mirror of
https://github.com/google/leveldb.git
synced 2026-08-30 11:27:52 +08:00
Compare commits
6 Commits
v1.20
...
reuse-mani
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1a9648e1f5 | ||
|
|
f79f4180cc | ||
|
|
36fc955971 | ||
|
|
bb61e00815 | ||
|
|
40c17c0b84 | ||
|
|
251ebf5dc7 |
13
.travis.yml
13
.travis.yml
@@ -1,13 +0,0 @@
|
||||
language: cpp
|
||||
compiler:
|
||||
- clang
|
||||
- gcc
|
||||
os:
|
||||
- linux
|
||||
- osx
|
||||
sudo: false
|
||||
before_install:
|
||||
- echo $LANG
|
||||
- echo $LC_ALL
|
||||
script:
|
||||
- make -j 4 check
|
||||
479
Makefile
479
Makefile
@@ -20,405 +20,214 @@ $(shell CC="$(CC)" CXX="$(CXX)" TARGET_OS="$(TARGET_OS)" \
|
||||
# this file is generated by the previous line to set build flags and sources
|
||||
include build_config.mk
|
||||
|
||||
TESTS = \
|
||||
db/autocompact_test \
|
||||
db/c_test \
|
||||
db/corruption_test \
|
||||
db/db_test \
|
||||
db/dbformat_test \
|
||||
db/fault_injection_test \
|
||||
db/filename_test \
|
||||
db/log_test \
|
||||
db/recovery_test \
|
||||
db/skiplist_test \
|
||||
db/version_edit_test \
|
||||
db/version_set_test \
|
||||
db/write_batch_test \
|
||||
helpers/memenv/memenv_test \
|
||||
issues/issue178_test \
|
||||
issues/issue200_test \
|
||||
table/filter_block_test \
|
||||
table/table_test \
|
||||
util/arena_test \
|
||||
util/bloom_test \
|
||||
util/cache_test \
|
||||
util/coding_test \
|
||||
util/crc32c_test \
|
||||
util/env_posix_test \
|
||||
util/env_test \
|
||||
util/hash_test
|
||||
|
||||
UTILS = \
|
||||
db/db_bench \
|
||||
db/leveldbutil
|
||||
|
||||
# Put the object files in a subdirectory, but the application at the top of the object dir.
|
||||
PROGNAMES := $(notdir $(TESTS) $(UTILS))
|
||||
|
||||
# On Linux may need libkyotocabinet-dev for dependency.
|
||||
BENCHMARKS = \
|
||||
doc/bench/db_bench_sqlite3 \
|
||||
doc/bench/db_bench_tree_db
|
||||
|
||||
CFLAGS += -I. -I./include $(PLATFORM_CCFLAGS) $(OPT)
|
||||
CXXFLAGS += -I. -I./include $(PLATFORM_CXXFLAGS) $(OPT)
|
||||
|
||||
LDFLAGS += $(PLATFORM_LDFLAGS)
|
||||
LIBS += $(PLATFORM_LIBS)
|
||||
|
||||
SIMULATOR_OUTDIR=out-ios-x86
|
||||
DEVICE_OUTDIR=out-ios-arm
|
||||
LIBOBJECTS = $(SOURCES:.cc=.o)
|
||||
MEMENVOBJECTS = $(MEMENV_SOURCES:.cc=.o)
|
||||
|
||||
TESTUTIL = ./util/testutil.o
|
||||
TESTHARNESS = ./util/testharness.o $(TESTUTIL)
|
||||
|
||||
ifeq ($(PLATFORM), IOS)
|
||||
# Note: iOS should probably be using libtool, not ar.
|
||||
ifeq ($(PLATFORM), IOS)
|
||||
AR=xcrun ar
|
||||
SIMULATORSDK=$(shell xcrun -sdk iphonesimulator --show-sdk-path)
|
||||
DEVICESDK=$(shell xcrun -sdk iphoneos --show-sdk-path)
|
||||
DEVICE_CFLAGS = -isysroot "$(DEVICESDK)" -arch armv6 -arch armv7 -arch armv7s -arch arm64
|
||||
SIMULATOR_CFLAGS = -isysroot "$(SIMULATORSDK)" -arch i686 -arch x86_64
|
||||
STATIC_OUTDIR=out-ios-universal
|
||||
else
|
||||
STATIC_OUTDIR=out-static
|
||||
SHARED_OUTDIR=out-shared
|
||||
STATIC_PROGRAMS := $(addprefix $(STATIC_OUTDIR)/, $(PROGNAMES))
|
||||
SHARED_PROGRAMS := $(addprefix $(SHARED_OUTDIR)/, db_bench)
|
||||
endif
|
||||
|
||||
STATIC_LIBOBJECTS := $(addprefix $(STATIC_OUTDIR)/, $(SOURCES:.cc=.o))
|
||||
STATIC_MEMENVOBJECTS := $(addprefix $(STATIC_OUTDIR)/, $(MEMENV_SOURCES:.cc=.o))
|
||||
TESTS = \
|
||||
arena_test \
|
||||
autocompact_test \
|
||||
bloom_test \
|
||||
c_test \
|
||||
cache_test \
|
||||
coding_test \
|
||||
corruption_test \
|
||||
crc32c_test \
|
||||
db_test \
|
||||
dbformat_test \
|
||||
env_test \
|
||||
fault_injection_test \
|
||||
filename_test \
|
||||
filter_block_test \
|
||||
hash_test \
|
||||
issue178_test \
|
||||
issue200_test \
|
||||
log_test \
|
||||
memenv_test \
|
||||
recovery_test \
|
||||
skiplist_test \
|
||||
table_test \
|
||||
version_edit_test \
|
||||
version_set_test \
|
||||
write_batch_test
|
||||
|
||||
DEVICE_LIBOBJECTS := $(addprefix $(DEVICE_OUTDIR)/, $(SOURCES:.cc=.o))
|
||||
DEVICE_MEMENVOBJECTS := $(addprefix $(DEVICE_OUTDIR)/, $(MEMENV_SOURCES:.cc=.o))
|
||||
PROGRAMS = db_bench leveldbutil $(TESTS)
|
||||
BENCHMARKS = db_bench_sqlite3 db_bench_tree_db
|
||||
|
||||
SIMULATOR_LIBOBJECTS := $(addprefix $(SIMULATOR_OUTDIR)/, $(SOURCES:.cc=.o))
|
||||
SIMULATOR_MEMENVOBJECTS := $(addprefix $(SIMULATOR_OUTDIR)/, $(MEMENV_SOURCES:.cc=.o))
|
||||
|
||||
SHARED_LIBOBJECTS := $(addprefix $(SHARED_OUTDIR)/, $(SOURCES:.cc=.o))
|
||||
SHARED_MEMENVOBJECTS := $(addprefix $(SHARED_OUTDIR)/, $(MEMENV_SOURCES:.cc=.o))
|
||||
|
||||
TESTUTIL := $(STATIC_OUTDIR)/util/testutil.o
|
||||
TESTHARNESS := $(STATIC_OUTDIR)/util/testharness.o $(TESTUTIL)
|
||||
|
||||
STATIC_TESTOBJS := $(addprefix $(STATIC_OUTDIR)/, $(addsuffix .o, $(TESTS)))
|
||||
STATIC_UTILOBJS := $(addprefix $(STATIC_OUTDIR)/, $(addsuffix .o, $(UTILS)))
|
||||
STATIC_ALLOBJS := $(STATIC_LIBOBJECTS) $(STATIC_MEMENVOBJECTS) $(STATIC_TESTOBJS) $(STATIC_UTILOBJS) $(TESTHARNESS)
|
||||
DEVICE_ALLOBJS := $(DEVICE_LIBOBJECTS) $(DEVICE_MEMENVOBJECTS)
|
||||
SIMULATOR_ALLOBJS := $(SIMULATOR_LIBOBJECTS) $(SIMULATOR_MEMENVOBJECTS)
|
||||
LIBRARY = libleveldb.a
|
||||
MEMENVLIBRARY = libmemenv.a
|
||||
|
||||
default: all
|
||||
|
||||
# Should we build shared libraries?
|
||||
ifneq ($(PLATFORM_SHARED_EXT),)
|
||||
|
||||
# Many leveldb test apps use non-exported API's. Only build a subset for testing.
|
||||
SHARED_ALLOBJS := $(SHARED_LIBOBJECTS) $(SHARED_MEMENVOBJECTS) $(TESTHARNESS)
|
||||
|
||||
ifneq ($(PLATFORM_SHARED_VERSIONED),true)
|
||||
SHARED_LIB1 = libleveldb.$(PLATFORM_SHARED_EXT)
|
||||
SHARED_LIB2 = $(SHARED_LIB1)
|
||||
SHARED_LIB3 = $(SHARED_LIB1)
|
||||
SHARED_LIBS = $(SHARED_LIB1)
|
||||
SHARED_MEMENVLIB = $(SHARED_OUTDIR)/libmemenv.a
|
||||
SHARED1 = libleveldb.$(PLATFORM_SHARED_EXT)
|
||||
SHARED2 = $(SHARED1)
|
||||
SHARED3 = $(SHARED1)
|
||||
SHARED = $(SHARED1)
|
||||
else
|
||||
# Update db.h if you change these.
|
||||
SHARED_VERSION_MAJOR = 1
|
||||
SHARED_VERSION_MINOR = 20
|
||||
SHARED_LIB1 = libleveldb.$(PLATFORM_SHARED_EXT)
|
||||
SHARED_LIB2 = $(SHARED_LIB1).$(SHARED_VERSION_MAJOR)
|
||||
SHARED_LIB3 = $(SHARED_LIB1).$(SHARED_VERSION_MAJOR).$(SHARED_VERSION_MINOR)
|
||||
SHARED_LIBS = $(SHARED_OUTDIR)/$(SHARED_LIB1) $(SHARED_OUTDIR)/$(SHARED_LIB2) $(SHARED_OUTDIR)/$(SHARED_LIB3)
|
||||
$(SHARED_OUTDIR)/$(SHARED_LIB1): $(SHARED_OUTDIR)/$(SHARED_LIB3)
|
||||
ln -fs $(SHARED_LIB3) $(SHARED_OUTDIR)/$(SHARED_LIB1)
|
||||
$(SHARED_OUTDIR)/$(SHARED_LIB2): $(SHARED_OUTDIR)/$(SHARED_LIB3)
|
||||
ln -fs $(SHARED_LIB3) $(SHARED_OUTDIR)/$(SHARED_LIB2)
|
||||
SHARED_MEMENVLIB = $(SHARED_OUTDIR)/libmemenv.a
|
||||
SHARED_MAJOR = 1
|
||||
SHARED_MINOR = 18
|
||||
SHARED1 = libleveldb.$(PLATFORM_SHARED_EXT)
|
||||
SHARED2 = $(SHARED1).$(SHARED_MAJOR)
|
||||
SHARED3 = $(SHARED1).$(SHARED_MAJOR).$(SHARED_MINOR)
|
||||
SHARED = $(SHARED1) $(SHARED2) $(SHARED3)
|
||||
$(SHARED1): $(SHARED3)
|
||||
ln -fs $(SHARED3) $(SHARED1)
|
||||
$(SHARED2): $(SHARED3)
|
||||
ln -fs $(SHARED3) $(SHARED2)
|
||||
endif
|
||||
|
||||
$(SHARED_OUTDIR)/$(SHARED_LIB3): $(SHARED_LIBOBJECTS)
|
||||
$(CXX) $(LDFLAGS) $(PLATFORM_SHARED_LDFLAGS)$(SHARED_LIB2) $(SHARED_LIBOBJECTS) -o $(SHARED_OUTDIR)/$(SHARED_LIB3) $(LIBS)
|
||||
$(SHARED3):
|
||||
$(CXX) $(LDFLAGS) $(PLATFORM_SHARED_LDFLAGS)$(SHARED2) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(SOURCES) -o $(SHARED3) $(LIBS)
|
||||
|
||||
endif # PLATFORM_SHARED_EXT
|
||||
|
||||
all: $(SHARED_LIBS) $(SHARED_PROGRAMS) $(STATIC_OUTDIR)/libleveldb.a $(STATIC_OUTDIR)/libmemenv.a $(STATIC_PROGRAMS)
|
||||
all: $(SHARED) $(LIBRARY)
|
||||
|
||||
check: $(STATIC_PROGRAMS)
|
||||
for t in $(notdir $(TESTS)); do echo "***** Running $$t"; $(STATIC_OUTDIR)/$$t || exit 1; done
|
||||
check: all $(PROGRAMS) $(TESTS)
|
||||
for t in $(TESTS); do echo "***** Running $$t"; ./$$t || exit 1; done
|
||||
|
||||
clean:
|
||||
-rm -rf out-static out-shared out-ios-x86 out-ios-arm out-ios-universal
|
||||
-rm -f build_config.mk
|
||||
-rm -rf ios-x86 ios-arm
|
||||
-rm -f $(PROGRAMS) $(BENCHMARKS) $(LIBRARY) $(SHARED) $(MEMENVLIBRARY) */*.o */*/*.o ios-x86/*/*.o ios-arm/*/*.o build_config.mk
|
||||
-rm -rf ios-x86/* ios-arm/*
|
||||
|
||||
$(STATIC_OUTDIR):
|
||||
mkdir $@
|
||||
$(LIBRARY): $(LIBOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(LIBOBJECTS)
|
||||
|
||||
$(STATIC_OUTDIR)/db: | $(STATIC_OUTDIR)
|
||||
mkdir $@
|
||||
db_bench: db/db_bench.o $(LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) db/db_bench.o $(LIBOBJECTS) $(TESTUTIL) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/helpers/memenv: | $(STATIC_OUTDIR)
|
||||
mkdir -p $@
|
||||
db_bench_sqlite3: doc/bench/db_bench_sqlite3.o $(LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) doc/bench/db_bench_sqlite3.o $(LIBOBJECTS) $(TESTUTIL) -o $@ -lsqlite3 $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/port: | $(STATIC_OUTDIR)
|
||||
mkdir $@
|
||||
db_bench_tree_db: doc/bench/db_bench_tree_db.o $(LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) doc/bench/db_bench_tree_db.o $(LIBOBJECTS) $(TESTUTIL) -o $@ -lkyotocabinet $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/table: | $(STATIC_OUTDIR)
|
||||
mkdir $@
|
||||
leveldbutil: db/leveldb_main.o $(LIBOBJECTS)
|
||||
$(CXX) $(LDFLAGS) db/leveldb_main.o $(LIBOBJECTS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/util: | $(STATIC_OUTDIR)
|
||||
mkdir $@
|
||||
arena_test: util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
.PHONY: STATIC_OBJDIRS
|
||||
STATIC_OBJDIRS: \
|
||||
$(STATIC_OUTDIR)/db \
|
||||
$(STATIC_OUTDIR)/port \
|
||||
$(STATIC_OUTDIR)/table \
|
||||
$(STATIC_OUTDIR)/util \
|
||||
$(STATIC_OUTDIR)/helpers/memenv
|
||||
autocompact_test: db/autocompact_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/autocompact_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR):
|
||||
mkdir $@
|
||||
bloom_test: util/bloom_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/bloom_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/db: | $(SHARED_OUTDIR)
|
||||
mkdir $@
|
||||
c_test: db/c_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/c_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/helpers/memenv: | $(SHARED_OUTDIR)
|
||||
mkdir -p $@
|
||||
cache_test: util/cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/cache_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/port: | $(SHARED_OUTDIR)
|
||||
mkdir $@
|
||||
coding_test: util/coding_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/coding_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/table: | $(SHARED_OUTDIR)
|
||||
mkdir $@
|
||||
corruption_test: db/corruption_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/corruption_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/util: | $(SHARED_OUTDIR)
|
||||
mkdir $@
|
||||
crc32c_test: util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
.PHONY: SHARED_OBJDIRS
|
||||
SHARED_OBJDIRS: \
|
||||
$(SHARED_OUTDIR)/db \
|
||||
$(SHARED_OUTDIR)/port \
|
||||
$(SHARED_OUTDIR)/table \
|
||||
$(SHARED_OUTDIR)/util \
|
||||
$(SHARED_OUTDIR)/helpers/memenv
|
||||
db_test: db/db_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/db_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR):
|
||||
mkdir $@
|
||||
dbformat_test: db/dbformat_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/dbformat_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR)/db: | $(DEVICE_OUTDIR)
|
||||
mkdir $@
|
||||
env_test: util/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/env_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR)/helpers/memenv: | $(DEVICE_OUTDIR)
|
||||
mkdir -p $@
|
||||
fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR)/port: | $(DEVICE_OUTDIR)
|
||||
mkdir $@
|
||||
filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR)/table: | $(DEVICE_OUTDIR)
|
||||
mkdir $@
|
||||
filter_block_test: table/filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) table/filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(DEVICE_OUTDIR)/util: | $(DEVICE_OUTDIR)
|
||||
mkdir $@
|
||||
hash_test: util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
.PHONY: DEVICE_OBJDIRS
|
||||
DEVICE_OBJDIRS: \
|
||||
$(DEVICE_OUTDIR)/db \
|
||||
$(DEVICE_OUTDIR)/port \
|
||||
$(DEVICE_OUTDIR)/table \
|
||||
$(DEVICE_OUTDIR)/util \
|
||||
$(DEVICE_OUTDIR)/helpers/memenv
|
||||
issue178_test: issues/issue178_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) issues/issue178_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR):
|
||||
mkdir $@
|
||||
issue200_test: issues/issue200_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) issues/issue200_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/db: | $(SIMULATOR_OUTDIR)
|
||||
mkdir $@
|
||||
log_test: db/log_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/log_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/helpers/memenv: | $(SIMULATOR_OUTDIR)
|
||||
mkdir -p $@
|
||||
recovery_test: db/recovery_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/recovery_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/port: | $(SIMULATOR_OUTDIR)
|
||||
mkdir $@
|
||||
table_test: table/table_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) table/table_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/table: | $(SIMULATOR_OUTDIR)
|
||||
mkdir $@
|
||||
skiplist_test: db/skiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/skiplist_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/util: | $(SIMULATOR_OUTDIR)
|
||||
mkdir $@
|
||||
version_edit_test: db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
.PHONY: SIMULATOR_OBJDIRS
|
||||
SIMULATOR_OBJDIRS: \
|
||||
$(SIMULATOR_OUTDIR)/db \
|
||||
$(SIMULATOR_OUTDIR)/port \
|
||||
$(SIMULATOR_OUTDIR)/table \
|
||||
$(SIMULATOR_OUTDIR)/util \
|
||||
$(SIMULATOR_OUTDIR)/helpers/memenv
|
||||
version_set_test: db/version_set_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/version_set_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_ALLOBJS): | STATIC_OBJDIRS
|
||||
$(DEVICE_ALLOBJS): | DEVICE_OBJDIRS
|
||||
$(SIMULATOR_ALLOBJS): | SIMULATOR_OBJDIRS
|
||||
$(SHARED_ALLOBJS): | SHARED_OBJDIRS
|
||||
write_batch_test: db/write_batch_test.o $(LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) db/write_batch_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(MEMENVLIBRARY) : $(MEMENVOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(MEMENVOBJECTS)
|
||||
|
||||
memenv_test : helpers/memenv/memenv_test.o $(MEMENVLIBRARY) $(LIBRARY) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) helpers/memenv/memenv_test.o $(MEMENVLIBRARY) $(LIBRARY) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
ifeq ($(PLATFORM), IOS)
|
||||
$(DEVICE_OUTDIR)/libleveldb.a: $(DEVICE_LIBOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(DEVICE_LIBOBJECTS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/libleveldb.a: $(SIMULATOR_LIBOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(SIMULATOR_LIBOBJECTS)
|
||||
|
||||
$(DEVICE_OUTDIR)/libmemenv.a: $(DEVICE_MEMENVOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(DEVICE_MEMENVOBJECTS)
|
||||
|
||||
$(SIMULATOR_OUTDIR)/libmemenv.a: $(SIMULATOR_MEMENVOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(SIMULATOR_MEMENVOBJECTS)
|
||||
|
||||
# For iOS, create universal object libraries to be used on both the simulator and
|
||||
# For iOS, create universal object files to be used on both the simulator and
|
||||
# a device.
|
||||
$(STATIC_OUTDIR)/libleveldb.a: $(STATIC_OUTDIR) $(DEVICE_OUTDIR)/libleveldb.a $(SIMULATOR_OUTDIR)/libleveldb.a
|
||||
lipo -create $(DEVICE_OUTDIR)/libleveldb.a $(SIMULATOR_OUTDIR)/libleveldb.a -output $@
|
||||
SIMULATORSDK=$(shell xcrun -sdk iphonesimulator --show-sdk-path)
|
||||
DEVICESDK=$(shell xcrun -sdk iphoneos --show-sdk-path)
|
||||
IOSARCH=-arch armv6 -arch armv7 -arch armv7s -arch arm64
|
||||
|
||||
.cc.o:
|
||||
mkdir -p ios-x86/$(dir $@)
|
||||
xcrun -sdk iphonesimulator $(CXX) $(CXXFLAGS) -isysroot "$(SIMULATORSDK)" -arch i686 -arch x86_64 -c $< -o ios-x86/$@
|
||||
mkdir -p ios-arm/$(dir $@)
|
||||
xcrun -sdk iphoneos $(CXX) $(CXXFLAGS) -isysroot "$(DEVICESDK)" $(IOSARCH) -c $< -o ios-arm/$@
|
||||
xcrun lipo ios-x86/$@ ios-arm/$@ -create -output $@
|
||||
|
||||
.c.o:
|
||||
mkdir -p ios-x86/$(dir $@)
|
||||
xcrun -sdk iphonesimulator $(CC) $(CFLAGS) -isysroot "$(SIMULATORSDK)" -arch i686 -arch x86_64 -c $< -o ios-x86/$@
|
||||
mkdir -p ios-arm/$(dir $@)
|
||||
xcrun -sdk iphoneos $(CC) $(CFLAGS) -isysroot "$(DEVICESDK)" $(IOSARCH) -c $< -o ios-arm/$@
|
||||
xcrun lipo ios-x86/$@ ios-arm/$@ -create -output $@
|
||||
|
||||
$(STATIC_OUTDIR)/libmemenv.a: $(STATIC_OUTDIR) $(DEVICE_OUTDIR)/libmemenv.a $(SIMULATOR_OUTDIR)/libmemenv.a
|
||||
lipo -create $(DEVICE_OUTDIR)/libmemenv.a $(SIMULATOR_OUTDIR)/libmemenv.a -output $@
|
||||
else
|
||||
$(STATIC_OUTDIR)/libleveldb.a:$(STATIC_LIBOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(STATIC_LIBOBJECTS)
|
||||
|
||||
$(STATIC_OUTDIR)/libmemenv.a:$(STATIC_MEMENVOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(STATIC_MEMENVOBJECTS)
|
||||
endif
|
||||
|
||||
$(SHARED_MEMENVLIB):$(SHARED_MEMENVOBJECTS)
|
||||
rm -f $@
|
||||
$(AR) -rs $@ $(SHARED_MEMENVOBJECTS)
|
||||
|
||||
$(STATIC_OUTDIR)/db_bench:db/db_bench.cc $(STATIC_LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/db_bench.cc $(STATIC_LIBOBJECTS) $(TESTUTIL) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/db_bench_sqlite3:doc/bench/db_bench_sqlite3.cc $(STATIC_LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) doc/bench/db_bench_sqlite3.cc $(STATIC_LIBOBJECTS) $(TESTUTIL) -o $@ -lsqlite3 $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/db_bench_tree_db:doc/bench/db_bench_tree_db.cc $(STATIC_LIBOBJECTS) $(TESTUTIL)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) doc/bench/db_bench_tree_db.cc $(STATIC_LIBOBJECTS) $(TESTUTIL) -o $@ -lkyotocabinet $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/leveldbutil:db/leveldbutil.cc $(STATIC_LIBOBJECTS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/leveldbutil.cc $(STATIC_LIBOBJECTS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/arena_test:util/arena_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/arena_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/autocompact_test:db/autocompact_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/autocompact_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/bloom_test:util/bloom_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/bloom_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/c_test:$(STATIC_OUTDIR)/db/c_test.o $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(STATIC_OUTDIR)/db/c_test.o $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/cache_test:util/cache_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/cache_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/coding_test:util/coding_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/coding_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/corruption_test:db/corruption_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/corruption_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/crc32c_test:util/crc32c_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/crc32c_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/db_test:db/db_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/db_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/dbformat_test:db/dbformat_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/dbformat_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/env_posix_test:util/env_posix_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/env_posix_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/env_test:util/env_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/env_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/fault_injection_test:db/fault_injection_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/fault_injection_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/filename_test:db/filename_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/filename_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/filter_block_test:table/filter_block_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) table/filter_block_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/hash_test:util/hash_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) util/hash_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/issue178_test:issues/issue178_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) issues/issue178_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/issue200_test:issues/issue200_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) issues/issue200_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/log_test:db/log_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/log_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/recovery_test:db/recovery_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/recovery_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/table_test:table/table_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) table/table_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/skiplist_test:db/skiplist_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/skiplist_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/version_edit_test:db/version_edit_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/version_edit_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/version_set_test:db/version_set_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/version_set_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/write_batch_test:db/write_batch_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS)
|
||||
$(CXX) $(LDFLAGS) $(CXXFLAGS) db/write_batch_test.cc $(STATIC_LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(STATIC_OUTDIR)/memenv_test:$(STATIC_OUTDIR)/helpers/memenv/memenv_test.o $(STATIC_OUTDIR)/libmemenv.a $(STATIC_OUTDIR)/libleveldb.a $(TESTHARNESS)
|
||||
$(XCRUN) $(CXX) $(LDFLAGS) $(STATIC_OUTDIR)/helpers/memenv/memenv_test.o $(STATIC_OUTDIR)/libmemenv.a $(STATIC_OUTDIR)/libleveldb.a $(TESTHARNESS) -o $@ $(LIBS)
|
||||
|
||||
$(SHARED_OUTDIR)/db_bench:$(SHARED_OUTDIR)/db/db_bench.o $(SHARED_LIBS) $(TESTUTIL)
|
||||
$(XCRUN) $(CXX) $(LDFLAGS) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(SHARED_OUTDIR)/db/db_bench.o $(TESTUTIL) $(SHARED_OUTDIR)/$(SHARED_LIB3) -o $@ $(LIBS)
|
||||
|
||||
.PHONY: run-shared
|
||||
run-shared: $(SHARED_OUTDIR)/db_bench
|
||||
LD_LIBRARY_PATH=$(SHARED_OUTDIR) $(SHARED_OUTDIR)/db_bench
|
||||
|
||||
$(SIMULATOR_OUTDIR)/%.o: %.cc
|
||||
xcrun -sdk iphonesimulator $(CXX) $(CXXFLAGS) $(SIMULATOR_CFLAGS) -c $< -o $@
|
||||
|
||||
$(DEVICE_OUTDIR)/%.o: %.cc
|
||||
xcrun -sdk iphoneos $(CXX) $(CXXFLAGS) $(DEVICE_CFLAGS) -c $< -o $@
|
||||
|
||||
$(SIMULATOR_OUTDIR)/%.o: %.c
|
||||
xcrun -sdk iphonesimulator $(CC) $(CFLAGS) $(SIMULATOR_CFLAGS) -c $< -o $@
|
||||
|
||||
$(DEVICE_OUTDIR)/%.o: %.c
|
||||
xcrun -sdk iphoneos $(CC) $(CFLAGS) $(DEVICE_CFLAGS) -c $< -o $@
|
||||
|
||||
$(STATIC_OUTDIR)/%.o: %.cc
|
||||
.cc.o:
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
$(STATIC_OUTDIR)/%.o: %.c
|
||||
.c.o:
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
|
||||
$(SHARED_OUTDIR)/%.o: %.cc
|
||||
$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) -c $< -o $@
|
||||
|
||||
$(SHARED_OUTDIR)/%.o: %.c
|
||||
$(CC) $(CFLAGS) $(PLATFORM_SHARED_CFLAGS) -c $< -o $@
|
||||
|
||||
$(STATIC_OUTDIR)/port/port_posix_sse.o: port/port_posix_sse.cc
|
||||
$(CXX) $(CXXFLAGS) $(PLATFORM_SSEFLAGS) -c $< -o $@
|
||||
|
||||
$(SHARED_OUTDIR)/port/port_posix_sse.o: port/port_posix_sse.cc
|
||||
$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) $(PLATFORM_SSEFLAGS) -c $< -o $@
|
||||
endif
|
||||
|
||||
62
README.md
62
README.md
@@ -1,7 +1,5 @@
|
||||
**LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.**
|
||||
|
||||
[](https://travis-ci.org/google/leveldb)
|
||||
|
||||
Authors: Sanjay Ghemawat (sanjay@google.com) and Jeff Dean (jeff@google.com)
|
||||
|
||||
# Features
|
||||
@@ -12,11 +10,9 @@ Authors: Sanjay Ghemawat (sanjay@google.com) and Jeff Dean (jeff@google.com)
|
||||
* Multiple changes can be made in one atomic batch.
