From 803d69203a62faf50f1b77897310a3a1fcae712b Mon Sep 17 00:00:00 2001 From: Chris Mumford Date: Tue, 16 Sep 2014 14:19:52 -0700 Subject: [PATCH] Release 1.18 Changes are: * Update version number to 1.18 * Replace the basic fprintf call with a call to fwrite in order to work around the apparent compiler optimization/rewrite failure that we are seeing with the new toolchain/iOS SDKs provided with Xcode6 and iOS8. * Fix ALL the header guards. * Createed a README.md with the LevelDB project description. * A new CONTRIBUTING file. * Don't implicitly convert uint64_t to size_t or int. Either preserve it as uint64_t, or explicitly cast. This fixes MSVC warnings about possible value truncation when compiling this code in Chromium. * Added a DumpFile() library function that encapsulates the guts of the "leveldbutil dump" command. This will allow clients to dump data to their log files instead of stdout. It will also allow clients to supply their own environment. * leveldb: Remove unused function 'ConsumeChar'. * leveldbutil: Remove unused member variables from WriteBatchItemPrinter. * OpenBSD, NetBSD and DragonflyBSD have _LITTLE_ENDIAN, so define PLATFORM_IS_LITTLE_ENDIAN like on FreeBSD. This fixes: * issue #143 * issue #198 * issue #249 * Switch from to . The former never made it into the standard and doesn't exist in modern gcc versions at all. The later contains everything that leveldb was using from the former. This problem was noticed when porting to Portable Native Client where no memory barrier is defined. The fact that is missing normally goes unnoticed since memory barriers are defined for most architectures. * Make Hash() treat its input as unsigned. Before this change LevelDB files from platforms with different signedness of char were not compatible. This change fixes: issue #243 * Verify checksums of index/meta/filter blocks when paranoid_checks set. * Invoke all tools for iOS with xcrun. (This was causing problems with the new XCode 5.1.1 image on pulse.) * include only once, and fix the following linter warning: "Found C system header after C++ system header" * When encountering a corrupted table file, return Status::Corruption instead of Status::InvalidArgument. * Support cygwin as build platform, patch is from https://code.google.com/p/leveldb/issues/detail?id=188 * Fix typo, merge patch from https://code.google.com/p/leveldb/issues/detail?id=159 * Fix typos and comments, and address the following two issues: * issue #166 * issue #241 * Add missing db synchronize after "fillseq" in the benchmark. * Removed unused variable in SeekRandom: value (issue #201) --- CONTRIBUTING.md | 36 +++++++ Makefile | 28 ++++-- README.md | 138 ++++++++++++++++++++++++++ build_detect_platform | 15 ++- db/db_bench.cc | 3 +- db/db_impl.cc | 4 +- db/db_test.cc | 2 +- db/dbformat.h | 6 +- db/dumpfile.cc | 225 ++++++++++++++++++++++++++++++++++++++++++ db/leveldb_main.cc | 204 +++----------------------------------- db/log_format.h | 4 +- db/log_reader.cc | 6 +- db/log_reader.h | 4 +- db/log_test.cc | 2 +- db/repair.cc | 2 +- db/skiplist.h | 5 + db/write_batch_internal.h | 4 +- doc/bench/db_bench_tree_db.cc | 2 +- doc/impl.html | 4 +- doc/log_format.txt | 6 +- helpers/memenv/memenv.cc | 9 +- include/leveldb/cache.h | 2 +- include/leveldb/db.h | 2 +- include/leveldb/dumpfile.h | 25 +++++ include/leveldb/env.h | 2 +- include/leveldb/iterator.h | 2 +- include/leveldb/options.h | 2 +- port/atomic_pointer.h | 21 ++-- port/port_posix.h | 9 +- port/thread_annotations.h | 5 +- table/block.cc | 2 +- table/block_builder.h | 2 +- table/format.cc | 2 +- table/table.cc | 14 ++- util/bloom.cc | 2 +- util/env_posix.cc | 10 +- util/hash.cc | 6 +- util/hash_test.cc | 54 ++++++++++ util/logging.cc | 9 -- util/logging.h | 4 - 40 files changed, 602 insertions(+), 282 deletions(-) create mode 100644 CONTRIBUTING.md create mode 100644 README.md create mode 100644 db/dumpfile.cc create mode 100644 include/leveldb/dumpfile.h create mode 100644 util/hash_test.cc diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md new file mode 100644 index 0000000..cd600ff --- /dev/null +++ b/CONTRIBUTING.md @@ -0,0 +1,36 @@ +# Contributing + +We'd love to accept your code patches! However, before we can take them, we +have to jump a couple of legal hurdles. + +## Contributor License Agreements + +Please fill out either the individual or corporate Contributor License +Agreement as appropriate. + +* If you are an individual writing original source code and you're sure you +own the intellectual property, then sign an [individual CLA](https://developers.google.com/open-source/cla/individual). +* If you work for a company that wants to allow you to contribute your work, +then sign a [corporate CLA](https://developers.google.com/open-source/cla/corporate). + +Follow either of the two links above to access the appropriate CLA and +instructions for how to sign and return it. + +## Submitting a Patch + +1. Sign the contributors license agreement above. +2. Decide which code you want to submit. A submission should be a set of changes +that addresses one issue in the [issue tracker](https://github.com/google/leveldb/issues). +Please don't mix more than one logical change per submission, because it makes +the history hard to follow. If you want to make a change +(e.g. add a sample or feature) that doesn't have a corresponding issue in the +issue tracker, please create one. +3. **Submitting**: When you are ready to submit, send us a Pull Request. Be +sure to include the issue number you fixed and the name you used to sign +the CLA. + +## Writing Code ## + +If your contribution contains code, please make sure that it follows +[the style guide](http://google-styleguide.googlecode.com/svn/trunk/cppguide.xml). +Otherwise we will have to ask you to make changes, and that's no fun for anyone. diff --git a/Makefile b/Makefile index f8903b6..2bd2cad 100644 --- a/Makefile +++ b/Makefile @@ -6,9 +6,12 @@ # Uncomment exactly one of the lines labelled (A), (B), and (C) below # to switch between compilation modes. -OPT ?= -O2 -DNDEBUG # (A) Production use (optimized mode) -# OPT ?= -g2 # (B) Debug mode, w/ full line-level debugging symbols -# OPT ?