diff options
author | Ian Boros <ian.boros@10gen.com> | 2019-01-10 09:42:25 -0500 |
---|---|---|
committer | Ian Boros <ian.boros@10gen.com> | 2019-01-10 09:42:25 -0500 |
commit | e62142e3dabbb333fe43dd799491dc6147756a15 (patch) | |
tree | f900cced087de240c867c4513a5f6080238e7b33 /src/third_party | |
parent | 7bda6fc29a4547c9c16b6405a86ce856888f70fe (diff) | |
download | mongo-e62142e3dabbb333fe43dd799491dc6147756a15.tar.gz |
Revert "SERVER-28073 Upgrade Snappy to version 1.1.7"
This reverts commit 46bb07958cdd0bbeb3402a3aab88954ecd63ce3c.
Diffstat (limited to 'src/third_party')
-rw-r--r-- | src/third_party/SConscript | 2 | ||||
-rw-r--r-- | src/third_party/scripts/snappy_get_sources.sh | 76 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/AUTHORS (renamed from src/third_party/snappy-1.1.7/AUTHORS) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/COPYING (renamed from src/third_party/snappy-1.1.7/COPYING) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/ChangeLog | 2468 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/INSTALL | 370 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/NEWS (renamed from src/third_party/snappy-1.1.7/NEWS) | 40 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/README (renamed from src/third_party/snappy-1.1.7/README.md) | 32 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/SConscript (renamed from src/third_party/snappy-1.1.7/SConscript) | 2 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/build_linux/config.h | 135 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/build_posix/config.h | 135 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/format_description.txt (renamed from src/third_party/snappy-1.1.7/format_description.txt) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/framing_format.txt (renamed from src/third_party/snappy-1.1.7/framing_format.txt) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-c.cc (renamed from src/third_party/snappy-1.1.7/snappy-c.cc) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-c.h (renamed from src/third_party/snappy-1.1.7/snappy-c.h) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-internal.h | 150 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-sinksource.cc (renamed from src/third_party/snappy-1.1.7/snappy-sinksource.cc) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-sinksource.h (renamed from src/third_party/snappy-1.1.7/snappy-sinksource.h) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-stubs-internal.cc (renamed from src/third_party/snappy-1.1.7/snappy-stubs-internal.cc) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-stubs-internal.h (renamed from src/third_party/snappy-1.1.7/snappy-stubs-internal.h) | 147 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-stubs-public.h (renamed from src/third_party/snappy-1.1.7/snappy-stubs-public.h) | 30 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-stubs-public.h.in (renamed from src/third_party/snappy-1.1.7/snappy-stubs-public.h.in) | 30 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-test.cc (renamed from src/third_party/snappy-1.1.7/snappy-test.cc) | 17 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy-test.h (renamed from src/third_party/snappy-1.1.7/snappy-test.h) | 52 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy.cc (renamed from src/third_party/snappy-1.1.7/snappy.cc) | 661 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy.h (renamed from src/third_party/snappy-1.1.7/snappy.h) | 0 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.3/snappy_unittest.cc (renamed from src/third_party/snappy-1.1.7/snappy_unittest.cc) | 278 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.7/CONTRIBUTING.md | 26 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.7/build_linux/config.h | 62 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.7/build_posix/config.h | 62 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.7/build_windows/config.h | 62 | ||||
-rw-r--r-- | src/third_party/snappy-1.1.7/snappy-internal.h | 224 |
32 files changed, 3910 insertions, 1151 deletions
diff --git a/src/third_party/SConscript b/src/third_party/SConscript index e8552441e21..b33fcf64396 100644 --- a/src/third_party/SConscript +++ b/src/third_party/SConscript @@ -7,7 +7,7 @@ Import("wiredtiger") Import("mobile_se") boostSuffix = "-1.69.0" -snappySuffix = '-1.1.7' +snappySuffix = '-1.1.3' zlibSuffix = '-1.2.11' zstdSuffix = '-1.3.7' pcreSuffix = "-8.42" diff --git a/src/third_party/scripts/snappy_get_sources.sh b/src/third_party/scripts/snappy_get_sources.sh index 251575961de..c3ff32b452b 100644 --- a/src/third_party/scripts/snappy_get_sources.sh +++ b/src/third_party/scripts/snappy_get_sources.sh @@ -3,26 +3,14 @@ set -o verbose set -o errexit # This script fetches and creates a copy of sources for snappy -# snappy uses CMake and this script will invoke CMake to generate a -# config.h for "posix", Linux, and Windows -# +# snappy uses autotools on posix, and nothing on Windows +# Snappy has the same config.h file on Darwin and Solaris, Linux is unique +# The difference is byteswap.h # To get the sources for Snappy, run this script as follows: -# -# 1. Run on Darwin +# 1. Run on Darwin or Solaris # 2. Run on Linux -# 3. Run on Windows via Cygwin -# -# For Windows you will need CMake installed. If using an Evergreen -# spawn host it is not installed by default but, you can easily -# install it with the following command. (this works in cygwin): -# -# choco install cmake -# -# You will also need to add it to the $PATH with the following: -# -# export PATH="/cygdrive/c/Program Files/CMake/bin/:$PATH" -VERSION=1.1.7 +VERSION=1.1.3 NAME=snappy TARBALL=$NAME-$VERSION.tar.gz TARBALL_DIR=$NAME-$VERSION @@ -31,10 +19,8 @@ TEMP_DIR=/tmp/temp-$NAME-$VERSION DEST_DIR=`git rev-parse --show-toplevel`/src/third_party/$NAME-$VERSION UNAME=`uname | tr A-Z a-z` -if [ "$UNAME" == "linux" ]; then +if [ $UNAME == "linux" ]; then TARGET_UNAME=linux -elif [[ "$UNAME" == "cygwin"* ]]; then - TARGET_UNAME=windows else TARGET_UNAME=posix fi @@ -43,7 +29,7 @@ echo TARGET_UNAME: $TARGET_UNAME if [ ! -f $TARBALL ]; then echo "Get tarball" - curl -L -o $NAME-$VERSION.tar.gz https://github.com/google/$NAME/archive/$VERSION.tar.gz + wget https://github.com/google/$NAME/releases/download/$VERSION/$NAME-$VERSION.tar.gz fi echo $TARBALL @@ -54,37 +40,23 @@ mv $TARBALL_DIR $TEMP_DIR mkdir $DEST_DIR || true cd $TEMP_DIR -cp $TEMP_DIR/* $DEST_DIR || true -rm -f $DEST_DIR/Makefile* $DEST_DIR/config* $DEST_DIR/*sh -rm -f $DEST_DIR/compile* $DEST_DIR/depcomp $DEST_DIR/libtool -rm -f $DEST_DIR/test-driver $DEST_DIR/*.m4 $DEST_DIR/missing - -echo "Generating Config.h and other files" -cmake $TEMP_DIR - -# Copy over the platform independent generated files -cp $TEMP_DIR/snappy-stubs-public.h $DEST_DIR - -# Copy over config.h -mkdir $DEST_DIR/build_$TARGET_UNAME -cp $TEMP_DIR/config.h $DEST_DIR/build_$TARGET_UNAME - -# Change the snappy-stubs-public.h to use the defined variables -# instead of hardcoded values generated by CMake -# -# Changes lines like: -# -# #if !0 // !HAVE_SYS_UIO_H -# #if 1 // HAVE_STDINT_H -# -# To: -# -# #if !HAVE_SYS_UIO_H -# #if HAVE_STDINT_H -if [ "$TARGET_UNAME" = "posix" ]; then - sed -i '' 's/if !\{0,1\}[0-9] \/\/ \(!\{0,1\}HAVE_.*\)/if \1/' snappy-stubs-public.h -else - sed -i 's/if !\{0,1\}[0-9] \/\/ \(!\{0,1\}HAVE_.*\)/if \1/' snappy-stubs-public.h +if [ $TARGET_UNAME != "windows" ]; then + # Do a shallow copy, it is all we need + cp $TEMP_DIR/* $DEST_DIR || true + rm -f $DEST_DIR/Makefile* $DEST_DIR/config* $DEST_DIR/*sh + rm -f $DEST_DIR/compile* $DEST_DIR/depcomp $DEST_DIR/libtool + rm -f $DEST_DIR/test-driver $DEST_DIR/*.m4 $DEST_DIR/missing + + echo "Generating Config.h and other files" + ./configure + + # Copy over the platform independent generated files + cp $TEMP_DIR/snappy-stubs-public.h $DEST_DIR + + # Copy over config.h + mkdir $DEST_DIR/build_$TARGET_UNAME + cp $TEMP_DIR/config.h $DEST_DIR/build_$TARGET_UNAME fi + echo "Done" diff --git a/src/third_party/snappy-1.1.7/AUTHORS b/src/third_party/snappy-1.1.3/AUTHORS index 4858b377c74..4858b377c74 100644 --- a/src/third_party/snappy-1.1.7/AUTHORS +++ b/src/third_party/snappy-1.1.3/AUTHORS diff --git a/src/third_party/snappy-1.1.7/COPYING b/src/third_party/snappy-1.1.3/COPYING index bd0e5971dbf..bd0e5971dbf 100644 --- a/src/third_party/snappy-1.1.7/COPYING +++ b/src/third_party/snappy-1.1.3/COPYING diff --git a/src/third_party/snappy-1.1.3/ChangeLog b/src/third_party/snappy-1.1.3/ChangeLog new file mode 100644 index 00000000000..1478db55014 --- /dev/null +++ b/src/third_party/snappy-1.1.3/ChangeLog @@ -0,0 +1,2468 @@ +commit eb66d8176b3d1f560ee012e1b488cb1540c45f88 +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 16:10:47 2015 +0200 + + Initialized members of SnappyArrayWriter and SnappyDecompressionValidator. + These members were almost surely initialized before use by other member + functions, but Coverity was warning about this. Eliminating these warnings + minimizes clutter in that report and the likelihood of overlooking a real bug. + + A=cmumford + R=jeff + +commit b2312c4c25883ab03b5110f1b006dce95f419a4f +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 16:03:28 2015 +0200 + + Add support for Uncompress(source, sink). Various changes to allow + Uncompress(source, sink) to get the same performance as the different + variants of Uncompress to Cord/DataBuffer/String/FlatBuffer. + + Changes to efficiently support Uncompress(source, sink) + -------- + + a) For strings - we add support to StringByteSink to do GetAppendBuffer so we + can write to it without copying. + b) For flat array buffers, we do GetAppendBuffer and see if we can get a full buffer. + + With the above changes we get performance with ByteSource/ByteSink + that is very close to directly using flat arrays and strings. + + We add various benchmark cases to demonstrate that. + + Orthogonal change + ------------------ + + Add support for TryFastAppend() for SnappyScatteredWriter. + + Benchmark results are below + + CPU: Intel Core2 dL1:32KB dL2:4096KB + Benchmark Time(ns) CPU(ns) Iterations + ----------------------------------------------------- + BM_UFlat/0 109065 108996 6410 896.0MB/s html + BM_UFlat/1 1012175 1012343 691 661.4MB/s urls + BM_UFlat/2 26775 26771 26149 4.4GB/s jpg + BM_UFlat/3 48947 48940 14363 1.8GB/s pdf + BM_UFlat/4 441029 440835 1589 886.1MB/s html4 + BM_UFlat/5 39861 39880 17823 588.3MB/s