|
||||
* Users can create a transient snapshot to get a consistent view of data.
|
||||
* Forward and backward iteration is supported over the data.
|
||||
* Data is automatically compressed using the [Snappy compression library](http://google.github.io/snappy/).
|
||||
* Data is automatically compressed using the [Snappy compression library](http://code.google.com/p/snappy).
|
||||
* External activity (file system operations etc.) is relayed through a virtual interface so users can customize the operating system interactions.
|
||||
|
||||
# Documentation
|
||||
[LevelDB library documentation](https://github.com/google/leveldb/blob/master/doc/index.md) is online and bundled with the source code.
|
||||
* [Detailed documentation](http://htmlpreview.github.io/?https://github.com/google/leveldb/blob/master/doc/index.html) about how to use the library is included with the source code.
|
||||
|
||||
|
||||
# Limitations
|
||||
@@ -24,37 +20,6 @@ Authors: Sanjay Ghemawat (sanjay@google.com) and Jeff Dean (jeff@google.com)
|
||||
* Only a single process (possibly multi-threaded) can access a particular database at a time.
|
||||
* There is no client-server support builtin to the library. An application that needs such support will have to wrap their own server around the library.
|
||||
|
||||
# Contributing to the leveldb Project
|
||||
The leveldb project welcomes contributions. leveldb's primary goal is to be
|
||||
a reliable and fast key/value store. Changes that are in line with the
|
||||
features/limitations outlined above, and meet the requirements below,
|
||||
will be considered.
|
||||
|
||||
Contribution requirements:
|
||||
|
||||
1. **POSIX only**. We _generally_ will only accept changes that are both
|
||||
compiled, and tested on a POSIX platform - usually Linux. Very small
|
||||
changes will sometimes be accepted, but consider that more of an
|
||||
exception than the rule.
|
||||
|
||||
2. **Stable API**. We strive very hard to maintain a stable API. Changes that
|
||||
require changes for projects using leveldb _might_ be rejected without
|
||||
sufficient benefit to the project.
|
||||
|
||||
3. **Tests**: All changes must be accompanied by a new (or changed) test, or
|
||||
a sufficient explanation as to why a new (or changed) test is not required.
|
||||
|
||||
## Submitting a Pull Request
|
||||
Before any pull request will be accepted the author must first sign a
|
||||
Contributor License Agreement (CLA) at https://cla.developers.google.com/.
|
||||
|
||||
In order to keep the commit timeline linear
|
||||
[squash](https://git-scm.com/book/en/v2/Git-Tools-Rewriting-History#Squashing-Commits)
|
||||
your changes down to a single commit and [rebase](https://git-scm.com/docs/git-rebase)
|
||||
on google/leveldb/master. This keeps the commit timeline linear and more easily sync'ed
|
||||
with the internal repository at Google. More information at GitHub's
|
||||
[About Git rebase](https://help.github.com/articles/about-git-rebase/) page.
|
||||
|
||||
# Performance
|
||||
|
||||
Here is a performance report (with explanations) from the run of the
|
||||
@@ -113,30 +78,29 @@ by the one or two disk seeks needed to fetch the data from disk.
|
||||
Write performance will be mostly unaffected by whether or not the
|
||||
working set fits in memory.
|
||||
|
||||
readrandom : 16.677 micros/op; (approximately 60,000 reads per second)
|
||||
readseq : 0.476 micros/op; 232.3 MB/s
|
||||
readreverse : 0.724 micros/op; 152.9 MB/s
|
||||
readrandom : 16.677 micros/op; (approximately 60,000 reads per second)
|
||||
readseq : 0.476 micros/op; 232.3 MB/s
|
||||
readreverse : 0.724 micros/op; 152.9 MB/s
|
||||
|
||||
LevelDB compacts its underlying storage data in the background to
|
||||
improve read performance. The results listed above were done
|
||||
immediately after a lot of random writes. The results after
|
||||
compactions (which are usually triggered automatically) are better.
|
||||
|
||||
readrandom : 11.602 micros/op; (approximately 85,000 reads per second)
|
||||
readseq : 0.423 micros/op; 261.8 MB/s
|
||||
readreverse : 0.663 micros/op; 166.9 MB/s
|
||||
readrandom : 11.602 micros/op; (approximately 85,000 reads per second)
|
||||
readseq : 0.423 micros/op; 261.8 MB/s
|
||||
readreverse : 0.663 micros/op; 166.9 MB/s
|
||||
|
||||
Some of the high cost of reads comes from repeated decompression of blocks
|
||||
read from disk. If we supply enough cache to the leveldb so it can hold the
|
||||
uncompressed blocks in memory, the read performance improves again:
|
||||
|
||||
readrandom : 9.775 micros/op; (approximately 100,000 reads per second before compaction)
|
||||
readrandom : 5.215 micros/op; (approximately 190,000 reads per second after compaction)
|
||||
readrandom : 9.775 micros/op; (approximately 100,000 reads per second before compaction)
|
||||
readrandom : 5.215 micros/op; (approximately 190,000 reads per second after compaction)
|
||||
|
||||
## Repository contents
|
||||
|
||||
See [doc/index.md](doc/index.md) for more explanation. See
|
||||
[doc/impl.md](doc/impl.md) for a brief overview of the implementation.
|
||||
See doc/index.html for more explanation. See doc/impl.html for a brief overview of the implementation.
|
||||
|
||||
The public interface is in include/*.h. Callers should not include or
|
||||
rely on the details of any other header files in this package. Those
|
||||
@@ -149,7 +113,7 @@ Guide to header files:
|
||||
* **include/options.h**: Control over the behavior of an entire database,
|
||||
and also control over the behavior of individual reads and writes.
|
||||
|
||||
* **include/comparator.h**: Abstraction for user-specified comparison function.
|
||||
* **include/comparator.h**: Abstraction for user-specified comparison function.
|
||||
If you want just bytewise comparison of keys, you can use the default
|
||||
comparator, but clients can write their own comparator implementations if they
|
||||
want custom ordering (e.g. to handle different character encodings, etc.)
|
||||
@@ -166,7 +130,7 @@ length into some other byte array.
|
||||
* **include/status.h**: Status is returned from many of the public interfaces
|
||||
and is used to report success and various kinds of errors.
|
||||
|
||||
* **include/env.h**:
|
||||
* **include/env.h**:
|
||||
Abstraction of the OS environment. A posix implementation of this interface is
|
||||
in util/env_posix.cc
|
||||
|
||||
|
||||
@@ -63,7 +63,6 @@ PLATFORM_SHARED_EXT="so"
|
||||
PLATFORM_SHARED_LDFLAGS="-shared -Wl,-soname -Wl,"
|
||||
PLATFORM_SHARED_CFLAGS="-fPIC"
|
||||
PLATFORM_SHARED_VERSIONED=true
|
||||
PLATFORM_SSEFLAGS=
|
||||
|
||||
MEMCMP_FLAG=
|
||||
if [ "$CXX" = "g++" ]; then
|
||||
@@ -78,7 +77,6 @@ case "$TARGET_OS" in
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -lpthread -DOS_LINUX -DCYGWIN"
|
||||
PLATFORM_LDFLAGS="-lpthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
Darwin)
|
||||
PLATFORM=OS_MACOSX
|
||||
@@ -87,56 +85,48 @@ case "$TARGET_OS" in
|
||||
[ -z "$INSTALL_PATH" ] && INSTALL_PATH=`pwd`
|
||||
PLATFORM_SHARED_LDFLAGS="-dynamiclib -install_name $INSTALL_PATH/"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
Linux)
|
||||
PLATFORM=OS_LINUX
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -pthread -DOS_LINUX"
|
||||
PLATFORM_LDFLAGS="-pthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
SunOS)
|
||||
PLATFORM=OS_SOLARIS
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_SOLARIS"
|
||||
PLATFORM_LIBS="-lpthread -lrt"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
FreeBSD)
|
||||
PLATFORM=OS_FREEBSD
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_FREEBSD"
|
||||
PLATFORM_LIBS="-lpthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
NetBSD)
|
||||
PLATFORM=OS_NETBSD
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_NETBSD"
|
||||
PLATFORM_LIBS="-lpthread -lgcc_s"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
OpenBSD)
|
||||
PLATFORM=OS_OPENBSD
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_OPENBSD"
|
||||
PLATFORM_LDFLAGS="-pthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
DragonFly)
|
||||
PLATFORM=OS_DRAGONFLYBSD
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_DRAGONFLYBSD"
|
||||
PLATFORM_LIBS="-lpthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
;;
|
||||
OS_ANDROID_CROSSCOMPILE)
|
||||
PLATFORM=OS_ANDROID
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_ANDROID -DLEVELDB_PLATFORM_POSIX"
|
||||
PLATFORM_LDFLAGS="" # All pthread features are in the Android C library
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
CROSS_COMPILE=true
|
||||
;;
|
||||
HP-UX)
|
||||
@@ -144,7 +134,6 @@ case "$TARGET_OS" in
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -D_REENTRANT -DOS_HPUX"
|
||||
PLATFORM_LDFLAGS="-pthread"
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
# man ld: +h internal_name
|
||||
PLATFORM_SHARED_LDFLAGS="-shared -Wl,+h -Wl,"
|
||||
;;
|
||||
@@ -153,7 +142,6 @@ case "$TARGET_OS" in
|
||||
COMMON_FLAGS="$MEMCMP_FLAG -DOS_MACOSX"
|
||||
[ -z "$INSTALL_PATH" ] && INSTALL_PATH=`pwd`
|
||||
PORT_FILE=port/port_posix.cc
|
||||
PORT_SSE_FILE=port/port_posix_sse.cc
|
||||
PLATFORM_SHARED_EXT=
|
||||
PLATFORM_SHARED_LDFLAGS=
|
||||
PLATFORM_SHARED_CFLAGS=
|
||||
@@ -173,14 +161,14 @@ DIRS="$PREFIX/db $PREFIX/util $PREFIX/table"
|
||||
set -f # temporarily disable globbing so that our patterns aren't expanded
|
||||
PRUNE_TEST="-name *test*.cc -prune"
|
||||
PRUNE_BENCH="-name *_bench.cc -prune"
|
||||
PRUNE_TOOL="-name leveldbutil.cc -prune"
|
||||
PRUNE_TOOL="-name leveldb_main.cc -prune"
|
||||
PORTABLE_FILES=`find $DIRS $PRUNE_TEST -o $PRUNE_BENCH -o $PRUNE_TOOL -o -name '*.cc' -print | sort | sed "s,^$PREFIX/,," | tr "\n" " "`
|
||||
|
||||
set +f # re-enable globbing
|
||||
|
||||
# The sources consist of the portable files, plus the platform-specific port
|
||||
# file.
|
||||
echo "SOURCES=$PORTABLE_FILES $PORT_FILE $PORT_SSE_FILE" >> $OUTPUT
|
||||
echo "SOURCES=$PORTABLE_FILES $PORT_FILE" >> $OUTPUT
|
||||
echo "MEMENV_SOURCES=helpers/memenv/memenv.cc" >> $OUTPUT
|
||||
|
||||
if [ "$CROSS_COMPILE" = "true" ]; then
|
||||
@@ -222,21 +210,6 @@ EOF
|
||||
fi
|
||||
|
||||
rm -f $CXXOUTPUT 2>/dev/null
|
||||
|
||||
# Test if gcc SSE 4.2 is supported
|
||||
$CXX $CXXFLAGS -x c++ - -o $CXXOUTPUT -msse4.2 2>/dev/null <<EOF
|
||||
int main() {}
|
||||
EOF
|
||||
if [ "$?" = 0 ]; then
|
||||
PLATFORM_SSEFLAGS="-msse4.2"
|
||||
fi
|
||||
|
||||
rm -f $CXXOUTPUT 2>/dev/null
|
||||
fi
|
||||
|
||||
# Use the SSE 4.2 CRC32C intrinsics iff runtime checks indicate compiler supports them.
|
||||
if [ -n "$PLATFORM_SSEFLAGS" ]; then
|
||||
PLATFORM_SSEFLAGS="$PLATFORM_SSEFLAGS -DLEVELDB_PLATFORM_POSIX_SSE"
|
||||
fi
|
||||
|
||||
PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
|
||||
@@ -249,7 +222,6 @@ echo "PLATFORM_LDFLAGS=$PLATFORM_LDFLAGS" >> $OUTPUT
|
||||
echo "PLATFORM_LIBS=$PLATFORM_LIBS" >> $OUTPUT
|
||||
echo "PLATFORM_CCFLAGS=$PLATFORM_CCFLAGS" >> $OUTPUT
|
||||
echo "PLATFORM_CXXFLAGS=$PLATFORM_CXXFLAGS" >> $OUTPUT
|
||||
echo "PLATFORM_SSEFLAGS=$PLATFORM_SSEFLAGS" >> $OUTPUT
|
||||
echo "PLATFORM_SHARED_CFLAGS=$PLATFORM_SHARED_CFLAGS" >> $OUTPUT
|
||||
echo "PLATFORM_SHARED_EXT=$PLATFORM_SHARED_EXT" >> $OUTPUT
|
||||
echo "PLATFORM_SHARED_LDFLAGS=$PLATFORM_SHARED_LDFLAGS" >> $OUTPUT
|
||||
|
||||
@@ -84,14 +84,6 @@ static bool FLAGS_histogram = false;
|
||||
// (initialized to default value by "main")
|
||||
static int FLAGS_write_buffer_size = 0;
|
||||
|
||||
// Number of bytes written to each file.
|
||||
// (initialized to default value by "main")
|
||||
static int FLAGS_max_file_size = 0;
|
||||
|
||||
// Approximate size of user data packed per block (before compression.
|
||||
// (initialized to default value by "main")
|
||||
static int FLAGS_block_size = 0;
|
||||
|
||||
// Number of bytes to use as a cache of uncompressed data.
|
||||
// Negative means use default settings.
|
||||
static int FLAGS_cache_size = -1;
|
||||
@@ -117,7 +109,6 @@ static const char* FLAGS_db = NULL;
|
||||
namespace leveldb {
|
||||
|
||||
namespace {
|
||||
leveldb::Env* g_env = NULL;
|
||||
|
||||
// Helper for quickly generating random data.
|
||||
class RandomGenerator {
|
||||
@@ -195,7 +186,7 @@ class Stats {
|
||||
done_ = 0;
|
||||
bytes_ = 0;
|
||||
seconds_ = 0;
|
||||
start_ = g_env->NowMicros();
|
||||
start_ = Env::Default()->NowMicros();
|
||||
finish_ = start_;
|
||||
message_.clear();
|
||||
}
|
||||
@@ -213,7 +204,7 @@ class Stats {
|
||||
}
|
||||
|
||||
void Stop() {
|
||||
finish_ = g_env->NowMicros();
|
||||
finish_ = Env::Default()->NowMicros();
|
||||
seconds_ = (finish_ - start_) * 1e-6;
|
||||
}
|
||||
|
||||
@@ -223,7 +214,7 @@ class Stats {
|
||||
|
||||
void FinishedSingleOp() {
|
||||
if (FLAGS_histogram) {
|
||||
double now = g_env->NowMicros();
|
||||
double now = Env::Default()->NowMicros();
|
||||
double micros = now - last_op_finish_;
|
||||
hist_.Add(micros);
|
||||
if (micros > 20000) {
|
||||
@@ -413,10 +404,10 @@ class Benchmark {
|
||||
reads_(FLAGS_reads < 0 ? FLAGS_num : FLAGS_reads),
|
||||
heap_counter_(0) {
|
||||
std::vector<std::string> files;
|
||||
g_env->GetChildren(FLAGS_db, &files);
|
||||
Env::Default()->GetChildren(FLAGS_db, &files);
|
||||
for (size_t i = 0; i < files.size(); i++) {
|
||||
if (Slice(files[i]).starts_with("heap-")) {
|
||||
g_env->DeleteFile(std::string(FLAGS_db) + "/" + files[i]);
|
||||
Env::Default()->DeleteFile(std::string(FLAGS_db) + "/" + files[i]);
|
||||
}
|
||||
}
|
||||
if (!FLAGS_use_existing_db) {
|
||||
@@ -598,7 +589,7 @@ class Benchmark {
|
||||
arg[i].shared = &shared;
|
||||
arg[i].thread = new ThreadState(i);
|
||||
arg[i].thread->shared = &shared;
|
||||
g_env->StartThread(ThreadBody, &arg[i]);
|
||||
Env::Default()->StartThread(ThreadBody, &arg[i]);
|
||||
}
|
||||
|
||||
shared.mu.Lock();
|
||||
@@ -709,12 +700,9 @@ class Benchmark {
|
||||
void Open() {
|
||||
assert(db_ == NULL);
|
||||
Options options;
|
||||
options.env = g_env;
|
||||
options.create_if_missing = !FLAGS_use_existing_db;
|
||||
options.block_cache = cache_;
|
||||
options.write_buffer_size = FLAGS_write_buffer_size;
|
||||
options.max_file_size = FLAGS_max_file_size;
|
||||
options.block_size = FLAGS_block_size;
|
||||
options.max_open_files = FLAGS_open_files;
|
||||
options.filter_policy = filter_policy_;
|
||||
options.reuse_logs = FLAGS_reuse_logs;
|
||||
@@ -937,7 +925,7 @@ class Benchmark {
|
||||
char fname[100];
|
||||
snprintf(fname, sizeof(fname), "%s/heap-%04d", FLAGS_db, ++heap_counter_);
|
||||
WritableFile* file;
|
||||
Status s = g_env->NewWritableFile(fname, &file);
|
||||
Status s = Env::Default()->NewWritableFile(fname, &file);
|
||||
if (!s.ok()) {
|
||||
fprintf(stderr, "%s\n", s.ToString().c_str());
|
||||
return;
|
||||
@@ -946,7 +934,7 @@ class Benchmark {
|
||||
delete file;
|
||||
if (!ok) {
|
||||
fprintf(stderr, "heap profiling not supported\n");
|
||||
g_env->DeleteFile(fname);
|
||||
Env::Default()->DeleteFile(fname);
|
||||
}
|
||||
}
|
||||
};
|
||||
@@ -955,8 +943,6 @@ class Benchmark {
|
||||
|
||||
int main(int argc, char** argv) {
|
||||
FLAGS_write_buffer_size = leveldb::Options().write_buffer_size;
|
||||
FLAGS_max_file_size = leveldb::Options().max_file_size;
|
||||
FLAGS_block_size = leveldb::Options().block_size;
|
||||
FLAGS_open_files = leveldb::Options().max_open_files;
|
||||
std::string default_db_path;
|
||||
|
||||
@@ -987,10 +973,6 @@ int main(int argc, char** argv) {
|
||||
FLAGS_value_size = n;
|
||||
} else if (sscanf(argv[i], "--write_buffer_size=%d%c", &n, &junk) == 1) {
|
||||
FLAGS_write_buffer_size = n;
|
||||
} else if (sscanf(argv[i], "--max_file_size=%d%c", &n, &junk) == 1) {
|
||||
FLAGS_max_file_size = n;
|
||||
} else if (sscanf(argv[i], "--block_size=%d%c", &n, &junk) == 1) {
|
||||
FLAGS_block_size = n;
|
||||
} else if (sscanf(argv[i], "--cache_size=%d%c", &n, &junk) == 1) {
|
||||
FLAGS_cache_size = n;
|
||||
} else if (sscanf(argv[i], "--bloom_bits=%d%c", &n, &junk) == 1) {
|
||||
@@ -1005,11 +987,9 @@ int main(int argc, char** argv) {
|
||||
}
|
||||
}
|
||||
|
||||
leveldb::g_env = leveldb::Env::Default();
|
||||
|
||||
// Choose a location for the test database if none given with --db=<path>
|
||||
if (FLAGS_db == NULL) {
|
||||
leveldb::g_env->GetTestDirectory(&default_db_path);
|
||||
leveldb::Env::Default()->GetTestDirectory(&default_db_path);
|
||||
default_db_path += "/dbbench";
|
||||
FLAGS_db = default_db_path.c_str();
|
||||
}
|
||||
|
||||
@@ -96,7 +96,6 @@ Options SanitizeOptions(const std::string& dbname,
|
||||
result.filter_policy = (src.filter_policy != NULL) ? ipolicy : NULL;
|
||||
ClipToRange(&result.max_open_files, 64 + kNumNonTableCacheFiles, 50000);
|
||||
ClipToRange(&result.write_buffer_size, 64<<10, 1<<30);
|
||||
ClipToRange(&result.max_file_size, 1<<20, 1<<30);
|
||||
ClipToRange(&result.block_size, 1<<10, 4<<20);
|
||||
if (result.info_log == NULL) {
|
||||
// Open a log file in the same directory as the db
|
||||
@@ -852,9 +851,8 @@ Status DBImpl::FinishCompactionOutputFile(CompactionState* compact,
|
||||
delete iter;
|
||||
if (s.ok()) {
|
||||
Log(options_.info_log,
|
||||
"Generated table #%llu@%d: %lld keys, %lld bytes",
|
||||
"Generated table #%llu: %lld keys, %lld bytes",
|
||||
(unsigned long long) output_number,
|
||||
compact->compaction->level(),
|
||||
(unsigned long long) current_entries,
|
||||
(unsigned long long) current_bytes);
|
||||
}
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||
//
|
||||
// Log format information shared by reader and writer.
|
||||
// See ../doc/log_format.md for more detail.
|
||||
// See ../doc/log_format.txt for more detail.