= -O2 -g2 -DNDEBUG # (C) Profiling mode: opt, but w/debugging symbols +# (A) Production use (optimized mode) +OPT ?= -O2 -DNDEBUG +# (B) Debug mode, w/ full line-level debugging symbols +# OPT ?= -g2 +# (C) Profiling mode: opt, but w/debugging symbols +# OPT ?= -O2 -g2 -DNDEBUG #----------------------------------------------- # detect what platform we're building on @@ -29,6 +32,11 @@ MEMENVOBJECTS = $(MEMENV_SOURCES:.cc=.o) TESTUTIL = ./util/testutil.o TESTHARNESS = ./util/testharness.o $(TESTUTIL) +# Note: iOS should probably be using libtool, not ar. +ifeq ($(PLATFORM), IOS) +AR=xcrun ar +endif + TESTS = \ arena_test \ autocompact_test \ @@ -43,6 +51,7 @@ TESTS = \ env_test \ filename_test \ filter_block_test \ + hash_test \ issue178_test \ issue200_test \ log_test \ @@ -72,7 +81,7 @@ SHARED = $(SHARED1) else # Update db.h if you change these. SHARED_MAJOR = 1 -SHARED_MINOR = 17 +SHARED_MINOR = 18 SHARED1 = libleveldb.$(PLATFORM_SHARED_EXT) SHARED2 = $(SHARED1).$(SHARED_MAJOR) SHARED3 = $(SHARED1).$(SHARED_MAJOR).$(SHARED_MINOR) @@ -152,6 +161,9 @@ filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS) filter_block_test: table/filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS) $(CXX) $(LDFLAGS) table/filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS) +hash_test: util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS) + $(CXX) $(LDFLAGS) util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS) + issue178_test: issues/issue178_test.o $(LIBOBJECTS) $(TESTHARNESS) $(CXX) $(LDFLAGS) issues/issue178_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS) @@ -194,17 +206,17 @@ IOSARCH=-arch armv6 -arch armv7 -arch armv7s -arch arm64 .cc.o: mkdir -p ios-x86/$(dir $@) - $(CXX) $(CXXFLAGS) -isysroot $(SIMULATORROOT)/SDKs/iPhoneSimulator$(IOSVERSION).sdk -arch i686 -arch x86_64 -c $< -o ios-x86/$@ + xcrun -sdk iphonesimulator $(CXX) $(CXXFLAGS) -isysroot $(SIMULATORROOT)/SDKs/iPhoneSimulator$(IOSVERSION).sdk -arch i686 -arch x86_64 -c $< -o ios-x86/$@ mkdir -p ios-arm/$(dir $@) xcrun -sdk iphoneos $(CXX) $(CXXFLAGS) -isysroot $(DEVICEROOT)/SDKs/iPhoneOS$(IOSVERSION).sdk $(IOSARCH) -c $< -o ios-arm/$@ - lipo ios-x86/$@ ios-arm/$@ -create -output $@ + xcrun lipo ios-x86/$@ ios-arm/$@ -create -output $@ .c.o: mkdir -p ios-x86/$(dir $@) - $(CC) $(CFLAGS) -isysroot $(SIMULATORROOT)/SDKs/iPhoneSimulator$(IOSVERSION).sdk -arch i686 -arch x86_64 -c $< -o ios-x86/$@ + xcrun -sdk iphonesimulator $(CC) $(CFLAGS) -isysroot $(SIMULATORROOT)/SDKs/iPhoneSimulator$(IOSVERSION).sdk -arch i686 -arch x86_64 -c $< -o ios-x86/$@ mkdir -p ios-arm/$(dir $@) xcrun -sdk iphoneos $(CC) $(CFLAGS) -isysroot $(DEVICEROOT)/SDKs/iPhoneOS$(IOSVERSION).sdk $(IOSARCH) -c $< -o ios-arm/$@ - lipo ios-x86/$@ ios-arm/$@ -create -output $@ + xcrun lipo ios-x86/$@ ios-arm/$@ -create -output $@ else .cc.o: diff --git a/README.md b/README.md new file mode 100644 index 0000000..480affb --- /dev/null +++ b/README.md @@ -0,0 +1,138 @@ +**LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.** + +Authors: Sanjay Ghemawat (sanjay@google.com) and Jeff Dean (jeff@google.com) + +# Features + * Keys and values are arbitrary byte arrays. + * Data is stored sorted by key. + * Callers can provide a custom comparison function to override the sort order. + * The basic operations are `Put(key,value)`, `Get(key)`, `Delete(key)`. + * 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://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. + * [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 + * This is not a SQL database. It does not have a relational data model, it does not support SQL queries, and it has no support for indexes. + * 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. + +# Performance + +Here is a performance report (with explanations) from the run of the +included db_bench program. The results are somewhat noisy, but should +be enough to get a ballpark performance estimate. + +## Setup + +We use a database with a million entries. Each entry has a 16 byte +key, and a 100 byte value. Values used by the benchmark compress to +about half their original size. + + LevelDB: version 1.1 + Date: Sun May 1 12:11:26 2011 + CPU: 4 x Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz + CPUCache: 4096 KB + Keys: 16 bytes each + Values: 100 bytes each (50 bytes after compression) + Entries: 1000000 + Raw Size: 110.6 MB (estimated) + File Size: 62.9 MB (estimated) + +## Write performance + +The "fill" benchmarks create a brand new database, in either +sequential, or random order. The "fillsync" benchmark flushes data +from the operating system to the disk after every operation; the other +write operations leave the data sitting in the operating system buffer +cache for a while. The "overwrite" benchmark does random writes that +update existing keys in the database. + + fillseq : 1.765 micros/op; 62.7 MB/s + fillsync : 268.409 micros/op; 0.4 MB/s (10000 ops) + fillrandom : 2.460 micros/op; 45.0 MB/s + overwrite : 2.380 micros/op; 46.5 MB/s + +Each "op" above corresponds to a write of a single key/value pair. +I.e., a random write benchmark goes at approximately 400,000 writes per second. + +Each "fillsync" operation costs much less (0.3 millisecond) +than a disk seek (typically 10 milliseconds). We suspect that this is +because the hard disk itself is buffering the update in its memory and +responding before the data has been written to the platter. This may +or may not be safe based on whether or not the hard disk has enough +power to save its memory in the event of a power failure. + +## Read performance + +We list the performance of reading sequentially in both the forward +and reverse direction, and also the performance of a random lookup. +Note that the database created by the benchmark is quite small. +Therefore the report characterizes the performance of leveldb when the +working set fits in memory. The cost of reading a piece of data that +is not present in the operating system buffer cache will be dominated +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 + +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 + +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) + +## Repository contents + +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 +internal APIs may be changed without warning. + +Guide to header files: + +* **include/db.h**: Main interface to the DB: Start here + +* **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. +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.) + +* **include/iterator.h**: Interface for iterating over data. You can get +an iterator from a DB object. + +* **include/write_batch.h**: Interface for atomically applying multiple +updates to a database. + +* **include/slice.h**: A simple module for maintaining a pointer and a +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**: +Abstraction of the OS environment. A posix implementation of this interface is +in util/env_posix.cc + +* **include/table.h, include/table_builder.h**: Lower-level modules that most +clients probably won't use directly diff --git a/build_detect_platform b/build_detect_platform index 6e59c6f..bb76c4f 100755 --- a/build_detect_platform +++ b/build_detect_platform @@ -20,7 +20,7 @@ # # The PLATFORM_CCFLAGS and PLATFORM_CXXFLAGS might include the following: # -# -DLEVELDB_CSTDATOMIC_PRESENT if is present +# -DLEVELDB_ATOMIC_PRESENT if is present # -DLEVELDB_PLATFORM_POSIX for Posix-based platforms # -DSNAPPY if the Snappy library is present # @@ -72,6 +72,12 @@ if [ "$CXX" = "g++" ]; then fi case "$TARGET_OS" in + CYGWIN_*) + PLATFORM=OS_LINUX + COMMON_FLAGS="$MEMCMP_FLAG -lpthread -DOS_LINUX -DCYGWIN" + PLATFORM_LDFLAGS="-lpthread" + PORT_FILE=port/port_posix.cc + ;; Darwin) PLATFORM=OS_MACOSX COMMON_FLAGS="$MEMCMP_FLAG -DOS_MACOSX" @@ -171,13 +177,14 @@ if [ "$CROSS_COMPILE" = "true" ]; then else CXXOUTPUT="${TMPDIR}/leveldb_build_detect_platform-cxx.$$" - # If -std=c++0x works, use . Otherwise use port_posix.h. + # If -std=c++0x works, use as fallback for when memory barriers + # are not available. $CXX $CXXFLAGS -std=c++0x -x c++ - -o $CXXOUTPUT 2>/dev/null < + #include int main() {} EOF if [ "$?" = 0 ]; then - COMMON_FLAGS="$COMMON_FLAGS -DLEVELDB_PLATFORM_POSIX -DLEVELDB_CSTDATOMIC_PRESENT" + COMMON_FLAGS="$COMMON_FLAGS -DLEVELDB_PLATFORM_POSIX -DLEVELDB_ATOMIC_PRESENT" PLATFORM_CXXFLAGS="-std=c++0x" else COMMON_FLAGS="$COMMON_FLAGS -DLEVELDB_PLATFORM_POSIX" diff --git a/db/db_bench.cc b/db/db_bench.cc index fc46d89..705a170 100644 --- a/db/db_bench.cc +++ b/db/db_bench.cc @@ -431,7 +431,7 @@ class Benchmark { benchmarks = sep + 1; } - // Reset parameters that may be overriddden bwlow + // Reset parameters that may be overridden below num_ = FLAGS_num; reads_ = (FLAGS_reads < 0 ? FLAGS_num : FLAGS_reads); value_size_ = FLAGS_value_size; @@ -811,7 +811,6 @@ class Benchmark { void SeekRandom(ThreadState* thread) { ReadOptions options; - std::string value; int found = 0; for (int i = 0; i < reads_; i++) { Iterator* iter = db_->NewIterator(options); diff --git a/db/db_impl.cc b/db/db_impl.cc index faf5e7d..49b9595 100644 --- a/db/db_impl.cc +++ b/db/db_impl.cc @@ -392,7 +392,7 @@ Status DBImpl::RecoverLogFile(uint64_t log_number, reporter.info_log = options_.info_log; reporter.fname = fname.c_str(); reporter.status = (options_.paranoid_checks ? &status : NULL); - // We intentially make log::Reader do checksumming even if + // We intentionally make log::Reader do checksumming even if // paranoid_checks==false so that corruptions cause entire commits // to be skipped instead of propagating bad information (like overly // large sequence numbers). @@ -1267,7 +1267,7 @@ WriteBatch* DBImpl::BuildBatchGroup(Writer** last_writer) { break; } - // Append to *reuslt + // Append to *result if (result == first->batch) { // Switch to temporary batch instead of disturbing caller's batch result = tmp_batch_; diff --git a/db/db_test.cc b/db/db_test.cc index 280b01c..0fed913 100644 --- a/db/db_test.cc +++ b/db/db_test.cc @@ -626,7 +626,7 @@ TEST(DBTest, GetEncountersEmptyLevel) { // * sstable B in level 2 // Then do enough Get() calls to arrange for an automatic compaction // of sstable A. A bug would cause the compaction to be marked as - // occuring at level 1 (instead of the correct level 0). + // occurring at level 1 (instead of the correct level 0). // Step 1: First place sstables in levels 0 and 2 int compaction_count = 0; diff --git a/db/dbformat.h b/db/dbformat.h index 5d8a032..ea897b1 100644 --- a/db/dbformat.h +++ b/db/dbformat.h @@ -2,8 +2,8 @@ // 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_DB_FORMAT_H_ -#define STORAGE_LEVELDB_DB_FORMAT_H_ +#ifndef STORAGE_LEVELDB_DB_DBFORMAT_H_ +#define STORAGE_LEVELDB_DB_DBFORMAT_H_ #include #include "leveldb/comparator.h" @@ -227,4 +227,4 @@ inline LookupKey::~LookupKey() { } // namespace leveldb -#endif // STORAGE_LEVELDB_DB_FORMAT_H_ +#endif // STORAGE_LEVELDB_DB_DBFORMAT_H_ diff --git a/db/dumpfile.cc b/db/dumpfile.cc new file mode 100644 index 0000000..61c47c2 --- /dev/null +++ b/db/dumpfile.cc @@ -0,0 +1,225 @@ +// Copyright (c) 2012 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 +#include "db/dbformat.h" +#include "db/filename.h" +#include "db/log_reader.h" +#include "db/version_edit.h" +#include "db/write_batch_internal.h" +#include "leveldb/env.h" +#include "leveldb/iterator.h" +#include "leveldb/options.h" +#include "leveldb/status.h" +#include "leveldb/table.h" +#include "leveldb/write_batch.h" +#include "util/logging.h" + +namespace leveldb { + +namespace { + +bool GuessType(const std::string& fname, FileType* type) { + size_t pos = fname.rfind('/'); + std::string basename; + if (pos == std::string::npos) { + basename = fname; + } else { + basename = std::string(fname.data() + pos + 1, fname.size() - pos - 1); + } + uint64_t ignored; + return ParseFileName(basename, &ignored, type); +} + +// Notified when log reader encounters corruption. +class CorruptionReporter : public log::Reader::Reporter { + public: + WritableFile* dst_; + virtual void Corruption(size_t bytes, const Status& status) { + std::string r = "corruption: "; + AppendNumberTo(&r, bytes); + r += " bytes; "; + r += status.ToString(); + r.push_back('\n'); + dst_->Append(r); + } +}; + +// Print contents of a log file. (*func)() is called on every record. +Status PrintLogContents(Env* env, const std::string& fname, + void (*func)(uint64_t, Slice, WritableFile*), + WritableFile* dst) { + SequentialFile* file; + Status