Merge upstream LevelDB 1.18

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.

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:

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 ([email protected]) and Jeff Dean ([email protected])
+
+# 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

build_detect_platform

@@ -20,7 +20,7 @@
 #
 # The PLATFORM_CCFLAGS and PLATFORM_CXXFLAGS might include the following:
 #
-#       -DLEVELDB_CSTDATOMIC_PRESENT if <cstdatomic> is present
+#       -DLEVELDB_ATOMIC_PRESENT     if <atomic> 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="$MEMCMP_FLAG -DOS_MACOSX"
@@ -185,13 +191,14 @@ if [ "$CROSS_COMPILE" = "true" ]; then
 else
     CXXOUTPUT="${TMPDIR}/leveldb_build_detect_platform-cxx.$$"
 
-    # If -std=c++0x works, use <cstdatomic>.  Otherwise use port_posix.h.
+    # If -std=c++0x works, use <atomic> as fallback for when memory barriers
+    # are not available.
     $CXX $CXXFLAGS -std=c++0x -x c++ - -o $CXXOUTPUT 2>/dev/null  <<EOF
-      #include <cstdatomic>
+      #include <atomic>
       int main() {}
 EOF
     if [ "$?" = 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"

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);

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_;

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;

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 <stdio.h>
 #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_