|
||||
|
||||
#ifndef STORAGE_LEVELDB_DB_LOG_FORMAT_H_
|
||||
#define STORAGE_LEVELDB_DB_LOG_FORMAT_H_
|
||||
|
||||
@@ -25,8 +25,7 @@ Reader::Reader(SequentialFile* file, Reporter* reporter, bool checksum,
|
||||
eof_(false),
|
||||
last_record_offset_(0),
|
||||
end_of_buffer_offset_(0),
|
||||
initial_offset_(initial_offset),
|
||||
resyncing_(initial_offset > 0) {
|
||||
initial_offset_(initial_offset) {
|
||||
}
|
||||
|
||||
Reader::~Reader() {
|
||||
@@ -73,25 +72,8 @@ bool Reader::ReadRecord(Slice* record, std::string* scratch) {
|
||||
|
||||
Slice fragment;
|
||||
while (true) {
|
||||
uint64_t physical_record_offset = end_of_buffer_offset_ - buffer_.size();
|
||||
const unsigned int record_type = ReadPhysicalRecord(&fragment);
|
||||
|
||||
// ReadPhysicalRecord may have only had an empty trailer remaining in its
|
||||
// internal buffer. Calculate the offset of the next physical record now
|
||||
// that it has returned, properly accounting for its header size.
|
||||
uint64_t physical_record_offset =
|
||||
end_of_buffer_offset_ - buffer_.size() - kHeaderSize - fragment.size();
|
||||
|
||||
if (resyncing_) {
|
||||
if (record_type == kMiddleType) {
|
||||
continue;
|
||||
} else if (record_type == kLastType) {
|
||||
resyncing_ = false;
|
||||
continue;
|
||||
} else {
|
||||
resyncing_ = false;
|
||||
}
|
||||
}
|
||||
|
||||
switch (record_type) {
|
||||
case kFullType:
|
||||
if (in_fragmented_record) {
|
||||
|
||||
@@ -73,11 +73,6 @@ class Reader {
|
||||
// Offset at which to start looking for the first record to return
|
||||
uint64_t const initial_offset_;
|
||||
|
||||
// True if we are resynchronizing after a seek (initial_offset_ > 0). In
|
||||
// particular, a run of kMiddleType and kLastType records can be silently
|
||||
// skipped in this mode
|
||||
bool resyncing_;
|
||||
|
||||
// Extend record types with the following special values
|
||||
enum {
|
||||
kEof = kMaxRecordType + 1,
|
||||
|
||||
@@ -79,7 +79,7 @@ class LogTest {
|
||||
virtual Status Skip(uint64_t n) {
|
||||
if (n > contents_.size()) {
|
||||
contents_.clear();
|
||||
return Status::NotFound("in-memory file skipped past end");
|
||||
return Status::NotFound("in-memory file skipepd past end");
|
||||
}
|
||||
|
||||
contents_.remove_prefix(n);
|
||||
@@ -105,23 +105,21 @@ class LogTest {
|
||||
ReportCollector report_;
|
||||
bool reading_;
|
||||
Writer* writer_;
|
||||
Reader* reader_;
|
||||
Reader reader_;
|
||||
|
||||
// Record metadata for testing initial offset functionality
|
||||
static size_t initial_offset_record_sizes_[];
|
||||
static uint64_t initial_offset_last_record_offsets_[];
|
||||
static int num_initial_offset_records_;
|
||||
|
||||
public:
|
||||
LogTest() : reading_(false),
|
||||
writer_(new Writer(&dest_)),
|
||||
reader_(new Reader(&source_, &report_, true/*checksum*/,
|
||||
0/*initial_offset*/)) {
|
||||
reader_(&source_, &report_, true/*checksum*/,
|
||||
0/*initial_offset*/) {
|
||||
}
|
||||
|
||||
~LogTest() {
|
||||
delete writer_;
|
||||
delete reader_;
|
||||
}
|
||||
|
||||
void ReopenForAppend() {
|
||||
@@ -145,7 +143,7 @@ class LogTest {
|
||||
}
|
||||
std::string scratch;
|
||||
Slice record;
|
||||
if (reader_->ReadRecord(&record, &scratch)) {
|
||||
if (reader_.ReadRecord(&record, &scratch)) {
|
||||
return record.ToString();
|
||||
} else {
|
||||
return "EOF";
|
||||
@@ -193,18 +191,13 @@ class LogTest {
|
||||
}
|
||||
|
||||
void WriteInitialOffsetLog() {
|
||||
for (int i = 0; i < num_initial_offset_records_; i++) {
|
||||
for (int i = 0; i < 4; i++) {
|
||||
std::string record(initial_offset_record_sizes_[i],
|
||||
static_cast<char>('a' + i));
|
||||
Write(record);
|
||||
}
|
||||
}
|
||||
|
||||
void StartReadingAt(uint64_t initial_offset) {
|
||||
delete reader_;
|
||||
reader_ = new Reader(&source_, &report_, true/*checksum*/, initial_offset);
|
||||
}
|
||||
|
||||
void CheckOffsetPastEndReturnsNoRecords(uint64_t offset_past_end) {
|
||||
WriteInitialOffsetLog();
|
||||
reading_ = true;
|
||||
@@ -224,48 +217,32 @@ class LogTest {
|
||||
source_.contents_ = Slice(dest_.contents_);
|
||||
Reader* offset_reader = new Reader(&source_, &report_, true/*checksum*/,
|
||||
initial_offset);
|
||||
|
||||
// Read all records from expected_record_offset through the last one.
|
||||
ASSERT_LT(expected_record_offset, num_initial_offset_records_);
|
||||
for (; expected_record_offset < num_initial_offset_records_;
|
||||
++expected_record_offset) {
|
||||
Slice record;
|
||||
std::string scratch;
|
||||
ASSERT_TRUE(offset_reader->ReadRecord(&record, &scratch));
|
||||
ASSERT_EQ(initial_offset_record_sizes_[expected_record_offset],
|
||||
record.size());
|
||||
ASSERT_EQ(initial_offset_last_record_offsets_[expected_record_offset],
|
||||
offset_reader->LastRecordOffset());
|
||||
ASSERT_EQ((char)('a' + expected_record_offset), record.data()[0]);
|
||||
}
|
||||
Slice record;
|
||||
std::string scratch;
|
||||
ASSERT_TRUE(offset_reader->ReadRecord(&record, &scratch));
|
||||
ASSERT_EQ(initial_offset_record_sizes_[expected_record_offset],
|
||||
record.size());
|
||||
ASSERT_EQ(initial_offset_last_record_offsets_[expected_record_offset],
|
||||
offset_reader->LastRecordOffset());
|
||||
ASSERT_EQ((char)('a' + expected_record_offset), record.data()[0]);
|
||||
delete offset_reader;
|
||||
}
|
||||
|
||||
};
|
||||
|
||||
size_t LogTest::initial_offset_record_sizes_[] =
|
||||
{10000, // Two sizable records in first block
|
||||
10000,
|
||||
2 * log::kBlockSize - 1000, // Span three blocks
|
||||
1,
|
||||
13716, // Consume all but two bytes of block 3.
|
||||
log::kBlockSize - kHeaderSize, // Consume the entirety of block 4.
|
||||
};
|
||||
1};
|
||||
|
||||
uint64_t LogTest::initial_offset_last_record_offsets_[] =
|
||||
{0,
|
||||
kHeaderSize + 10000,
|
||||
2 * (kHeaderSize + 10000),
|
||||
2 * (kHeaderSize + 10000) +
|
||||
(2 * log::kBlockSize - 1000) + 3 * kHeaderSize,
|
||||
2 * (kHeaderSize + 10000) +
|
||||
(2 * log::kBlockSize - 1000) + 3 * kHeaderSize
|
||||
+ kHeaderSize + 1,
|
||||
3 * log::kBlockSize,
|
||||
};
|
||||
(2 * log::kBlockSize - 1000) + 3 * kHeaderSize};
|
||||
|
||||
// LogTest::initial_offset_last_record_offsets_ must be defined before this.
|
||||
int LogTest::num_initial_offset_records_ =
|
||||
sizeof(LogTest::initial_offset_last_record_offsets_)/sizeof(uint64_t);
|
||||
|
||||
TEST(LogTest, Empty) {
|
||||
ASSERT_EQ("EOF", Read());
|
||||
@@ -486,22 +463,6 @@ TEST(LogTest, PartialLastIsIgnored) {
|
||||
ASSERT_EQ(0, DroppedBytes());
|
||||
}
|
||||
|
||||
TEST(LogTest, SkipIntoMultiRecord) {
|
||||
// Consider a fragmented record:
|
||||
// first(R1), middle(R1), last(R1), first(R2)
|
||||
// If initial_offset points to a record after first(R1) but before first(R2)
|
||||
// incomplete fragment errors are not actual errors, and must be suppressed
|
||||
// until a new first or full record is encountered.
|
||||
Write(BigString("foo", 3*kBlockSize));
|
||||
Write("correct");
|
||||
StartReadingAt(kBlockSize);
|
||||
|
||||
ASSERT_EQ("correct", Read());
|
||||
ASSERT_EQ("", ReportMessage());
|
||||
ASSERT_EQ(0, DroppedBytes());
|
||||
ASSERT_EQ("EOF", Read());
|
||||
}
|
||||
|
||||
TEST(LogTest, ErrorJoinsRecords) {
|
||||
// Consider two fragmented records:
|
||||
// first(R1) last(R1) first(R2) last(R2)
|
||||
@@ -571,10 +532,6 @@ TEST(LogTest, ReadFourthStart) {
|
||||
3);
|
||||
}
|
||||
|
||||
TEST(LogTest, ReadInitialOffsetIntoBlockPadding) {
|
||||
CheckInitialOffsetRecord(3 * log::kBlockSize - 3, 5);
|
||||
}
|
||||
|
||||
TEST(LogTest, ReadEnd) {
|
||||
CheckOffsetPastEndReturnsNoRecords(0);
|
||||
}
|
||||
|
||||
@@ -36,7 +36,10 @@ class MemTable {
|
||||
}
|
||||
|
||||
// Returns an estimate of the number of bytes of data in use by this
|
||||
// data structure. It is safe to call when MemTable is being modified.
|
||||
// data structure.
|
||||
//
|
||||
// REQUIRES: external synchronization to prevent simultaneous
|
||||
// operations on the same MemTable.
|
||||
size_t ApproximateMemoryUsage();
|
||||
|
||||
// Return an iterator that yields the contents of the memtable.
|
||||
|
||||
@@ -104,10 +104,10 @@ class RecoveryTest {
|
||||
return GetFiles(kLogFile)[0];
|
||||
}
|
||||
|
||||
std::vector<uint64_t> GetFiles(FileType t) {
|
||||
std::vector<std::uint64_t> GetFiles(FileType t) {
|
||||
std::vector<std::string> filenames;
|
||||
ASSERT_OK(env_->GetChildren(dbname_, &filenames));
|
||||
std::vector<uint64_t> result;
|
||||
std::vector<std::uint64_t> result;
|
||||
for (size_t i = 0; i < filenames.size(); i++) {
|
||||
uint64_t number;
|
||||
FileType type;
|
||||
|
||||
@@ -250,7 +250,7 @@ class ConcurrentTest {
|
||||
// Note that generation 0 is never inserted, so it is ok if
|
||||
// <*,0,*> is missing.
|
||||
ASSERT_TRUE((gen(pos) == 0) ||
|
||||
(gen(pos) > static_cast<Key>(initial_state.Get(key(pos))))
|
||||
(gen(pos) > initial_state.Get(key(pos)))
|
||||
) << "key: " << key(pos)
|
||||
<< "; gen: " << gen(pos)
|
||||
<< "; initgen: "
|
||||
|
||||
@@ -20,29 +20,21 @@
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
static int TargetFileSize(const Options* options) {
|
||||
return options->max_file_size;
|
||||
}
|
||||
static const int kTargetFileSize = 2 * 1048576;
|
||||
|
||||
// Maximum bytes of overlaps in grandparent (i.e., level+2) before we
|
||||
// stop building a single file in a level->level+1 compaction.
|
||||
static int64_t MaxGrandParentOverlapBytes(const Options* options) {
|
||||
return 10 * TargetFileSize(options);
|
||||
}
|
||||
static const int64_t kMaxGrandParentOverlapBytes = 10 * kTargetFileSize;
|
||||
|
||||
// Maximum number of bytes in all compacted files. We avoid expanding
|
||||
// the lower level file set of a compaction if it would make the
|
||||
// total compaction cover more than this many bytes.
|
||||
static int64_t ExpandedCompactionByteSizeLimit(const Options* options) {
|
||||
return 25 * TargetFileSize(options);
|
||||
}
|
||||
static const int64_t kExpandedCompactionByteSizeLimit = 25 * kTargetFileSize;
|
||||
|
||||
static double MaxBytesForLevel(const Options* options, int level) {
|
||||
static double MaxBytesForLevel(int level) {
|
||||
// Note: the result for level zero is not really used since we set
|
||||
// the level-0 compaction threshold based on number of files.
|
||||
|
||||
// Result for both level-0 and level-1
|
||||
double result = 10. * 1048576.0;
|
||||
double result = 10 * 1048576.0; // Result for both level-0 and level-1
|
||||
while (level > 1) {
|
||||
result *= 10;
|
||||
level--;
|
||||
@@ -50,9 +42,8 @@ static double MaxBytesForLevel(const Options* options, int level) {
|
||||
return result;
|
||||
}
|
||||
|
||||
static uint64_t MaxFileSizeForLevel(const Options* options, int level) {
|
||||
// We could vary per level to reduce number of files?
|
||||
return TargetFileSize(options);
|
||||
static uint64_t MaxFileSizeForLevel(int level) {
|
||||
return kTargetFileSize; // We could vary per level to reduce number of files?
|
||||
}
|
||||
|
||||
static int64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
|
||||
@@ -517,7 +508,7 @@ int Version::PickLevelForMemTableOutput(
|
||||
// Check that file does not overlap too many grandparent bytes.
|
||||
GetOverlappingInputs(level + 2, &start, &limit, &overlaps);
|
||||
const int64_t sum = TotalFileSize(overlaps);
|
||||
if (sum > MaxGrandParentOverlapBytes(vset_->options_)) {
|
||||
if (sum > kMaxGrandParentOverlapBytes) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
@@ -1036,7 +1027,7 @@ bool VersionSet::ReuseManifest(const std::string& dscname,
|
||||
manifest_type != kDescriptorFile ||
|
||||
!env_->GetFileSize(dscname, &manifest_size).ok() ||
|
||||
// Make new compacted MANIFEST if old one is too big
|
||||
manifest_size >= TargetFileSize(options_)) {
|
||||
manifest_size >= kTargetFileSize) {
|
||||
return false;
|
||||
}
|
||||
|
||||
@@ -1085,8 +1076,7 @@ void VersionSet::Finalize(Version* v) {
|
||||
} else {
|
||||
// Compute the ratio of current size to size limit.
|
||||
const uint64_t level_bytes = TotalFileSize(v->files_[level]);
|
||||
score =
|
||||
static_cast<double>(level_bytes) / MaxBytesForLevel(options_, level);
|
||||
score = static_cast<double>(level_bytes) / MaxBytesForLevel(level);
|
||||
}
|
||||
|
||||
if (score > best_score) {
|
||||
@@ -1300,7 +1290,7 @@ Compaction* VersionSet::PickCompaction() {
|
||||
level = current_->compaction_level_;
|
||||
assert(level >= 0);
|
||||
assert(level+1 < config::kNumLevels);
|
||||
c = new Compaction(options_, level);
|
||||
c = new Compaction(level);
|
||||
|
||||
// Pick the first file that comes after compact_pointer_[level]
|
||||
for (size_t i = 0; i < current_->files_[level].size(); i++) {
|
||||
@@ -1317,7 +1307,7 @@ Compaction* VersionSet::PickCompaction() {
|
||||
}
|
||||
} else if (seek_compaction) {
|
||||
level = current_->file_to_compact_level_;
|
||||
c = new Compaction(options_, level);
|
||||
c = new Compaction(level);
|
||||
c->inputs_[0].push_back(current_->file_to_compact_);
|
||||
} else {
|
||||
return NULL;
|
||||
@@ -1362,8 +1352,7 @@ void VersionSet::SetupOtherInputs(Compaction* c) {
|
||||
const int64_t inputs1_size = TotalFileSize(c->inputs_[1]);
|
||||
const int64_t expanded0_size = TotalFileSize(expanded0);
|
||||
if (expanded0.size() > c->inputs_[0].size() &&
|
||||
inputs1_size + expanded0_size <
|
||||
ExpandedCompactionByteSizeLimit(options_)) {
|
||||
inputs1_size + expanded0_size < kExpandedCompactionByteSizeLimit) {
|
||||
InternalKey new_start, new_limit;
|
||||
GetRange(expanded0, &new_start, &new_limit);
|
||||
std::vector<FileMetaData*> expanded1;
|
||||
@@ -1425,7 +1414,7 @@ Compaction* VersionSet::CompactRange(
|
||||
// and we must not pick one file and drop another older file if the
|
||||
// two files overlap.
|
||||
if (level > 0) {
|
||||
const uint64_t limit = MaxFileSizeForLevel(options_, level);
|
||||
const uint64_t limit = MaxFileSizeForLevel(level);
|
||||
uint64_t total = 0;
|
||||
for (size_t i = 0; i < inputs.size(); i++) {
|
||||
uint64_t s = inputs[i]->file_size;
|
||||
@@ -1437,7 +1426,7 @@ Compaction* VersionSet::CompactRange(
|
||||
}
|
||||
}
|
||||
|
||||
Compaction* c = new Compaction(options_, level);
|
||||
Compaction* c = new Compaction(level);
|
||||
c->input_version_ = current_;
|
||||
c->input_version_->Ref();
|
||||
c->inputs_[0] = inputs;
|
||||
@@ -1445,9 +1434,9 @@ Compaction* VersionSet::CompactRange(
|
||||
return c;
|
||||
}
|
||||
|
||||
Compaction::Compaction(const Options* options, int level)
|
||||
Compaction::Compaction(int level)
|
||||
: level_(level),
|
||||
max_output_file_size_(MaxFileSizeForLevel(options, level)),
|
||||
max_output_file_size_(MaxFileSizeForLevel(level)),
|
||||
input_version_(NULL),
|
||||
grandparent_index_(0),
|
||||
seen_key_(false),
|
||||
@@ -1464,13 +1453,12 @@ Compaction::~Compaction() {
|
||||
}
|
||||
|
||||
bool Compaction::IsTrivialMove() const {
|
||||
const VersionSet* vset = input_version_->vset_;
|
||||
// Avoid a move if there is lots of overlapping grandparent data.
|
||||
// Otherwise, the move could create a parent file that will require
|
||||
// a very expensive merge later on.
|
||||
return (num_input_files(0) == 1 && num_input_files(1) == 0 &&
|
||||
TotalFileSize(grandparents_) <=
|
||||
MaxGrandParentOverlapBytes(vset->options_));
|
||||
return (num_input_files(0) == 1 &&
|
||||
num_input_files(1) == 0 &&
|
||||
TotalFileSize(grandparents_) <= kMaxGrandParentOverlapBytes);
|
||||
}
|
||||
|
||||
void Compaction::AddInputDeletions(VersionEdit* edit) {
|
||||
@@ -1503,9 +1491,8 @@ bool Compaction::IsBaseLevelForKey(const Slice& user_key) {
|
||||
}
|
||||
|
||||
bool Compaction::ShouldStopBefore(const Slice& internal_key) {
|
||||
const VersionSet* vset = input_version_->vset_;
|
||||
// Scan to find earliest grandparent file that contains key.
|
||||
const InternalKeyComparator* icmp = &vset->icmp_;
|
||||
const InternalKeyComparator* icmp = &input_version_->vset_->icmp_;
|
||||
while (grandparent_index_ < grandparents_.size() &&
|
||||
icmp->Compare(internal_key,
|
||||
grandparents_[grandparent_index_]->largest.Encode()) > 0) {
|
||||
@@ -1516,7 +1503,7 @@ bool Compaction::ShouldStopBefore(const Slice& internal_key) {
|
||||
}
|
||||
seen_key_ = true;
|
||||
|
||||
if (overlapped_bytes_ > MaxGrandParentOverlapBytes(vset->options_)) {
|
||||
if (overlapped_bytes_ > kMaxGrandParentOverlapBytes) {
|
||||
// Too much overlap for current output; start new output
|
||||
overlapped_bytes_ = 0;
|
||||
return true;
|
||||
|
||||
@@ -366,7 +366,7 @@ class Compaction {
|
||||
friend class Version;
|
||||
friend class VersionSet;
|
||||
|
||||
Compaction(const Options* options, int level);
|
||||
explicit Compaction(int level);
|
||||
|
||||
int level_;
|
||||
uint64_t max_output_file_size_;
|
||||
|
||||
89
doc/doc.css
Normal file
89
doc/doc.css
Normal file
@@ -0,0 +1,89 @@
|
||||
body {
|
||||
margin-left: 0.5in;
|
||||
margin-right: 0.5in;
|
||||
background: white;
|
||||
color: black;
|
||||
}
|
||||
|
||||
h1 {
|
||||
margin-left: -0.2in;
|
||||
font-size: 14pt;
|
||||
}
|
||||
h2 {
|
||||
margin-left: -0in;
|
||||
font-size: 12pt;
|
||||
}
|
||||
h3 {
|
||||
margin-left: -0in;
|
||||
}
|
||||
h4 {
|
||||
margin-left: -0in;
|
||||
}
|
||||
hr {
|
||||
margin-left: -0in;
|
||||
}
|
||||
|
||||
/* Definition lists: definition term bold */
|
||||
dt {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
address {
|
||||
text-align: center;
|
||||
}
|
||||
code,samp,var {
|
||||
color: blue;
|
||||
}
|
||||
kbd {
|
||||
color: #600000;
|
||||
}
|
||||
div.note p {
|
||||
float: right;
|
||||
width: 3in;
|
||||
margin-right: 0%;
|
||||
padding: 1px;
|
||||
border: 2px solid #6060a0;
|
||||
background-color: #fffff0;
|
||||
}
|
||||
|
||||
ul {
|
||||
margin-top: -0em;
|
||||
margin-bottom: -0em;
|
||||
}
|
||||
|
||||
ol {
|
||||
margin-top: -0em;
|
||||
margin-bottom: -0em;
|
||||
}
|
||||
|
||||
UL.nobullets {
|
||||
list-style-type: none;
|
||||
list-style-image: none;
|
||||
margin-left: -1em;
|
||||
}
|
||||
|
||||
p {
|
||||
margin: 1em 0 1em 0;
|
||||
padding: 0 0 0 0;
|
||||
}
|
||||
|
||||
pre {
|
||||
line-height: 1.3em;
|
||||
padding: 0.4em 0 0.8em 0;
|
||||
margin: 0 0 0 0;
|
||||
border: 0 0 0 0;
|
||||
color: blue;
|
||||
}
|
||||
|
||||
.datatable {
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
margin-top: 2em;
|
||||
margin-bottom: 2em;
|
||||
border: 1px solid;
|
||||
}
|
||||
|
||||
.datatable td,th {
|
||||
padding: 0 0.5em 0 0.5em;
|
||||
text-align: right;
|
||||
}
|
||||
213
doc/impl.html
Normal file
213
doc/impl.html
Normal file
@@ -0,0 +1,213 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<link rel="stylesheet" type="text/css" href="doc.css" />
|
||||
<title>Leveldb file layout and compactions</title>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
|
||||
<h1>Files</h1>
|
||||
|
||||
The implementation of leveldb is similar in spirit to the
|
||||
representation of a single
|
||||
<a href="http://research.google.com/archive/bigtable.html">
|
||||
Bigtable tablet (section 5.3)</a>.
|
||||
However the organization of the files that make up the representation
|
||||
is somewhat different and is explained below.
|
||||
|
||||
<p>
|
||||
Each database is represented by a set of files stored in a directory.
|
||||
There are several different types of files as documented below:
|
||||
<p>
|
||||
<h2>Log files</h2>
|
||||
<p>
|
||||
A log file (*.log) stores a sequence of recent updates. Each update
|
||||
is appended to the current log file. When the log file reaches a
|
||||
pre-determined size (approximately 4MB by default), it is converted
|
||||
to a sorted table (see below) and a new log file is created for future
|
||||
updates.
|
||||
<p>
|
||||
A copy of the current log file is kept in an in-memory structure (the
|
||||
<code>memtable</code>). This copy is consulted on every read so that read
|
||||
operations reflect all logged updates.
|
||||
<p>
|
||||
<h2>Sorted tables</h2>
|
||||
<p>
|
||||
A sorted table (*.sst) stores a sequence of entries sorted by key.
|
||||
Each entry is either a value for the key, or a deletion marker for the
|
||||
key. (Deletion markers are kept around to hide obsolete values
|
||||
present in older sorted tables).
|
||||
<p>
|
||||
The set of sorted tables are organized into a sequence of levels. The
|
||||
sorted table generated from a log file is placed in a special <code>young</code>
|
||||
level (also called level-0). When the number of young files exceeds a
|
||||
certain threshold (currently four), all of the young files are merged
|
||||
together with all of the overlapping level-1 files to produce a
|
||||
sequence of new level-1 files (we create a new level-1 file for every
|
||||
2MB of data.)