s = env->NewSequentialFile(fname, &file); + if (!s.ok()) { + return s; + } + CorruptionReporter reporter; + reporter.dst_ = dst; + log::Reader reader(file, &reporter, true, 0); + Slice record; + std::string scratch; + while (reader.ReadRecord(&record, &scratch)) { + (*func)(reader.LastRecordOffset(), record, dst); + } + delete file; + return Status::OK(); +} + +// Called on every item found in a WriteBatch. +class WriteBatchItemPrinter : public WriteBatch::Handler { + public: + WritableFile* dst_; + virtual void Put(const Slice& key, const Slice& value) { + std::string r = " put '"; + AppendEscapedStringTo(&r, key); + r += "' '"; + AppendEscapedStringTo(&r, value); + r += "'\n"; + dst_->Append(r); + } + virtual void Delete(const Slice& key) { + std::string r = " del '"; + AppendEscapedStringTo(&r, key); + r += "'\n"; + dst_->Append(r); + } +}; + + +// Called on every log record (each one of which is a WriteBatch) +// found in a kLogFile. +static void WriteBatchPrinter(uint64_t pos, Slice record, WritableFile* dst) { + std::string r = "--- offset "; + AppendNumberTo(&r, pos); + r += "; "; + if (record.size() < 12) { + r += "log record length "; + AppendNumberTo(&r, record.size()); + r += " is too small\n"; + dst->Append(r); + return; + } + WriteBatch batch; + WriteBatchInternal::SetContents(&batch, record); + r += "sequence "; + AppendNumberTo(&r, WriteBatchInternal::Sequence(&batch)); + r.push_back('\n'); + dst->Append(r); + WriteBatchItemPrinter batch_item_printer; + batch_item_printer.dst_ = dst; + Status s = batch.Iterate(&batch_item_printer); + if (!s.ok()) { + dst->Append(" error: " + s.ToString() + "\n"); + } +} + +Status DumpLog(Env* env, const std::string& fname, WritableFile* dst) { + return PrintLogContents(env, fname, WriteBatchPrinter, dst); +} + +// Called on every log record (each one of which is a WriteBatch) +// found in a kDescriptorFile. +static void VersionEditPrinter(uint64_t pos, Slice record, WritableFile* dst) { + std::string r = "--- offset "; + AppendNumberTo(&r, pos); + r += "; "; + VersionEdit edit; + Status s = edit.DecodeFrom(record); + if (!s.ok()) { + r += s.ToString(); + r.push_back('\n'); + } else { + r += edit.DebugString(); + } + dst->Append(r); +} + +Status DumpDescriptor(Env* env, const std::string& fname, WritableFile* dst) { + return PrintLogContents(env, fname, VersionEditPrinter, dst); +} + +Status DumpTable(Env* env, const std::string& fname, WritableFile* dst) { + uint64_t file_size; + RandomAccessFile* file = NULL; + Table* table = NULL; + Status s = env->GetFileSize(fname, &file_size); + if (s.ok()) { + s = env->NewRandomAccessFile(fname, &file); + } + if (s.ok()) { + // We use the default comparator, which may or may not match the + // comparator used in this database. However this should not cause + // problems since we only use Table operations that do not require + // any comparisons. In particular, we do not call Seek or Prev. + s = Table::Open(Options(), file, file_size, &table); + } + if (!s.ok()) { + delete table; + delete file; + return s; + } + + ReadOptions ro; + ro.fill_cache = false; + Iterator* iter = table->NewIterator(ro); + std::string r; + for (iter->SeekToFirst(); iter->Valid(); iter->Next()) { + r.clear(); + ParsedInternalKey key; + if (!ParseInternalKey(iter->key(), &key)) { + r = "badkey '"; + AppendEscapedStringTo(&r, iter->key()); + r += "' => '"; + AppendEscapedStringTo(&r, iter->value()); + r += "'\n"; + dst->Append(r); + } else { + r = "'"; + AppendEscapedStringTo(&r, key.user_key); + r += "' @ "; + AppendNumberTo(&r, key.sequence); + r += " : "; + if (key.type == kTypeDeletion) { + r += "del"; + } else if (key.type == kTypeValue) { + r += "val"; + } else { + AppendNumberTo(&r, key.type); + } + r += " => '"; + AppendEscapedStringTo(&r, iter->value()); + r += "'\n"; + dst->Append(r); + } + } + s = iter->status(); + if (!s.ok()) { + dst->Append("iterator error: " + s.ToString() + "\n"); + } + + delete iter; + delete table; + delete file; + return Status::OK(); +} + +} // namespace + +Status DumpFile(Env* env, const std::string& fname, WritableFile* dst) { + FileType ftype; + if (!GuessType(fname, &ftype)) { + return Status::InvalidArgument(fname + ": unknown file type"); + } + switch (ftype) { + case kLogFile: return DumpLog(env, fname, dst); + case kDescriptorFile: return DumpDescriptor(env, fname, dst); + case kTableFile: return DumpTable(env, fname, dst); + default: + break; + } + return Status::InvalidArgument(fname + ": not a dump-able file type"); +} + +} // namespace leveldb diff --git a/db/leveldb_main.cc b/db/leveldb_main.cc index 995d761..9f4b7dd 100644 --- a/db/leveldb_main.cc +++ b/db/leveldb_main.cc @@ -3,212 +3,38 @@ // found in the LICENSE file. See the AUTHORS file for names of contributors. #include -#include "db/dbformat.h" -#include "db/filename.h" -#include "db/log_reader.h" -#include "db/version_edit.h" -#include "db/write_batch_internal.h" +#include "leveldb/dumpfile.h" #include "leveldb/env.h" -#include "leveldb/iterator.h" -#include "leveldb/options.h" #include "leveldb/status.h" -#include "leveldb/table.h" -#include "leveldb/write_batch.h" -#include "util/logging.h" namespace leveldb { - namespace { -bool GuessType(const std::string& fname, FileType* type) { - size_t pos = fname.rfind('/'); - std::string basename; - if (pos == std::string::npos) { - basename = fname; - } else { - basename = std::string(fname.data() + pos + 1, fname.size() - pos - 1); - } - uint64_t ignored; - return ParseFileName(basename, &ignored, type); -} - -// Notified when log reader encounters corruption. -class CorruptionReporter : public log::Reader::Reporter { - public: - virtual void Corruption(size_t bytes, const Status& status) { - printf("corruption: %d bytes; %s\n", - static_cast(bytes), - status.ToString().c_str()); - } -}; - -// Print contents of a log file. (*func)() is called on every record. -bool PrintLogContents(Env* env, const std::string& fname, - void (*func)(Slice)) { - SequentialFile* file; - Status s = env->NewSequentialFile(fname, &file); - if (!s.ok()) { - fprintf(stderr, "%s\n", s.ToString().c_str()); - return false; - } - CorruptionReporter reporter; - log::Reader