamBuffer Buffer::WriteEnd::Allocate() { return buffer_->Allocate(); }
 
 void Buffer::WriteEnd::Written(size_t len) { buffer_->Written(len); }
 
@@ -40,7 +37,7 @@ uint8_t *Buffer::data() { return data_.data(); }
 size_t Buffer::size() const { return have_; }
 
 void Buffer::Shift(size_t len) {
-  DCHECK(len <= have_) << "Tried to shift more data than the buffer has!";
+  DMG_ASSERT(len <= have_, "Tried to shift more data than the buffer has!");
   if (len == have_) {
     have_ = 0;
   } else {
@@ -50,15 +47,16 @@ void Buffer::Shift(size_t len) {
 }
 
 io::network::StreamBuffer Buffer::Allocate() {
-  DCHECK(data_.size() > have_) << "The buffer thinks that there is more data "
-                                  "in the buffer than there is underlying "
-                                  "storage space!";
+  DMG_ASSERT(data_.size() > have_,
+             "The buffer thinks that there is more data "
+             "in the buffer than there is underlying "
+             "storage space!");
   return {data_.data() + have_, data_.size() - have_};
 }
 
 void Buffer::Written(size_t len) {
   have_ += len;
-  DCHECK(have_ <= data_.size()) << "Written more than storage has space!";
+  DMG_ASSERT(have_ <= data_.size(), "Written more than storage has space!");
 }
 
 void Buffer::Resize(size_t len) {

src/communication/client.cpp

@@ -1,7 +1,7 @@
-#include <glog/logging.h>
-
 #include "communication/client.hpp"
+
 #include "communication/helpers.hpp"
+#include "utils/logging.hpp"
 
 namespace communication {
 
@@ -32,7 +32,7 @@ bool Client::Connect(const io::network::Endpoint &endpoint) {
     // Create a new SSL object that will be used for SSL communication.
     ssl_ = SSL_new(context_->context());
     if (ssl_ == nullptr) {
-      DLOG(ERROR) << "Couldn't create client SSL object!";
+      SPDLOG_ERROR("Couldn't create client SSL object!");
       socket_.Close();
       return false;
     }
@@ -43,7 +43,7 @@ bool Client::Connect(const io::network::Endpoint &endpoint) {
     // handle that in our socket destructor).
     bio_ = BIO_new_socket(socket_.fd(), BIO_NOCLOSE);
     if (bio_ == nullptr) {
-      DLOG(ERROR) << "Couldn't create client BIO object!";
+      SPDLOG_ERROR("Couldn't create client BIO object!");
       socket_.Close();
       return false;
     }
@@ -59,7 +59,7 @@ bool Client::Connect(const io::network::Endpoint &endpoint) {
     // Perform the TLS handshake.
     auto ret = SSL_connect(ssl_);
     if (ret != 1) {
-      DLOG(WARNING) << "Couldn't connect to SSL server: " << SslGetLastError();
+      SPDLOG_WARN("Couldn't connect to SSL server: {}", SslGetLastError());
       socket_.Close();
       return false;
     }
@@ -114,7 +114,7 @@ bool Client::Read(size_t len, bool exactly_len) {
           continue;
         } else {
           // This is a fatal error.
-          DLOG(ERROR) << "Received an unexpected SSL error: " << err;
+          SPDLOG_ERROR("Received an unexpected SSL error: {}", err);
           return false;
         }
       } else if (got == 0) {
@@ -195,8 +195,7 @@ bool Client::Write(const uint8_t *data, size_t len, bool have_more) {
 }
 
 bool Client::Write(const std::string &str, bool have_more) {
-  return Write(reinterpret_cast<const uint8_t *>(str.data()), str.size(),
-               have_more);
+  return Write(reinterpret_cast<const uint8_t *>(str.data()), str.size(), have_more);
 }
 
 const io::network::Endpoint &Client::endpoint() { return socket_.endpoint(); }
@@ -224,12 +223,9 @@ void ClientInputStream::Clear() { client_.ClearData(); }
 
 ClientOutputStream::ClientOutputStream(Client &client) : client_(client) {}
 
-bool ClientOutputStream::Write(const uint8_t *data, size_t len,
-                               bool have_more) {
+bool ClientOutputStream::Write(const uint8_t *data, size_t len, bool have_more) {
   return client_.Write(data, len, have_more);
 }
-bool ClientOutputStream::Write(const std::string &str, bool have_more) {
-  return client_.Write(str, have_more);
-}
+bool ClientOutputStream::Write(const std::string &str, bool have_more) { return client_.Write(str, have_more); }
 
 }  // namespace communication