|
||||
<p>
|
||||
Files in the young level may contain overlapping keys. However files
|
||||
in other levels have distinct non-overlapping key ranges. Consider
|
||||
level number L where L >= 1. When the combined size of files in
|
||||
level-L exceeds (10^L) MB (i.e., 10MB for level-1, 100MB for level-2,
|
||||
...), one file in level-L, and all of the overlapping files in
|
||||
level-(L+1) are merged to form a set of new files for level-(L+1).
|
||||
These merges have the effect of gradually migrating new updates from
|
||||
the young level to the largest level using only bulk reads and writes
|
||||
(i.e., minimizing expensive seeks).
|
||||
|
||||
<h2>Manifest</h2>
|
||||
<p>
|
||||
A MANIFEST file lists the set of sorted tables that make up each
|
||||
level, the corresponding key ranges, and other important metadata.
|
||||
A new MANIFEST file (with a new number embedded in the file name)
|
||||
is created whenever the database is reopened. The MANIFEST file is
|
||||
formatted as a log, and changes made to the serving state (as files
|
||||
are added or removed) are appended to this log.
|
||||
<p>
|
||||
<h2>Current</h2>
|
||||
<p>
|
||||
CURRENT is a simple text file that contains the name of the latest
|
||||
MANIFEST file.
|
||||
<p>
|
||||
<h2>Info logs</h2>
|
||||
<p>
|
||||
Informational messages are printed to files named LOG and LOG.old.
|
||||
<p>
|
||||
<h2>Others</h2>
|
||||
<p>
|
||||
Other files used for miscellaneous purposes may also be present
|
||||
(LOCK, *.dbtmp).
|
||||
|
||||
<h1>Level 0</h1>
|
||||
When the log file grows above a certain size (1MB by default):
|
||||
<ul>
|
||||
<li>Create a brand new memtable and log file and direct future updates here
|
||||
<li>In the background:
|
||||
<ul>
|
||||
<li>Write the contents of the previous memtable to an sstable
|
||||
<li>Discard the memtable
|
||||
<li>Delete the old log file and the old memtable
|
||||
<li>Add the new sstable to the young (level-0) level.
|
||||
</ul>
|
||||
</ul>
|
||||
|
||||
<h1>Compactions</h1>
|
||||
|
||||
<p>
|
||||
When the size of level L exceeds its limit, we compact it in a
|
||||
background thread. The compaction picks a file from level L and all
|
||||
overlapping files from the next level L+1. Note that if a level-L
|
||||
file overlaps only part of a level-(L+1) file, the entire file at
|
||||
level-(L+1) is used as an input to the compaction and will be
|
||||
discarded after the compaction. Aside: because level-0 is special
|
||||
(files in it may overlap each other), we treat compactions from
|
||||
level-0 to level-1 specially: a level-0 compaction may pick more than
|
||||
one level-0 file in case some of these files overlap each other.
|
||||
|
||||
<p>
|
||||
A compaction merges the contents of the picked files to produce a
|
||||
sequence of level-(L+1) files. We switch to producing a new
|
||||
level-(L+1) file after the current output file has reached the target
|
||||
file size (2MB). We also switch to a new output file when the key
|
||||
range of the current output file has grown enough to overlap more than
|
||||
ten level-(L+2) files. This last rule ensures that a later compaction
|
||||
of a level-(L+1) file will not pick up too much data from level-(L+2).
|
||||
|
||||
<p>
|
||||
The old files are discarded and the new files are added to the serving
|
||||
state.
|
||||
|
||||
<p>
|
||||
Compactions for a particular level rotate through the key space. In
|
||||
more detail, for each level L, we remember the ending key of the last
|
||||
compaction at level L. The next compaction for level L will pick the
|
||||
first file that starts after this key (wrapping around to the
|
||||
beginning of the key space if there is no such file).
|
||||
|
||||
<p>
|
||||
Compactions drop overwritten values. They also drop deletion markers
|
||||
if there are no higher numbered levels that contain a file whose range
|
||||
overlaps the current key.
|
||||
|
||||
<h2>Timing</h2>
|
||||
|
||||
Level-0 compactions will read up to four 1MB files from level-0, and
|
||||
at worst all the level-1 files (10MB). I.e., we will read 14MB and
|
||||
write 14MB.
|
||||
|
||||
<p>
|
||||
Other than the special level-0 compactions, we will pick one 2MB file
|
||||
from level L. In the worst case, this will overlap ~ 12 files from
|
||||
level L+1 (10 because level-(L+1) is ten times the size of level-L,
|
||||
and another two at the boundaries since the file ranges at level-L
|
||||
will usually not be aligned with the file ranges at level-L+1). The
|
||||
compaction will therefore read 26MB and write 26MB. Assuming a disk
|
||||
IO rate of 100MB/s (ballpark range for modern drives), the worst
|
||||
compaction cost will be approximately 0.5 second.
|
||||
|
||||
<p>
|
||||
If we throttle the background writing to something small, say 10% of
|
||||
the full 100MB/s speed, a compaction may take up to 5 seconds. If the
|
||||
user is writing at 10MB/s, we might build up lots of level-0 files
|
||||
(~50 to hold the 5*10MB). This may significantly increase the cost of
|
||||
reads due to the overhead of merging more files together on every
|
||||
read.
|
||||
|
||||
<p>
|
||||
Solution 1: To reduce this problem, we might want to increase the log
|
||||
switching threshold when the number of level-0 files is large. Though
|
||||
the downside is that the larger this threshold, the more memory we will
|
||||
need to hold the corresponding memtable.
|
||||
|
||||
<p>
|
||||
Solution 2: We might want to decrease write rate artificially when the
|
||||
number of level-0 files goes up.
|
||||
|
||||
<p>
|
||||
Solution 3: We work on reducing the cost of very wide merges.
|
||||
Perhaps most of the level-0 files will have their blocks sitting
|
||||
uncompressed in the cache and we will only need to worry about the
|
||||
O(N) complexity in the merging iterator.
|
||||
|
||||
<h2>Number of files</h2>
|
||||
|
||||
Instead of always making 2MB files, we could make larger files for
|
||||
larger levels to reduce the total file count, though at the expense of
|
||||
more bursty compactions. Alternatively, we could shard the set of
|
||||
files into multiple directories.
|
||||
|
||||
<p>
|
||||
An experiment on an <code>ext3</code> filesystem on Feb 04, 2011 shows
|
||||
the following timings to do 100K file opens in directories with
|
||||
varying number of files:
|
||||
<table class="datatable">
|
||||
<tr><th>Files in directory</th><th>Microseconds to open a file</th></tr>
|
||||
<tr><td>1000</td><td>9</td>
|
||||
<tr><td>10000</td><td>10</td>
|
||||
<tr><td>100000</td><td>16</td>
|
||||
</table>
|
||||
So maybe even the sharding is not necessary on modern filesystems?
|
||||
|
||||
<h1>Recovery</h1>
|
||||
|
||||
<ul>
|
||||
<li> Read CURRENT to find name of the latest committed MANIFEST
|
||||
<li> Read the named MANIFEST file
|
||||
<li> Clean up stale files
|
||||
<li> We could open all sstables here, but it is probably better to be lazy...
|
||||
<li> Convert log chunk to a new level-0 sstable
|
||||
<li> Start directing new writes to a new log file with recovered sequence#
|
||||
</ul>
|
||||
|
||||
<h1>Garbage collection of files</h1>
|
||||
|
||||
<code>DeleteObsoleteFiles()</code> is called at the end of every
|
||||
compaction and at the end of recovery. It finds the names of all
|
||||
files in the database. It deletes all log files that are not the
|
||||
current log file. It deletes all table files that are not referenced
|
||||
from some level and are not the output of an active compaction.
|
||||
|
||||
</body>
|
||||
</html>
|
||||
170
doc/impl.md
170
doc/impl.md
@@ -1,170 +0,0 @@
|
||||
## Files
|
||||
|
||||
The implementation of leveldb is similar in spirit to the representation of a
|
||||
single [Bigtable tablet (section 5.3)](http://research.google.com/archive/bigtable.html).
|
||||
However the organization of the files that make up the representation is
|
||||
somewhat different and is explained below.
|
||||
|
||||
Each database is represented by a set of files stored in a directory. There are
|
||||
several different types of files as documented below:
|
||||
|
||||
### Log files
|
||||
|
||||
A log file (*.log) stores a sequence of recent updates. Each update is appended
|
||||
to the current log file. When the log file reaches a pre-determined size
|
||||
(approximately 4MB by default), it is converted to a sorted table (see below)
|
||||
and a new log file is created for future updates.
|
||||
|
||||
A copy of the current log file is kept in an in-memory structure (the
|
||||
`memtable`). This copy is consulted on every read so that read operations
|
||||
reflect all logged updates.
|
||||
|
||||
## Sorted tables
|
||||
|
||||
A sorted table (*.ldb) stores a sequence of entries sorted by key. Each entry is
|
||||
either a value for the key, or a deletion marker for the key. (Deletion markers
|
||||
are kept around to hide obsolete values present in older sorted tables).
|
||||
|
||||
The set of sorted tables are organized into a sequence of levels. The sorted
|
||||
table generated from a log file is placed in a special **young** level (also
|
||||
called level-0). When the number of young files exceeds a certain threshold
|
||||
(currently four), all of the young files are merged together with all of the
|
||||
overlapping level-1 files to produce a sequence of new level-1 files (we create
|
||||
a new level-1 file for every 2MB of data.)
|
||||
|
||||
Files in the young level may contain overlapping keys. However files in other
|
||||
levels have distinct non-overlapping key ranges. Consider level number L where
|
||||
L >= 1. When the combined size of files in level-L exceeds (10^L) MB (i.e., 10MB
|
||||
for level-1, 100MB for level-2, ...), one file in level-L, and all of the
|
||||
overlapping files in level-(L+1) are merged to form a set of new files for
|
||||
level-(L+1). These merges have the effect of gradually migrating new updates
|
||||
from the young level to the largest level using only bulk reads and writes
|
||||
(i.e., minimizing expensive seeks).
|
||||
|
||||
### Manifest
|
||||
|
||||
A MANIFEST file lists the set of sorted tables that make up each level, the
|
||||
corresponding key ranges, and other important metadata. A new MANIFEST file
|
||||
(with a new number embedded in the file name) is created whenever the database
|
||||
is reopened. The MANIFEST file is formatted as a log, and changes made to the
|
||||
serving state (as files are added or removed) are appended to this log.
|
||||
|
||||
### Current
|
||||
|
||||
CURRENT is a simple text file that contains the name of the latest MANIFEST
|
||||
file.
|
||||
|
||||
### Info logs
|
||||
|
||||
Informational messages are printed to files named LOG and LOG.old.
|
||||
|
||||
### Others
|
||||
|
||||
Other files used for miscellaneous purposes may also be present (LOCK, *.dbtmp).
|
||||
|
||||
## Level 0
|
||||
|
||||
When the log file grows above a certain size (1MB by default):
|
||||
Create a brand new memtable and log file and direct future updates here
|
||||
In the background:
|
||||
Write the contents of the previous memtable to an sstable
|
||||
Discard the memtable
|
||||
Delete the old log file and the old memtable
|
||||
Add the new sstable to the young (level-0) level.
|
||||
|
||||
## Compactions
|
||||
|
||||
When the size of level L exceeds its limit, we compact it in a background
|
||||
thread. The compaction picks a file from level L and all overlapping files from
|
||||
the next level L+1. Note that if a level-L file overlaps only part of a
|
||||
level-(L+1) file, the entire file at level-(L+1) is used as an input to the
|
||||
compaction and will be discarded after the compaction. Aside: because level-0
|
||||
is special (files in it may overlap each other), we treat compactions from
|
||||
level-0 to level-1 specially: a level-0 compaction may pick more than one
|
||||
level-0 file in case some of these files overlap each other.
|
||||
|
||||
A compaction merges the contents of the picked files to produce a sequence of
|
||||
level-(L+1) files. We switch to producing a new level-(L+1) file after the
|
||||
current output file has reached the target file size (2MB). We also switch to a
|
||||
new output file when the key range of the current output file has grown enough
|
||||
to overlap more than ten level-(L+2) files. This last rule ensures that a later
|
||||
compaction of a level-(L+1) file will not pick up too much data from
|
||||
level-(L+2).
|
||||
|
||||
The old files are discarded and the new files are added to the serving state.
|
||||
|
||||
Compactions for a particular level rotate through the key space. In more detail,
|
||||
for each level L, we remember the ending key of the last compaction at level L.
|
||||
The next compaction for level L will pick the first file that starts after this
|
||||
key (wrapping around to the beginning of the key space if there is no such
|
||||
file).
|
||||
|
||||
Compactions drop overwritten values. They also drop deletion markers if there
|
||||
are no higher numbered levels that contain a file whose range overlaps the
|
||||
current key.
|
||||
|
||||
### Timing
|
||||
|
||||
Level-0 compactions will read up to four 1MB files from level-0, and at worst
|
||||
all the level-1 files (10MB). I.e., we will read 14MB and write 14MB.
|
||||
|
||||
Other than the special level-0 compactions, we will pick one 2MB file from level
|
||||
L. In the worst case, this will overlap ~ 12 files from level L+1 (10 because
|
||||
level-(L+1) is ten times the size of level-L, and another two at the boundaries
|
||||
since the file ranges at level-L will usually not be aligned with the file
|
||||
ranges at level-L+1). The compaction will therefore read 26MB and write 26MB.
|
||||
Assuming a disk IO rate of 100MB/s (ballpark range for modern drives), the worst
|
||||
compaction cost will be approximately 0.5 second.
|
||||
|
||||
If we throttle the background writing to something small, say 10% of the full
|
||||
100MB/s speed, a compaction may take up to 5 seconds. If the user is writing at
|
||||
10MB/s, we might build up lots of level-0 files (~50 to hold the 5*10MB). This
|
||||
may significantly increase the cost of reads due to the overhead of merging more
|
||||
files together on every read.
|
||||
|
||||
Solution 1: To reduce this problem, we might want to increase the log switching
|
||||
threshold when the number of level-0 files is large. Though the downside is that
|
||||
the larger this threshold, the more memory we will need to hold the
|
||||
corresponding memtable.
|
||||
|
||||
Solution 2: We might want to decrease write rate artificially when the number of
|
||||
level-0 files goes up.
|
||||
|
||||
Solution 3: We work on reducing the cost of very wide merges. Perhaps most of
|
||||
the level-0 files will have their blocks sitting uncompressed in the cache and
|
||||
we will only need to worry about the O(N) complexity in the merging iterator.
|
||||
|
||||
### Number of files
|
||||
|
||||
Instead of always making 2MB files, we could make larger files for larger levels
|
||||
to reduce the total file count, though at the expense of more bursty
|
||||
compactions. Alternatively, we could shard the set of files into multiple
|
||||
directories.
|
||||
|
||||
An experiment on an ext3 filesystem on Feb 04, 2011 shows the following timings
|
||||
to do 100K file opens in directories with varying number of files:
|
||||
|
||||
|
||||
| Files in directory | Microseconds to open a file |
|
||||
|-------------------:|----------------------------:|
|
||||
| 1000 | 9 |
|
||||
| 10000 | 10 |
|
||||
| 100000 | 16 |
|
||||
|
||||
So maybe even the sharding is not necessary on modern filesystems?
|
||||
|
||||
## Recovery
|
||||
|
||||
* Read CURRENT to find name of the latest committed MANIFEST
|
||||
* Read the named MANIFEST file
|
||||
* Clean up stale files
|
||||
* We could open all sstables here, but it is probably better to be lazy...
|
||||
* Convert log chunk to a new level-0 sstable
|
||||
* Start directing new writes to a new log file with recovered sequence#
|
||||
|
||||
## Garbage collection of files
|
||||
|
||||
`DeleteObsoleteFiles()` is called at the end of every compaction and at the end
|
||||
of recovery. It finds the names of all files in the database. It deletes all log
|
||||
files that are not the current log file. It deletes all table files that are not
|
||||
referenced from some level and are not the output of an active compaction.
|
||||
549
doc/index.html
Normal file
549
doc/index.html
Normal file
@@ -0,0 +1,549 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<link rel="stylesheet" type="text/css" href="doc.css" />
|
||||
<title>Leveldb</title>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<h1>Leveldb</h1>
|
||||
<address>Jeff Dean, Sanjay Ghemawat</address>
|
||||
<p>
|
||||
The <code>leveldb</code> library provides a persistent key value store. Keys and
|
||||
values are arbitrary byte arrays. The keys are ordered within the key
|
||||
value store according to a user-specified comparator function.
|
||||
|
||||
<p>
|
||||
<h1>Opening A Database</h1>
|
||||
<p>
|
||||
A <code>leveldb</code> database has a name which corresponds to a file system
|
||||
directory. All of the contents of database are stored in this
|
||||
directory. The following example shows how to open a database,
|
||||
creating it if necessary:
|
||||
<p>
|
||||
<pre>
|
||||
#include <assert>
|
||||
#include "leveldb/db.h"
|
||||
|
||||
leveldb::DB* db;
|
||||
leveldb::Options options;
|
||||
options.create_if_missing = true;
|
||||
leveldb::Status status = leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
assert(status.ok());
|
||||
...
|
||||
</pre>
|
||||
If you want to raise an error if the database already exists, add
|
||||
the following line before the <code>leveldb::DB::Open</code> call:
|
||||
<pre>
|
||||
options.error_if_exists = true;
|
||||
</pre>
|
||||
<h1>Status</h1>
|
||||
<p>
|
||||
You may have noticed the <code>leveldb::Status</code> type above. Values of this
|
||||
type are returned by most functions in <code>leveldb</code> that may encounter an
|
||||
error. You can check if such a result is ok, and also print an
|
||||
associated error message:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Status s = ...;
|
||||
if (!s.ok()) cerr << s.ToString() << endl;
|
||||
</pre>
|
||||
<h1>Closing A Database</h1>
|
||||
<p>
|
||||
When you are done with a database, just delete the database object.
|
||||
Example:
|
||||
<p>
|
||||
<pre>
|
||||
... open the db as described above ...
|
||||
... do something with db ...
|
||||
delete db;
|
||||
</pre>
|
||||
<h1>Reads And Writes</h1>
|
||||
<p>
|
||||
The database provides <code>Put</code>, <code>Delete</code>, and <code>Get</code> methods to
|
||||
modify/query the database. For example, the following code
|
||||
moves the value stored under key1 to key2.
|
||||
<pre>
|
||||
std::string value;
|
||||
leveldb::Status s = db->Get(leveldb::ReadOptions(), key1, &value);
|
||||
if (s.ok()) s = db->Put(leveldb::WriteOptions(), key2, value);
|
||||
if (s.ok()) s = db->Delete(leveldb::WriteOptions(), key1);
|
||||
</pre>
|
||||
|
||||
<h1>Atomic Updates</h1>
|
||||
<p>
|
||||
Note that if the process dies after the Put of key2 but before the
|
||||
delete of key1, the same value may be left stored under multiple keys.
|
||||
Such problems can be avoided by using the <code>WriteBatch</code> class to
|
||||
atomically apply a set of updates:
|
||||
<p>
|
||||
<pre>
|
||||
#include "leveldb/write_batch.h"
|
||||
...
|
||||
std::string value;
|
||||
leveldb::Status s = db->Get(leveldb::ReadOptions(), key1, &value);
|
||||
if (s.ok()) {
|
||||
leveldb::WriteBatch batch;
|
||||
batch.Delete(key1);
|
||||
batch.Put(key2, value);
|
||||
s = db->Write(leveldb::WriteOptions(), &batch);
|
||||
}
|
||||
</pre>
|
||||
The <code>WriteBatch</code> holds a sequence of edits to be made to the database,
|
||||
and these edits within the batch are applied in order. Note that we
|
||||
called <code>Delete</code> before <code>Put</code> so that if <code>key1</code> is identical to <code>key2</code>,
|
||||
we do not end up erroneously dropping the value entirely.
|
||||
<p>
|
||||
Apart from its atomicity benefits, <code>WriteBatch</code> may also be used to
|
||||
speed up bulk updates by placing lots of individual mutations into the
|
||||
same batch.
|
||||
|
||||
<h1>Synchronous Writes</h1>
|
||||
By default, each write to <code>leveldb</code> is asynchronous: it
|
||||
returns after pushing the write from the process into the operating
|
||||
system. The transfer from operating system memory to the underlying
|
||||
persistent storage happens asynchronously. The <code>sync</code> flag
|
||||
can be turned on for a particular write to make the write operation
|
||||
not return until the data being written has been pushed all the way to
|
||||
persistent storage. (On Posix systems, this is implemented by calling
|
||||
either <code>fsync(...)</code> or <code>fdatasync(...)</code> or
|
||||
<code>msync(..., MS_SYNC)</code> before the write operation returns.)
|
||||
<pre>
|
||||
leveldb::WriteOptions write_options;
|
||||
write_options.sync = true;
|
||||
db->Put(write_options, ...);
|
||||
</pre>
|
||||
Asynchronous writes are often more than a thousand times as fast as
|
||||
synchronous writes. The downside of asynchronous writes is that a
|
||||
crash of the machine may cause the last few updates to be lost. Note
|
||||
that a crash of just the writing process (i.e., not a reboot) will not
|
||||
cause any loss since even when <code>sync</code> is false, an update
|
||||
is pushed from the process memory into the operating system before it
|
||||
is considered done.
|
||||
|
||||
<p>
|
||||
Asynchronous writes can often be used safely. For example, when
|
||||
loading a large amount of data into the database you can handle lost
|
||||
updates by restarting the bulk load after a crash. A hybrid scheme is
|
||||
also possible where every Nth write is synchronous, and in the event
|
||||
of a crash, the bulk load is restarted just after the last synchronous
|
||||
write finished by the previous run. (The synchronous write can update
|
||||
a marker that describes where to restart on a crash.)
|
||||
|
||||
<p>
|
||||
<code>WriteBatch</code> provides an alternative to asynchronous writes.
|
||||
Multiple updates may be placed in the same <code>WriteBatch</code> and
|
||||
applied together using a synchronous write (i.e.,
|
||||
<code>write_options.sync</code> is set to true). The extra cost of
|
||||
the synchronous write will be amortized across all of the writes in
|
||||
the batch.
|
||||
|
||||
<p>
|
||||
<h1>Concurrency</h1>
|
||||
<p>
|
||||
A database may only be opened by one process at a time.
|
||||
The <code>leveldb</code> implementation acquires a lock from the
|
||||
operating system to prevent misuse. Within a single process, the
|
||||
same <code>leveldb::DB</code> object may be safely shared by multiple
|
||||
concurrent threads. I.e., different threads may write into or fetch
|
||||
iterators or call <code>Get</code> on the same database without any
|
||||
external synchronization (the leveldb implementation will
|
||||
automatically do the required synchronization). However other objects
|
||||
(like Iterator and WriteBatch) may require external synchronization.
|
||||
If two threads share such an object, they must protect access to it
|
||||
using their own locking protocol. More details are available in
|
||||
the public header files.
|
||||
<p>
|
||||
<h1>Iteration</h1>
|
||||
<p>
|
||||
The following example demonstrates how to print all key,value pairs
|
||||
in a database.