reader(file, &reporter, true, 0); - Slice record; - std::string scratch; - while (reader.ReadRecord(&record, &scratch)) { - printf("--- offset %llu; ", - static_cast(reader.LastRecordOffset())); - (*func)(record); - } - delete file; - return true; -} - -// Called on every item found in a WriteBatch. -class WriteBatchItemPrinter : public WriteBatch::Handler { +class StdoutPrinter : public WritableFile { public: - uint64_t offset_; - uint64_t sequence_; - - virtual void Put(const Slice& key, const Slice& value) { - printf(" put '%s' '%s'\n", - EscapeString(key).c_str(), - EscapeString(value).c_str()); - } - virtual void Delete(const Slice& key) { - printf(" del '%s'\n", - EscapeString(key).c_str()); + virtual Status Append(const Slice& data) { + fwrite(data.data(), 1, data.size(), stdout); + return Status::OK(); } + virtual Status Close() { return Status::OK(); } + virtual Status Flush() { return Status::OK(); } + virtual Status Sync() { return Status::OK(); } }; - -// Called on every log record (each one of which is a WriteBatch) -// found in a kLogFile. -static void WriteBatchPrinter(Slice record) { - if (record.size() < 12) { - printf("log record length %d is too small\n", - static_cast(record.size())); - return; - } - WriteBatch batch; - WriteBatchInternal::SetContents(&batch, record); - printf("sequence %llu\n", - static_cast(WriteBatchInternal::Sequence(&batch))); - WriteBatchItemPrinter batch_item_printer; - Status s = batch.Iterate(&batch_item_printer); - if (!s.ok()) { - printf(" error: %s\n", s.ToString().c_str()); - } -} - -bool DumpLog(Env* env, const std::string& fname) { - return PrintLogContents(env, fname, WriteBatchPrinter); -} - -// Called on every log record (each one of which is a WriteBatch) -// found in a kDescriptorFile. -static void VersionEditPrinter(Slice record) { - VersionEdit edit; - Status s = edit.DecodeFrom(record); - if (!s.ok()) { - printf("%s\n", s.ToString().c_str()); - return; - } - printf("%s", edit.DebugString().c_str()); -} - -bool DumpDescriptor(Env* env, const std::string& fname) { - return PrintLogContents(env, fname, VersionEditPrinter); -} - -bool DumpTable(Env* env, const std::string& fname) { - uint64_t file_size; - RandomAccessFile* file = NULL; - Table* table = NULL; - Status s = env->GetFileSize(fname, &file_size); - if (s.ok()) { - s = env->NewRandomAccessFile(fname, &file); - } - if (s.ok()) { - // We use the default comparator, which may or may not match the - // comparator used in this database. However this should not cause - // problems since we only use Table operations that do not require - // any comparisons. In particular, we do not call Seek or Prev. - s = Table::Open(Options(), file, file_size, &table); - } - if (!s.ok()) { - fprintf(stderr, "%s\n", s.ToString().c_str()); - delete table; - delete file; - return false; - } - - ReadOptions ro; - ro.fill_cache = false; - Iterator* iter = table->NewIterator(ro); - for (iter->SeekToFirst(); iter->Valid(); iter->Next()) { - ParsedInternalKey key; - if (!ParseInternalKey(iter->key(), &key)) { - printf("badkey '%s' => '%s'\n", - EscapeString(iter->key()).c_str(), - EscapeString(iter->value()).c_str()); - } else { - char kbuf[20]; - const char* type; - if (key.type == kTypeDeletion) { - type = "del"; - } else if (key.type == kTypeValue) { - type = "val"; - } else { - snprintf(kbuf, sizeof(kbuf), "%d", static_cast(key.type)); - type = kbuf; - } - printf("'%s' @ %8llu : %s => '%s'\n", - EscapeString(key.user_key).c_str(), - static_cast(key.sequence), - type, - EscapeString(iter->value()).c_str()); - } - } - s = iter->status(); - if (!s.ok()) { - printf("iterator error: %s\n", s.ToString().c_str()); - } - - delete iter; - delete table; - delete file; - return true; -} - -bool DumpFile(Env* env, const std::string& fname) { - FileType ftype; - if (!GuessType(fname, &ftype)) { - fprintf(stderr, "%s: unknown file type\n", fname.c_str()); - return false; - } - switch (ftype) { - case kLogFile: return DumpLog(env, fname); - case kDescriptorFile: return DumpDescriptor(env, fname); - case kTableFile: return DumpTable(env, fname); - - default: { - fprintf(stderr, "%s: not a dump-able file type\n", fname.c_str()); - break; - } - } - return false; -} - bool HandleDumpCommand(Env* env, char** files, int num) { + StdoutPrinter printer; bool ok = true; for (int i = 0; i < num; i++) { - ok &= DumpFile(env, files[i]); + Status s = DumpFile(env, files[i], &printer); + if (!s.ok()) { + fprintf(stderr, "%s\n", s.ToString().c_str()); + ok = false; + } } return ok; } -} +} // namespace } // namespace leveldb static void Usage() { diff --git a/db/log_format.h b/db/log_format.h index 2690cb9..a8c06ef 100644 --- a/db/log_format.h +++ b/db/log_format.h @@ -26,8 +26,8 @@ static const int kMaxRecordType = kLastType; static const int kBlockSize = 32768; -// Header is checksum (4 bytes), type (1 byte), length (2 bytes). -static const int kHeaderSize = 4 + 1 + 2; +// Header is checksum (4 bytes), length (2 bytes), type (1 byte). +static const int kHeaderSize = 4 + 2 + 1; } // namespace log } // namespace leveldb diff --git a/db/log_reader.cc b/db/log_reader.cc index 4919216..e44b66c 100644 --- a/db/log_reader.cc +++ b/db/log_reader.cc @@ -167,14 +167,14 @@ uint64_t Reader::LastRecordOffset() { return last_record_offset_; } -void Reader::ReportCorruption(size_t bytes, const char* reason) { +void Reader::ReportCorruption(uint64_t bytes, const char* reason) { ReportDrop(bytes, Status::Corruption(reason)); } -void Reader::ReportDrop(size_t bytes, const Status& reason) { +void Reader::ReportDrop(uint64_t bytes, const Status& reason) { if (reporter_ != NULL && end_of_buffer_offset_ - buffer_.size() - bytes >= initial_offset_) { - reporter_->Corruption(bytes, reason); + reporter_->Corruption(static_cast(bytes), reason); } } diff --git a/db/log_reader.h b/db/log_reader.h index 82d4bee..6aff791 100644 --- a/db/log_reader.h +++ b/db/log_reader.h @@ -94,8 +94,8 @@ class Reader { // Reports dropped bytes to the reporter. // buffer_ must be updated to remove the dropped bytes prior to invocation. - void ReportCorruption(size_t bytes, const char* reason); - void ReportDrop(size_t bytes, const Status& reason); + void ReportCorruption(uint64_t