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Iterator* it = db->NewIterator(leveldb::ReadOptions());
|
||||
for (it->SeekToFirst(); it->Valid(); it->Next()) {
|
||||
cout << it->key().ToString() << ": " << it->value().ToString() << endl;
|
||||
}
|
||||
assert(it->status().ok()); // Check for any errors found during the scan
|
||||
delete it;
|
||||
</pre>
|
||||
The following variation shows how to process just the keys in the
|
||||
range <code>[start,limit)</code>:
|
||||
<p>
|
||||
<pre>
|
||||
for (it->Seek(start);
|
||||
it->Valid() && it->key().ToString() < limit;
|
||||
it->Next()) {
|
||||
...
|
||||
}
|
||||
</pre>
|
||||
You can also process entries in reverse order. (Caveat: reverse
|
||||
iteration may be somewhat slower than forward iteration.)
|
||||
<p>
|
||||
<pre>
|
||||
for (it->SeekToLast(); it->Valid(); it->Prev()) {
|
||||
...
|
||||
}
|
||||
</pre>
|
||||
<h1>Snapshots</h1>
|
||||
<p>
|
||||
Snapshots provide consistent read-only views over the entire state of
|
||||
the key-value store. <code>ReadOptions::snapshot</code> may be non-NULL to indicate
|
||||
that a read should operate on a particular version of the DB state.
|
||||
If <code>ReadOptions::snapshot</code> is NULL, the read will operate on an
|
||||
implicit snapshot of the current state.
|
||||
<p>
|
||||
Snapshots are created by the DB::GetSnapshot() method:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::ReadOptions options;
|
||||
options.snapshot = db->GetSnapshot();
|
||||
... apply some updates to db ...
|
||||
leveldb::Iterator* iter = db->NewIterator(options);
|
||||
... read using iter to view the state when the snapshot was created ...
|
||||
delete iter;
|
||||
db->ReleaseSnapshot(options.snapshot);
|
||||
</pre>
|
||||
Note that when a snapshot is no longer needed, it should be released
|
||||
using the DB::ReleaseSnapshot interface. This allows the
|
||||
implementation to get rid of state that was being maintained just to
|
||||
support reading as of that snapshot.
|
||||
<h1>Slice</h1>
|
||||
<p>
|
||||
The return value of the <code>it->key()</code> and <code>it->value()</code> calls above
|
||||
are instances of the <code>leveldb::Slice</code> type. <code>Slice</code> is a simple
|
||||
structure that contains a length and a pointer to an external byte
|
||||
array. Returning a <code>Slice</code> is a cheaper alternative to returning a
|
||||
<code>std::string</code> since we do not need to copy potentially large keys and
|
||||
values. In addition, <code>leveldb</code> methods do not return null-terminated
|
||||
C-style strings since <code>leveldb</code> keys and values are allowed to
|
||||
contain '\0' bytes.
|
||||
<p>
|
||||
C++ strings and null-terminated C-style strings can be easily converted
|
||||
to a Slice:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Slice s1 = "hello";
|
||||
|
||||
std::string str("world");
|
||||
leveldb::Slice s2 = str;
|
||||
</pre>
|
||||
A Slice can be easily converted back to a C++ string:
|
||||
<pre>
|
||||
std::string str = s1.ToString();
|
||||
assert(str == std::string("hello"));
|
||||
</pre>
|
||||
Be careful when using Slices since it is up to the caller to ensure that
|
||||
the external byte array into which the Slice points remains live while
|
||||
the Slice is in use. For example, the following is buggy:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Slice slice;
|
||||
if (...) {
|
||||
std::string str = ...;
|
||||
slice = str;
|
||||
}
|
||||
Use(slice);
|
||||
</pre>
|
||||
When the <code>if</code> statement goes out of scope, <code>str</code> will be destroyed and the
|
||||
backing storage for <code>slice</code> will disappear.
|
||||
<p>
|
||||
<h1>Comparators</h1>
|
||||
<p>
|
||||
The preceding examples used the default ordering function for key,
|
||||
which orders bytes lexicographically. You can however supply a custom
|
||||
comparator when opening a database. For example, suppose each
|
||||
database key consists of two numbers and we should sort by the first
|
||||
number, breaking ties by the second number. First, define a proper
|
||||
subclass of <code>leveldb::Comparator</code> that expresses these rules:
|
||||
<p>
|
||||
<pre>
|
||||
class TwoPartComparator : public leveldb::Comparator {
|
||||
public:
|
||||
// Three-way comparison function:
|
||||
// if a < b: negative result
|
||||
// if a > b: positive result
|
||||
// else: zero result
|
||||
int Compare(const leveldb::Slice& a, const leveldb::Slice& b) const {
|
||||
int a1, a2, b1, b2;
|
||||
ParseKey(a, &a1, &a2);
|
||||
ParseKey(b, &b1, &b2);
|
||||
if (a1 < b1) return -1;
|
||||
if (a1 > b1) return +1;
|
||||
if (a2 < b2) return -1;
|
||||
if (a2 > b2) return +1;
|
||||
return 0;
|
||||
}
|
||||
|
||||
// Ignore the following methods for now:
|
||||
const char* Name() const { return "TwoPartComparator"; }
|
||||
void FindShortestSeparator(std::string*, const leveldb::Slice&) const { }
|
||||
void FindShortSuccessor(std::string*) const { }
|
||||
};
|
||||
</pre>
|
||||
Now create a database using this custom comparator:
|
||||
<p>
|
||||
<pre>
|
||||
TwoPartComparator cmp;
|
||||
leveldb::DB* db;
|
||||
leveldb::Options options;
|
||||
options.create_if_missing = true;
|
||||
options.comparator = &cmp;
|
||||
leveldb::Status status = leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
...
|
||||
</pre>
|
||||
<h2>Backwards compatibility</h2>
|
||||
<p>
|
||||
The result of the comparator's <code>Name</code> method is attached to the
|
||||
database when it is created, and is checked on every subsequent
|
||||
database open. If the name changes, the <code>leveldb::DB::Open</code> call will
|
||||
fail. Therefore, change the name if and only if the new key format
|
||||
and comparison function are incompatible with existing databases, and
|
||||
it is ok to discard the contents of all existing databases.
|
||||
<p>
|
||||
You can however still gradually evolve your key format over time with
|
||||
a little bit of pre-planning. For example, you could store a version
|
||||
number at the end of each key (one byte should suffice for most uses).
|
||||
When you wish to switch to a new key format (e.g., adding an optional
|
||||
third part to the keys processed by <code>TwoPartComparator</code>),
|
||||
(a) keep the same comparator name (b) increment the version number
|
||||
for new keys (c) change the comparator function so it uses the
|
||||
version numbers found in the keys to decide how to interpret them.
|
||||
<p>
|
||||
<h1>Performance</h1>
|
||||
<p>
|
||||
Performance can be tuned by changing the default values of the
|
||||
types defined in <code>include/leveldb/options.h</code>.
|
||||
|
||||
<p>
|
||||
<h2>Block size</h2>
|
||||
<p>
|
||||
<code>leveldb</code> groups adjacent keys together into the same block and such a
|
||||
block is the unit of transfer to and from persistent storage. The
|
||||
default block size is approximately 4096 uncompressed bytes.
|
||||
Applications that mostly do bulk scans over the contents of the
|
||||
database may wish to increase this size. Applications that do a lot
|
||||
of point reads of small values may wish to switch to a smaller block
|
||||
size if performance measurements indicate an improvement. There isn't
|
||||
much benefit in using blocks smaller than one kilobyte, or larger than
|
||||
a few megabytes. Also note that compression will be more effective
|
||||
with larger block sizes.
|
||||
<p>
|
||||
<h2>Compression</h2>
|
||||
<p>
|
||||
Each block is individually compressed before being written to
|
||||
persistent storage. Compression is on by default since the default
|
||||
compression method is very fast, and is automatically disabled for
|
||||
uncompressible data. In rare cases, applications may want to disable
|
||||
compression entirely, but should only do so if benchmarks show a
|
||||
performance improvement:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Options options;
|
||||
options.compression = leveldb::kNoCompression;
|
||||
... leveldb::DB::Open(options, name, ...) ....
|
||||
</pre>
|
||||
<h2>Cache</h2>
|
||||
<p>
|
||||
The contents of the database are stored in a set of files in the
|
||||
filesystem and each file stores a sequence of compressed blocks. If
|
||||
<code>options.cache</code> is non-NULL, it is used to cache frequently used
|
||||
uncompressed block contents.
|
||||
<p>
|
||||
<pre>
|
||||
#include "leveldb/cache.h"
|
||||
|
||||
leveldb::Options options;
|
||||
options.cache = leveldb::NewLRUCache(100 * 1048576); // 100MB cache
|
||||
leveldb::DB* db;
|
||||
leveldb::DB::Open(options, name, &db);
|
||||
... use the db ...
|
||||
delete db
|
||||
delete options.cache;
|
||||
</pre>
|
||||
Note that the cache holds uncompressed data, and therefore it should
|
||||
be sized according to application level data sizes, without any
|
||||
reduction from compression. (Caching of compressed blocks is left to
|
||||
the operating system buffer cache, or any custom <code>Env</code>
|
||||
implementation provided by the client.)
|
||||
<p>
|
||||
When performing a bulk read, the application may wish to disable
|
||||
caching so that the data processed by the bulk read does not end up
|
||||
displacing most of the cached contents. A per-iterator option can be
|
||||
used to achieve this:
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::ReadOptions options;
|
||||
options.fill_cache = false;
|
||||
leveldb::Iterator* it = db->NewIterator(options);
|
||||
for (it->SeekToFirst(); it->Valid(); it->Next()) {
|
||||
...
|
||||
}
|
||||
</pre>
|
||||
<h2>Key Layout</h2>
|
||||
<p>
|
||||
Note that the unit of disk transfer and caching is a block. Adjacent
|
||||
keys (according to the database sort order) will usually be placed in
|
||||
the same block. Therefore the application can improve its performance
|
||||
by placing keys that are accessed together near each other and placing
|
||||
infrequently used keys in a separate region of the key space.
|
||||
<p>
|
||||
For example, suppose we are implementing a simple file system on top
|
||||
of <code>leveldb</code>. The types of entries we might wish to store are:
|
||||
<p>
|
||||
<pre>
|
||||
filename -> permission-bits, length, list of file_block_ids
|
||||
file_block_id -> data
|
||||
</pre>
|
||||
We might want to prefix <code>filename</code> keys with one letter (say '/') and the
|
||||
<code>file_block_id</code> keys with a different letter (say '0') so that scans
|
||||
over just the metadata do not force us to fetch and cache bulky file
|
||||
contents.
|
||||
<p>
|
||||
<h2>Filters</h2>
|
||||
<p>
|
||||
Because of the way <code>leveldb</code> data is organized on disk,
|
||||
a single <code>Get()</code> call may involve multiple reads from disk.
|
||||
The optional <code>FilterPolicy</code> mechanism can be used to reduce
|
||||
the number of disk reads substantially.
|
||||
<pre>
|
||||
leveldb::Options options;
|
||||
options.filter_policy = NewBloomFilterPolicy(10);
|
||||
leveldb::DB* db;
|
||||
leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
... use the database ...
|
||||
delete db;
|
||||
delete options.filter_policy;
|
||||
</pre>
|
||||
The preceding code associates a
|
||||
<a href="http://en.wikipedia.org/wiki/Bloom_filter">Bloom filter</a>
|
||||
based filtering policy with the database. Bloom filter based
|
||||
filtering relies on keeping some number of bits of data in memory per
|
||||
key (in this case 10 bits per key since that is the argument we passed
|
||||
to NewBloomFilterPolicy). This filter will reduce the number of unnecessary
|
||||
disk reads needed for <code>Get()</code> calls by a factor of
|
||||
approximately a 100. Increasing the bits per key will lead to a
|
||||
larger reduction at the cost of more memory usage. We recommend that
|
||||
applications whose working set does not fit in memory and that do a
|
||||
lot of random reads set a filter policy.
|
||||
<p>
|
||||
If you are using a custom comparator, you should ensure that the filter
|
||||
policy you are using is compatible with your comparator. For example,
|
||||
consider a comparator that ignores trailing spaces when comparing keys.
|
||||
<code>NewBloomFilterPolicy</code> must not be used with such a comparator.
|
||||
Instead, the application should provide a custom filter policy that
|
||||
also ignores trailing spaces. For example:
|
||||
<pre>
|
||||
class CustomFilterPolicy : public leveldb::FilterPolicy {
|
||||
private:
|
||||
FilterPolicy* builtin_policy_;
|
||||
public:
|
||||
CustomFilterPolicy() : builtin_policy_(NewBloomFilterPolicy(10)) { }
|
||||
~CustomFilterPolicy() { delete builtin_policy_; }
|
||||
|
||||
const char* Name() const { return "IgnoreTrailingSpacesFilter"; }
|
||||
|
||||
void CreateFilter(const Slice* keys, int n, std::string* dst) const {
|
||||
// Use builtin bloom filter code after removing trailing spaces
|
||||
std::vector<Slice> trimmed(n);
|
||||
for (int i = 0; i < n; i++) {
|
||||
trimmed[i] = RemoveTrailingSpaces(keys[i]);
|
||||
}
|
||||
return builtin_policy_->CreateFilter(&trimmed[i], n, dst);
|
||||
}
|
||||
|
||||
bool KeyMayMatch(const Slice& key, const Slice& filter) const {
|
||||
// Use builtin bloom filter code after removing trailing spaces
|
||||
return builtin_policy_->KeyMayMatch(RemoveTrailingSpaces(key), filter);
|
||||
}
|
||||
};
|
||||
</pre>
|
||||
<p>
|
||||
Advanced applications may provide a filter policy that does not use
|
||||
a bloom filter but uses some other mechanism for summarizing a set
|
||||
of keys. See <code>leveldb/filter_policy.h</code> for detail.
|
||||
<p>
|
||||
<h1>Checksums</h1>
|
||||
<p>
|
||||
<code>leveldb</code> associates checksums with all data it stores in the file system.
|
||||
There are two separate controls provided over how aggressively these
|
||||
checksums are verified:
|
||||
<p>
|
||||
<ul>
|
||||
<li> <code>ReadOptions::verify_checksums</code> may be set to true to force
|
||||
checksum verification of all data that is read from the file system on
|
||||
behalf of a particular read. By default, no such verification is
|
||||
done.
|
||||
<p>
|
||||
<li> <code>Options::paranoid_checks</code> may be set to true before opening a
|
||||
database to make the database implementation raise an error as soon as
|
||||
it detects an internal corruption. Depending on which portion of the
|
||||
database has been corrupted, the error may be raised when the database
|
||||
is opened, or later by another database operation. By default,
|
||||
paranoid checking is off so that the database can be used even if
|
||||
parts of its persistent storage have been corrupted.
|
||||
<p>
|
||||
If a database is corrupted (perhaps it cannot be opened when
|
||||
paranoid checking is turned on), the <code>leveldb::RepairDB</code> function
|
||||
may be used to recover as much of the data as possible
|
||||
<p>
|
||||
</ul>
|
||||
<h1>Approximate Sizes</h1>
|
||||
<p>
|
||||
The <code>GetApproximateSizes</code> method can used to get the approximate
|
||||
number of bytes of file system space used by one or more key ranges.
|
||||
<p>
|
||||
<pre>
|
||||
leveldb::Range ranges[2];
|
||||
ranges[0] = leveldb::Range("a", "c");
|
||||
ranges[1] = leveldb::Range("x", "z");
|
||||
uint64_t sizes[2];
|
||||
leveldb::Status s = db->GetApproximateSizes(ranges, 2, sizes);
|
||||
</pre>
|
||||
The preceding call will set <code>sizes[0]</code> to the approximate number of
|
||||
bytes of file system space used by the key range <code>[a..c)</code> and
|
||||
<code>sizes[1]</code> to the approximate number of bytes used by the key range
|
||||
<code>[x..z)</code>.
|
||||
<p>
|
||||
<h1>Environment</h1>
|
||||
<p>
|
||||
All file operations (and other operating system calls) issued by the
|
||||
<code>leveldb</code> implementation are routed through a <code>leveldb::Env</code> object.
|
||||
Sophisticated clients may wish to provide their own <code>Env</code>
|
||||
implementation to get better control. For example, an application may
|
||||
introduce artificial delays in the file IO paths to limit the impact
|
||||
of <code>leveldb</code> on other activities in the system.
|
||||
<p>
|
||||
<pre>
|
||||
class SlowEnv : public leveldb::Env {
|
||||
.. implementation of the Env interface ...
|
||||
};
|
||||
|
||||
SlowEnv env;
|
||||
leveldb::Options options;
|
||||
options.env = &env;
|
||||
Status s = leveldb::DB::Open(options, ...);
|
||||
</pre>
|
||||
<h1>Porting</h1>
|
||||
<p>
|
||||
<code>leveldb</code> may be ported to a new platform by providing platform
|
||||
specific implementations of the types/methods/functions exported by
|
||||
<code>leveldb/port/port.h</code>. See <code>leveldb/port/port_example.h</code> for more
|
||||
details.
|
||||
<p>
|
||||
In addition, the new platform may need a new default <code>leveldb::Env</code>
|
||||
implementation. See <code>leveldb/util/env_posix.h</code> for an example.
|
||||
|
||||
<h1>Other Information</h1>
|
||||
|
||||
<p>
|
||||
Details about the <code>leveldb</code> implementation may be found in
|
||||
the following documents:
|
||||
<ul>
|
||||
<li> <a href="impl.html">Implementation notes</a>
|
||||
<li> <a href="table_format.txt">Format of an immutable Table file</a>
|
||||
<li> <a href="log_format.txt">Format of a log file</a>
|
||||
</ul>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
523
doc/index.md
523
doc/index.md
@@ -1,523 +0,0 @@
|
||||
leveldb
|
||||
=======
|
||||
|
||||
_Jeff Dean, Sanjay Ghemawat_
|
||||
|
||||
The leveldb library provides a persistent key value store. Keys and values are
|
||||
arbitrary byte arrays. The keys are ordered within the key value store
|
||||
according to a user-specified comparator function.
|
||||
|
||||
## Opening A Database
|
||||
|
||||
A leveldb database has a name which corresponds to a file system directory. All
|
||||
of the contents of database are stored in this directory. The following example
|
||||
shows how to open a database, creating it if necessary:
|
||||
|
||||
```c++
|
||||
#include <cassert>
|
||||
#include "leveldb/db.h"
|
||||
|
||||
leveldb::DB* db;
|
||||
leveldb::Options options;
|
||||
options.create_if_missing = true;
|
||||
leveldb::Status status = leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
assert(status.ok());
|
||||
...
|
||||
```
|
||||
|
||||
If you want to raise an error if the database already exists, add the following
|
||||
line before the `leveldb::DB::Open` call:
|
||||
|
||||
```c++
|
||||
options.error_if_exists = true;
|
||||
```
|
||||
|
||||
## Status
|
||||
|
||||
You may have noticed the `leveldb::Status` type above. Values of this type are
|
||||
returned by most functions in leveldb that may encounter an error. You can check
|
||||
if such a result is ok, and also print an associated error message:
|
||||
|
||||
```c++
|
||||
leveldb::Status s = ...;
|
||||
if (!s.ok()) cerr << s.ToString() << endl;
|
||||
```
|
||||
|
||||
## Closing A Database
|
||||
|
||||
When you are done with a database, just delete the database object. Example:
|
||||
|
||||
```c++
|
||||
... open the db as described above ...
|
||||
... do something with db ...
|
||||
delete db;
|
||||
```
|
||||
|
||||
## Reads And Writes
|
||||
|
||||
The database provides Put, Delete, and Get methods to modify/query the database.
|
||||
For example, the following code moves the value stored under key1 to key2.
|
||||
|
||||
```c++
|
||||
std::string value;
|
||||
leveldb::Status s = db->Get(leveldb::ReadOptions(), key1, &value);
|
||||
if (s.ok()) s = db->Put(leveldb::WriteOptions(), key2, value);
|
||||
if (s.ok()) s = db->Delete(leveldb::WriteOptions(), key1);
|
||||
```
|
||||
|
||||
## Atomic Updates
|
||||
|
||||
Note that if the process dies after the Put of key2 but before the delete of
|
||||
key1, the same value may be left stored under multiple keys. Such problems can
|
||||
be avoided by using the `WriteBatch` class to atomically apply a set of updates:
|
||||
|
||||
```c++
|
||||
#include "leveldb/write_batch.h"
|
||||
...
|
||||
std::string value;
|
||||
leveldb::Status s = db->Get(leveldb::ReadOptions(), key1, &value);
|
||||
if (s.ok()) {
|
||||
leveldb::WriteBatch batch;
|
||||
batch.Delete(key1);
|
||||
batch.Put(key2, value);
|
||||
s = db->Write(leveldb::WriteOptions(), &batch);
|
||||
}
|
||||
```
|
||||
|
||||
The `WriteBatch` holds a sequence of edits to be made to the database, and these
|
||||
edits within the batch are applied in order. Note that we called Delete before
|
||||
Put so that if key1 is identical to key2, we do not end up erroneously dropping
|
||||
the value entirely.
|
||||
|
||||
Apart from its atomicity benefits, `WriteBatch` may also be used to speed up
|
||||
bulk updates by placing lots of individual mutations into the same batch.
|
||||
|
||||
## Synchronous Writes
|
||||
|
||||
By default, each write to leveldb is asynchronous: it returns after pushing the
|
||||
write from the process into the operating system. The transfer from operating
|
||||
system memory to the underlying persistent storage happens asynchronously. The
|
||||
sync flag can be turned on for a particular write to make the write operation
|
||||
not return until the data being written has been pushed all the way to
|
||||
persistent storage. (On Posix systems, this is implemented by calling either
|
||||
`fsync(...)` or `fdatasync(...)` or `msync(..., MS_SYNC)` before the write
|
||||
operation returns.)
|
||||
|
||||
```c++
|
||||
leveldb::WriteOptions write_options;
|
||||
write_options.sync = true;
|
||||
db->Put(write_options, ...);
|
||||
```
|
||||
|
||||
Asynchronous writes are often more than a thousand times as fast as synchronous
|
||||
writes. The downside of asynchronous writes is that a crash of the machine may
|
||||
cause the last few updates to be lost. Note that a crash of just the writing
|
||||
process (i.e., not a reboot) will not cause any loss since even when sync is
|
||||
false, an update is pushed from the process memory into the operating system
|
||||
before it is considered done.
|
||||
|
||||
Asynchronous writes can often be used safely. For example, when loading a large
|
||||
amount of data into the database you can handle lost updates by restarting the
|
||||
bulk load after a crash. A hybrid scheme is also possible where every Nth write
|
||||
is synchronous, and in the event of a crash, the bulk load is restarted just
|
||||
after the last synchronous write finished by the previous run. (The synchronous
|
||||
write can update a marker that describes where to restart on a crash.)
|
||||
|
||||
`WriteBatch` provides an alternative to asynchronous writes. Multiple updates
|
||||
may be placed in the same WriteBatch and applied together using a synchronous
|
||||
write (i.e., `write_options.sync` is set to true). The extra cost of the
|
||||
synchronous write will be amortized across all of the writes in the batch.
|
||||
|
||||
## Concurrency
|
||||
|
||||
A database may only be opened by one process at a time. The leveldb
|
||||
implementation acquires a lock from the operating system to prevent misuse.
|
||||
Within a single process, the same `leveldb::DB` object may be safely shared by
|
||||
multiple concurrent threads. I.e., different threads may write into or fetch
|
||||
iterators or call Get on the same database without any external synchronization
|
||||
(the leveldb implementation will automatically do the required synchronization).
|
||||
However other objects (like Iterator and `WriteBatch`) may require external
|
||||
synchronization. If two threads share such an object, they must protect access
|
||||
to it using their own locking protocol. More details are available in the public
|
||||
header files.
|
||||
|
||||
## Iteration
|
||||
|
||||
The following example demonstrates how to print all key,value pairs in a
|
||||
database.
|
||||
|
||||
```c++
|
||||
leveldb::Iterator* it = db->NewIterator(leveldb::ReadOptions());
|
||||
for (it->SeekToFirst(); it->Valid(); it->Next()) {
|
||||
cout << it->key().ToString() << ": " << it->value().ToString() << endl;
|
||||
}
|
||||
assert(it->status().ok()); // Check for any errors found during the scan
|
||||
delete it;
|
||||
```
|
||||
|
||||
The following variation shows how to process just the keys in the range
|
||||
[start,limit):
|
||||
|
||||
```c++
|
||||
for (it->Seek(start);
|
||||
it->Valid() && it->key().ToString() < limit;
|
||||
it->Next()) {
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
You can also process entries in reverse order. (Caveat: reverse iteration may be
|
||||
somewhat slower than forward iteration.)
|
||||
|
||||
```c++
|
||||
for (it->SeekToLast(); it->Valid(); it->Prev()) {
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
## Snapshots
|
||||
|
||||
Snapshots provide consistent read-only views over the entire state of the
|
||||
key-value store. `ReadOptions::snapshot` may be non-NULL to indicate that a
|
||||
read should operate on a particular version of the DB state. If
|
||||
`ReadOptions::snapshot` is NULL, the read will operate on an implicit snapshot
|
||||
of the current state.
|
||||
|
||||
Snapshots are created by the `DB::GetSnapshot()` method:
|
||||
|
||||
```c++
|
||||
leveldb::ReadOptions options;
|
||||
options.snapshot = db->GetSnapshot();
|
||||
... apply some updates to db ...
|
||||
leveldb::Iterator* iter = db->NewIterator(options);
|
||||
... read using iter to view the state when the snapshot was created ...
|
||||
delete iter;
|
||||
db->ReleaseSnapshot(options.snapshot);
|
||||
```
|
||||
|
||||
Note that when a snapshot is no longer needed, it should be released using the
|
||||
`DB::ReleaseSnapshot` interface. This allows the implementation to get rid of
|
||||
state that was being maintained just to support reading as of that snapshot.
|
||||
|
||||
## Slice
|
||||
|
||||
The return value of the `it->key()` and `it->value()` calls above are instances
|
||||
of the `leveldb::Slice` type. Slice is a simple structure that contains a length
|
||||
and a pointer to an external byte array. Returning a Slice is a cheaper
|
||||
alternative to returning a `std::string` since we do not need to copy
|
||||
potentially large keys and values. In addition, leveldb methods do not return
|
||||
null-terminated C-style strings since leveldb keys and values are allowed to
|
||||
contain `'\0'` bytes.
|
||||
|
||||
C++ strings and null-terminated C-style strings can be easily converted to a
|
||||
Slice:
|
||||
|
||||
```c++
|
||||
leveldb::Slice s1 = "hello";
|
||||
|
||||
std::string str("world");
|
||||
leveldb::Slice s2 = str;
|
||||
```
|
||||
|
||||
A Slice can be easily converted back to a C++ string:
|
||||
|
||||
```c++
|
||||
std::string str = s1.ToString();
|
||||
assert(str == std::string("hello"));
|
||||
```
|
||||
|
||||
Be careful when using Slices since it is up to the caller to ensure that the
|
||||
external byte array into which the Slice points remains live while the Slice is
|
||||
in use. For example, the following is buggy:
|
||||
|
||||
```c++
|
||||
leveldb::Slice slice;
|
||||
if (...) {
|
||||
std::string str = ...;
|
||||
slice = str;
|
||||
}
|
||||
Use(slice);
|
||||
```
|
||||
|
||||
When the if statement goes out of scope, str will be destroyed and the backing
|
||||
storage for slice will disappear.
|
||||
|
||||
## Comparators
|
||||
|
||||
The preceding examples used the default ordering function for key, which orders
|
||||
bytes lexicographically. You can however supply a custom comparator when opening
|
||||
a database. For example, suppose each database key consists of two numbers and
|
||||
we should sort by the first number, breaking ties by the second number. First,
|
||||
define a proper subclass of `leveldb::Comparator` that expresses these rules:
|
||||
|
||||
```c++
|
||||
class TwoPartComparator : public leveldb::Comparator {
|
||||
public:
|
||||
// Three-way comparison function:
|
||||
// if a < b: negative result
|
||||
// if a > b: positive result
|
||||
// else: zero result
|
||||
int Compare(const leveldb::Slice& a, const leveldb::Slice& b) const {
|
||||
int a1, a2, b1, b2;
|
||||
ParseKey(a, &a1, &a2);
|
||||
ParseKey(b, &b1, &b2);
|
||||
if (a1 < b1) return -1;
|
||||
if (a1 > b1) return +1;
|
||||
if (a2 < b2) return -1;
|
||||
if (a2 > b2) return +1;
|
||||
return 0;
|
||||
}
|
||||
|
||||
// Ignore the following methods for now:
|
||||
const char* Name() const { return "TwoPartComparator"; }
|
||||
void FindShortestSeparator(std::string*, const leveldb::Slice&) const {}
|
||||
void FindShortSuccessor(std::string*) const {}
|
||||
};
|
||||
```
|
||||
|
||||
Now create a database using this custom comparator:
|
||||
|
||||
```c++
|
||||
TwoPartComparator cmp;
|
||||
leveldb::DB* db;
|
||||
leveldb::Options options;
|
||||
options.create_if_missing = true;
|
||||
options.comparator = &cmp;
|
||||
leveldb::Status status = leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
...
|
||||
```
|
||||
|
||||
### Backwards compatibility
|
||||
|
||||
The result of the comparator's Name method is attached to the database when it
|
||||
is created, and is checked on every subsequent database open. If the name
|
||||
changes, the `leveldb::DB::Open` call will fail. Therefore, change the name if
|
||||
and only if the new key format and comparison function are incompatible with
|
||||
existing databases, and it is ok to discard the contents of all existing
|
||||
databases.
|
||||
|
||||
You can however still gradually evolve your key format over time with a little
|
||||
bit of pre-planning. For example, you could store a version number at the end of
|
||||
each key (one byte should suffice for most uses). When you wish to switch to a
|
||||
new key format (e.g., adding an optional third part to the keys processed by
|
||||
`TwoPartComparator`), (a) keep the same comparator name (b) increment the
|
||||
version number for new keys (c) change the comparator function so it uses the
|
||||
version numbers found in the keys to decide how to interpret them.
|
||||
|
||||
## Performance
|
||||
|
||||
Performance can be tuned by changing the default values of the types defined in
|
||||
`include/leveldb/options.h`.
|
||||
|
||||
### Block size
|
||||
|
||||
leveldb groups adjacent keys together into the same block and such a block is
|
||||
the unit of transfer to and from persistent storage. The default block size is
|
||||
approximately 4096 uncompressed bytes. Applications that mostly do bulk scans
|
||||
over the contents of the database may wish to increase this size. Applications
|
||||
that do a lot of point reads of small values may wish to switch to a smaller
|
||||
block size if performance measurements indicate an improvement. There isn't much
|
||||
benefit in using blocks smaller than one kilobyte, or larger than a few
|
||||
megabytes. Also note that compression will be more effective with larger block
|
||||
sizes.
|
||||
|
||||
### Compression
|
||||
|
||||
Each block is individually compressed before being written to persistent
|
||||
storage. Compression is on by default since the default compression method is
|
||||
very fast, and is automatically disabled for uncompressible data. In rare cases,
|
||||
applications may want to disable compression entirely, but should only do so if
|
||||
benchmarks show a performance improvement:
|
||||
|
||||
```c++
|
||||
leveldb::Options options;
|
||||
options.compression = leveldb::kNoCompression;
|
||||
... leveldb::DB::Open(options, name, ...) ....
|
||||
```
|
||||
|
||||
### Cache
|
||||
|
||||
The contents of the database are stored in a set of files in the filesystem and
|
||||
each file stores a sequence of compressed blocks. If options.cache is non-NULL,
|
||||
it is used to cache frequently used uncompressed block contents.
|
||||
|
||||
```c++
|
||||
#include "leveldb/cache.h"
|
||||
|
||||
leveldb::Options options;
|
||||
options.cache = leveldb::NewLRUCache(100 * 1048576); // 100MB cache
|
||||
leveldb::DB* db;
|
||||
leveldb::DB::Open(options, name, &db);
|
||||
... use the db ...
|
||||
delete db
|
||||
delete options.cache;
|
||||
```
|
||||
|
||||
Note that the cache holds uncompressed data, and therefore it should be sized
|
||||
according to application level data sizes, without any reduction from
|
||||
compression. (Caching of compressed blocks is left to the operating system
|
||||
buffer cache, or any custom Env implementation provided by the client.)
|
||||
|
||||
When performing a bulk read, the application may wish to disable caching so that
|
||||
the data processed by the bulk read does not end up displacing most of the
|
||||
cached contents. A per-iterator option can be used to achieve this:
|
||||
|
||||
```c++
|
||||
leveldb::ReadOptions options;
|
||||
options.fill_cache = false;
|
||||
leveldb::Iterator* it = db->NewIterator(options);
|
||||
for (it->SeekToFirst(); it->Valid(); it->Next()) {
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
### Key Layout
|
||||
|
||||
Note that the unit of disk transfer and caching is a block. Adjacent keys
|
||||
(according to the database sort order) will usually be placed in the same block.
|
||||
Therefore the application can improve its performance by placing keys that are
|
||||
accessed together near each other and placing infrequently used keys in a
|
||||
separate region of the key space.
|
||||
|
||||
For example, suppose we are implementing a simple file system on top of leveldb.
|
||||
The types of entries we might wish to store are:
|
||||
|
||||
filename -> permission-bits, length, list of file_block_ids
|
||||
file_block_id -> data
|
||||
|
||||
We might want to prefix filename keys with one letter (say '/') and the
|
||||
`file_block_id` keys with a different letter (say '0') so that scans over just
|
||||
the metadata do not force us to fetch and cache bulky file contents.
|
||||
|
||||
### Filters
|
||||
|
||||
Because of the way leveldb data is organized on disk, a single `Get()` call may
|
||||
involve multiple reads from disk. The optional FilterPolicy mechanism can be
|
||||
used to reduce the number of disk reads substantially.
|
||||
|
||||
```c++
|
||||
leveldb::Options options;
|
||||
options.filter_policy = NewBloomFilterPolicy(10);
|
||||
leveldb::DB* db;
|
||||
leveldb::DB::Open(options, "/tmp/testdb", &db);
|
||||
... use the database ...
|
||||
delete db;
|
||||
delete options.filter_policy;
|
||||
```
|
||||
|
||||
The preceding code associates a Bloom filter based filtering policy with the
|
||||
database. Bloom filter based filtering relies on keeping some number of bits of
|
||||
data in memory per key (in this case 10 bits per key since that is the argument
|
||||
we passed to `NewBloomFilterPolicy`). This filter will reduce the number of
|
||||
unnecessary disk reads needed for Get() calls by a factor of approximately
|
||||
a 100. Increasing the bits per key will lead to a larger reduction at the cost
|
||||
of more memory usage. We recommend that applications whose working set does not
|
||||
fit in memory and that do a lot of random reads set a filter policy.
|
||||
|
||||
If you are using a custom comparator, you should ensure that the filter policy
|
||||
you are using is compatible with your comparator. For example, consider a
|
||||
comparator that ignores trailing spaces when comparing keys.
|
||||
`NewBloomFilterPolicy` must not be used with such a comparator. Instead, the
|
||||
application should provide a custom filter policy that also ignores trailing
|
||||
spaces. For example:
|
||||
|
||||
```c++
|
||||
class CustomFilterPolicy : public leveldb::FilterPolicy {
|
||||
private:
|
||||
FilterPolicy* builtin_policy_;
|
||||
|
||||
public:
|
||||
CustomFilterPolicy() : builtin_policy_(NewBloomFilterPolicy(10)) {}
|
||||
~CustomFilterPolicy() { delete builtin_policy_; }
|
||||
|
||||
const char* Name() const { return "IgnoreTrailingSpacesFilter"; }
|
||||
|
||||
void CreateFilter(const Slice* keys, int n, std::string* dst) const {
|
||||
// Use builtin bloom filter code after removing trailing spaces
|
||||
std::vector<Slice> trimmed(n);
|
||||
for (int i = 0; i < n; i++) {
|
||||
trimmed[i] = RemoveTrailingSpaces(keys[i]);
|
||||
}
|
||||
return builtin_policy_->CreateFilter(&trimmed[i], n, dst);
|
||||
}
|
||||
};
|
||||
```
|
||||
|
||||
Advanced applications may provide a filter policy that does not use a bloom
|
||||
filter but uses some other mechanism for summarizing a set of keys. See
|
||||
`leveldb/filter_policy.h` for detail.
|
||||
|
||||
## Checksums
|
||||
|
||||
leveldb associates checksums with all data it stores in the file system. There
|
||||
are two separate controls provided over how aggressively these checksums are
|
||||
verified:
|
||||
|
||||
`ReadOptions::verify_checksums` may be set to true to force checksum
|
||||
verification of all data that is read from the file system on behalf of a
|
||||
particular read. By default, no such verification is done.
|
||||
|
||||
`Options::paranoid_checks` may be set to true before opening a database to make
|
||||
the database implementation raise an error as soon as it detects an internal
|
||||
corruption. Depending on which portion of the database has been corrupted, the
|
||||
error may be raised when the database is opened, or later by another database
|
||||
operation. By default, paranoid checking is off so that the database can be used
|
||||
even if parts of its persistent storage have been corrupted.
|
||||
|
||||
If a database is corrupted (perhaps it cannot be opened when paranoid checking
|
||||
is turned on), the `leveldb::RepairDB` function may be used to recover as much
|
||||
of the data as possible
|
||||
|
||||
## Approximate Sizes
|
||||
|
||||
The `GetApproximateSizes` method can used to get the approximate number of bytes
|
||||
of file system space used by one or more key ranges.
|
||||
|
||||
```c++
|
||||
leveldb::Range ranges[2];
|
||||
ranges[0] = leveldb::Range("a", "c");
|
||||
ranges[1] = leveldb::Range("x", "z");
|
||||
uint64_t sizes[2];
|
||||
leveldb::Status s = db->GetApproximateSizes(ranges, 2, sizes);
|
||||
```
|
||||
|
||||
The preceding call will set `sizes[0]` to the approximate number of bytes of
|
||||
file system space used by the key range `[a..c)` and `sizes[1]` to the
|
||||
approximate number of bytes used by the key range `[x..z)`.
|
||||
|
||||
## Environment
|
||||
|
||||
All file operations (and other operating system calls) issued by the leveldb
|
||||
implementation are routed through a `leveldb::Env` object. Sophisticated clients
|
||||
may wish to provide their own Env implementation to get better control.
|
||||
For example, an application may introduce artificial delays in the file IO
|
||||
paths to limit the impact of leveldb on other activities in the system.
|
||||
|
||||
```c++
|
||||
class SlowEnv : public leveldb::Env {
|
||||
... implementation of the Env interface ...
|
||||
};
|
||||
|
||||
SlowEnv env;
|
||||
leveldb::Options options;
|
||||
options.env = &env;
|
||||
Status s = leveldb::DB::Open(options, ...);
|
||||
```
|
||||
|
||||
## Porting
|
||||
|
||||
leveldb may be ported to a new platform by providing platform specific
|
||||
implementations of the types/methods/functions exported by
|
||||
`leveldb/port/port.h`. See `leveldb/port/port_example.h` for more details.
|
||||
|
||||
In addition, the new platform may need a new default `leveldb::Env`
|
||||
implementation. See `leveldb/util/env_posix.h` for an example.
|
||||
|
||||
## Other Information
|
||||
|
||||
Details about the leveldb implementation may be found in the following
|
||||
documents:
|
||||
|
||||
1. [Implementation notes](impl.md)
|
||||
2. [Format of an immutable Table file](table_format.md)
|
||||
3. [Format of a log file](log_format.md)
|
||||
@@ -1,75 +0,0 @@
|
||||
leveldb Log format
|
||||
==================
|
||||
The log file contents are a sequence of 32KB blocks. The only exception is that
|
||||
the tail of the file may contain a partial block.
|
||||
|
||||
Each block consists of a sequence of records:
|
||||
|
||||
block := record* trailer?
|
||||
record :=
|
||||
checksum: uint32 // crc32c of type and data[] ; little-endian
|
||||
length: uint16 // little-endian
|
||||
type: uint8 // One of FULL, FIRST, MIDDLE, LAST
|
||||
data: uint8[length]
|
||||
|
||||
A record never starts within the last six bytes of a block (since it won't fit).
|
||||
Any leftover bytes here form the trailer, which must consist entirely of zero
|
||||
bytes and must be skipped by readers.
|
||||
|
||||
Aside: if exactly seven bytes are left in the current block, and a new non-zero
|
||||
length record is added, the writer must emit a FIRST record (which contains zero
|
||||
bytes of user data) to fill up the trailing seven bytes of the block and then
|
||||
emit all of the user data in subsequent blocks.
|
||||
|
||||
More types may be added in the future. Some Readers may skip record types they
|
||||
do not understand, others may report that some data was skipped.
|
||||
|
||||
FULL == 1
|
||||
FIRST == 2
|
||||
MIDDLE == 3
|
||||
LAST == 4
|
||||
|
||||
The FULL record contains the contents of an entire user record.
|
||||
|
||||
FIRST, MIDDLE, LAST are types used for user records that have been split into
|
||||
multiple fragments (typically because of block boundaries). FIRST is the type
|
||||
of the first fragment of a user record, LAST is the type of the last fragment of
|
||||
a user record, and MIDDLE is the type of all interior fragments of a user
|
||||
record.
|
||||
|
||||
Example: consider a sequence of user records:
|
||||
|
||||
A: length 1000
|
||||
B: length 97270
|
||||
C: length 8000
|
||||
|
||||
**A** will be stored as a FULL record in the first block.
|
||||
|
||||
**B** will be split into three fragments: first fragment occupies the rest of
|
||||
the first block, second fragment occupies the entirety of the second block, and
|
||||
the third fragment occupies a prefix of the third block. This will leave six
|
||||
bytes free in the third block, which will be left empty as the trailer.
|
||||
|
||||
**C** will be stored as a FULL record in the fourth block.
|
||||
|
||||
----
|
||||
|
||||
## Some benefits over the recordio format:
|
||||
|
||||
1. We do not need any heuristics for resyncing - just go to next block boundary
|
||||
and scan. If there is a corruption, skip to the next block. As a
|
||||
side-benefit, we do not get confused when part of the contents of one log
|
||||
file are embedded as a record inside another log file.
|
||||
|
||||
2. Splitting at approximate boundaries (e.g., for mapreduce) is simple: find the
|
||||
next block boundary and skip records until we hit a FULL or FIRST record.
|
||||
|
||||
3. We do not need extra buffering for large records.
|
||||
|
||||
## Some downsides compared to recordio format:
|
||||
|
||||
1. No packing of tiny records. This could be fixed by adding a new record type,
|
||||
so it is a shortcoming of the current implementation, not necessarily the
|
||||
format.
|
||||
|
||||
2. No compression. Again, this could be fixed by adding new record types.
|
||||
75
doc/log_format.txt
Normal file
75
doc/log_format.txt
Normal file
@@ -0,0 +1,75 @@
|
||||
The log file contents are a sequence of 32KB blocks. The only
|
||||
exception is that the tail of the file may contain a partial block.
|
||||
|
||||
Each block consists of a sequence of records:
|
||||
block := record* trailer?
|
||||
record :=
|
||||
checksum: uint32 // crc32c of type and data[] ; little-endian
|
||||
length: uint16 // little-endian
|
||||
type: uint8 // One of FULL, FIRST, MIDDLE, LAST
|
||||
data: uint8[length]
|
||||
|
||||
A record never starts within the last six bytes of a block (since it
|
||||
won't fit). Any leftover bytes here form the trailer, which must
|
||||
consist entirely of zero bytes and must be skipped by readers.
|
||||
|
||||
Aside: if exactly seven bytes are left in the current block, and a new
|
||||
non-zero length record is added, the writer must emit a FIRST record
|
||||
(which contains zero bytes of user data) to fill up the trailing seven
|
||||
bytes of the block and then emit all of the user data in subsequent
|
||||
blocks.
|
||||
|
||||
More types may be added in the future. Some Readers may skip record
|
||||
types they do not understand, others may report that some data was
|
||||
skipped.
|
||||
|
||||
FULL == 1
|
||||
FIRST == 2
|
||||
MIDDLE == 3
|
||||
LAST == 4
|
||||
|
||||
The FULL record contains the contents of an entire user record.
|
||||
|
||||
FIRST, MIDDLE, LAST are types used for user records that have been
|
||||
split into multiple fragments (typically because of block boundaries).
|
||||
FIRST is the type of the first fragment of a user record, LAST is the
|
||||
type of the last fragment of a user record, and MIDDLE is the type of
|
||||
all interior fragments of a user record.
|
||||
|
||||
Example: consider a sequence of user records:
|
||||
A: length 1000
|
||||
B: length 97270
|
||||
C: length 8000
|
||||
A will be stored as a FULL record in the first block.
|
||||
|
||||
B will be split into three fragments: first fragment occupies the rest
|
||||
of the first block, second fragment occupies the entirety of the
|
||||
second block, and the third fragment occupies a prefix of the third
|
||||
block. This will leave six bytes free in the third block, which will
|
||||
be left empty as the trailer.
|
||||
|
||||
C will be stored as a FULL record in the fourth block.
|
||||
|
||||
===================
|
||||
|
||||
Some benefits over the recordio format:
|
||||
|
||||
(1) We do not need any heuristics for resyncing - just go to next
|
||||
block boundary and scan. If there is a corruption, skip to the next
|
||||
block. As a side-benefit, we do not get confused when part of the
|
||||
contents of one log file are embedded as a record inside another log
|
||||
file.
|
||||
|
||||
(2) Splitting at approximate boundaries (e.g., for mapreduce) is
|
||||
simple: find the next block boundary and skip records until we
|
||||
hit a FULL or FIRST record.
|
||||
|
||||
(3) We do not need extra buffering for large records.
|
||||
|
||||
Some downsides compared to recordio format:
|
||||
|
||||
(1) No packing of tiny records. This could be fixed by adding a new
|
||||
record type, so it is a shortcoming of the current implementation,
|
||||
not necessarily the format.
|
||||
|
||||
(2) No compression. Again, this could be fixed by adding new record types.
|
||||
@@ -1,107 +0,0 @@
|
||||
leveldb File format
|
||||
===================
|
||||
|
||||
<beginning_of_file>
|
||||
[data block 1]
|
||||
[data block 2]
|
||||
...
|
||||
[data block N]
|
||||
[meta block 1]
|
||||
...
|
||||
[meta block K]
|
||||
[metaindex block]
|
||||
[index block]
|
||||
[Footer] (fixed size; starts at file_size - sizeof(Footer))
|
||||
<end_of_file>
|
||||
|
||||
The file contains internal pointers. Each such pointer is called
|
||||
a BlockHandle and contains the following information:
|
||||
|
||||
offset: varint64
|
||||
size: varint64
|
||||
|
||||
See [varints](https://developers.google.com/protocol-buffers/docs/encoding#varints)
|
||||
for an explanation of varint64 format.
|
||||
|
||||
1. The sequence of key/value pairs in the file are stored in sorted
|
||||
order and partitioned into a sequence of data blocks. These blocks
|
||||
come one after another at the beginning of the file. Each data block
|
||||
is formatted according to the code in `block_builder.cc`, and then
|
||||
optionally compressed.
|
||||
|
||||
2. After the data blocks we store a bunch of meta blocks. The
|
||||
supported meta block types are described below. More meta block types
|
||||
may be added in the future. Each meta block is again formatted using
|
||||
`block_builder.cc` and then optionally compressed.
|
||||
|
||||
3. A "metaindex" block. It contains one entry for every other meta
|
||||
block where the key is the name of the meta block and the value is a
|
||||
BlockHandle pointing to that meta block.
|
||||
|
||||
4. An "index" block. This block contains one entry per data block,
|
||||
where the key is a string >= last key in that data block and before
|
||||
the first key in the successive data block. The value is the
|
||||
BlockHandle for the data block.
|
||||
|
||||
5. At the very end of the file is a fixed length footer that contains
|
||||
the BlockHandle of the metaindex and index blocks as well as a magic number.
|
||||
|
||||
metaindex_handle: char[p]; // Block handle for metaindex
|
||||
index_handle: char[q]; // Block handle for index
|
||||
padding: char[40-p-q];// zeroed bytes to make fixed length
|
||||
// (40==2*BlockHandle::kMaxEncodedLength)
|
||||
magic: fixed64; // == 0xdb4775248b80fb57 (little-endian)
|
||||
|
||||
## "filter" Meta Block
|
||||
|
||||
If a `FilterPolicy` was specified when the database was opened, a
|
||||
filter block is stored in each table. The "metaindex" block contains
|
||||
an entry that maps from `filter.<N>` to the BlockHandle for the filter
|
||||
block where `<N>` is the string returned by the filter policy's
|
||||
`Name()` method.
|
||||
|
||||
The filter block stores a sequence of filters, where filter i contains
|
||||
the output of `FilterPolicy::CreateFilter()` on all keys that are stored
|
||||
in a block whose file offset falls within the range
|
||||
|
||||
[ i*base ... (i+1)*base-1 ]
|
||||
|
||||
Currently, "base" is 2KB. So for example, if blocks X and Y start in
|
||||
the range `[ 0KB .. 2KB-1 ]`, all of the keys in X and Y will be
|
||||
converted to a filter by calling `FilterPolicy::CreateFilter()`, and the
|
||||
resulting filter will be stored as the first filter in the filter
|
||||
block.
|
||||
|
||||
The filter block is formatted as follows:
|
||||
|
||||
[filter 0]
|
||||
[filter 1]
|
||||
[filter 2]
|
||||
...
|
||||
[filter N-1]
|
||||
|
||||
[offset of filter 0] : 4 bytes
|
||||
[offset of filter 1] : 4 bytes
|
||||
[offset of filter 2] : 4 bytes
|
||||
...
|
||||
[offset of filter N-1] : 4 bytes
|
||||
|
||||
[offset of beginning of offset array] : 4 bytes
|
||||
lg(base) : 1 byte
|
||||
|
||||
The offset array at the end of the filter block allows efficient
|
||||
mapping from a data block offset to the corresponding filter.
|
||||
|
||||
## "stats" Meta Block
|
||||
|
||||
This meta block contains a bunch of stats. The key is the name
|
||||
of the statistic. The value contains the statistic.
|
||||
|
||||
TODO(postrelease): record following stats.
|
||||
|
||||
data size
|
||||
index size
|
||||
key size (uncompressed)
|
||||
value size (uncompressed)
|
||||
number of entries
|
||||
number of data blocks
|
||||
104
doc/table_format.txt
Normal file
104
doc/table_format.txt
Normal file
@@ -0,0 +1,104 @@
|
||||
File format
|
||||
===========
|
||||
|
||||
<beginning_of_file>
|
||||
[data block 1]
|
||||
[data block 2]
|
||||
...
|
||||
[data block N]
|
||||
[meta block 1]
|
||||
...
|
||||
[meta block K]
|
||||
[metaindex block]
|
||||
[index block]
|
||||
[Footer] (fixed size; starts at file_size - sizeof(Footer))
|
||||
<end_of_file>
|
||||
|
||||
The file contains internal pointers. Each such pointer is called
|
||||
a BlockHandle and contains the following information:
|
||||
offset: varint64
|
||||
size: varint64
|
||||
See https://developers.google.com/protocol-buffers/docs/encoding#varints
|
||||
for an explanation of varint64 format.
|
||||
|
||||
(1) The sequence of key/value pairs in the file are stored in sorted
|
||||
order and partitioned into a sequence of data blocks. These blocks
|
||||
come one after another at the beginning of the file. Each data block
|
||||
is formatted according to the code in block_builder.cc, and then
|
||||
optionally compressed.
|
||||
|
||||
(2) After the data blocks we store a bunch of meta blocks. The
|
||||
supported meta block types are described below. More meta block types
|
||||
may be added in the future. Each meta block is again formatted using
|
||||
block_builder.cc and then optionally compressed.
|
||||
|
||||
(3) A "metaindex" block. It contains one entry for every other meta
|
||||
block where the key is the name of the meta block and the value is a
|
||||
BlockHandle pointing to that meta block.
|
||||
|
||||
(4) An "index" block. This block contains one entry per data block,
|
||||
where the key is a string >= last key in that data block and before
|
||||
the first key in the successive data block. The value is the
|
||||
BlockHandle for the data block.
|
||||
|
||||
(6) At the very end of the file is a fixed length footer that contains
|
||||
the BlockHandle of the metaindex and index blocks as well as a magic number.