bytes, const char* reason); + void ReportDrop(uint64_t bytes, const Status& reason); // No copying allowed Reader(const Reader&); diff --git a/db/log_test.cc b/db/log_test.cc index 91d3caa..dcf0562 100644 --- a/db/log_test.cc +++ b/db/log_test.cc @@ -463,7 +463,7 @@ TEST(LogTest, ErrorJoinsRecords) { ASSERT_EQ("correct", Read()); ASSERT_EQ("EOF", Read()); - const int dropped = DroppedBytes(); + const size_t dropped = DroppedBytes(); ASSERT_LE(dropped, 2*kBlockSize + 100); ASSERT_GE(dropped, 2*kBlockSize); } diff --git a/db/repair.cc b/db/repair.cc index 7727faf..4cd4bb0 100644 --- a/db/repair.cc +++ b/db/repair.cc @@ -186,7 +186,7 @@ class Repairer { reporter.env = env_; reporter.info_log = options_.info_log; reporter.lognum = log; - // We intentially make log::Reader do checksumming so that + // We intentionally make log::Reader do checksumming so that // corruptions cause entire commits to be skipped instead of // propagating bad information (like overly large sequence // numbers). diff --git a/db/skiplist.h b/db/skiplist.h index af85be6..ed8b092 100644 --- a/db/skiplist.h +++ b/db/skiplist.h @@ -1,3 +1,6 @@ +#ifndef STORAGE_LEVELDB_DB_SKIPLIST_H_ +#define STORAGE_LEVELDB_DB_SKIPLIST_H_ + // 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. @@ -377,3 +380,5 @@ bool SkipList::Contains(const Key& key) const { } } // namespace leveldb + +#endif // STORAGE_LEVELDB_DB_SKIPLIST_H_ diff --git a/db/write_batch_internal.h b/db/write_batch_internal.h index 4423a7f..310a3c8 100644 --- a/db/write_batch_internal.h +++ b/db/write_batch_internal.h @@ -21,10 +21,10 @@ class WriteBatchInternal { // Set the count for the number of entries in the batch. static void SetCount(WriteBatch* batch, int n); - // Return the seqeunce number for the start of this batch. + // Return the sequence number for the start of this batch. static SequenceNumber Sequence(const WriteBatch* batch); - // Store the specified number as the seqeunce number for the start of + // Store the specified number as the sequence number for the start of // this batch. static void SetSequence(WriteBatch* batch, SequenceNumber seq); diff --git a/doc/bench/db_bench_tree_db.cc b/doc/bench/db_bench_tree_db.cc index ed86f03..4ca381f 100644 --- a/doc/bench/db_bench_tree_db.cc +++ b/doc/bench/db_bench_tree_db.cc @@ -338,7 +338,7 @@ class Benchmark { bool write_sync = false; if (name == Slice("fillseq")) { Write(write_sync, SEQUENTIAL, FRESH, num_, FLAGS_value_size, 1); - + DBSynchronize(db_); } else if (name == Slice("fillrandom")) { Write(write_sync, RANDOM, FRESH, num_, FLAGS_value_size, 1); DBSynchronize(db_); diff --git a/doc/impl.html b/doc/impl.html index 28817fe..6a468be 100644 --- a/doc/impl.html +++ b/doc/impl.html @@ -111,7 +111,7 @@ 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 then +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). @@ -151,7 +151,7 @@ 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 signficantly increase the cost of +(~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. diff --git a/doc/log_format.txt b/doc/log_format.txt index 5228f62..4cca5ef 100644 --- a/doc/log_format.txt +++ b/doc/log_format.txt @@ -11,7 +11,7 @@ Each block consists of a sequence of records: 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. +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 @@ -33,8 +33,8 @@ 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 MID is the type of all -interior fragments of a user record. +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 diff --git a/helpers/memenv/memenv.cc b/helpers/memenv/memenv.cc index 5879de1..43ef2e0 100644 --- a/helpers/memenv/memenv.cc +++ b/helpers/memenv/memenv.cc @@ -55,14 +55,15 @@ class FileState { } const uint64_t available = size_ - offset; if (n > available) { - n = available; + n = static_cast(available); } if (n == 0) { *result = Slice(); return Status::OK(); } - size_t block = offset / kBlockSize; + assert(offset / kBlockSize <= SIZE_MAX); + size_t block = static_cast(offset / kBlockSize); size_t block_offset = offset % kBlockSize; if (n <= kBlockSize - block_offset) { @@ -167,7 +168,7 @@ class SequentialFileImpl : public SequentialFile { if (pos_ > file_->Size()) { return Status::IOError("pos_ > file_->Size()"); } - const size_t available = file_->Size() - pos_; + const uint64_t available = file_->Size() - pos_; if (n > available) { n = available; } @@ -177,7 +178,7 @@ class SequentialFileImpl : public SequentialFile { private: FileState* file_; - size_t pos_; + uint64_t pos_; }; class RandomAccessFileImpl : public RandomAccessFile { diff --git a/include/leveldb/cache.h b/include/leveldb/cache.h index 5e3b476..1a201e5 100644 --- a/include/leveldb/cache.h +++ b/include/leveldb/cache.h @@ -96,4 +96,4 @@ class Cache { } // namespace leveldb -#endif // STORAGE_LEVELDB_UTIL_CACHE_H_ +#endif // STORAGE_LEVELDB_INCLUDE_CACHE_H_ diff --git a/include/leveldb/db.h b/include/leveldb/db.h index 40851b2..4c169bf 100644 --- a/include/leveldb/db.h +++ b/include/leveldb/db.h @@ -14,7 +14,7 @@ namespace leveldb { // Update Makefile if you change these static const int kMajorVersion = 1; -static const int kMinorVersion = 17; +static const int kMinorVersion = 18; struct Options; struct ReadOptions; diff --git a/include/leveldb/dumpfile.h b/include/leveldb/dumpfile.h new file mode 100644 index 0000000..3f97fda --- /dev/null +++ b/include/leveldb/dumpfile.h @@ -0,0 +1,25 @@ +// Copyright (c) 2014 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_INCLUDE_DUMPFILE_H_ +#define STORAGE_LEVELDB_INCLUDE_DUMPFILE_H_ + +#include +#include "leveldb/env.h" +#include "leveldb/status.h" + +namespace leveldb { + +// Dump the contents of the file named by fname in text format to +// *dst. Makes a sequence of dst->Append() calls; each call is passed +// the newline-terminated text corresponding to a single item found +// in the file. +// +// Returns a non-OK result if fname does not name a leveldb storage +// file, or if the file cannot be read. +Status DumpFile(Env* env, const std::string& fname, WritableFile* dst); + +} // namespace leveldb + +#endif // STORAGE_LEVELDB_INCLUDE_DUMPFILE_H_ diff --git a/include/leveldb/env.h b/include/leveldb/env.h index b2072d0..f709514 100644 --- a/include/leveldb/env.h +++ b/include/leveldb/env.h @@ -142,7 +142,7 @@ class Env { // useful for computing deltas of time. virtual uint64_t NowMicros() = 0; - // Sleep/delay the thread for the perscribed number of micro-seconds. + // Sleep/delay the thread for the prescribed number of micro-seconds. virtual void SleepForMicroseconds(int micros) = 0; private: diff --git a/include/leveldb/iterator.h b/include/leveldb/iterator.h index ad543eb..76aced0 100644 --- a/include/leveldb/iterator.h +++ b/include/leveldb/iterator.h @@ -61,7 +61,7 @@ class Iterator { // Return the value for the current entry. The underlying storage for // the returned slice is valid only until the next modification of // the iterator. - // REQUIRES: !AtEnd() && !AtStart() + // REQUIRES: Valid() virtual Slice value() const = 0; // If an error has occurred, return it. Else return an ok status. diff --git a/include/leveldb/options.h b/include/leveldb/options.h index fdda718..7c9b973 100644 --- a/include/leveldb/options.h +++ b/include/leveldb/options.h @@ -153,7 +153,7 @@ struct ReadOptions { // If "snapshot" is non-NULL, read as of the supplied snapshot // (which must belong to the DB that is being read and which must - // not have been released). If "snapshot" is NULL, use an impliicit + // not have been released). If "snapshot" is NULL, use an implicit // snapshot of the state at the beginning of this read operation. // Default: NULL const Snapshot* snapshot; diff --git a/port/atomic_pointer.h b/port/atomic_pointer.h index a9866b2..9bf091f 100644 --- a/port/atomic_pointer.h +++ b/port/atomic_pointer.h @@ -5,14 +5,13 @@ // AtomicPointer provides storage for a lock-free pointer. // Platform-dependent implementation of AtomicPointer: // - If the platform provides a cheap barrier, we use it with raw pointers -// - If cstdatomic is present (on newer versions of gcc, it is), we use -// a cstdatomic-based AtomicPointer. However we prefer the memory +// - If is present (on newer versions of gcc, it is), we use +// a -based AtomicPointer. However we prefer the memory // barrier based version, because at least on a gcc 4.4 32-bit build -// on linux, we have encountered a buggy -// implementation. Also, some implementations are much -// slower than a memory-barrier based implementation (~16ns for -// based acquire-load vs. ~1ns for a barrier based -// acquire-load). +// on linux, we have encountered a buggy implementation. +// Also, some implementations are much slower than a memory-barrier +// based implementation (~16ns for based acquire-load vs. ~1ns for +// a barrier based acquire-load). // This code is based on atomicops-internals-* in Google's perftools: // http://code.google.com/p/google-perftools/source/browse/#svn%2Ftrunk%2Fsrc%2Fbase @@ -20,8 +19,8 @@ #define PORT_ATOMIC_POINTER_H_ #include -#ifdef LEVELDB_CSTDATOMIC_PRESENT -#include +#ifdef LEVELDB_ATOMIC_PRESENT +#include #endif #ifdef OS_WIN #include @@ -126,7 +125,7 @@ class AtomicPointer { }; // AtomicPointer based on -#elif defined(LEVELDB_CSTDATOMIC_PRESENT) +#elif defined(LEVELDB_ATOMIC_PRESENT) class AtomicPointer { private: std::atomic rep_; @@ -207,7 +206,7 @@ class AtomicPointer { inline void NoBarrier_Store(void* v) { rep_ = v; } }; -// We have neither MemoryBarrier(), nor +// We have neither MemoryBarrier(), nor #else #error Please implement AtomicPointer for this platform. diff --git a/port/port_posix.h b/port/port_posix.h index f2b89bf..89fc222 100644 --- a/port/port_posix.h +++ b/port/port_posix.h @@ -21,14 +21,11 @@ #else #define PLATFORM_IS_LITTLE_ENDIAN false #endif -#elif defined(OS_FREEBSD) +#elif defined(OS_FREEBSD) || defined(OS_OPENBSD) ||\ + defined(OS_NETBSD) || defined(OS_DRAGONFLYBSD) #include #include #define PLATFORM_IS_LITTLE_ENDIAN (_BYTE_ORDER == _LITTLE_ENDIAN) -#elif defined(OS_OPENBSD) || defined(OS_NETBSD) ||\ - defined(OS_DRAGONFLYBSD) - #include - #include #elif defined(OS_HPUX) #define PLATFORM_IS_LITTLE_ENDIAN false #elif defined(OS_ANDROID) @@ -55,7 +52,7 @@ #if defined(OS_MACOSX) || defined(OS_SOLARIS) || defined(OS_FREEBSD) ||\ defined(OS_NETBSD) || defined(OS_OPENBSD) || defined(OS_DRAGONFLYBSD) ||\ - defined(OS_ANDROID) || defined(OS_HPUX) + defined(OS_ANDROID) || defined(OS_HPUX) || defined(CYGWIN) // Use fread/fwrite/fflush on platforms without _unlocked variants #define fread_unlocked fread #define fwrite_unlocked fwrite diff --git a/port/thread_annotations.h b/port/thread_annotations.h index 6f9b6a7..9470ef5 100644 --- a/port/thread_annotations.h +++ b/port/thread_annotations.h @@ -2,7 +2,8 @@ // 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_PORT_THREAD_ANNOTATIONS_H +#ifndef STORAGE_LEVELDB_PORT_THREAD_ANNOTATIONS_H_ +#define STORAGE_LEVELDB_PORT_THREAD_ANNOTATIONS_H_ // Some environments provide custom macros to aid in static thread-safety // analysis. Provide empty definitions of such macros unless they are already @@ -56,4 +57,4 @@ #define NO_THREAD_SAFETY_ANALYSIS #endif -#endif // STORAGE_LEVELDB_PORT_THREAD_ANNOTATIONS_H +#endif // STORAGE_LEVELDB_PORT_THREAD_ANNOTATIONS_H_ diff --git a/table/block.cc b/table/block.cc index 79ea9d9..43e402c 100644 --- a/table/block.cc +++ b/table/block.cc @@ -46,7 +46,7 @@ Block::~Block() { // Helper routine: decode the next block entry starting at "p", // storing the number of shared key bytes, non_shared key bytes, // and the length of the value in "*shared", "*non_shared", and -// "*value_length", respectively. Will not derefence past "limit". +// "*value_length", respectively. Will not dereference past "limit". // // If any errors are detected, returns NULL. Otherwise, returns a // pointer to the key delta (just past the three decoded values). diff --git a/table/block_builder.h b/table/block_builder.h index 5b545bd..4fbcb33 100644 --- a/table/block_builder.h +++ b/table/block_builder.h @@ -21,7 +21,7 @@ class BlockBuilder { // Reset the contents as if the BlockBuilder was just constructed. void Reset(); - // REQUIRES: Finish() has not been callled since the last call to Reset(). + // REQUIRES: Finish() has not been called since the last call to Reset(). // REQUIRES: key is larger than any previously added key void Add(const Slice& key, const Slice& value); diff --git