|
||||
metaindex_handle: char[p]; // Block handle for metaindex
|
||||
index_handle: char[q]; // Block handle for index
|
||||
padding: char[40-p-q]; // zeroed bytes to make fixed length
|
||||
// (40==2*BlockHandle::kMaxEncodedLength)
|
||||
magic: fixed64; // == 0xdb4775248b80fb57 (little-endian)
|
||||
|
||||
"filter" Meta Block
|
||||
-------------------
|
||||
|
||||
If a "FilterPolicy" was specified when the database was opened, a
|
||||
filter block is stored in each table. The "metaindex" block contains
|
||||
an entry that maps from "filter.<N>" to the BlockHandle for the filter
|
||||
block where "<N>" is the string returned by the filter policy's
|
||||
"Name()" method.
|
||||
|
||||
The filter block stores a sequence of filters, where filter i contains
|
||||
the output of FilterPolicy::CreateFilter() on all keys that are stored
|
||||
in a block whose file offset falls within the range
|
||||
|
||||
[ i*base ... (i+1)*base-1 ]
|
||||
|
||||
Currently, "base" is 2KB. So for example, if blocks X and Y start in
|
||||
the range [ 0KB .. 2KB-1 ], all of the keys in X and Y will be
|
||||
converted to a filter by calling FilterPolicy::CreateFilter(), and the
|
||||
resulting filter will be stored as the first filter in the filter
|
||||
block.
|
||||
|
||||
The filter block is formatted as follows:
|
||||
|
||||
[filter 0]
|
||||
[filter 1]
|
||||
[filter 2]
|
||||
...
|
||||
[filter N-1]
|
||||
|
||||
[offset of filter 0] : 4 bytes
|
||||
[offset of filter 1] : 4 bytes
|
||||
[offset of filter 2] : 4 bytes
|
||||
...
|
||||
[offset of filter N-1] : 4 bytes
|
||||
|
||||
[offset of beginning of offset array] : 4 bytes
|
||||
lg(base) : 1 byte
|
||||
|
||||
The offset array at the end of the filter block allows efficient
|
||||
mapping from a data block offset to the corresponding filter.
|
||||
|
||||
"stats" Meta Block
|
||||
------------------
|
||||
|
||||
This meta block contains a bunch of stats. The key is the name
|
||||
of the statistic. The value contains the statistic.
|
||||
TODO(postrelease): record following stats.
|
||||
data size
|
||||
index size
|
||||
key size (uncompressed)
|
||||
value size (uncompressed)
|
||||
number of entries
|
||||
number of data blocks
|
||||
@@ -14,7 +14,7 @@ namespace leveldb {
|
||||
|
||||
// Update Makefile if you change these
|
||||
static const int kMajorVersion = 1;
|
||||
static const int kMinorVersion = 20;
|
||||
static const int kMinorVersion = 18;
|
||||
|
||||
struct Options;
|
||||
struct ReadOptions;
|
||||
|
||||
@@ -112,18 +112,6 @@ struct Options {
|
||||
// Default: 16
|
||||
int block_restart_interval;
|
||||
|
||||
// Leveldb will write up to this amount of bytes to a file before
|
||||
// switching to a new one.
|
||||
// Most clients should leave this parameter alone. However if your
|
||||
// filesystem is more efficient with larger files, you could
|
||||
// consider increasing the value. The downside will be longer
|
||||
// compactions and hence longer latency/performance hiccups.
|
||||
// Another reason to increase this parameter might be when you are
|
||||
// initially populating a large database.
|
||||
//
|
||||
// Default: 2MB
|
||||
size_t max_file_size;
|
||||
|
||||
// Compress blocks using the specified compression algorithm. This
|
||||
// parameter can be changed dynamically.
|
||||
//
|
||||
|
||||
@@ -63,9 +63,6 @@ class Status {
|
||||
// Returns true iff the status indicates a NotSupportedError.
|
||||
bool IsNotSupportedError() const { return code() == kNotSupported; }
|
||||
|
||||
// Returns true iff the status indicates an InvalidArgument.
|
||||
bool IsInvalidArgument() const { return code() == kInvalidArgument; }
|
||||
|
||||
// Return a string representation of this status suitable for printing.
|
||||
// Returns the string "OK" for success.
|
||||
std::string ToString() const;
|
||||
|
||||
@@ -39,8 +39,6 @@
|
||||
#define ARCH_CPU_ARM64_FAMILY 1
|
||||
#elif defined(__ppc__) || defined(__powerpc__) || defined(__powerpc64__)
|
||||
#define ARCH_CPU_PPC_FAMILY 1
|
||||
#elif defined(__mips__)
|
||||
#define ARCH_CPU_MIPS_FAMILY 1
|
||||
#endif
|
||||
|
||||
namespace leveldb {
|
||||
@@ -112,13 +110,6 @@ inline void MemoryBarrier() {
|
||||
}
|
||||
#define LEVELDB_HAVE_MEMORY_BARRIER
|
||||
|
||||
// MIPS
|
||||
#elif defined(ARCH_CPU_MIPS_FAMILY) && defined(__GNUC__)
|
||||
inline void MemoryBarrier() {
|
||||
__asm__ __volatile__("sync" : : : "memory");
|
||||
}
|
||||
#define LEVELDB_HAVE_MEMORY_BARRIER
|
||||
|
||||
#endif
|
||||
|
||||
// AtomicPointer built using platform-specific MemoryBarrier()
|
||||
|
||||
@@ -129,12 +129,6 @@ extern bool Snappy_Uncompress(const char* input_data, size_t input_length,
|
||||
// The concatenation of all "data[0,n-1]" fragments is the heap profile.
|
||||
extern bool GetHeapProfile(void (*func)(void*, const char*, int), void* arg);
|
||||
|
||||
// Extend the CRC to include the first n bytes of buf.
|
||||
//
|
||||
// Returns zero if the CRC cannot be extended using acceleration, else returns
|
||||
// the newly extended CRC value (which may also be zero).
|
||||
uint32_t AcceleratedCRC32C(uint32_t crc, const char* buf, size_t size);
|
||||
|
||||
} // namespace port
|
||||
} // namespace leveldb
|
||||
|
||||
|
||||
@@ -7,6 +7,7 @@
|
||||
#include <cstdlib>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include "util/logging.h"
|
||||
|
||||
namespace leveldb {
|
||||
namespace port {
|
||||
|
||||
@@ -148,8 +148,6 @@ inline bool GetHeapProfile(void (*func)(void*, const char*, int), void* arg) {
|
||||
return false;
|
||||
}
|
||||
|
||||
uint32_t AcceleratedCRC32C(uint32_t crc, const char* buf, size_t size);
|
||||
|
||||
} // namespace port
|
||||
} // namespace leveldb
|
||||
|
||||
|
||||
@@ -1,129 +0,0 @@
|
||||
// Copyright 2016 The LevelDB Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style license that can be
|
||||
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||
//
|
||||
// A portable implementation of crc32c, optimized to handle
|
||||
// four bytes at a time.
|
||||
//
|
||||
// In a separate source file to allow this accelerated CRC32C function to be
|
||||
// compiled with the appropriate compiler flags to enable x86 SSE 4.2
|
||||
// instructions.
|
||||
|
||||
#include <stdint.h>
|
||||
#include <string.h>
|
||||
#include "port/port.h"
|
||||
|
||||
#if defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
|
||||
#if defined(_MSC_VER)
|
||||
#include <intrin.h>
|
||||
#elif defined(__GNUC__) && defined(__SSE4_2__)
|
||||
#include <nmmintrin.h>
|
||||
#include <cpuid.h>
|
||||
#endif
|
||||
|
||||
#endif // defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
|
||||
namespace leveldb {
|
||||
namespace port {
|
||||
|
||||
#if defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
|
||||
// Used to fetch a naturally-aligned 32-bit word in little endian byte-order
|
||||
static inline uint32_t LE_LOAD32(const uint8_t *p) {
|
||||
// SSE is x86 only, so ensured that |p| is always little-endian.
|
||||
uint32_t word;
|
||||
memcpy(&word, p, sizeof(word));
|
||||
return word;
|
||||
}
|
||||
|
||||
#if defined(_M_X64) || defined(__x86_64__) // LE_LOAD64 is only used on x64.
|
||||
|
||||
// Used to fetch a naturally-aligned 64-bit word in little endian byte-order
|
||||
static inline uint64_t LE_LOAD64(const uint8_t *p) {
|
||||
uint64_t dword;
|
||||
memcpy(&dword, p, sizeof(dword));
|
||||
return dword;
|
||||
}
|
||||
|
||||
#endif // defined(_M_X64) || defined(__x86_64__)
|
||||
|
||||
static inline bool HaveSSE42() {
|
||||
#if defined(_MSC_VER)
|
||||
int cpu_info[4];
|
||||
__cpuid(cpu_info, 1);
|
||||
return (cpu_info[2] & (1 << 20)) != 0;
|
||||
#elif defined(__GNUC__)
|
||||
unsigned int eax, ebx, ecx, edx;
|
||||
__get_cpuid(1, &eax, &ebx, &ecx, &edx);
|
||||
return (ecx & (1 << 20)) != 0;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
#endif // defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
|
||||
// For further improvements see Intel publication at:
|
||||
// http://download.intel.com/design/intarch/papers/323405.pdf
|
||||
uint32_t AcceleratedCRC32C(uint32_t crc, const char* buf, size_t size) {
|
||||
#if !defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
return 0;
|
||||
#else
|
||||
static bool have = HaveSSE42();
|
||||
if (!have) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
const uint8_t *p = reinterpret_cast<const uint8_t *>(buf);
|
||||
const uint8_t *e = p + size;
|
||||
uint32_t l = crc ^ 0xffffffffu;
|
||||
|
||||
#define STEP1 do { \
|
||||
l = _mm_crc32_u8(l, *p++); \
|
||||
} while (0)
|
||||
#define STEP4 do { \
|
||||
l = _mm_crc32_u32(l, LE_LOAD32(p)); \
|
||||
p += 4; \
|
||||
} while (0)
|
||||
#define STEP8 do { \
|
||||
l = _mm_crc32_u64(l, LE_LOAD64(p)); \
|
||||
p += 8; \
|
||||
} while (0)
|
||||
|
||||
if (size > 16) {
|
||||
// Process unaligned bytes
|
||||
for (unsigned int i = reinterpret_cast<uintptr_t>(p) % 8; i; --i) {
|
||||
STEP1;
|
||||
}
|
||||
|
||||
// _mm_crc32_u64 is only available on x64.
|
||||
#if defined(_M_X64) || defined(__x86_64__)
|
||||
// Process 8 bytes at a time
|
||||
while ((e-p) >= 8) {
|
||||
STEP8;
|
||||
}
|
||||
// Process 4 bytes at a time
|
||||
if ((e-p) >= 4) {
|
||||
STEP4;
|
||||
}
|
||||
#else // !(defined(_M_X64) || defined(__x86_64__))
|
||||
// Process 4 bytes at a time
|
||||
while ((e-p) >= 4) {
|
||||
STEP4;
|
||||
}
|
||||
#endif // defined(_M_X64) || defined(__x86_64__)
|
||||
}
|
||||
// Process the last few bytes
|
||||
while (p != e) {
|
||||
STEP1;
|
||||
}
|
||||
#undef STEP8
|
||||
#undef STEP4
|
||||
#undef STEP1
|
||||
return l ^ 0xffffffffu;
|
||||
#endif // defined(LEVELDB_PLATFORM_POSIX_SSE)
|
||||
}
|
||||
|
||||
} // namespace port
|
||||
} // namespace leveldb
|
||||
@@ -9,7 +9,7 @@
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
// See doc/table_format.md for an explanation of the filter block format.
|
||||
// See doc/table_format.txt for an explanation of the filter block format.
|
||||
|
||||
// Generate new filter every 2KB of data
|
||||
static const size_t kFilterBaseLg = 11;
|
||||
@@ -68,7 +68,7 @@ void FilterBlockBuilder::GenerateFilter() {
|
||||
|
||||
// Generate filter for current set of keys and append to result_.
|
||||
filter_offsets_.push_back(result_.size());
|
||||
policy_->CreateFilter(&tmp_keys_[0], static_cast<int>(num_keys), &result_);
|
||||
policy_->CreateFilter(&tmp_keys_[0], num_keys, &result_);
|
||||
|
||||
tmp_keys_.clear();
|
||||
keys_.clear();
|
||||
@@ -97,7 +97,7 @@ bool FilterBlockReader::KeyMayMatch(uint64_t block_offset, const Slice& key) {
|
||||
if (index < num_) {
|
||||
uint32_t start = DecodeFixed32(offset_ + index*4);
|
||||
uint32_t limit = DecodeFixed32(offset_ + index*4 + 4);
|
||||
if (start <= limit && limit <= static_cast<size_t>(offset_ - data_)) {
|
||||
if (start <= limit && limit <= (offset_ - data_)) {
|
||||
Slice filter = Slice(data_ + start, limit - start);
|
||||
return policy_->KeyMayMatch(key, filter);
|
||||
} else if (start == limit) {
|
||||
|
||||
@@ -30,14 +30,15 @@ Status BlockHandle::DecodeFrom(Slice* input) {
|
||||
}
|
||||
|
||||
void Footer::EncodeTo(std::string* dst) const {
|
||||
#ifndef NDEBUG
|
||||
const size_t original_size = dst->size();
|
||||
#endif
|
||||
metaindex_handle_.EncodeTo(dst);
|
||||
index_handle_.EncodeTo(dst);
|
||||
dst->resize(2 * BlockHandle::kMaxEncodedLength); // Padding
|
||||
PutFixed32(dst, static_cast<uint32_t>(kTableMagicNumber & 0xffffffffu));
|
||||
PutFixed32(dst, static_cast<uint32_t>(kTableMagicNumber >> 32));
|
||||
assert(dst->size() == original_size + kEncodedLength);
|
||||
(void)original_size; // Disable unused variable warning.
|
||||
}
|
||||
|
||||
Status Footer::DecodeFrom(Slice* input) {
|
||||
|
||||
@@ -82,7 +82,7 @@ Status Table::Open(const Options& options,
|
||||
*table = new Table(rep);
|
||||
(*table)->ReadMeta(footer);
|
||||
} else {
|
||||
delete index_block;
|
||||
if (index_block) delete index_block;
|
||||
}
|
||||
|
||||
return s;
|
||||
|
||||
@@ -853,20 +853,12 @@ TEST(TableTest, ApproximateOffsetOfCompressed) {
|
||||
options.compression = kSnappyCompression;
|
||||
c.Finish(options, &keys, &kvmap);
|
||||
|
||||
// Expected upper and lower bounds of space used by compressible strings.
|
||||
static const int kSlop = 1000; // Compressor effectiveness varies.
|
||||
const int expected = 2500; // 10000 * compression ratio (0.25)
|
||||
const int min_z = expected - kSlop;
|
||||
const int max_z = expected + kSlop;
|
||||
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("abc"), 0, kSlop));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k01"), 0, kSlop));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k02"), 0, kSlop));
|
||||
// Have now emitted a large compressible string, so adjust expected offset.
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k03"), min_z, max_z));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k04"), min_z, max_z));
|
||||
// Have now emitted two large compressible strings, so adjust expected offset.
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("xyz"), 2 * min_z, 2 * max_z));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("abc"), 0, 0));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k01"), 0, 0));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k02"), 0, 0));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k03"), 2000, 3000));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("k04"), 2000, 3000));
|
||||
ASSERT_TRUE(Between(c.ApproximateOffsetOf("xyz"), 4000, 6000));
|
||||
}
|
||||
|
||||
} // namespace leveldb
|
||||
|
||||
@@ -9,7 +9,8 @@ namespace leveldb {
|
||||
|
||||
static const int kBlockSize = 4096;
|
||||
|
||||
Arena::Arena() : memory_usage_(0) {
|
||||
Arena::Arena() {
|
||||
blocks_memory_ = 0;
|
||||
alloc_ptr_ = NULL; // First allocation will allocate a block
|
||||
alloc_bytes_remaining_ = 0;
|
||||
}
|
||||
@@ -59,9 +60,8 @@ char* Arena::AllocateAligned(size_t bytes) {
|
||||
|
||||
char* Arena::AllocateNewBlock(size_t block_bytes) {
|
||||
char* result = new char[block_bytes];
|
||||
blocks_memory_ += block_bytes;
|
||||
blocks_.push_back(result);
|
||||
memory_usage_.NoBarrier_Store(
|
||||
reinterpret_cast<void*>(MemoryUsage() + block_bytes + sizeof(char*)));
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
10
util/arena.h
10
util/arena.h
@@ -9,7 +9,6 @@
|
||||
#include <assert.h>
|
||||
#include <stddef.h>
|
||||
#include <stdint.h>
|
||||
#include "port/port.h"
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
@@ -25,9 +24,10 @@ class Arena {
|
||||
char* AllocateAligned(size_t bytes);
|
||||
|
||||
// Returns an estimate of the total memory usage of data allocated
|
||||
// by the arena.
|
||||
// by the arena (including space allocated but not yet used for user
|
||||
// allocations).
|
||||
size_t MemoryUsage() const {
|
||||
return reinterpret_cast<uintptr_t>(memory_usage_.NoBarrier_Load());
|
||||
return blocks_memory_ + blocks_.capacity() * sizeof(char*);
|
||||
}
|
||||
|
||||
private:
|
||||
@@ -41,8 +41,8 @@ class Arena {
|
||||
// Array of new[] allocated memory blocks
|
||||
std::vector<char*> blocks_;
|
||||
|
||||
// Total memory usage of the arena.
|
||||
port::AtomicPointer memory_usage_;
|
||||
// Bytes of memory in blocks allocated so far
|
||||
size_t blocks_memory_;
|
||||
|
||||
// No copying allowed
|
||||
Arena(const Arena&);
|
||||
|
||||
@@ -47,7 +47,7 @@ class BloomFilterPolicy : public FilterPolicy {
|
||||
dst->resize(init_size + bytes, 0);
|
||||
dst->push_back(static_cast<char>(k_)); // Remember # of probes in filter
|
||||
char* array = &(*dst)[init_size];
|
||||
for (int i = 0; i < n; i++) {
|
||||
for (size_t i = 0; i < n; i++) {
|
||||
// Use double-hashing to generate a sequence of hash values.
|
||||
// See analysis in [Kirsch,Mitzenmacher 2006].
|
||||
uint32_t h = BloomHash(keys[i]);
|
||||
|
||||
@@ -46,8 +46,7 @@ class BloomTest {
|
||||
key_slices.push_back(Slice(keys_[i]));
|
||||
}
|
||||
filter_.clear();
|
||||
policy_->CreateFilter(&key_slices[0], static_cast<int>(key_slices.size()),
|
||||
&filter_);
|
||||
policy_->CreateFilter(&key_slices[0], key_slices.size(), &filter_);
|
||||
keys_.clear();
|
||||
if (kVerbose >= 2) DumpFilter();
|
||||
}
|
||||
|
||||
122
util/cache.cc
122
util/cache.cc
@@ -19,23 +19,6 @@ Cache::~Cache() {
|
||||
namespace {
|
||||
|
||||
// LRU cache implementation
|
||||
//
|
||||
// Cache entries have an "in_cache" boolean indicating whether the cache has a
|
||||
// reference on the entry. The only ways that this can become false without the
|
||||
// entry being passed to its "deleter" are via Erase(), via Insert() when
|
||||
// an element with a duplicate key is inserted, or on destruction of the cache.
|
||||
//
|
||||
// The cache keeps two linked lists of items in the cache. All items in the
|
||||
// cache are in one list or the other, and never both. Items still referenced
|
||||
// by clients but erased from the cache are in neither list. The lists are:
|
||||
// - in-use: contains the items currently referenced by clients, in no
|
||||
// particular order. (This list is used for invariant checking. If we
|
||||
// removed the check, elements that would otherwise be on this list could be
|
||||
// left as disconnected singleton lists.)
|
||||
// - LRU: contains the items not currently referenced by clients, in LRU order
|
||||
// Elements are moved between these lists by the Ref() and Unref() methods,
|
||||
// when they detect an element in the cache acquiring or losing its only
|
||||
// external reference.
|
||||
|
||||
// An entry is a variable length heap-allocated structure. Entries
|
||||
// are kept in a circular doubly linked list ordered by access time.
|
||||
@@ -47,8 +30,7 @@ struct LRUHandle {
|
||||
LRUHandle* prev;
|
||||
size_t charge; // TODO(opt): Only allow uint32_t?
|
||||
size_t key_length;
|
||||
bool in_cache; // Whether entry is in the cache.
|
||||
uint32_t refs; // References, including cache reference, if present.
|
||||
uint32_t refs;
|
||||
uint32_t hash; // Hash of key(); used for fast sharding and comparisons
|
||||
char key_data[1]; // Beginning of key
|
||||
|
||||
@@ -173,10 +155,8 @@ class LRUCache {
|
||||
|
||||
private:
|
||||
void LRU_Remove(LRUHandle* e);
|
||||
void LRU_Append(LRUHandle*list, LRUHandle* e);
|
||||
void Ref(LRUHandle* e);
|
||||
void LRU_Append(LRUHandle* e);
|
||||
void Unref(LRUHandle* e);
|
||||
bool FinishErase(LRUHandle* e);
|
||||
|
||||
// Initialized before use.
|
||||
size_t capacity_;
|
||||
@@ -187,55 +167,34 @@ class LRUCache {
|
||||
|
||||
// Dummy head of LRU list.
|
||||
// lru.prev is newest entry, lru.next is oldest entry.
|
||||
// Entries have refs==1 and in_cache==true.
|
||||
LRUHandle lru_;
|
||||
|
||||
// Dummy head of in-use list.
|
||||
// Entries are in use by clients, and have refs >= 2 and in_cache==true.
|
||||
LRUHandle in_use_;
|
||||
|
||||
HandleTable table_;
|
||||
};
|
||||
|
||||
LRUCache::LRUCache()
|
||||
: usage_(0) {
|
||||
// Make empty circular linked lists.
|
||||
// Make empty circular linked list
|
||||
lru_.next = &lru_;
|
||||
lru_.prev = &lru_;
|
||||
in_use_.next = &in_use_;
|
||||
in_use_.prev = &in_use_;
|
||||
}
|
||||
|
||||
LRUCache::~LRUCache() {
|
||||
assert(in_use_.next == &in_use_); // Error if caller has an unreleased handle
|
||||
for (LRUHandle* e = lru_.next; e != &lru_; ) {
|
||||
LRUHandle* next = e->next;
|
||||
assert(e->in_cache);
|
||||
e->in_cache = false;
|
||||
assert(e->refs == 1); // Invariant of lru_ list.
|
||||
assert(e->refs == 1); // Error if caller has an unreleased handle
|
||||
Unref(e);
|
||||
e = next;
|
||||
}
|
||||
}
|
||||
|
||||
void LRUCache::Ref(LRUHandle* e) {
|
||||
if (e->refs == 1 && e->in_cache) { // If on lru_ list, move to in_use_ list.
|
||||
LRU_Remove(e);
|
||||
LRU_Append(&in_use_, e);
|
||||
}
|
||||
e->refs++;
|
||||
}
|
||||
|
||||
void LRUCache::Unref(LRUHandle* e) {
|
||||
assert(e->refs > 0);
|
||||
e->refs--;
|
||||
if (e->refs == 0) { // Deallocate.
|
||||
assert(!e->in_cache);
|
||||
if (e->refs <= 0) {
|
||||
usage_ -= e->charge;
|
||||
(*e->deleter)(e->key(), e->value);
|
||||
free(e);
|
||||
} else if (e->in_cache && e->refs == 1) { // No longer in use; move to lru_ list.
|
||||
LRU_Remove(e);
|
||||
LRU_Append(&lru_, e);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -244,10 +203,10 @@ void LRUCache::LRU_Remove(LRUHandle* e) {
|
||||
e->prev->next = e->next;
|
||||
}
|
||||
|
||||
void LRUCache::LRU_Append(LRUHandle* list, LRUHandle* e) {
|
||||
// Make "e" newest entry by inserting just before *list
|
||||
e->next = list;
|
||||
e->prev = list->prev;
|
||||
void LRUCache::LRU_Append(LRUHandle* e) {
|
||||
// Make "e" newest entry by inserting just before lru_
|
||||
e->next = &lru_;
|
||||
e->prev = lru_.prev;
|
||||
e->prev->next = e;
|
||||
e->next->prev = e;
|
||||
}
|
||||
@@ -256,7 +215,9 @@ Cache::Handle* LRUCache::Lookup(const Slice& key, uint32_t hash) {
|
||||
MutexLock l(&mutex_);
|
||||
LRUHandle* e = table_.Lookup(key, hash);
|
||||
if (e != NULL) {
|
||||
Ref(e);
|
||||
e->refs++;
|
||||
LRU_Remove(e);
|
||||
LRU_Append(e);
|
||||
}
|
||||
return reinterpret_cast<Cache::Handle*>(e);
|
||||
}
|
||||
@@ -278,57 +239,46 @@ Cache::Handle* LRUCache::Insert(
|
||||
e->charge = charge;
|
||||
e->key_length = key.size();
|
||||
e->hash = hash;
|
||||
e->in_cache = false;
|
||||
e->refs = 1; // for the returned handle.