a/table/format.cc b/table/format.cc index cda1dec..aa63144 100644 --- a/table/format.cc +++ b/table/format.cc @@ -48,7 +48,7 @@ Status Footer::DecodeFrom(Slice* input) { const uint64_t magic = ((static_cast(magic_hi) << 32) | (static_cast(magic_lo))); if (magic != kTableMagicNumber) { - return Status::InvalidArgument("not an sstable (bad magic number)"); + return Status::Corruption("not an sstable (bad magic number)"); } Status result = metaindex_handle_.DecodeFrom(input); diff --git a/table/table.cc b/table/table.cc index 71c1756..dff8a82 100644 --- a/table/table.cc +++ b/table/table.cc @@ -41,7 +41,7 @@ Status Table::Open(const Options& options, Table** table) { *table = NULL; if (size < Footer::kEncodedLength) { - return Status::InvalidArgument("file is too short to be an sstable"); + return Status::Corruption("file is too short to be an sstable"); } char footer_space[Footer::kEncodedLength]; @@ -58,7 +58,11 @@ Status Table::Open(const Options& options, BlockContents contents; Block* index_block = NULL; if (s.ok()) { - s = ReadBlock(file, ReadOptions(), footer.index_handle(), &contents); + ReadOptions opt; + if (options.paranoid_checks) { + opt.verify_checksums = true; + } + s = ReadBlock(file, opt, footer.index_handle(), &contents); if (s.ok()) { index_block = new Block(contents); } @@ -92,6 +96,9 @@ void Table::ReadMeta(const Footer& footer) { // TODO(sanjay): Skip this if footer.metaindex_handle() size indicates // it is an empty block. ReadOptions opt; + if (rep_->options.paranoid_checks) { + opt.verify_checksums = true; + } BlockContents contents; if (!ReadBlock(rep_->file, opt, footer.metaindex_handle(), &contents).ok()) { // Do not propagate errors since meta info is not needed for operation @@ -120,6 +127,9 @@ void Table::ReadFilter(const Slice& filter_handle_value) { // We might want to unify with ReadBlock() if we start // requiring checksum verification in Table::Open. ReadOptions opt; + if (rep_->options.paranoid_checks) { + opt.verify_checksums = true; + } BlockContents block; if (!ReadBlock(rep_->file, opt, filter_handle, &block).ok()) { return; diff --git a/util/bloom.cc b/util/bloom.cc index d7941cd..a27a2ac 100644 --- a/util/bloom.cc +++ b/util/bloom.cc @@ -29,7 +29,7 @@ class BloomFilterPolicy : public FilterPolicy { } virtual const char* Name() const { - return "leveldb.BuiltinBloomFilter"; + return "leveldb.BuiltinBloomFilter2"; } virtual void CreateFilter(const Slice* keys, int n, std::string* dst) const { diff --git a/util/env_posix.cc b/util/env_posix.cc index e1cbebd..ad56131 100644 --- a/util/env_posix.cc +++ b/util/env_posix.cc @@ -2,8 +2,6 @@ // 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 -#include #include #include #include @@ -17,9 +15,8 @@ #include #include #include -#if defined(LEVELDB_PLATFORM_ANDROID) -#include -#endif +#include +#include #include "leveldb/env.h" #include "leveldb/slice.h" #include "port/port.h" @@ -295,7 +292,8 @@ class PosixEnv : public Env { public: PosixEnv(); virtual ~PosixEnv() { - fprintf(stderr, "Destroying Env::Default()\n"); + char msg[] = "Destroying Env::Default()\n"; + fwrite(msg, 1, sizeof(msg), stderr); abort(); } diff --git a/util/hash.cc b/util/hash.cc index 07cf022..ed439ce 100644 --- a/util/hash.cc +++ b/util/hash.cc @@ -34,13 +34,13 @@ uint32_t Hash(const char* data, size_t n, uint32_t seed) { // Pick up remaining bytes switch (limit - data) { case 3: - h += data[2] << 16; + h += static_cast(data[2]) << 16; FALLTHROUGH_INTENDED; case 2: - h += data[1] << 8; + h += static_cast(data[1]) << 8; FALLTHROUGH_INTENDED; case 1: - h += data[0]; + h += static_cast(data[0]); h *= m; h ^= (h >> r); break; diff --git a/util/hash_test.cc b/util/hash_test.cc new file mode 100644 index 0000000..eaa1c92 --- /dev/null +++ b/util/hash_test.cc @@ -0,0 +1,54 @@ +// 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 "util/hash.h" +#include "util/testharness.h" + +namespace leveldb { + +class HASH { }; + +TEST(HASH, SignedUnsignedIssue) { + const unsigned char data1[1] = {0x62}; + const unsigned char data2[2] = {0xc3, 0x97}; + const unsigned char data3[3] = {0xe2, 0x99, 0xa5}; + const unsigned char data4[4] = {0xe1, 0x80, 0xb9, 0x32}; + const unsigned char data5[48] = { + 0x01, 0xc0, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x14, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x04, 0x00, + 0x00, 0x00, 0x00, 0x14, + 0x00, 0x00, 0x00, 0x18, + 0x28, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x02, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + }; + + ASSERT_EQ(Hash(0, 0, 0xbc9f1d34), 0xbc9f1d34); + ASSERT_EQ( + Hash(reinterpret_cast(data1), sizeof(data1), 0xbc9f1d34), + 0xef1345c4); + ASSERT_EQ( + Hash(reinterpret_cast(data2), sizeof(data2), 0xbc9f1d34), + 0x5b663814); + ASSERT_EQ( + Hash(reinterpret_cast(data3), sizeof(data3), 0xbc9f1d34), + 0x323c078f); + ASSERT_EQ( + Hash(reinterpret_cast(data4), sizeof(data4), 0xbc9f1d34), + 0xed21633a); + ASSERT_EQ( + Hash(reinterpret_cast(data5), sizeof(data5), 0x12345678), + 0xf333dabb); +} + +} // namespace leveldb + +int main(int argc, char** argv) { + return leveldb::test::RunAllTests(); +} diff --git a/util/logging.cc b/util/logging.cc index 22cf278..ca6b324 100644 --- a/util/logging.cc +++ b/util/logging.cc @@ -45,15 +45,6 @@ std::string EscapeString(const Slice& value) { return r; } -bool ConsumeChar(Slice* in, char c) { - if (!in->empty() && (*in)[0] == c) { - in->remove_prefix(1); - return true; - } else { - return false; - } -} - bool ConsumeDecimalNumber(Slice* in, uint64_t* val) { uint64_t v = 0; int digits = 0; diff --git a/util/logging.h b/util/logging.h index b0c5da8..1b450d2 100644 --- a/util/logging.h +++ b/util/logging.h @@ -32,10 +32,6 @@ extern std::string NumberToString(uint64_t num); // Escapes any non-printable characters found in "value". extern std::string EscapeString(const Slice& value); -// If *in starts with "c", advances *in past the first character and -// returns true. Otherwise, returns false. -extern bool ConsumeChar(Slice* in, char c); - // Parse a human-readable number from "*in" into *value. On success, // advances "*in" past the consumed number and sets "*val" to the // numeric value. Otherwise, returns false and leaves *in in an