|
||||
e->refs = 2; // One from LRUCache, one for the returned handle
|
||||
memcpy(e->key_data, key.data(), key.size());
|
||||
LRU_Append(e);
|
||||
usage_ += charge;
|
||||
|
||||
if (capacity_ > 0) {
|
||||
e->refs++; // for the cache's reference.
|
||||
e->in_cache = true;
|
||||
LRU_Append(&in_use_, e);
|
||||
usage_ += charge;
|
||||
FinishErase(table_.Insert(e));
|
||||
} // else don't cache. (Tests use capacity_==0 to turn off caching.)
|
||||
LRUHandle* old = table_.Insert(e);
|
||||
if (old != NULL) {
|
||||
LRU_Remove(old);
|
||||
Unref(old);
|
||||
}
|
||||
|
||||
while (usage_ > capacity_ && lru_.next != &lru_) {
|
||||
LRUHandle* old = lru_.next;
|
||||
assert(old->refs == 1);
|
||||
bool erased = FinishErase(table_.Remove(old->key(), old->hash));
|
||||
if (!erased) { // to avoid unused variable when compiled NDEBUG
|
||||
assert(erased);
|
||||
}
|
||||
LRU_Remove(old);
|
||||
table_.Remove(old->key(), old->hash);
|
||||
Unref(old);
|
||||
}
|
||||
|
||||
return reinterpret_cast<Cache::Handle*>(e);
|
||||
}
|
||||
|
||||
// If e != NULL, finish removing *e from the cache; it has already been removed
|
||||
// from the hash table. Return whether e != NULL. Requires mutex_ held.
|
||||
bool LRUCache::FinishErase(LRUHandle* e) {
|
||||
if (e != NULL) {
|
||||
assert(e->in_cache);
|
||||
LRU_Remove(e);
|
||||
e->in_cache = false;
|
||||
usage_ -= e->charge;
|
||||
Unref(e);
|
||||
}
|
||||
return e != NULL;
|
||||
}
|
||||
|
||||
void LRUCache::Erase(const Slice& key, uint32_t hash) {
|
||||
MutexLock l(&mutex_);
|
||||
FinishErase(table_.Remove(key, hash));
|
||||
LRUHandle* e = table_.Remove(key, hash);
|
||||
if (e != NULL) {
|
||||
LRU_Remove(e);
|
||||
Unref(e);
|
||||
}
|
||||
}
|
||||
|
||||
void LRUCache::Prune() {
|
||||
MutexLock l(&mutex_);
|
||||
while (lru_.next != &lru_) {
|
||||
LRUHandle* e = lru_.next;
|
||||
assert(e->refs == 1);
|
||||
bool erased = FinishErase(table_.Remove(e->key(), e->hash));
|
||||
if (!erased) { // to avoid unused variable when compiled NDEBUG
|
||||
assert(erased);
|
||||
for (LRUHandle* e = lru_.next; e != &lru_; ) {
|
||||
LRUHandle* next = e->next;
|
||||
if (e->refs == 1) {
|
||||
table_.Remove(e->key(), e->hash);
|
||||
LRU_Remove(e);
|
||||
Unref(e);
|
||||
}
|
||||
e = next;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -59,11 +59,6 @@ class CacheTest {
|
||||
&CacheTest::Deleter));
|
||||
}
|
||||
|
||||
Cache::Handle* InsertAndReturnHandle(int key, int value, int charge = 1) {
|
||||
return cache_->Insert(EncodeKey(key), EncodeValue(value), charge,
|
||||
&CacheTest::Deleter);
|
||||
}
|
||||
|
||||
void Erase(int key) {
|
||||
cache_->Erase(EncodeKey(key));
|
||||
}
|
||||
@@ -140,11 +135,8 @@ TEST(CacheTest, EntriesArePinned) {
|
||||
TEST(CacheTest, EvictionPolicy) {
|
||||
Insert(100, 101);
|
||||
Insert(200, 201);
|
||||
Insert(300, 301);
|
||||
Cache::Handle* h = cache_->Lookup(EncodeKey(300));
|
||||
|
||||
// Frequently used entry must be kept around,
|
||||
// as must things that are still in use.
|
||||
// Frequently used entry must be kept around
|
||||
for (int i = 0; i < kCacheSize + 100; i++) {
|
||||
Insert(1000+i, 2000+i);
|
||||
ASSERT_EQ(2000+i, Lookup(1000+i));
|
||||
@@ -152,25 +144,6 @@ TEST(CacheTest, EvictionPolicy) {
|
||||
}
|
||||
ASSERT_EQ(101, Lookup(100));
|
||||
ASSERT_EQ(-1, Lookup(200));
|
||||
ASSERT_EQ(301, Lookup(300));
|
||||
cache_->Release(h);
|
||||
}
|
||||
|
||||
TEST(CacheTest, UseExceedsCacheSize) {
|
||||
// Overfill the cache, keeping handles on all inserted entries.
|
||||
std::vector<Cache::Handle*> h;
|
||||
for (int i = 0; i < kCacheSize + 100; i++) {
|
||||
h.push_back(InsertAndReturnHandle(1000+i, 2000+i));
|
||||
}
|
||||
|
||||
// Check that all the entries can be found in the cache.
|
||||
for (int i = 0; i < h.size(); i++) {
|
||||
ASSERT_EQ(2000+i, Lookup(1000+i));
|
||||
}
|
||||
|
||||
for (int i = 0; i < h.size(); i++) {
|
||||
cache_->Release(h[i]);
|
||||
}
|
||||
}
|
||||
|
||||
TEST(CacheTest, HeavyEntries) {
|
||||
|
||||
@@ -8,8 +8,6 @@
|
||||
#include "util/crc32c.h"
|
||||
|
||||
#include <stdint.h>
|
||||
|
||||
#include "port/port.h"
|
||||
#include "util/coding.h"
|
||||
|
||||
namespace leveldb {
|
||||
@@ -285,23 +283,7 @@ static inline uint32_t LE_LOAD32(const uint8_t *p) {
|
||||
return DecodeFixed32(reinterpret_cast<const char*>(p));
|
||||
}
|
||||
|
||||
// Determine if the CPU running this program can accelerate the CRC32C
|
||||
// calculation.
|
||||
static bool CanAccelerateCRC32C() {
|
||||
// port::AcceleretedCRC32C returns zero when unable to accelerate.
|
||||
static const char kTestCRCBuffer[] = "TestCRCBuffer";
|
||||
static const char kBufSize = sizeof(kTestCRCBuffer) - 1;
|
||||
static const uint32_t kTestCRCValue = 0xdcbc59fa;
|
||||
|
||||
return port::AcceleratedCRC32C(0, kTestCRCBuffer, kBufSize) == kTestCRCValue;
|
||||
}
|
||||
|
||||
uint32_t Extend(uint32_t crc, const char* buf, size_t size) {
|
||||
static bool accelerate = CanAccelerateCRC32C();
|
||||
if (accelerate) {
|
||||
return port::AcceleratedCRC32C(crc, buf, size);
|
||||
}
|
||||
|
||||
const uint8_t *p = reinterpret_cast<const uint8_t *>(buf);
|
||||
const uint8_t *e = p + size;
|
||||
uint32_t l = crc ^ 0xffffffffu;
|
||||
|
||||
@@ -10,14 +10,12 @@
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <sys/mman.h>
|
||||
#include <sys/resource.h>
|
||||
#include <sys/stat.h>
|
||||
#include <sys/time.h>
|
||||
#include <sys/types.h>
|
||||
#include <time.h>
|
||||
#include <unistd.h>
|
||||
#include <deque>
|
||||
#include <limits>
|
||||
#include <set>
|
||||
#include "leveldb/env.h"
|
||||
#include "leveldb/slice.h"
|
||||
@@ -25,70 +23,15 @@
|
||||
#include "util/logging.h"
|
||||
#include "util/mutexlock.h"
|
||||
#include "util/posix_logger.h"
|
||||
#include "util/env_posix_test_helper.h"
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
namespace {
|
||||
|
||||
static int open_read_only_file_limit = -1;
|
||||
static int mmap_limit = -1;
|
||||
|
||||
static Status IOError(const std::string& context, int err_number) {
|
||||
return Status::IOError(context, strerror(err_number));
|
||||
}
|
||||
|
||||
// Helper class to limit resource usage to avoid exhaustion.
|
||||
// Currently used to limit read-only file descriptors and mmap file usage
|
||||
// so that we do not end up running out of file descriptors, virtual memory,
|
||||
// or running into kernel performance problems for very large databases.
|
||||
class Limiter {
|
||||
public:
|
||||
// Limit maximum number of resources to |n|.
|
||||
Limiter(intptr_t n) {
|
||||
SetAllowed(n);
|
||||
}
|
||||
|
||||
// If another resource is available, acquire it and return true.
|
||||
// Else return false.
|
||||
bool Acquire() {
|
||||
if (GetAllowed() <= 0) {
|
||||
return false;
|
||||
}
|
||||
MutexLock l(&mu_);
|
||||
intptr_t x = GetAllowed();
|
||||
if (x <= 0) {
|
||||
return false;
|
||||
} else {
|
||||
SetAllowed(x - 1);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
// Release a resource acquired by a previous call to Acquire() that returned
|
||||
// true.
|
||||
void Release() {
|
||||
MutexLock l(&mu_);
|
||||
SetAllowed(GetAllowed() + 1);
|
||||
}
|
||||
|
||||
private:
|
||||
port::Mutex mu_;
|
||||
port::AtomicPointer allowed_;
|
||||
|
||||
intptr_t GetAllowed() const {
|
||||
return reinterpret_cast<intptr_t>(allowed_.Acquire_Load());
|
||||
}
|
||||
|
||||
// REQUIRES: mu_ must be held
|
||||
void SetAllowed(intptr_t v) {
|
||||
allowed_.Release_Store(reinterpret_cast<void*>(v));
|
||||
}
|
||||
|
||||
Limiter(const Limiter&);
|
||||
void operator=(const Limiter&);
|
||||
};
|
||||
|
||||
class PosixSequentialFile: public SequentialFile {
|
||||
private:
|
||||
std::string filename_;
|
||||
@@ -126,65 +69,87 @@ class PosixSequentialFile: public SequentialFile {
|
||||
class PosixRandomAccessFile: public RandomAccessFile {
|
||||
private:
|
||||
std::string filename_;
|
||||
bool temporary_fd_; // If true, fd_ is -1 and we open on every read.
|
||||
int fd_;
|
||||
Limiter* limiter_;
|
||||
|
||||
public:
|
||||
PosixRandomAccessFile(const std::string& fname, int fd, Limiter* limiter)
|
||||
: filename_(fname), fd_(fd), limiter_(limiter) {
|
||||
temporary_fd_ = !limiter->Acquire();
|
||||
if (temporary_fd_) {
|
||||
// Open file on every access.
|
||||
close(fd_);
|
||||
fd_ = -1;
|
||||
}
|
||||
}
|
||||
|
||||
virtual ~PosixRandomAccessFile() {
|
||||
if (!temporary_fd_) {
|
||||
close(fd_);
|
||||
limiter_->Release();
|
||||
}
|
||||
}
|
||||
PosixRandomAccessFile(const std::string& fname, int fd)
|
||||
: filename_(fname), fd_(fd) { }
|
||||
virtual ~PosixRandomAccessFile() { close(fd_); }
|
||||
|
||||
virtual Status Read(uint64_t offset, size_t n, Slice* result,
|
||||
char* scratch) const {
|
||||
int fd = fd_;
|
||||
if (temporary_fd_) {
|
||||
fd = open(filename_.c_str(), O_RDONLY);
|
||||
if (fd < 0) {
|
||||
return IOError(filename_, errno);
|
||||
}
|
||||
}
|
||||
|
||||
Status s;
|
||||
ssize_t r = pread(fd, scratch, n, static_cast<off_t>(offset));
|
||||
ssize_t r = pread(fd_, scratch, n, static_cast<off_t>(offset));
|
||||
*result = Slice(scratch, (r < 0) ? 0 : r);
|
||||
if (r < 0) {
|
||||
// An error: return a non-ok status
|
||||
s = IOError(filename_, errno);
|
||||
}
|
||||
if (temporary_fd_) {
|
||||
// Close the temporary file descriptor opened earlier.
|
||||
close(fd);
|
||||
}
|
||||
return s;
|
||||
}
|
||||
};
|
||||
|
||||
// Helper class to limit mmap file usage so that we do not end up
|
||||
// running out virtual memory or running into kernel performance
|
||||
// problems for very large databases.
|
||||
class MmapLimiter {
|
||||
public:
|
||||
// Up to 1000 mmaps for 64-bit binaries; none for smaller pointer sizes.
|
||||
MmapLimiter() {
|
||||
SetAllowed(sizeof(void*) >= 8 ? 1000 : 0);
|
||||
}
|
||||
|
||||
// If another mmap slot is available, acquire it and return true.
|
||||
// Else return false.
|
||||
bool Acquire() {
|
||||
if (GetAllowed() <= 0) {
|
||||
return false;
|
||||
}
|
||||
MutexLock l(&mu_);
|
||||
intptr_t x = GetAllowed();
|
||||
if (x <= 0) {
|
||||
return false;
|
||||
} else {
|
||||
SetAllowed(x - 1);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
// Release a slot acquired by a previous call to Acquire() that returned true.
|
||||
void Release() {
|
||||
MutexLock l(&mu_);
|
||||
SetAllowed(GetAllowed() + 1);
|
||||
}
|
||||
|
||||
private:
|
||||
port::Mutex mu_;
|
||||
port::AtomicPointer allowed_;
|
||||
|
||||
intptr_t GetAllowed() const {
|
||||
return reinterpret_cast<intptr_t>(allowed_.Acquire_Load());
|
||||
}
|
||||
|
||||
// REQUIRES: mu_ must be held
|
||||
void SetAllowed(intptr_t v) {
|
||||
allowed_.Release_Store(reinterpret_cast<void*>(v));
|
||||
}
|
||||
|
||||
MmapLimiter(const MmapLimiter&);
|
||||
void operator=(const MmapLimiter&);
|
||||
};
|
||||
|
||||
// mmap() based random-access
|
||||
class PosixMmapReadableFile: public RandomAccessFile {
|
||||
private:
|
||||
std::string filename_;
|
||||
void* mmapped_region_;
|
||||
size_t length_;
|
||||
Limiter* limiter_;
|
||||
MmapLimiter* limiter_;
|
||||
|
||||
public:
|
||||
// base[0,length-1] contains the mmapped contents of the file.
|
||||
PosixMmapReadableFile(const std::string& fname, void* base, size_t length,
|
||||
Limiter* limiter)
|
||||
MmapLimiter* limiter)
|
||||
: filename_(fname), mmapped_region_(base), length_(length),
|
||||
limiter_(limiter) {
|
||||
}
|
||||
@@ -367,7 +332,7 @@ class PosixEnv : public Env {
|
||||
mmap_limit_.Release();
|
||||
}
|
||||
} else {
|
||||
*result = new PosixRandomAccessFile(fname, fd, &fd_limit_);
|
||||
*result = new PosixRandomAccessFile(fname, fd);
|
||||
}
|
||||
return s;
|
||||
}
|
||||
@@ -567,42 +532,10 @@ class PosixEnv : public Env {
|
||||
BGQueue queue_;
|
||||
|
||||
PosixLockTable locks_;
|
||||
Limiter mmap_limit_;
|
||||
Limiter fd_limit_;
|
||||
MmapLimiter mmap_limit_;
|
||||
};
|
||||
|
||||
// Return the maximum number of concurrent mmaps.
|
||||
static int MaxMmaps() {
|
||||
if (mmap_limit >= 0) {
|
||||
return mmap_limit;
|
||||
}
|
||||
// Up to 1000 mmaps for 64-bit binaries; none for smaller pointer sizes.
|
||||
mmap_limit = sizeof(void*) >= 8 ? 1000 : 0;
|
||||
return mmap_limit;
|
||||
}
|
||||
|
||||
// Return the maximum number of read-only files to keep open.
|
||||
static intptr_t MaxOpenFiles() {
|
||||
if (open_read_only_file_limit >= 0) {
|
||||
return open_read_only_file_limit;
|
||||
}
|
||||
struct rlimit rlim;
|
||||
if (getrlimit(RLIMIT_NOFILE, &rlim)) {
|
||||
// getrlimit failed, fallback to hard-coded default.
|
||||
open_read_only_file_limit = 50;
|
||||
} else if (rlim.rlim_cur == RLIM_INFINITY) {
|
||||
open_read_only_file_limit = std::numeric_limits<int>::max();
|
||||
} else {
|
||||
// Allow use of 20% of available file descriptors for read-only files.
|
||||
open_read_only_file_limit = rlim.rlim_cur / 5;
|
||||
}
|
||||
return open_read_only_file_limit;
|
||||
}
|
||||
|
||||
PosixEnv::PosixEnv()
|
||||
: started_bgthread_(false),
|
||||
mmap_limit_(MaxMmaps()),
|
||||
fd_limit_(MaxOpenFiles()) {
|
||||
PosixEnv::PosixEnv() : started_bgthread_(false) {
|
||||
PthreadCall("mutex_init", pthread_mutex_init(&mu_, NULL));
|
||||
PthreadCall("cvar_init", pthread_cond_init(&bgsignal_, NULL));
|
||||
}
|
||||
@@ -677,16 +610,6 @@ static pthread_once_t once = PTHREAD_ONCE_INIT;
|
||||
static Env* default_env;
|
||||
static void InitDefaultEnv() { default_env = new PosixEnv; }
|
||||
|
||||
void EnvPosixTestHelper::SetReadOnlyFDLimit(int limit) {
|
||||
assert(default_env == NULL);
|
||||
open_read_only_file_limit = limit;
|
||||
}
|
||||
|
||||
void EnvPosixTestHelper::SetReadOnlyMMapLimit(int limit) {
|
||||
assert(default_env == NULL);
|
||||
mmap_limit = limit;
|
||||
}
|
||||
|
||||
Env* Env::Default() {
|
||||
pthread_once(&once, InitDefaultEnv);
|
||||
return default_env;
|
||||
|
||||
@@ -1,66 +0,0 @@
|
||||
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style license that can be
|
||||
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||
|
||||
#include "leveldb/env.h"
|
||||
|
||||
#include "port/port.h"
|
||||
#include "util/testharness.h"
|
||||
#include "util/env_posix_test_helper.h"
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
static const int kDelayMicros = 100000;
|
||||
static const int kReadOnlyFileLimit = 4;
|
||||
static const int kMMapLimit = 4;
|
||||
|
||||
class EnvPosixTest {
|
||||
public:
|
||||
Env* env_;
|
||||
EnvPosixTest() : env_(Env::Default()) { }
|
||||
|
||||
static void SetFileLimits(int read_only_file_limit, int mmap_limit) {
|
||||
EnvPosixTestHelper::SetReadOnlyFDLimit(read_only_file_limit);
|
||||
EnvPosixTestHelper::SetReadOnlyMMapLimit(mmap_limit);
|
||||
}
|
||||
};
|
||||
|
||||
TEST(EnvPosixTest, TestOpenOnRead) {
|
||||
// Write some test data to a single file that will be opened |n| times.
|
||||
std::string test_dir;
|
||||
ASSERT_OK(env_->GetTestDirectory(&test_dir));
|
||||
std::string test_file = test_dir + "/open_on_read.txt";
|
||||
|
||||
FILE* f = fopen(test_file.c_str(), "w");
|
||||
ASSERT_TRUE(f != NULL);
|
||||
const char kFileData[] = "abcdefghijklmnopqrstuvwxyz";
|
||||
fputs(kFileData, f);
|
||||
fclose(f);
|
||||
|
||||
// Open test file some number above the sum of the two limits to force
|
||||
// open-on-read behavior of POSIX Env leveldb::RandomAccessFile.
|
||||
const int kNumFiles = kReadOnlyFileLimit + kMMapLimit + 5;
|
||||
leveldb::RandomAccessFile* files[kNumFiles] = {0};
|
||||
for (int i = 0; i < kNumFiles; i++) {
|
||||
ASSERT_OK(env_->NewRandomAccessFile(test_file, &files[i]));
|
||||
}
|
||||
char scratch;
|
||||
Slice read_result;
|
||||
for (int i = 0; i < kNumFiles; i++) {
|
||||
ASSERT_OK(files[i]->Read(i, 1, &read_result, &scratch));
|
||||
ASSERT_EQ(kFileData[i], read_result[0]);
|
||||
}
|
||||
for (int i = 0; i < kNumFiles; i++) {
|
||||
delete files[i];
|
||||
}
|
||||
ASSERT_OK(env_->DeleteFile(test_file));
|
||||
}
|
||||
|
||||
} // namespace leveldb
|
||||
|
||||
int main(int argc, char** argv) {
|
||||
// All tests currently run with the same read-only file limits.
|
||||
leveldb::EnvPosixTest::SetFileLimits(leveldb::kReadOnlyFileLimit,
|
||||
leveldb::kMMapLimit);
|
||||
return leveldb::test::RunAllTests();
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
// Copyright 2017 The LevelDB Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style license that can be
|
||||
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||
|
||||
#ifndef STORAGE_LEVELDB_UTIL_ENV_POSIX_TEST_HELPER_H_
|
||||
#define STORAGE_LEVELDB_UTIL_ENV_POSIX_TEST_HELPER_H_
|
||||
|
||||
namespace leveldb {
|
||||
|
||||
class EnvPosixTest;
|
||||
|
||||
// A helper for the POSIX Env to facilitate testing.
|
||||
class EnvPosixTestHelper {
|
||||
private:
|
||||
friend class EnvPosixTest;
|
||||
|
||||
// Set the maximum number of read-only files that will be opened.
|
||||
// Must be called before creating an Env.
|
||||
static void SetReadOnlyFDLimit(int limit);
|
||||
|
||||
// Set the maximum number of read-only files that will be mapped via mmap.
|
||||
// Must be called before creating an Env.
|
||||
static void SetReadOnlyMMapLimit(int limit);
|
||||
};
|
||||
|
||||
} // namespace leveldb
|
||||
|
||||
#endif // STORAGE_LEVELDB_UTIL_ENV_POSIX_TEST_HELPER_H_
|
||||
@@ -10,31 +10,29 @@
|
||||
namespace leveldb {
|
||||
|
||||
static const int kDelayMicros = 100000;
|
||||
static const int kReadOnlyFileLimit = 4;
|
||||
static const int kMMapLimit = 4;
|
||||
|
||||
class EnvTest {
|
||||
class EnvPosixTest {
|
||||
private:
|
||||
port::Mutex mu_;
|
||||
std::string events_;
|
||||
|
||||
public:
|
||||
Env* env_;
|
||||
EnvTest() : env_(Env::Default()) { }
|
||||
EnvPosixTest() : env_(Env::Default()) { }
|
||||
};
|
||||
|
||||
static void SetBool(void* ptr) {
|
||||
reinterpret_cast<port::AtomicPointer*>(ptr)->NoBarrier_Store(ptr);
|
||||
}
|
||||
|
||||
TEST(EnvTest, RunImmediately) {
|
||||
TEST(EnvPosixTest, RunImmediately) {
|
||||
port::AtomicPointer called (NULL);
|
||||
env_->Schedule(&SetBool, &called);
|
||||
env_->SleepForMicroseconds(kDelayMicros);
|
||||
Env::Default()->SleepForMicroseconds(kDelayMicros);
|
||||
ASSERT_TRUE(called.NoBarrier_Load() != NULL);
|
||||
}
|
||||
|
||||
TEST(EnvTest, RunMany) {
|
||||
TEST(EnvPosixTest, RunMany) {
|
||||
port::AtomicPointer last_id (NULL);
|
||||
|
||||
struct CB {
|
||||
@@ -61,7 +59,7 @@ TEST(EnvTest, RunMany) {
|
||||
env_->Schedule(&CB::Run, &cb3);
|
||||
env_->Schedule(&CB::Run, &cb4);
|
||||
|
||||
env_->SleepForMicroseconds(kDelayMicros);
|
||||
Env::Default()->SleepForMicroseconds(kDelayMicros);
|
||||
void* cur = last_id.Acquire_Load();
|
||||
ASSERT_EQ(4, reinterpret_cast<uintptr_t>(cur));
|
||||
}
|
||||
@@ -80,7 +78,7 @@ static void ThreadBody(void* arg) {
|
||||
s->mu.Unlock();
|
||||
}
|
||||
|
||||
TEST(EnvTest, StartThread) {
|
||||
TEST(EnvPosixTest, StartThread) {
|
||||
State state;
|
||||
state.val = 0;
|
||||
state.num_running = 3;
|
||||
@@ -94,7 +92,7 @@ TEST(EnvTest, StartThread) {
|
||||
if (num == 0) {
|
||||
break;
|
||||
}
|
||||
env_->SleepForMicroseconds(kDelayMicros);
|
||||
Env::Default()->SleepForMicroseconds(kDelayMicros);
|
||||
}
|
||||
ASSERT_EQ(state.val, 3);
|
||||
}
|
||||
|
||||
@@ -21,7 +21,6 @@ Options::Options()
|
||||
block_cache(NULL),
|
||||
block_size(4096),
|
||||
block_restart_interval(16),
|
||||
max_file_size(2<<20),
|
||||
compression(kSnappyCompression),
|
||||
reuse_logs(false),
|
||||
filter_policy(NULL) {
|
||||
|
||||
Reference in New Issue
Block a user