cp + BM_UFlat/6 18315 18300 38126 581.1MB/s c + BM_UFlat/7 5254 5254 100000 675.4MB/s lsp + BM_UFlat/8 1568060 1567376 447 626.6MB/s xls + BM_UFlat/9 337512 337734 2073 429.5MB/s txt1 + BM_UFlat/10 287269 287054 2434 415.9MB/s txt2 + BM_UFlat/11 890098 890219 787 457.2MB/s txt3 + BM_UFlat/12 1186593 1186863 590 387.2MB/s txt4 + BM_UFlat/13 573927 573318 1000 853.7MB/s bin + BM_UFlat/14 64250 64294 10000 567.2MB/s sum + BM_UFlat/15 7301 7300 96153 552.2MB/s man + BM_UFlat/16 109617 109636 6375 1031.5MB/s pb + BM_UFlat/17 364438 364497 1921 482.3MB/s gaviota + BM_UFlatSink/0 108518 108465 6450 900.4MB/s html + BM_UFlatSink/1 991952 991997 705 675.0MB/s urls + BM_UFlatSink/2 26815 26798 26065 4.4GB/s jpg + BM_UFlatSink/3 49127 49122 14255 1.8GB/s pdf + BM_UFlatSink/4 436674 436731 1604 894.4MB/s html4 + BM_UFlatSink/5 39738 39733 17345 590.5MB/s cp + BM_UFlatSink/6 18413 18416 37962 577.4MB/s c + BM_UFlatSink/7 5677 5676 100000 625.2MB/s lsp + BM_UFlatSink/8 1552175 1551026 451 633.2MB/s xls + BM_UFlatSink/9 338526 338489 2065 428.5MB/s txt1 + BM_UFlatSink/10 289387 289307 2420 412.6MB/s txt2 + BM_UFlatSink/11 893803 893706 783 455.4MB/s txt3 + BM_UFlatSink/12 1195919 1195459 586 384.4MB/s txt4 + BM_UFlatSink/13 559637 559779 1000 874.3MB/s bin + BM_UFlatSink/14 65073 65094 10000 560.2MB/s sum + BM_UFlatSink/15 7618 7614 92823 529.5MB/s man + BM_UFlatSink/16 110085 110121 6352 1027.0MB/s pb + BM_UFlatSink/17 369196 368915 1896 476.5MB/s gaviota + BM_UValidate/0 46954 46957 14899 2.0GB/s html + BM_UValidate/1 500621 500868 1000 1.3GB/s urls + BM_UValidate/2 283 283 2481447 417.2GB/s jpg + BM_UValidate/3 16230 16228 43137 5.4GB/s pdf + BM_UValidate/4 189129 189193 3701 2.0GB/s html4 + + A=uday + R=sanjay + +commit b2ad96006741d40935db2f73194a3e489b467338 +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 15:48:29 2015 +0200 + + Changes to eliminate compiler warnings on MSVC + + This code was not compiling under Visual Studio 2013 with warnings being treated + as errors. Specifically: + + 1. Changed int -> size_t to eliminate signed/unsigned mismatch warning. + 2. Added some missing return values to functions. + 3. Inserting character instead of integer literals into strings to avoid type + conversions. + + A=cmumford + R=jeff + +commit e7a897e187e90b33f87bd9e64872cf561de9ebca +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 15:45:11 2015 +0200 + + Fixed unit tests to compile under MSVC. + + 1. Including config.h in test. + 2. Including windows.h before zippy-test.h. + 3. Removed definition of WIN32_LEAN_AND_MEAN. This caused problems in + build environments that define WIN32_LEAN_AND_MEAN as our + definition didn't check for prior existence. This constant is old + and no longer needed anyhow. + 4. Disable MSVC warning 4722 since ~LogMessageCrash() never returns. + + A=cmumford + R=jeff + +commit 86eb8b152bdb065ad11bf331a9f7d65b72616acf +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 15:41:30 2015 +0200 + + Change a few branch annotations that profiling found to be wrong. + Overall performance is neutral or slightly positive. + + Westmere (64-bit, opt): + + Benchmark Base (ns) New (ns) Improvement + -------------------------------------------------------------------------------------- + BM_UFlat/0 73798 71464 1.3GB/s html +3.3% + BM_UFlat/1 715223 704318 953.5MB/s urls +1.5% + BM_UFlat/2 8137 8871 13.0GB/s jpg -8.3% + BM_UFlat/3 200 204 935.5MB/s jpg_200 -2.0% + BM_UFlat/4 21627 21281 4.5GB/s pdf +1.6% + BM_UFlat/5 302806 290350 1.3GB/s html4 +4.3% + BM_UFlat/6 218920 219017 664.1MB/s txt1 -0.0% + BM_UFlat/7 190437 191212 626.1MB/s txt2 -0.4% + BM_UFlat/8 584192 580484 703.4MB/s txt3 +0.6% + BM_UFlat/9 776537 779055 591.6MB/s txt4 -0.3% + BM_UFlat/10 76056 72606 1.5GB/s pb +4.8% + BM_UFlat/11 235962 239043 737.4MB/s gaviota -1.3% + BM_UFlat/12 28049 28000 840.1MB/s cp +0.2% + BM_UFlat/13 12225 12021 886.9MB/s c +1.7% + BM_UFlat/14 3362 3544 1004.0MB/s lsp -5.1% + BM_UFlat/15 937015 939206 1048.9MB/s xls -0.2% + BM_UFlat/16 236 233 823.1MB/s xls_200 +1.3% + BM_UFlat/17 373170 361947 1.3GB/s bin +3.1% + BM_UFlat/18 264 264 725.5MB/s bin_200 +0.0% + BM_UFlat/19 42834 43577 839.2MB/s sum -1.7% + BM_UFlat/20 4770 4736 853.6MB/s man +0.7% + BM_UValidate/0 39671 39944 2.4GB/s html -0.7% + BM_UValidate/1 443391 443391 1.5GB/s urls +0.0% + BM_UValidate/2 163 163 703.3GB/s jpg +0.0% + BM_UValidate/3 113 112 1.7GB/s jpg_200 +0.9% + BM_UValidate/4 7555 7608 12.6GB/s pdf -0.7% + BM_ZFlat/0 157616 157568 621.5MB/s html (22.31 %) +0.0% + BM_ZFlat/1 1997290 2014486 333.4MB/s urls (47.77 %) -0.9% + BM_ZFlat/2 23035 22237 5.2GB/s jpg (99.95 %) +3.6% + BM_ZFlat/3 539 540 354.5MB/s jpg_200 (73.00 %) -0.2% + BM_ZFlat/4 80709 81369 1.2GB/s pdf (81.85 %) -0.8% + BM_ZFlat/5 639059 639220 613.0MB/s html4 (22.51 %) -0.0% + BM_ZFlat/6 577203 583370 249.3MB/s txt1 (57.87 %) -1.1% + BM_ZFlat/7 510887 516094 232.0MB/s txt2 (61.93 %) -1.0% + BM_ZFlat/8 1535843 1556973 262.2MB/s txt3 (54.92 %) -1.4% + BM_ZFlat/9 2070068 2102380 219.3MB/s txt4 (66.22 %) -1.5% + BM_ZFlat/10 152396 152148 745.5MB/s pb (19.64 %) +0.2% + BM_ZFlat/11 447367 445859 395.4MB/s gaviota (37.72 %) +0.3% + BM_ZFlat/12 76375 76797 306.3MB/s cp (48.12 %) -0.5% + BM_ZFlat/13 31518 31987 333.3MB/s c (42.40 %) -1.5% + BM_ZFlat/14 10598 10827 328.6MB/s lsp (48.37 %) -2.1% + BM_ZFlat/15 1782243 1802728 546.5MB/s xls (41.23 %) -1.1% + BM_ZFlat/16 526 539 355.0MB/s xls_200 (78.00 %) -2.4% + BM_ZFlat/17 598141 597311 822.1MB/s bin (18.11 %) +0.1% + BM_ZFlat/18 121 120 1.6GB/s bin_200 (7.50 %) +0.8% + BM_ZFlat/19 109981 112173 326.0MB/s sum (48.96 %) -2.0% + BM_ZFlat/20 14355 14575 277.4MB/s man (59.36 %) -1.5% + Sum of all benchmarks 33882722 33879325 +0.0% + + Sandy Bridge (64-bit, opt): + + Benchmark Base (ns) New (ns) Improvement + -------------------------------------------------------------------------------------- + BM_UFlat/0 43764 41600 2.3GB/s html +5.2% + BM_UFlat/1 517990 507058 1.3GB/s urls +2.2% + BM_UFlat/2 6625 5529 20.8GB/s jpg +19.8% + BM_UFlat/3 154 155 1.2GB/s jpg_200 -0.6% + BM_UFlat/4 12795 11747 8.1GB/s pdf +8.9% + BM_UFlat/5 200335 193413 2.0GB/s html4 +3.6% + BM_UFlat/6 156574 156426 929.2MB/s txt1 +0.1% + BM_UFlat/7 137574 137464 870.4MB/s txt2 +0.1% + BM_UFlat/8 422551 421603 967.4MB/s txt3 +0.2% + BM_UFlat/9 577749 578985 795.6MB/s txt4 -0.2% + BM_UFlat/10 42329 39362 2.8GB/s pb +7.5% + BM_UFlat/11 170615 169751 1037.9MB/s gaviota +0.5% + BM_UFlat/12 12800 12719 1.8GB/s cp +0.6% + BM_UFlat/13 6585 6579 1.6GB/s c +0.1% + BM_UFlat/14 2066 2044 1.7GB/s lsp +1.1% + BM_UFlat/15 750861 746911 1.3GB/s xls +0.5% + BM_UFlat/16 188 192 996.0MB/s xls_200 -2.1% + BM_UFlat/17 271622 264333 1.8GB/s bin +2.8% + BM_UFlat/18 208 207 923.6MB/s bin_200 +0.5% + BM_UFlat/19 24667 24845 1.4GB/s sum -0.7% + BM_UFlat/20 2663 2662 1.5GB/s man +0.0% + BM_ZFlat/0 115173 115624 846.5MB/s html (22.31 %) -0.4% + BM_ZFlat/1 1530331 1537769 436.5MB/s urls (47.77 %) -0.5% + BM_ZFlat/2 17503 17013 6.8GB/s jpg (99.95 %) +2.9% + BM_ZFlat/3 385 385 496.3MB/s jpg_200 (73.00 %) +0.0% + BM_ZFlat/4 61753 61540 1.6GB/s pdf (81.85 %) +0.3% + BM_ZFlat/5 484806 483356 810.1MB/s html4 (22.51 %) +0.3% + BM_ZFlat/6 464143 467609 310.9MB/s txt1 (57.87 %) -0.7% + BM_ZFlat/7 410315 413319 289.5MB/s txt2 (61.93 %) -0.7% + BM_ZFlat/8 1244082 1249381 326.5MB/s txt3 (54.92 %) -0.4% + BM_ZFlat/9 1696914 1709685 269.4MB/s txt4 (66.22 %) -0.7% + BM_ZFlat/10 104148 103372 1096.7MB/s pb (19.64 %) +0.8% + BM_ZFlat/11 363522 359722 489.8MB/s gaviota (37.72 %) +1.1% + BM_ZFlat/12 47021 50095 469.3MB/s cp (48.12 %) -6.1% + BM_ZFlat/13 16888 16985 627.4MB/s c (42.40 %) -0.6% + BM_ZFlat/14 5496 5469 650.3MB/s lsp (48.37 %) +0.5% + BM_ZFlat/15 1460713 1448760 679.5MB/s xls (41.23 %) +0.8% + BM_ZFlat/16 387 393 486.8MB/s xls_200 (78.00 %) -1.5% + BM_ZFlat/17 457654 451462 1086.6MB/s bin (18.11 %) +1.4% + BM_ZFlat/18 97 87 2.1GB/s bin_200 (7.50 %) +11.5% + BM_ZFlat/19 77904 80924 451.7MB/s sum (48.96 %) -3.7% + BM_ZFlat/20 7648 7663 527.1MB/s man (59.36 %) -0.2% + Sum of all benchmarks 25493635 25482069 +0.0% + + A=dehao + R=sesse + +commit 11ccdfb868387e56d845766d89ddab9d489c4128 +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 16:07:58 2015 +0200 + + Sync with various Google-internal changes. + + Should not mean much for the open-source version. + +commit 22acaf438ed93ab21a2ff1919d173206798b996e +Author: Steinar H. Gunderson <sesse@google.com> +Date: Mon Jun 22 15:39:08 2015 +0200 + + Change some internal path names. + + This is mostly to sync up with some changes from Google's internal + repositories; it does not affect the open-source distribution in itself. + +commit 1ff9be9b8fafc8528ca9e055646f5932aa5db9c4 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Feb 28 11:18:07 2014 +0000 + + Release Snappy 1.1.2. + + R=jeff + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@84 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 19690d78e83f8963f497585031efa3d9ca66b807 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Feb 19 10:31:49 2014 +0000 + + Fix public issue 82: Stop distributing benchmark data files that have + unclear or unsuitable licensing. + + In general, we replace the files we can with liberally licensed data, + and remove all the others (in particular all the parts of the Canterbury + corpus that are not clearly in the public domain). The replacements + do not always have the exact same characteristics as the original ones, + but they are more than good enough to be useful for benchmarking. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@83 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f82bff66afe0de4c9ae22f8c4ef84e3c2233e799 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Oct 25 13:31:27 2013 +0000 + + Add support for padding in the Snappy framed format. + + This is specifically motivated by DICOM's demands that embedded data + must be of an even number of bytes, but could in principle be used for + any sort of padding/alignment needed. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@82 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit eeead8dc38ea359f027fb6e89f345448e8e9d723 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Oct 15 15:21:31 2013 +0000 + + Release Snappy 1.1.1. + + R=jeff + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@81 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 6bc39e24c76adbbff26ae629fafbf7dfc795f554 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Aug 13 12:55:00 2013 +0000 + + Add autoconf tests for size_t and ssize_t. Sort-of resolves public issue 79; + it would solve the problem if MSVC typically used autoconf. However, it gives + a natural place (config.h) to put the typedef even for MSVC. + + R=jsbell + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@80 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 7c3c01df77e191ad1f8377448961fe88db2802e9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon Jul 29 11:06:44 2013 +0000 + + When we compare the number of bytes produced with the offset for a + backreference, make the signedness of the bytes produced clear, + by sticking it into a size_t. This avoids a signed/unsigned compare + warning from MSVC (public issue 71), and also is slightly clearer. + + Since the line is now so long the explanatory comment about the -1u + trick has to go somewhere else anyway, I used the opportunity to + explain it in slightly more detail. + + This is a purely stylistic change; the emitted assembler from GCC + is identical. + + R=jeff + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@79 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 2f0aaf8631d8fb2475ca1a6687c181efb14ed286 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sun Jun 30 19:24:03 2013 +0000 + + In the fast path for decompressing literals, instead of checking + whether there's 16 bytes free and then checking right afterwards + (when having subtracted the literal size) that there are now + 5 bytes free, just check once for 21 bytes. This skips a compare + and a branch; although it is easily predictable, it is still + a few cycles on a fast path that we would like to get rid of. + + Benchmarking this yields very confusing results. On open-source + GCC 4.8.1 on Haswell, we get exactly the expected results; the + benchmarks where we hit the fast path for literals (in particular + the two HTML benchmarks and the protobuf benchmark) give very nice + speedups, and the others are not really affected. + + However, benchmarks with Google's GCC branch on other hardware + is much less clear. It seems that we have a weak loss in some cases + (and the win for the “typical” win cases are not nearly as clear), + but that it depends on microarchitecture and plain luck in how we run + the benchmark. Looking at the generated assembler, it seems that + the removal of the if causes other large-scale changes in how the + function is laid out, which makes it likely that this is just bad luck. + + Thus, we should keep this change, even though its exact current impact is + unclear; it's a sensible change per se, and dropping it on the basis of + microoptimization for a given compiler (or even branch of a compiler) + would seem like a bad strategy in the long run. + + Microbenchmark results (all in 64-bit, opt mode): + + Nehalem, Google GCC: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------ + BM_UFlat/0 76747 75591 1.3GB/s html +1.5% + BM_UFlat/1 765756 757040 886.3MB/s urls +1.2% + BM_UFlat/2 10867 10893 10.9GB/s jpg -0.2% + BM_UFlat/3 124 131 1.4GB/s jpg_200 -5.3% + BM_UFlat/4 31663 31596 2.8GB/s pdf +0.2% + BM_UFlat/5 314162 308176 1.2GB/s html4 +1.9% + BM_UFlat/6 29668 29746 790.6MB/s cp -0.3% + BM_UFlat/7 12958 13386 796.4MB/s c -3.2% + BM_UFlat/8 3596 3682 966.0MB/s lsp -2.3% + BM_UFlat/9 1019193 1033493 953.3MB/s xls -1.4% + BM_UFlat/10 239 247 775.3MB/s xls_200 -3.2% + BM_UFlat/11 236411 240271 606.9MB/s txt1 -1.6% + BM_UFlat/12 206639 209768 571.2MB/s txt2 -1.5% + BM_UFlat/13 627803 635722 641.4MB/s txt3 -1.2% + BM_UFlat/14 845932 857816 538.2MB/s txt4 -1.4% + BM_UFlat/15 402107 391670 1.2GB/s bin +2.7% + BM_UFlat/16 283 279 683.6MB/s bin_200 +1.4% + BM_UFlat/17 46070 46815 781.5MB/s sum -1.6% + BM_UFlat/18 5053 5163 782.0MB/s man -2.1% + BM_UFlat/19 79721 76581 1.4GB/s pb +4.1% + BM_UFlat/20 251158 252330 697.5MB/s gaviota -0.5% + Sum of all benchmarks 4966150 4980396 -0.3% + + + Sandy Bridge, Google GCC: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------ + BM_UFlat/0 42850 42182 2.3GB/s html +1.6% + BM_UFlat/1 525660 515816 1.3GB/s urls +1.9% + BM_UFlat/2 7173 7283 16.3GB/s jpg -1.5% + BM_UFlat/3 92 91 2.1GB/s jpg_200 +1.1% + BM_UFlat/4 15147 14872 5.9GB/s pdf +1.8% + BM_UFlat/5 199936 192116 2.0GB/s html4 +4.1% + BM_UFlat/6 12796 12443 1.8GB/s cp +2.8% + BM_UFlat/7 6588 6400 1.6GB/s c +2.9% + BM_UFlat/8 2010 1951 1.8GB/s lsp +3.0% + BM_UFlat/9 761124 763049 1.3GB/s xls -0.3% + BM_UFlat/10 186 189 1016.1MB/s xls_200 -1.6% + BM_UFlat/11 159354 158460 918.6MB/s txt1 +0.6% + BM_UFlat/12 139732 139950 856.1MB/s txt2 -0.2% + BM_UFlat/13 429917 425027 961.7MB/s txt3 +1.2% + BM_UFlat/14 585255 587324 785.8MB/s txt4 -0.4% + BM_UFlat/15 276186 266173 1.8GB/s bin +3.8% + BM_UFlat/16 205 207 925.5MB/s bin_200 -1.0% + BM_UFlat/17 24925 24935 1.4GB/s sum -0.0% + BM_UFlat/18 2632 2576 1.5GB/s man +2.2% + BM_UFlat/19 40546 39108 2.8GB/s pb +3.7% + BM_UFlat/20 175803 168209 1048.9MB/s gaviota +4.5% + Sum of all benchmarks 3408117 3368361 +1.2% + + + Haswell, upstream GCC 4.8.1: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------ + BM_UFlat/0 46308 40641 2.3GB/s html +13.9% + BM_UFlat/1 513385 514706 1.3GB/s urls -0.3% + BM_UFlat/2 6197 6151 19.2GB/s jpg +0.7% + BM_UFlat/3 61 61 3.0GB/s jpg_200 +0.0% + BM_UFlat/4 13551 13429 6.5GB/s pdf +0.9% + BM_UFlat/5 198317 190243 2.0GB/s html4 +4.2% + BM_UFlat/6 14768 12560 1.8GB/s cp +17.6% + BM_UFlat/7 6453 6447 1.6GB/s c +0.1% + BM_UFlat/8 1991 1980 1.8GB/s lsp +0.6% + BM_UFlat/9 766947 770424 1.2GB/s xls -0.5% + BM_UFlat/10 170 169 1.1GB/s xls_200 +0.6% + BM_UFlat/11 164350 163554 888.7MB/s txt1 +0.5% + BM_UFlat/12 145444 143830 832.1MB/s txt2 +1.1% + BM_UFlat/13 437849 438413 929.2MB/s txt3 -0.1% + BM_UFlat/14 603587 605309 759.8MB/s txt4 -0.3% + BM_UFlat/15 249799 248067 1.9GB/s bin +0.7% + BM_UFlat/16 191 188 1011.4MB/s bin_200 +1.6% + BM_UFlat/17 26064 24778 1.4GB/s sum +5.2% + BM_UFlat/18 2620 2601 1.5GB/s man +0.7% + BM_UFlat/19 44551 37373 3.0GB/s pb +19.2% + BM_UFlat/20 165408 164584 1.0GB/s gaviota +0.5% + Sum of all benchmarks 3408011 3385508 +0.7% + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@78 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 062bf544a61107db730b6d08cb0b159c4dd9b24c +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Jun 14 21:42:26 2013 +0000 + + Make the two IncrementalCopy* functions take in an ssize_t instead of a len, + in order to avoid having to do 32-to-64-bit signed conversions on a hot path + during decompression. (Also fixes some MSVC warnings, mentioned in public + issue 75, but more of those remain.) They cannot be size_t because we expect + them to go negative and test for that. + + This saves a few movzwl instructions, yielding ~2% speedup in decompression. + + + Sandy Bridge: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 48009 41283 2.3GB/s html +16.3% + BM_UFlat/1 531274 513419 1.3GB/s urls +3.5% + BM_UFlat/2 7378 7062 16.8GB/s jpg +4.5% + BM_UFlat/3 92 92 2.0GB/s jpg_200 +0.0% + BM_UFlat/4 15057 14974 5.9GB/s pdf +0.6% + BM_UFlat/5 204323 193140 2.0GB/s html4 +5.8% + BM_UFlat/6 13282 12611 1.8GB/s cp +5.3% + BM_UFlat/7 6511 6504 1.6GB/s c +0.1% + BM_UFlat/8 2014 2030 1.7GB/s lsp -0.8% + BM_UFlat/9 775909 768336 1.3GB/s xls +1.0% + BM_UFlat/10 182 184 1043.2MB/s xls_200 -1.1% + BM_UFlat/11 167352 161630 901.2MB/s txt1 +3.5% + BM_UFlat/12 147393 142246 842.8MB/s txt2 +3.6% + BM_UFlat/13 449960 432853 944.4MB/s txt3 +4.0% + BM_UFlat/14 620497 594845 775.9MB/s txt4 +4.3% + BM_UFlat/15 265610 267356 1.8GB/s bin -0.7% + BM_UFlat/16 206 205 932.7MB/s bin_200 +0.5% + BM_UFlat/17 25561 24730 1.4GB/s sum +3.4% + BM_UFlat/18 2620 2644 1.5GB/s man -0.9% + BM_UFlat/19 45766 38589 2.9GB/s pb +18.6% + BM_UFlat/20 171107 169832 1039.5MB/s gaviota +0.8% + Sum of all benchmarks 3500103 3394565 +3.1% + + + Westmere: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 72624 71526 1.3GB/s html +1.5% + BM_UFlat/1 735821 722917 930.8MB/s urls +1.8% + BM_UFlat/2 10450 10172 11.7GB/s jpg +2.7% + BM_UFlat/3 117 117 1.6GB/s jpg_200 +0.0% + BM_UFlat/4 29817 29648 3.0GB/s pdf +0.6% + BM_UFlat/5 297126 293073 1.3GB/s html4 +1.4% + BM_UFlat/6 28252 27994 842.0MB/s cp +0.9% + BM_UFlat/7 12672 12391 862.1MB/s c +2.3% + BM_UFlat/8 3507 3425 1040.9MB/s lsp +2.4% + BM_UFlat/9 1004268 969395 1018.0MB/s xls +3.6% + BM_UFlat/10 233 227 844.8MB/s xls_200 +2.6% + BM_UFlat/11 230054 224981 647.8MB/s txt1 +2.3% + BM_UFlat/12 201229 196447 610.5MB/s txt2 +2.4% + BM_UFlat/13 609547 596761 685.3MB/s txt3 +2.1% + BM_UFlat/14 824362 804821 573.8MB/s txt4 +2.4% + BM_UFlat/15 371095 374899 1.3GB/s bin -1.0% + BM_UFlat/16 267 267 717.8MB/s bin_200 +0.0% + BM_UFlat/17 44623 43828 835.9MB/s sum +1.8% + BM_UFlat/18 5077 4815 841.0MB/s man +5.4% + BM_UFlat/19 74964 73210 1.5GB/s pb +2.4% + BM_UFlat/20 237987 236745 746.0MB/s gaviota +0.5% + Sum of all benchmarks 4794092 4697659 +2.1% + + + Istanbul: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 98614 96376 1020.4MB/s html +2.3% + BM_UFlat/1 963740 953241 707.2MB/s urls +1.1% + BM_UFlat/2 25042 24769 4.8GB/s jpg +1.1% + BM_UFlat/3 180 180 1065.6MB/s jpg_200 +0.0% + BM_UFlat/4 45942 45403 1.9GB/s pdf +1.2% + BM_UFlat/5 400135 390226 1008.2MB/s html4 +2.5% + BM_UFlat/6 37768 37392 631.9MB/s cp +1.0% + BM_UFlat/7 18585 18200 588.2MB/s c +2.1% + BM_UFlat/8 5751 5690 627.7MB/s lsp +1.1% + BM_UFlat/9 1543154 1542209 641.4MB/s xls +0.1% + BM_UFlat/10 381 388 494.6MB/s xls_200 -1.8% + BM_UFlat/11 339715 331973 440.1MB/s txt1 +2.3% + BM_UFlat/12 294807 289418 415.4MB/s txt2 +1.9% + BM_UFlat/13 906160 884094 463.3MB/s txt3 +2.5% + BM_UFlat/14 1224221 1198435 386.1MB/s txt4 +2.2% + BM_UFlat/15 516277 502923 979.5MB/s bin +2.7% + BM_UFlat/16 405 402 477.2MB/s bin_200 +0.7% + BM_UFlat/17 61640 60621 605.6MB/s sum +1.7% + BM_UFlat/18 7326 7383 549.5MB/s man -0.8% + BM_UFlat/19 94720 92653 1.2GB/s pb +2.2% + BM_UFlat/20 360435 346687 510.6MB/s gaviota +4.0% + Sum of all benchmarks 6944998 6828663 +1.7% + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@77 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 328aafa1980824a9afdcd50edc30d9d5157e417f +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Jun 13 16:19:52 2013 +0000 + + Add support for uncompressing to iovecs (scatter I/O). + Windows does not have struct iovec defined anywhere, + so we define our own version that's equal to what UNIX + typically has. + + The bulk of this patch was contributed by Mohit Aron. + + R=jeff + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@76 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit cd92eb0852e2339187b693eef3595a07d2276c1d +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Jun 12 19:51:15 2013 +0000 + + Some code reorganization needed for an internal change. + + R=fikes + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@75 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit a3e928d62bbd61b523b988c07b560253950cf73b +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Apr 9 15:33:30 2013 +0000 + + Supports truncated test data in zippy benchmark. + + R=sesse + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@74 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit bde324c0169763688f35ee44630a26ad1f49eec3 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Feb 5 14:36:15 2013 +0000 + + Release Snappy 1.1.0. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@73 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 8168446c7eaaa0594e1f4ca923376dcf3a2846fa +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Feb 5 14:30:05 2013 +0000 + + Make ./snappy_unittest pass without "srcdir" being defined. + + Previously, snappy_unittests would read from an absolute path /testdata/..; + convert it to use a relative path instead. + + Patch from Marc-Antonie Ruel. + + R=maruel + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@72 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 27a0cc394950ebdad2e8d67322f0862835b10bd9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Jan 18 12:16:36 2013 +0000 + + Increase the Zippy block size from 32 kB to 64 kB, winning ~3% density + while being effectively performance neutral. + + The longer story about density is that we win 3-6% density on the benchmarks + where this has any effect at all; many of the benchmarks (cp, c, lsp, man) + are smaller than 32 kB and thus will have no effect. Binary data also seems + to win little or nothing; of course, the already-compressed data wins nothing. + The protobuf benchmark wins as much as ~18% depending on architecture, + but I wouldn't be too sure that this is representative of protobuf data in + general. + + As of performance, we lose a tiny amount since we get more tags (e.g., a long + literal might be broken up into literal-copy-literal), but we win it back with + less clearing of the hash table, and more opportunities to skip incompressible + data (e.g. in the jpg benchmark). Decompression seems to get ever so slightly + slower, again due to more tags. The total net change is about as close to zero + as we can get, so the end effect seems to be simply more density and no + real performance change. + + The comment about not changing kBlockSize, scary as it is, is not really + relevant, since we're never going to have a block-level decompressor without + explicitly marked blocks. Replace it with something more appropriate. + + This affects the framing format, but it's okay to change it since it basically + has no users yet. + + + Density (note that cp, c, lsp and man are all smaller than 32 kB): + + Benchmark Description Base (%) New (%) Improvement + -------------------------------------------------------------- + ZFlat/0 html 22.57 22.31 +5.6% + ZFlat/1 urls 50.89 47.77 +6.5% + ZFlat/2 jpg 99.88 99.87 +0.0% + ZFlat/3 pdf 82.13 82.07 +0.1% + ZFlat/4 html4 23.55 22.51 +4.6% + ZFlat/5 cp 48.12 48.12 +0.0% + ZFlat/6 c 42.40 42.40 +0.0% + ZFlat/7 lsp 48.37 48.37 +0.0% + ZFlat/8 xls 41.34 41.23 +0.3% + ZFlat/9 txt1 59.81 57.87 +3.4% + ZFlat/10 txt2 64.07 61.93 +3.5% + ZFlat/11 txt3 57.11 54.92 +4.0% + ZFlat/12 txt4 68.35 66.22 +3.2% + ZFlat/13 bin 18.21 18.11 +0.6% + ZFlat/14 sum 51.88 48.96 +6.0% + ZFlat/15 man 59.36 59.36 +0.0% + ZFlat/16 pb 23.15 19.64 +17.9% + ZFlat/17 gaviota 38.27 37.72 +1.5% + Geometric mean 45.51 44.15 +3.1% + + + Microbenchmarks (64-bit, opt): + + Westmere 2.8 GHz: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 75342 75027 1.3GB/s html +0.4% + BM_UFlat/1 723767 744269 899.6MB/s urls -2.8% + BM_UFlat/2 10072 10072 11.7GB/s jpg +0.0% + BM_UFlat/3 30747 30388 2.9GB/s pdf +1.2% + BM_UFlat/4 307353 306063 1.2GB/s html4 +0.4% + BM_UFlat/5 28593 28743 816.3MB/s cp -0.5% + BM_UFlat/6 12958 12998 818.1MB/s c -0.3% + BM_UFlat/7 3700 3792 935.8MB/s lsp -2.4% + BM_UFlat/8 999685 999905 982.1MB/s xls -0.0% + BM_UFlat/9 232954 230079 630.4MB/s txt1 +1.2% + BM_UFlat/10 200785 201468 592.6MB/s txt2 -0.3% + BM_UFlat/11 617267 610968 666.1MB/s txt3 +1.0% + BM_UFlat/12 821595 822475 558.7MB/s txt4 -0.1% + BM_UFlat/13 377097 377632 1.3GB/s bin -0.1% + BM_UFlat/14 45476 45260 805.8MB/s sum +0.5% + BM_UFlat/15 4985 5003 805.7MB/s man -0.4% + BM_UFlat/16 80813 77494 1.4GB/s pb +4.3% + BM_UFlat/17 251792 241553 727.7MB/s gaviota +4.2% + BM_UValidate/0 40343 40354 2.4GB/s html -0.0% + BM_UValidate/1 426890 451574 1.4GB/s urls -5.5% + BM_UValidate/2 187 179 661.9GB/s jpg +4.5% + BM_UValidate/3 13783 13827 6.4GB/s pdf -0.3% + BM_UValidate/4 162393 163335 2.3GB/s html4 -0.6% + BM_UDataBuffer/0 93756 93302 1046.7MB/s html +0.5% + BM_UDataBuffer/1 886714 916292 730.7MB/s urls -3.2% + BM_UDataBuffer/2 15861 16401 7.2GB/s jpg -3.3% + BM_UDataBuffer/3 38934 39224 2.2GB/s pdf -0.7% + BM_UDataBuffer/4 381008 379428 1029.5MB/s html4 +0.4% + BM_UCord/0 92528 91098 1072.0MB/s html +1.6% + BM_UCord/1 858421 885287 756.3MB/s urls -3.0% + BM_UCord/2 13140 13464 8.8GB/s jpg -2.4% + BM_UCord/3 39012 37773 2.3GB/s pdf +3.3% + BM_UCord/4 376869 371267 1052.1MB/s html4 +1.5% + BM_UCordString/0 75810 75303 1.3GB/s html +0.7% + BM_UCordString/1 735290 753841 888.2MB/s urls -2.5% + BM_UCordString/2 11945 13113 9.0GB/s jpg -8.9% + BM_UCordString/3 33901 32562 2.7GB/s pdf +4.1% + BM_UCordString/4 310985 309390 1.2GB/s html4 +0.5% + BM_UCordValidate/0 40952 40450 2.4GB/s html +1.2% + BM_UCordValidate/1 433842 456531 1.4GB/s urls -5.0% + BM_UCordValidate/2 1179 1173 100.8GB/s jpg +0.5% + BM_UCordValidate/3 14481 14392 6.1GB/s pdf +0.6% + BM_UCordValidate/4 164364 164151 2.3GB/s html4 +0.1% + BM_ZFlat/0 160610 156601 623.6MB/s html (22.31 %) +2.6% + BM_ZFlat/1 1995238 1993582 335.9MB/s urls (47.77 %) +0.1% + BM_ZFlat/2 30133 24983 4.7GB/s jpg (99.87 %) +20.6% + BM_ZFlat/3 74453 73128 1.2GB/s pdf (82.07 %) +1.8% + BM_ZFlat/4 647674 633729 616.4MB/s html4 (22.51 %) +2.2% + BM_ZFlat/5 76259 76090 308.4MB/s cp (48.12 %) +0.2% + BM_ZFlat/6 31106 31084 342.1MB/s c (42.40 %) +0.1% + BM_ZFlat/7 10507 10443 339.8MB/s lsp (48.37 %) +0.6% + BM_ZFlat/8 1811047 1793325 547.6MB/s xls (41.23 %) +1.0% + BM_ZFlat/9 597903 581793 249.3MB/s txt1 (57.87 %) +2.8% + BM_ZFlat/10 525320 514522 232.0MB/s txt2 (61.93 %) +2.1% + BM_ZFlat/11 1596591 1551636 262.3MB/s txt3 (54.92 %) +2.9% + BM_ZFlat/12 2134523 2094033 219.5MB/s txt4 (66.22 %) +1.9% + BM_ZFlat/13 593024 587869 832.6MB/s bin (18.11 %) +0.9% + BM_ZFlat/14 114746 110666 329.5MB/s sum (48.96 %) +3.7% + BM_ZFlat/15 14376 14485 278.3MB/s man (59.36 %) -0.8% + BM_ZFlat/16 167908 150070 753.6MB/s pb (19.64 %) +11.9% + BM_ZFlat/17 460228 442253 397.5MB/s gaviota (37.72 %) +4.1% + BM_ZCord/0 164896 160241 609.4MB/s html +2.9% + BM_ZCord/1 2070239 2043492 327.7MB/s urls +1.3% + BM_ZCord/2 54402 47002 2.5GB/s jpg +15.7% + BM_ZCord/3 85871 83832 1073.1MB/s pdf +2.4% + BM_ZCord/4 664078 648825 602.0MB/s html4 +2.4% + BM_ZDataBuffer/0 174874 172549 566.0MB/s html +1.3% + BM_ZDataBuffer/1 2134410 2139173 313.0MB/s urls -0.2% + BM_ZDataBuffer/2 71911 69551 1.7GB/s jpg +3.4% + BM_ZDataBuffer/3 98236 99727 902.1MB/s pdf -1.5% + BM_ZDataBuffer/4 710776 699104 558.8MB/s html4 +1.7% + Sum of all benchmarks 27358908 27200688 +0.6% + + + Sandy Bridge 2.6 GHz: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 49356 49018 1.9GB/s html +0.7% + BM_UFlat/1 516764 531955 1.2GB/s urls -2.9% + BM_UFlat/2 6982 7304 16.2GB/s jpg -4.4% + BM_UFlat/3 15285 15598 5.6GB/s pdf -2.0% + BM_UFlat/4 206557 206669 1.8GB/s html4 -0.1% + BM_UFlat/5 13681 13567 1.7GB/s cp +0.8% + BM_UFlat/6 6571 6592 1.6GB/s c -0.3% + BM_UFlat/7 2008 1994 1.7GB/s lsp +0.7% + BM_UFlat/8 775700 773286 1.2GB/s xls +0.3% + BM_UFlat/9 165578 164480 881.8MB/s txt1 +0.7% + BM_UFlat/10 143707 144139 828.2MB/s txt2 -0.3% + BM_UFlat/11 443026 436281 932.8MB/s txt3 +1.5% + BM_UFlat/12 603129 595856 771.2MB/s txt4 +1.2% + BM_UFlat/13 271682 270450 1.8GB/s bin +0.5% + BM_UFlat/14 26200 25666 1.4GB/s sum +2.1% + BM_UFlat/15 2620 2608 1.5GB/s man +0.5% + BM_UFlat/16 48908 47756 2.3GB/s pb +2.4% + BM_UFlat/17 174638 170346 1031.9MB/s gaviota +2.5% + BM_UValidate/0 31922 31898 3.0GB/s html +0.1% + BM_UValidate/1 341265 363554 1.8GB/s urls -6.1% + BM_UValidate/2 160 151 782.8GB/s jpg +6.0% + BM_UValidate/3 10402 10380 8.5GB/s pdf +0.2% + BM_UValidate/4 129490 130587 2.9GB/s html4 -0.8% + BM_UDataBuffer/0 59383 58736 1.6GB/s html +1.1% + BM_UDataBuffer/1 619222 637786 1049.8MB/s urls -2.9% + BM_UDataBuffer/2 10775 11941 9.9GB/s jpg -9.8% + BM_UDataBuffer/3 18002 17930 4.9GB/s pdf +0.4% + BM_UDataBuffer/4 259182 259306 1.5GB/s html4 -0.0% + BM_UCord/0 59379 57814 1.6GB/s html +2.7% + BM_UCord/1 598456 615162 1088.4MB/s urls -2.7% + BM_UCord/2 8519 8628 13.7GB/s jpg -1.3% + BM_UCord/3 18123 17537 5.0GB/s pdf +3.3% + BM_UCord/4 252375 252331 1.5GB/s html4 +0.0% + BM_UCordString/0 49494 49790 1.9GB/s html -0.6% + BM_UCordString/1 524659 541803 1.2GB/s urls -3.2% + BM_UCordString/2 8206 8354 14.2GB/s jpg -1.8% + BM_UCordString/3 17235 16537 5.3GB/s pdf +4.2% + BM_UCordString/4 210188 211072 1.8GB/s html4 -0.4% + BM_UCordValidate/0 31956 31587 3.0GB/s html +1.2% + BM_UCordValidate/1 340828 362141 1.8GB/s urls -5.9% + BM_UCordValidate/2 783 744 158.9GB/s jpg +5.2% + BM_UCordValidate/3 10543 10462 8.4GB/s pdf +0.8% + BM_UCordValidate/4 130150 129789 2.9GB/s html4 +0.3% + BM_ZFlat/0 113873 111200 878.2MB/s html (22.31 %) +2.4% + BM_ZFlat/1 1473023 1489858 449.4MB/s urls (47.77 %) -1.1% + BM_ZFlat/2 23569 19486 6.1GB/s jpg (99.87 %) +21.0% + BM_ZFlat/3 49178 48046 1.8GB/s pdf (82.07 %) +2.4% + BM_ZFlat/4 475063 469394 832.2MB/s html4 (22.51 %) +1.2% + BM_ZFlat/5 46910 46816 501.2MB/s cp (48.12 %) +0.2% + BM_ZFlat/6 16883 16916 628.6MB/s c (42.40 %) -0.2% + BM_ZFlat/7 5381 5447 651.5MB/s lsp (48.37 %) -1.2% + BM_ZFlat/8 1466870 1473861 666.3MB/s xls (41.23 %) -0.5% + BM_ZFlat/9 468006 464101 312.5MB/s txt1 (57.87 %) +0.8% + BM_ZFlat/10 408157 408957 291.9MB/s txt2 (61.93 %) -0.2% + BM_ZFlat/11 1253348 1232910 330.1MB/s txt3 (54.92 %) +1.7% + BM_ZFlat/12 1702373 1702977 269.8MB/s txt4 (66.22 %) -0.0% + BM_ZFlat/13 439792 438557 1116.0MB/s bin (18.11 %) +0.3% + BM_ZFlat/14 80766 78851 462.5MB/s sum (48.96 %) +2.4% + BM_ZFlat/15 7420 7542 534.5MB/s man (59.36 %) -1.6% + BM_ZFlat/16 112043 100126 1.1GB/s pb (19.64 %) +11.9% + BM_ZFlat/17 368877 357703 491.4MB/s gaviota (37.72 %) +3.1% + BM_ZCord/0 116402 113564 859.9MB/s html +2.5% + BM_ZCord/1 1507156 1519911 440.5MB/s urls -0.8% + BM_ZCord/2 39860 33686 3.5GB/s jpg +18.3% + BM_ZCord/3 56211 54694 1.6GB/s pdf +2.8% + BM_ZCord/4 485594 479212 815.1MB/s html4 +1.3% + BM_ZDataBuffer/0 123185 121572 803.3MB/s html +1.3% + BM_ZDataBuffer/1 1569111 1589380 421.3MB/s urls -1.3% + BM_ZDataBuffer/2 53143 49556 2.4GB/s jpg +7.2% + BM_ZDataBuffer/3 65725 66826 1.3GB/s pdf -1.6% + BM_ZDataBuffer/4 517871 514750 758.9MB/s html4 +0.6% + Sum of all benchmarks 20258879 20315484 -0.3% + + + AMD Instanbul 2.4 GHz: + + Benchmark Base (ns) New (ns) Improvement + ------------------------------------------------------------------------------------------------- + BM_UFlat/0 97120 96585 1011.1MB/s html +0.6% + BM_UFlat/1 917473 948016 706.3MB/s urls -3.2% + BM_UFlat/2 21496 23938 4.9GB/s jpg -10.2% + BM_UFlat/3 44751 45639 1.9GB/s pdf -1.9% + BM_UFlat/4 391950 391413 998.0MB/s html4 +0.1% + BM_UFlat/5 37366 37201 630.7MB/s cp +0.4% + BM_UFlat/6 18350 18318 580.5MB/s c +0.2% + BM_UFlat/7 5672 5661 626.9MB/s lsp +0.2% + BM_UFlat/8 1533390 1529441 642.1MB/s xls +0.3% + BM_UFlat/9 335477 336553 431.0MB/s txt1 -0.3% + BM_UFlat/10 285140 292080 408.7MB/s txt2 -2.4% + BM_UFlat/11 888507 894758 454.9MB/s txt3 -0.7% + BM_UFlat/12 1187643 1210928 379.5MB/s txt4 -1.9% + BM_UFlat/13 493717 507447 964.5MB/s bin -2.7% + BM_UFlat/14 61740 60870 599.1MB/s sum +1.4% + BM_UFlat/15 7211 7187 560.9MB/s man +0.3% + BM_UFlat/16 97435 93100 1.2GB/s pb +4.7% + BM_UFlat/17 362662 356395 493.2MB/s gaviota +1.8% + BM_UValidate/0 47475 47118 2.0GB/s html +0.8% + BM_UValidate/1 501304 529741 1.2GB/s urls -5.4% + BM_UValidate/2 276 243 486.2GB/s jpg +13.6% + BM_UValidate/3 16361 16261 5.4GB/s pdf +0.6% + BM_UValidate/4 190741 190353 2.0GB/s html4 +0.2% + BM_UDataBuffer/0 111080 109771 889.6MB/s html +1.2% + BM_UDataBuffer/1 1051035 1085999 616.5MB/s urls -3.2% + BM_UDataBuffer/2 25801 25463 4.6GB/s jpg +1.3% + BM_UDataBuffer/3 50493 49946 1.8GB/s pdf +1.1% + BM_UDataBuffer/4 447258 444138 879.5MB/s html4 +0.7% + BM_UCord/0 109350 107909 905.0MB/s html +1.3% + BM_UCord/1 1023396 1054964 634.7MB/s urls -3.0% + BM_UCord/2 25292 24371 4.9GB/s jpg +3.8% + BM_UCord/3 48955 49736 1.8GB/s pdf -1.6% + BM_UCord/4 440452 437331 893.2MB/s html4 +0.7% + BM_UCordString/0 98511 98031 996.2MB/s html +0.5% + BM_UCordString/1 933230 963495 694.9MB/s urls -3.1% + BM_UCordString/2 23311 24076 4.9GB/s jpg -3.2% + BM_UCordString/3 45568 46196 1.9GB/s pdf -1.4% + BM_UCordString/4 397791 396934 984.1MB/s html4 +0.2% + BM_UCordValidate/0 47537 46921 2.0GB/s html +1.3% + BM_UCordValidate/1 505071 532716 1.2GB/s urls -5.2% + BM_UCordValidate/2 1663 1621 72.9GB/s jpg +2.6% + BM_UCordValidate/3 16890 16926 5.2GB/s pdf -0.2% + BM_UCordValidate/4 192365 191984 2.0GB/s html4 +0.2% + BM_ZFlat/0 184708 179103 545.3MB/s html (22.31 %) +3.1% + BM_ZFlat/1 2293864 2302950 290.7MB/s urls (47.77 %) -0.4% + BM_ZFlat/2 52852 47618 2.5GB/s jpg (99.87 %) +11.0% + BM_ZFlat/3 100766 96179 935.3MB/s pdf (82.07 %) +4.8% + BM_ZFlat/4 741220 727977 536.6MB/s html4 (22.51 %) +1.8% + BM_ZFlat/5 85402 85418 274.7MB/s cp (48.12 %) -0.0% + BM_ZFlat/6 36558 36494 291.4MB/s c (42.40 %) +0.2% + BM_ZFlat/7 12706 12507 283.7MB/s lsp (48.37 %) +1.6% + BM_ZFlat/8 2336823 2335688 420.5MB/s xls (41.23 %) +0.0% + BM_ZFlat/9 701804 681153 212.9MB/s txt1 (57.87 %) +3.0% + BM_ZFlat/10 606700 597194 199.9MB/s txt2 (61.93 %) +1.6% + BM_ZFlat/11 1852283 1803238 225.7MB/s txt3 (54.92 %) +2.7% + BM_ZFlat/12 2475527 2443354 188.1MB/s txt4 (66.22 %) +1.3% + BM_ZFlat/13 694497 696654 702.6MB/s bin (18.11 %) -0.3% + BM_ZFlat/14 136929 129855 280.8MB/s sum (48.96 %) +5.4% + BM_ZFlat/15 17172 17124 235.4MB/s man (59.36 %) +0.3% + BM_ZFlat/16 190364 171763 658.4MB/s pb (19.64 %) +10.8% + BM_ZFlat/17 567285 555190 316.6MB/s gaviota (37.72 %) +2.2% + BM_ZCord/0 193490 187031 522.1MB/s html +3.5% + BM_ZCord/1 2427537 2415315 277.2MB/s urls +0.5% + BM_ZCord/2 85378 81412 1.5GB/s jpg +4.9% + BM_ZCord/3 121898 119419 753.3MB/s pdf +2.1% + BM_ZCord/4 779564 762961 512.0MB/s html4 +2.2% + BM_ZDataBuffer/0 213820 207272 471.1MB/s html +3.2% + BM_ZDataBuffer/1 2589010 2586495 258.9MB/s urls +0.1% + BM_ZDataBuffer/2 121871 118885 1018.4MB/s jpg +2.5% + BM_ZDataBuffer/3 145382 145986 616.2MB/s pdf -0.4% + BM_ZDataBuffer/4 868117 852754 458.1MB/s html4 +1.8% + Sum of all benchmarks 33771833 33744763 +0.1% + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@71 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 81f34784b7b812dcda956ee489dfdc74ec2da990 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sun Jan 6 19:21:26 2013 +0000 + + Adjust the Snappy open-source distribution for the changes in Google's + internal file API. + + R=sanjay + + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@70 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 698af469b47fe809905e2ed173ad84241de5800f +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Jan 4 11:54:20 2013 +0000 + + Change a few ORs to additions where they don't matter. This helps the compiler + use the LEA instruction more efficiently, since e.g. a + (b << 2) can be encoded + as one instruction. Even more importantly, it can constant-fold the + COPY_* enums together with the shifted negative constants, which also saves + some instructions. (We don't need it for LITERAL, since it happens to be 0.) + + I am unsure why the compiler couldn't do this itself, but the theory is that + it cannot prove that len-1 and len-4 cannot underflow/wrap, and thus can't + do the optimization safely. + + The gains are small but measurable; 0.5-1.0% over the BM_Z* benchmarks + (measured on Westmere, Sandy Bridge and Istanbul). + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@69 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 55209f9b92efd97e0a61be28ed94210de04c3bfc +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon Oct 8 11:37:16 2012 +0000 + + Stop giving -Werror to automake, due to an incompatibility between current + versions of libtool and automake on non-GNU platforms (e.g. Mac OS X). + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@68 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit b86e81c8b3426a62d8ab3a7674c2506e9e678740 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Aug 17 13:54:47 2012 +0000 + + Fix public issue 66: Document GetUncompressedLength better, in particular that + it leaves the source in a state that's not appropriate for RawUncompress. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@67 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 2e225ba821b420ae28e1d427075d5589c1e892d9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Jul 31 11:44:44 2012 +0000 + + Fix public issue 64: Check for <sys/time.h> at configure time, + since MSVC seemingly does not have it. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@66 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit e89f20ab46ee11050760c6d57f05c2a3825a911c +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Jul 4 09:34:48 2012 +0000 + + Handle the case where gettimeofday() goes backwards or returns the same value + twice; it could cause division by zero in the unit test framework. + (We already had one fix for this in place, but it was incomplete.) + + This could in theory happen on any system, since there are few guarantees + about gettimeofday(), but seems to only happen in practice on GNU/Hurd, where + gettimeofday() is cached and only updated ever so often. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@65 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 3ec60ac9878de5d0317ad38fc545080a4bfaa74f +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Jul 4 09:28:33 2012 +0000 + + Mark ARMv4 as not supporting unaligned accesses (not just ARMv5 and ARMv6); + apparently Debian still targets these by default, giving us segfaults on + armel. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@64 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit be80d6f74f9d82220e952a54f3f129aae1f13f95 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue May 22 09:46:05 2012 +0000 + + Fix public bug #62: Remove an extraneous comma at the end of an enum list, + causing compile errors when embedded in Mozilla on OpenBSD. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@63 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 8b95464146dddab1c7068f879162db9a885cdafe +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue May 22 09:32:50 2012 +0000 + + Snappy library no longer depends on iostream. + + Achieved by moving logging macro definitions to a test-only + header file, and by changing non-test code to use assert, + fprintf, and abort instead of LOG/CHECK macros. + + R=sesse + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@62 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit fc723b212d6972af7051261754770b3f70a7dc03 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Feb 24 15:46:37 2012 +0000 + + Release Snappy 1.0.5. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@61 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit dc63e0ad9693e13390ba31b00d92ecccaf7605c3 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Feb 23 17:00:36 2012 +0000 + + For 32-bit platforms, do not try to accelerate multiple neighboring + 32-bit loads with a 64-bit load during compression (it's not a win). + + The main target for this optimization is ARM, but 32-bit x86 gets + a small gain, too, although there is noise in the microbenchmarks. + It's a no-op for 64-bit x86. It does not affect decompression. + + Microbenchmark results on a Cortex-A9 1GHz, using g++ 4.6.2 (from + Ubuntu/Linaro), -O2 -DNDEBUG -Wa,-march=armv7a -mtune=cortex-a9 + -mthumb-interwork, minimum 1000 iterations: + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_ZFlat/0 1158277 1160000 1000 84.2MB/s html (23.57 %) [ +4.3%] + BM_ZFlat/1 14861782 14860000 1000 45.1MB/s urls (50.89 %) [ +1.1%] + BM_ZFlat/2 393595 390000 1000 310.5MB/s jpg (99.88 %) [ +0.0%] + BM_ZFlat/3 650583 650000 1000 138.4MB/s pdf (82.13 %) [ +3.1%] + BM_ZFlat/4 4661480 4660000 1000 83.8MB/s html4 (23.55 %) [ +4.3%] + BM_ZFlat/5 491973 490000 1000 47.9MB/s cp (48.12 %) [ +2.0%] + BM_ZFlat/6 193575 192678 1038 55.2MB/s c (42.40 %) [ +9.0%] + BM_ZFlat/7 62343 62754 3187 56.5MB/s lsp (48.37 %) [ +2.6%] + BM_ZFlat/8 17708468 17710000 1000 55.5MB/s xls (41.34 %) [ -0.3%] + BM_ZFlat/9 3755345 3760000 1000 38.6MB/s txt1 (59.81 %) [ +8.2%] + BM_ZFlat/10 3324217 3320000 1000 36.0MB/s txt2 (64.07 %) [ +4.2%] + BM_ZFlat/11 10139932 10140000 1000 40.1MB/s txt3 (57.11 %) [ +6.4%] + BM_ZFlat/12 13532109 13530000 1000 34.0MB/s txt4 (68.35 %) [ +5.0%] + BM_ZFlat/13 4690847 4690000 1000 104.4MB/s bin (18.21 %) [ +4.1%] + BM_ZFlat/14 830682 830000 1000 43.9MB/s sum (51.88 %) [ +1.2%] + BM_ZFlat/15 84784 85011 2235 47.4MB/s man (59.36 %) [ +1.1%] + BM_ZFlat/16 1293254 1290000 1000 87.7MB/s pb (23.15 %) [ +2.3%] + BM_ZFlat/17 2775155 2780000 1000 63.2MB/s gaviota (38.27 %) [+12.2%] + + Core i7 in 32-bit mode (only one run and 100 iterations, though, so noisy): + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_ZFlat/0 227582 223464 3043 437.0MB/s html (23.57 %) [ +7.4%] + BM_ZFlat/1 2982430 2918455 233 229.4MB/s urls (50.89 %) [ +2.9%] + BM_ZFlat/2 46967 46658 15217 2.5GB/s jpg (99.88 %) [ +0.0%] + BM_ZFlat/3 115298 114864 5833 783.2MB/s pdf (82.13 %) [ +1.5%] + BM_ZFlat/4 913440 899743 778 434.2MB/s html4 (23.55 %) [ +0.3%] + BM_ZFlat/5 110302 108571 7000 216.1MB/s cp (48.12 %) [ +0.0%] + BM_ZFlat/6 44409 43372 15909 245.2MB/s c (42.40 %) [ +0.8%] + BM_ZFlat/7 15713 15643 46667 226.9MB/s lsp (48.37 %) [ +2.7%] + BM_ZFlat/8 2625539 2602230 269 377.4MB/s xls (41.34 %) [ +1.4%] + BM_ZFlat/9 808884 811429 875 178.8MB/s txt1 (59.81 %) [ -3.9%] + BM_ZFlat/10 709532 700000 1000 170.5MB/s txt2 (64.07 %) [ +0.0%] + BM_ZFlat/11 2177682 2162162 333 188.2MB/s txt3 (57.11 %) [ -1.4%] + BM_ZFlat/12 2849640 2840000 250 161.8MB/s txt4 (68.35 %) [ -1.4%] + BM_ZFlat/13 849760 835476 778 585.8MB/s bin (18.21 %) [ +1.2%] + BM_ZFlat/14 165940 164571 4375 221.6MB/s sum (51.88 %) [ +1.4%] + BM_ZFlat/15 20939 20571 35000 196.0MB/s man (59.36 %) [ +2.1%] + BM_ZFlat/16 239209 236544 2917 478.1MB/s pb (23.15 %) [ +4.2%] + BM_ZFlat/17 616206 610000 1000 288.2MB/s gaviota (38.27 %) [ -1.6%] + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@60 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f8829ea39d51432ba4e6a26ddaec57acea779f4c +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Feb 21 17:02:17 2012 +0000 + + Enable the use of unaligned loads and stores for ARM-based architectures + where they are available (ARMv7 and higher). This gives a significant + speed boost on ARM, both for compression and decompression. + It should not affect x86 at all. + + There are more changes possible to speed up ARM, but it might not be + that easy to do without hurting x86 or making the code uglier. + Also, we de not try to use NEON yet. + + Microbenchmark results on a Cortex-A9 1GHz, using g++ 4.6.2 (from Ubuntu/Linaro), + -O2 -DNDEBUG -Wa,-march=armv7a -mtune=cortex-a9 -mthumb-interwork: + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_UFlat/0 524806 529100 378 184.6MB/s html [+33.6%] + BM_UFlat/1 5139790 5200000 100 128.8MB/s urls [+28.8%] + BM_UFlat/2 86540 84166 1901 1.4GB/s jpg [ +0.6%] + BM_UFlat/3 215351 210176 904 428.0MB/s pdf [+29.8%] + BM_UFlat/4 2144490 2100000 100 186.0MB/s html4 [+33.3%] + BM_UFlat/5 194482 190000 1000 123.5MB/s cp [+36.2%] + BM_UFlat/6 91843 90175 2107 117.9MB/s c [+38.6%] + BM_UFlat/7 28535 28426 6684 124.8MB/s lsp [+34.7%] + BM_UFlat/8 9206600 9200000 100 106.7MB/s xls [+42.4%] + BM_UFlat/9 1865273 1886792 106 76.9MB/s txt1 [+32.5%] + BM_UFlat/10 1576809 1587301 126 75.2MB/s txt2 [+32.3%] + BM_UFlat/11 4968450 4900000 100 83.1MB/s txt3 [+32.7%] + BM_UFlat/12 6673970 6700000 100 68.6MB/s txt4 [+32.8%] + BM_UFlat/13 2391470 2400000 100 203.9MB/s bin [+29.2%] + BM_UFlat/14 334601 344827 522 105.8MB/s sum [+30.6%] + BM_UFlat/15 37404 38080 5252 105.9MB/s man [+33.8%] + BM_UFlat/16 535470 540540 370 209.2MB/s pb [+31.2%] + BM_UFlat/17 1875245 1886792 106 93.2MB/s gaviota [+37.8%] + BM_UValidate/0 178425 179533 1114 543.9MB/s html [ +2.7%] + BM_UValidate/1 2100450 2000000 100 334.8MB/s urls [ +5.0%] + BM_UValidate/2 1039 1044 172413 113.3GB/s jpg [ +3.4%] + BM_UValidate/3 59423 59470 3363 1.5GB/s pdf [ +7.8%] + BM_UValidate/4 760716 766283 261 509.8MB/s html4 [ +6.5%] + BM_ZFlat/0 1204632 1204819 166 81.1MB/s html (23.57 %) [+32.8%] + BM_ZFlat/1 15656190 15600000 100 42.9MB/s urls (50.89 %) [+27.6%] + BM_ZFlat/2 403336 410677 487 294.8MB/s jpg (99.88 %) [+16.5%] + BM_ZFlat/3 664073 671140 298 134.0MB/s pdf (82.13 %) [+28.4%] + BM_ZFlat/4 4961940 4900000 100 79.7MB/s html4 (23.55 %) [+30.6%] + BM_ZFlat/5 500664 501253 399 46.8MB/s cp (48.12 %) [+33.4%] + BM_ZFlat/6 217276 215982 926 49.2MB/s c (42.40 %) [+25.0%] + BM_ZFlat/7 64122 65487 3054 54.2MB/s lsp (48.37 %) [+36.1%] + BM_ZFlat/8 18045730 18000000 100 54.6MB/s xls (41.34 %) [+34.4%] + BM_ZFlat/9 4051530 4000000 100 36.3MB/s txt1 (59.81 %) [+25.0%] + BM_ZFlat/10 3451800 3500000 100 34.1MB/s txt2 (64.07 %) [+25.7%] + BM_ZFlat/11 11052340 11100000 100 36.7MB/s txt3 (57.11 %) [+24.3%] + BM_ZFlat/12 14538690 14600000 100 31.5MB/s txt4 (68.35 %) [+24.7%] + BM_ZFlat/13 5041850 5000000 100 97.9MB/s bin (18.21 %) [+32.0%] + BM_ZFlat/14 908840 909090 220 40.1MB/s sum (51.88 %) [+22.2%] + BM_ZFlat/15 86921 86206 1972 46.8MB/s man (59.36 %) [+42.2%] + BM_ZFlat/16 1312315 1315789 152 86.0MB/s pb (23.15 %) [+34.5%] + BM_ZFlat/17 3173120 3200000 100 54.9MB/s gaviota (38.27%) [+28.1%] + + + The move from 64-bit to 32-bit operations for the copies also affected 32-bit x86; + positive on the decompression side, and slightly negative on the compression side + (unless that is noise; I only ran once): + + Benchmark Time(ns) CPU(ns) Iterations + ----------------------------------------------------- + BM_UFlat/0 86279 86140 7778 1.1GB/s html [ +7.5%] + BM_UFlat/1 839265 822622 778 813.9MB/s urls [ +9.4%] + BM_UFlat/2 9180 9143 87500 12.9GB/s jpg [ +1.2%] + BM_UFlat/3 35080 35000 20000 2.5GB/s pdf [+10.1%] + BM_UFlat/4 350318 345000 2000 1.1GB/s html4 [ +7.0%] + BM_UFlat/5 33808 33472 21212 701.0MB/s cp [ +9.0%] + BM_UFlat/6 15201 15214 46667 698.9MB/s c [+14.9%] + BM_UFlat/7 4652 4651 159091 762.9MB/s lsp [ +7.5%] + BM_UFlat/8 1285551 1282528 538 765.7MB/s xls [+10.7%] + BM_UFlat/9 282510 281690 2414 514.9MB/s txt1 [+13.6%] + BM_UFlat/10 243494 239286 2800 498.9MB/s txt2 [+14.4%] + BM_UFlat/11 743625 740000 1000 550.0MB/s txt3 [+14.3%] + BM_UFlat/12 999441 989717 778 464.3MB/s txt4 [+16.1%] + BM_UFlat/13 412402 410076 1707 1.2GB/s bin [ +7.3%] + BM_UFlat/14 54876 54000 10000 675.3MB/s sum [+13.0%] + BM_UFlat/15 6146 6100 100000 660.8MB/s man [+14.8%] + BM_UFlat/16 90496 90286 8750 1.2GB/s pb [ +4.0%] + BM_UFlat/17 292650 292000 2500 602.0MB/s gaviota [+18.1%] + BM_UValidate/0 49620 49699 14286 1.9GB/s html [ +0.0%] + BM_UValidate/1 501371 500000 1000 1.3GB/s urls [ +0.0%] + BM_UValidate/2 232 227 3043478 521.5GB/s jpg [ +1.3%] + BM_UValidate/3 17250 17143 43750 5.1GB/s pdf [ -1.3%] + BM_UValidate/4 198643 200000 3500 1.9GB/s html4 [ -0.9%] + BM_ZFlat/0 227128 229415 3182 425.7MB/s html (23.57 %) [ -1.4%] + BM_ZFlat/1 2970089 2960000 250 226.2MB/s urls (50.89 %) [ -1.9%] + BM_ZFlat/2 45683 44999 15556 2.6GB/s jpg (99.88 %) [ +2.2%] + BM_ZFlat/3 114661 113136 6364 795.1MB/s pdf (82.13 %) [ -1.5%] + BM_ZFlat/4 919702 914286 875 427.2MB/s html4 (23.55%) [ -1.3%] + BM_ZFlat/5 108189 108422 6364 216.4MB/s cp (48.12 %) [ -1.2%] + BM_ZFlat/6 44525 44000 15909 241.7MB/s c (42.40 %) [ -2.9%] + BM_ZFlat/7 15973 15857 46667 223.8MB/s lsp (48.37 %) [ +0.0%] + BM_ZFlat/8 2677888 2639405 269 372.1MB/s xls (41.34 %) [ -1.4%] + BM_ZFlat/9 800715 780000 1000 186.0MB/s txt1 (59.81 %) [ -0.4%] + BM_ZFlat/10 700089 700000 1000 170.5MB/s txt2 (64.07 %) [ -2.9%] + BM_ZFlat/11 2159356 2138365 318 190.3MB/s txt3 (57.11 %) [ -0.3%] + BM_ZFlat/12 2796143 2779923 259 165.3MB/s txt4 (68.35 %) [ -1.4%] + BM_ZFlat/13 856458 835476 778 585.8MB/s bin (18.21 %) [ -0.1%] + BM_ZFlat/14 166908 166857 4375 218.6MB/s sum (51.88 %) [ -1.4%] + BM_ZFlat/15 21181 20857 35000 193.3MB/s man (59.36 %) [ -0.8%] + BM_ZFlat/16 244009 239973 2917 471.3MB/s pb (23.15 %) [ -1.4%] + BM_ZFlat/17 596362 590000 1000 297.9MB/s gaviota (38.27%) [ +0.0%] + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@59 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f2e184f638bdc7905f26c24faaf10fc0f5d33403 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sat Feb 11 22:11:22 2012 +0000 + + Lower the size allocated in the "corrupted input" unit test from 256 MB + to 2 MB. This fixes issues with running the unit test on platforms with + little RAM (e.g. some ARM boards). + + Also, reactivate the 2 MB test for 64-bit platforms; there's no good + reason why it shouldn't be. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@58 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit e750dc0f054ba74b0ce76dd2013e6728cc7a41c5 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sun Jan 8 17:55:48 2012 +0000 + + Minor refactoring to accomodate changes in Google's internal code tree. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@57 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit d9068ee301bdf893a4d8cb7c6518eacc44c4c1f2 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Jan 4 13:10:46 2012 +0000 + + Fix public issue r57: Fix most warnings with -Wall, mostly signed/unsigned + warnings. There are still some in the unit test, but the main .cc file should + be clean. We haven't enabled -Wall for the default build, since the unit test + is still not clean. + + This also fixes a real bug in the open-source implementation of + ReadFileToStringOrDie(); it would not detect errors correctly. + + I had to go through some pains to avoid performance loss as the types + were changed; I think there might still be some with 32-bit if and only if LFS + is enabled (ie., size_t is 64-bit), but for regular 32-bit and 64-bit I can't + see any losses, and I've diffed the generated GCC assembler between the old and + new code without seeing any significant choices. If anything, it's ever so + slightly faster. + + This may or may not enable compression of very large blocks (>2^32 bytes) + when size_t is 64-bit, but I haven't checked, and it is still not a supported + case. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@56 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 0755c815197dacc77d8971ae917c86d7aa96bf8e +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Jan 4 10:46:39 2012 +0000 + + Add a framing format description. We do not have any implementation of this at + the current point, but there seems to be enough of a general interest in the + topic (cf. public bug #34). + + R=csilvers,sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@55 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit d7eb2dc4133794b62cba691f9be40d1549bc32e2 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon Dec 5 21:27:26 2011 +0000 + + Speed up decompression by moving the refill check to the end of the loop. + + This seems to work because in most of the branches, the compiler can evaluate + “ip_limit_ - ip” in a more efficient way than reloading ip_limit_ from memory + (either by already having the entire expression in a register, or reconstructing + it from “avail”, or something else). Memory loads, even from L1, are seemingly + costly in the big picture at the current decompression speeds. + + Microbenchmarks (64-bit, opt mode): + + Westmere (Intel Core i7): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 74492 74491 187894 1.3GB/s html [ +5.9%] + BM_UFlat/1 712268 712263 19644 940.0MB/s urls [ +3.8%] + BM_UFlat/2 10591 10590 1000000 11.2GB/s jpg [ -6.8%] + BM_UFlat/3 29643 29643 469915 3.0GB/s pdf [ +7.9%] + BM_UFlat/4 304669 304667 45930 1.3GB/s html4 [ +4.8%] + BM_UFlat/5 28508 28507 490077 823.1MB/s cp [ +4.0%] + BM_UFlat/6 12415 12415 1000000 856.5MB/s c [ +8.6%] + BM_UFlat/7 3415 3415 4084723 1039.0MB/s lsp [+18.0%] + BM_UFlat/8 979569 979563 14261 1002.5MB/s xls [ +5.8%] + BM_UFlat/9 230150 230148 60934 630.2MB/s txt1 [ +5.2%] + BM_UFlat/10 197167 197166 71135 605.5MB/s txt2 [ +4.7%] + BM_UFlat/11 607394 607390 23041 670.1MB/s txt3 [ +5.6%] + BM_UFlat/12 808502 808496 17316 568.4MB/s txt4 [ +5.0%] + BM_UFlat/13 372791 372788 37564 1.3GB/s bin [ +3.3%] + BM_UFlat/14 44541 44541 313969 818.8MB/s sum [ +5.7%] + BM_UFlat/15 4833 4833 2898697 834.1MB/s man [ +4.8%] + BM_UFlat/16 79855 79855 175356 1.4GB/s pb [ +4.8%] + BM_UFlat/17 245845 245843 56838 715.0MB/s gaviota [ +5.8%] + + Clovertown (Intel Core 2): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 107911 107890 100000 905.1MB/s html [ +2.2%] + BM_UFlat/1 1011237 1011041 10000 662.3MB/s urls [ +2.5%] + BM_UFlat/2 26775 26770 523089 4.4GB/s jpg [ +0.0%] + BM_UFlat/3 48103 48095 290618 1.8GB/s pdf [ +3.4%] + BM_UFlat/4 437724 437644 31937 892.6MB/s html4 [ +2.1%] + BM_UFlat/5 39607 39600 358284 592.5MB/s cp [ +2.4%] + BM_UFlat/6 18227 18224 768191 583.5MB/s c [ +2.7%] + BM_UFlat/7 5171 5170 2709437 686.4MB/s lsp [ +3.9%] + BM_UFlat/8 1560291 1559989 8970 629.5MB/s xls [ +3.6%] + BM_UFlat/9 335401 335343 41731 432.5MB/s txt1 [ +3.0%] + BM_UFlat/10 287014 286963 48758 416.0MB/s txt2 [ +2.8%] + BM_UFlat/11 888522 888356 15752 458.1MB/s txt3 [ +2.9%] + BM_UFlat/12 1186600 1186378 10000 387.3MB/s txt4 [ +3.1%] + BM_UFlat/13 572295 572188 24468 855.4MB/s bin [ +2.1%] + BM_UFlat/14 64060 64049 218401 569.4MB/s sum [ +4.1%] + BM_UFlat/15 7264 7263 1916168 555.0MB/s man [ +1.4%] + BM_UFlat/16 108853 108836 100000 1039.1MB/s pb [ +1.7%] + BM_UFlat/17 364289 364223 38419 482.6MB/s gaviota [ +4.9%] + + Barcelona (AMD Opteron): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 103900 103871 100000 940.2MB/s html [ +8.3%] + BM_UFlat/1 1000435 1000107 10000 669.5MB/s urls [ +6.6%] + BM_UFlat/2 24659 24652 567362 4.8GB/s jpg [ +0.1%] + BM_UFlat/3 48206 48193 291121 1.8GB/s pdf [ +5.0%] + BM_UFlat/4 421980 421850 33174 926.0MB/s html4 [ +7.3%] + BM_UFlat/5 40368 40357 346994 581.4MB/s cp [ +8.7%] + BM_UFlat/6 19836 19830 708695 536.2MB/s c [ +8.0%] + BM_UFlat/7 6100 6098 2292774 581.9MB/s lsp [ +9.0%] + BM_UFlat/8 1693093 1692514 8261 580.2MB/s xls [ +8.0%] + BM_UFlat/9 365991 365886 38225 396.4MB/s txt1 [ +7.1%] + BM_UFlat/10 311330 311238 44950 383.6MB/s txt2 [ +7.6%] + BM_UFlat/11 975037 974737 14376 417.5MB/s txt3 [ +6.9%] + BM_UFlat/12 1303558 1303175 10000 352.6MB/s txt4 [ +7.3%] + BM_UFlat/13 517448 517290 27144 946.2MB/s bin [ +5.5%] + BM_UFlat/14 66537 66518 210352 548.3MB/s sum [ +7.5%] + BM_UFlat/15 7976 7974 1760383 505.6MB/s man [ +5.6%] + BM_UFlat/16 103121 103092 100000 1097.0MB/s pb [ +8.7%] + BM_UFlat/17 391431 391314 35733 449.2MB/s gaviota [ +6.5%] + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@54 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 5ed51ce15fc4ff8d2f7235704eb6b0c3f762fb88 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Nov 23 11:14:17 2011 +0000 + + Speed up decompression by making the fast path for literals faster. + + We do the fast-path step as soon as possible; in fact, as soon as we know the + literal length. Since we usually hit the fast path, we can then skip the checks + for long literals and available input space (beyond what the fast path check + already does). + + Note that this changes the decompression Writer API; however, it does not + change the ABI, since writers are always templatized and as such never + cross compilation units. The new API is slightly more general, in that it + doesn't hard-code the value 16. Note that we also take care to check + for len <= 16 first, since the other two checks almost always succeed + (so we don't want to waste time checking for them until we have to). + + The improvements are most marked on Nehalem, but are generally positive + on other platforms as well. All microbenchmarks are 64-bit, opt. + + Clovertown (Core 2): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 110226 110224 100000 886.0MB/s html [ +1.5%] + BM_UFlat/1 1036523 1036508 10000 646.0MB/s urls [ -0.8%] + BM_UFlat/2 26775 26775 522570 4.4GB/s jpg [ +0.0%] + BM_UFlat/3 49738 49737 280974 1.8GB/s pdf [ +0.3%] + BM_UFlat/4 446790 446792 31334 874.3MB/s html4 [ +0.8%] + BM_UFlat/5 40561 40562 350424 578.5MB/s cp [ +1.3%] + BM_UFlat/6 18722 18722 746903 568.0MB/s c [ +1.4%] + BM_UFlat/7 5373 5373 2608632 660.5MB/s lsp [ +8.3%] + BM_UFlat/8 1615716 1615718 8670 607.8MB/s xls [ +2.0%] + BM_UFlat/9 345278 345281 40481 420.1MB/s txt1 [ +1.4%] + BM_UFlat/10 294855 294855 47452 404.9MB/s txt2 [ +1.6%] + BM_UFlat/11 914263 914263 15316 445.2MB/s txt3 [ +1.1%] + BM_UFlat/12 1222694 1222691 10000 375.8MB/s txt4 [ +1.4%] + BM_UFlat/13 584495 584489 23954 837.4MB/s bin [ -0.6%] + BM_UFlat/14 66662 66662 210123 547.1MB/s sum [ +1.2%] + BM_UFlat/15 7368 7368 1881856 547.1MB/s man [ +4.0%] + BM_UFlat/16 110727 110726 100000 1021.4MB/s pb [ +2.3%] + BM_UFlat/17 382138 382141 36616 460.0MB/s gaviota [ -0.7%] + + Westmere (Core i7): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 78861 78853 177703 1.2GB/s html [ +2.1%] + BM_UFlat/1 739560 739491 18912 905.4MB/s urls [ +3.4%] + BM_UFlat/2 9867 9866 1419014 12.0GB/s jpg [ +3.4%] + BM_UFlat/3 31989 31986 438385 2.7GB/s pdf [ +0.2%] + BM_UFlat/4 319406 319380 43771 1.2GB/s html4 [ +1.9%] + BM_UFlat/5 29639 29636 472862 791.7MB/s cp [ +5.2%] + BM_UFlat/6 13478 13477 1000000 789.0MB/s c [ +2.3%] + BM_UFlat/7 4030 4029 3475364 880.7MB/s lsp [ +8.7%] + BM_UFlat/8 1036585 1036492 10000 947.5MB/s xls [ +6.9%] + BM_UFlat/9 242127 242105 57838 599.1MB/s txt1 [ +3.0%] + BM_UFlat/10 206499 206480 67595 578.2MB/s txt2 [ +3.4%] + BM_UFlat/11 641635 641570 21811 634.4MB/s txt3 [ +2.4%] + BM_UFlat/12 848847 848769 16443 541.4MB/s txt4 [ +3.1%] + BM_UFlat/13 384968 384938 36366 1.2GB/s bin [ +0.3%] + BM_UFlat/14 47106 47101 297770 774.3MB/s sum [ +4.4%] + BM_UFlat/15 5063 5063 2772202 796.2MB/s man [ +7.7%] + BM_UFlat/16 83663 83656 167697 1.3GB/s pb [ +1.8%] + BM_UFlat/17 260224 260198 53823 675.6MB/s gaviota [ -0.5%] + + Barcelona (Opteron): + + Benchmark Time(ns) CPU(ns) Iterations + -------------------------------------------- + BM_UFlat/0 112490 112457 100000 868.4MB/s html [ -0.4%] + BM_UFlat/1 1066719 1066339 10000 627.9MB/s urls [ +1.0%] + BM_UFlat/2 24679 24672 563802 4.8GB/s jpg [ +0.7%] + BM_UFlat/3 50603 50589 277285 1.7GB/s pdf [ +2.6%] + BM_UFlat/4 452982 452849 30900 862.6MB/s html4 [ -0.2%] + BM_UFlat/5 43860 43848 319554 535.1MB/s cp [ +1.2%] + BM_UFlat/6 21419 21413 653573 496.6MB/s c [ +1.0%] + BM_UFlat/7 6646 6645 2105405 534.1MB/s lsp [ +0.3%] + BM_UFlat/8 1828487 1827886 7658 537.3MB/s xls [ +2.6%] + BM_UFlat/9 391824 391714 35708 370.3MB/s txt1 [ +2.2%] + BM_UFlat/10 334913 334816 41885 356.6MB/s txt2 [ +1.7%] + BM_UFlat/11 1042062 1041674 10000 390.7MB/s txt3 [ +1.1%] + BM_UFlat/12 1398902 1398456 10000 328.6MB/s txt4 [ +1.7%] + BM_UFlat/13 545706 545530 25669 897.2MB/s bin [ -0.4%] + BM_UFlat/14 71512 71505 196035 510.0MB/s sum [ +1.4%] + BM_UFlat/15 8422 8421 1665036 478.7MB/s man [ +2.6%] + BM_UFlat/16 112053 112048 100000 1009.3MB/s pb [ -0.4%] + BM_UFlat/17 416723 416713 33612 421.8MB/s gaviota [ -2.0%] + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@53 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 0c1b9c3904430f5b399bd057d76de4bc36b7a123 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Nov 8 14:46:39 2011 +0000 + + Fix public issue #53: Update the README to the API we actually open-sourced + with. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@52 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit b61134bc0a6a904b41522b4e5c9e80874c730cef +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Oct 5 12:27:12 2011 +0000 + + In the format description, use a clearer example to emphasize that varints are + stored in little-endian. Patch from Christian von Roques. + + R=csilvers + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@51 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 21a2e4f55758e759302cd84ad0f3580affcba7d9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Sep 15 19:34:06 2011 +0000 + + Release Snappy 1.0.4. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@50 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit e2e303286813c759c5b1cdb46dad63c494f0a061 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Sep 15 09:50:05 2011 +0000 + + Fix public issue #50: Include generic byteswap macros. + Also include Solaris 10 and FreeBSD versions. + + R=csilvers + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@49 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 593002da3c051f4721312869f816b41485bad3b7 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Aug 10 18:57:27 2011 +0000 + + Partially fix public issue 50: Remove an extra comma from the end of some + enum declarations, as it seems the Sun compiler does not like it. + + Based on patch by Travis Vitek. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@48 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f1063a5dc43891eed37f0586bfea57b84dddd756 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Aug 10 18:44:16 2011 +0000 + + Use the right #ifdef test for sys/mman.h. + + Based on patch by Travis Vitek. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@47 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 41c827a2fa9ce048202d941187f211180feadde4 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Aug 10 01:22:09 2011 +0000 + + Fix public issue #47: Small comment cleanups in the unit test. + + Originally based on a patch by Patrick Pelletier. + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@46 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 59aeffa6049b5c2a3a467e7602c1f93630b870e7 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Aug 10 01:14:43 2011 +0000 + + Fix public issue #46: Format description said "3-byte offset" + instead of "4-byte offset" for the longest copies. + + Also fix an inconsistency in the heading for section 2.2.3. + Both patches by Patrick Pelletier. + + R=csilvers + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@45 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 57e7cd72559cb022ef32856f2252a4c4585e562e +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Jun 28 11:40:25 2011 +0000 + + Fix public issue #44: Make the definition and declaration of CompressFragment + identical, even regarding cv-qualifiers. + + This is required to work around a bug in the Solaris Studio C++ compiler + (it does not properly disregard cv-qualifiers when doing name mangling). + + R=sanjay + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@44 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 13c4a449a8ea22139c9aa441e8024eebc9dbdf6e +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sat Jun 4 10:19:05 2011 +0000 + + Correct an inaccuracy in the Snappy format description. + (I stumbled into this when changing the way we decompress literals.) + + R=csilvers + + Revision created by MOE tool push_codebase. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@43 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f5406737403119e1483a71d2084d17728663a114 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Jun 3 20:53:06 2011 +0000 + + Speed up decompression by removing a fast-path attempt. + + Whenever we try to enter a copy fast-path, there is a certain cost in checking + that all the preconditions are in place, but it's normally offset by the fact + that we can usually take the cheaper path. However, in a certain path we've + already established that "avail < literal_length", which usually means that + either the available space is small, or the literal is big. Both will disqualify + us from taking the fast path, and thus we take the hit from the precondition + checking without gaining much from having a fast path. Thus, simply don't try + the fast path in this situation -- we're already on a slow path anyway + (one where we need to refill more data from the reader). + + I'm a bit surprised at how much this gained; it could be that this path is + more common than I thought, or that the simpler structure somehow makes the + compiler happier. I haven't looked at the assembler, but it's a win across + the board on both Core 2, Core i7 and Opteron, at least for the cases we + typically care about. The gains seem to be the largest on Core i7, though. + Results from my Core i7 workstation: + + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_UFlat/0 73337 73091 190996 1.3GB/s html [ +1.7%] + BM_UFlat/1 696379 693501 20173 965.5MB/s urls [ +2.7%] + BM_UFlat/2 9765 9734 1472135 12.1GB/s jpg [ +0.7%] + BM_UFlat/3 29720 29621 472973 3.0GB/s pdf [ +1.8%] + BM_UFlat/4 294636 293834 47782 1.3GB/s html4 [ +2.3%] + BM_UFlat/5 28399 28320 494700 828.5MB/s cp [ +3.5%] + BM_UFlat/6 12795 12760 1000000 833.3MB/s c [ +1.2%] + BM_UFlat/7 3984 3973 3526448 893.2MB/s lsp [ +5.7%] + BM_UFlat/8 991996 989322 14141 992.6MB/s xls [ +3.3%] + BM_UFlat/9 228620 227835 61404 636.6MB/s txt1 [ +4.0%] + BM_UFlat/10 197114 196494 72165 607.5MB/s txt2 [ +3.5%] + BM_UFlat/11 605240 603437 23217 674.4MB/s txt3 [ +3.7%] + BM_UFlat/12 804157 802016 17456 573.0MB/s txt4 [ +3.9%] + BM_UFlat/13 347860 346998 40346 1.4GB/s bin [ +1.2%] + BM_UFlat/14 44684 44559 315315 818.4MB/s sum [ +2.3%] + BM_UFlat/15 5120 5106 2739726 789.4MB/s man [ +3.3%] + BM_UFlat/16 76591 76355 183486 1.4GB/s pb [ +2.8%] + BM_UFlat/17 238564 237828 58824 739.1MB/s gaviota [ +1.6%] + BM_UValidate/0 42194 42060 333333 2.3GB/s html [ -0.1%] + BM_UValidate/1 433182 432005 32407 1.5GB/s urls [ -0.1%] + BM_UValidate/2 197 196 71428571 603.3GB/s jpg [ +0.5%] + BM_UValidate/3 14494 14462 972222 6.1GB/s pdf [ +0.5%] + BM_UValidate/4 168444 167836 83832 2.3GB/s html4 [ +0.1%] + + R=jeff + + Revision created by MOE tool push_codebase. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@42 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 197f3ee9f9397e98c9abf07f9da875fbcb725dba +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Jun 3 20:47:14 2011 +0000 + + Speed up decompression by not needing a lookup table for literal items. + + Looking up into and decoding the values from char_table has long shown up as a + hotspot in the decompressor. While it turns out that it's hard to make a more + efficient decoder for the copy ops, the literals are simple enough that we can + decode them without needing a table lookup. (This means that 1/4 of the table + is now unused, although that in itself doesn't buy us anything.) + + The gains are small, but definitely present; some tests win as much as 10%, + but 1-4% is more typical. These results are from Core i7, in 64-bit mode; + Core 2 and Opteron show similar results. (I've run with more iterations + than unusual to make sure the smaller gains don't drown entirely in noise.) + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_UFlat/0 74665 74428 182055 1.3GB/s html [ +3.1%] + BM_UFlat/1 714106 711997 19663 940.4MB/s urls [ +4.4%] + BM_UFlat/2 9820 9789 1427115 12.1GB/s jpg [ -1.2%] + BM_UFlat/3 30461 30380 465116 2.9GB/s pdf [ +0.8%] + BM_UFlat/4 301445 300568 46512 1.3GB/s html4 [ +2.2%] + BM_UFlat/5 29338 29263 479452 801.8MB/s cp [ +1.6%] + BM_UFlat/6 13004 12970 1000000 819.9MB/s c [ +2.1%] + BM_UFlat/7 4180 4168 3349282 851.4MB/s lsp [ +1.3%] + BM_UFlat/8 1026149 1024000 10000 959.0MB/s xls [+10.7%] + BM_UFlat/9 237441 236830 59072 612.4MB/s txt1 [ +0.3%] + BM_UFlat/10 203966 203298 69307 587.2MB/s txt2 [ +0.8%] + BM_UFlat/11 627230 625000 22400 651.2MB/s txt3 [ +0.7%] + BM_UFlat/12 836188 833979 16787 551.0MB/s txt4 [ +1.3%] + BM_UFlat/13 351904 350750 39886 1.4GB/s bin [ +3.8%] + BM_UFlat/14 45685 45562 308370 800.4MB/s sum [ +5.9%] + BM_UFlat/15 5286 5270 2656546 764.9MB/s man [ +1.5%] + BM_UFlat/16 78774 78544 178117 1.4GB/s pb [ +4.3%] + BM_UFlat/17 242270 241345 58091 728.3MB/s gaviota [ +1.2%] + BM_UValidate/0 42149 42000 333333 2.3GB/s html [ -3.0%] + BM_UValidate/1 432741 431303 32483 1.5GB/s urls [ +7.8%] + BM_UValidate/2 198 197 71428571 600.7GB/s jpg [+16.8%] + BM_UValidate/3 14560 14521 965517 6.1GB/s pdf [ -4.1%] + BM_UValidate/4 169065 168671 83832 2.3GB/s html4 [ -2.9%] + + R=jeff + + Revision created by MOE tool push_codebase. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@41 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 8efa2639e885ac467e7b11c662975c5844019fb9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Jun 2 22:57:41 2011 +0000 + + Release Snappy 1.0.3. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@40 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 2e12124bd87f39296709decc65195fa5bfced538 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Jun 2 18:06:54 2011 +0000 + + Remove an unneeded goto in the decompressor; it turns out that the + state of ip_ after decompression (or attempted decompresion) is + completely irrelevant, so we don't need the trailer. + + Performance is, as expected, mostly flat -- there's a curious ~3-5% + loss in the "lsp" test, but that test case is so short it is hard to say + anything definitive about why (most likely, it's some sort of + unrelated effect). + + R=jeff + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@39 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit c266bbf32103f8ed4a83e2272ed3d8828d5b8b34 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Jun 2 17:59:40 2011 +0000 + + Speed up decompression by caching ip_. + + It is seemingly hard for the compiler to understand that ip_, the current input + pointer into the compressed data stream, can not alias on anything else, and + thus using it directly will incur memory traffic as it cannot be kept in a + register. The code already knew about this and cached it into a local + variable, but since Step() only decoded one tag, it had to move ip_ back into + place between every tag. This seems to have cost us a significant amount of + performance, so changing Step() into a function that decodes as much as it can + before it saves ip_ back and returns. (Note that Step() was already inlined, + so it is not the manual inlining that buys the performance here.) + + The wins are about 3-6% for Core 2, 6-13% on Core i7 and 5-12% on Opteron + (for plain array-to-array decompression, in 64-bit opt mode). + + There is a tiny difference in the behavior here; if an invalid literal is + encountered (ie., the writer refuses the Append() operation), ip_ will now + point to the byte past the tag byte, instead of where the literal was + originally thought to end. However, we don't use ip_ for anything after + DecompressAllTags() has returned, so this should not change external behavior + in any way. + + Microbenchmark results for Core i7, 64-bit (Opteron results are similar): + + Benchmark Time(ns) CPU(ns) Iterations + --------------------------------------------------- + BM_UFlat/0 79134 79110 8835 1.2GB/s html [ +6.2%] + BM_UFlat/1 786126 786096 891 851.8MB/s urls [+10.0%] + BM_UFlat/2 9948 9948 69125 11.9GB/s jpg [ -1.3%] + BM_UFlat/3 31999 31998 21898 2.7GB/s pdf [ +6.5%] + BM_UFlat/4 318909 318829 2204 1.2GB/s html4 [ +6.5%] + BM_UFlat/5 31384 31390 22363 747.5MB/s cp [ +9.2%] + BM_UFlat/6 14037 14034 49858 757.7MB/s c [+10.6%] + BM_UFlat/7 4612 4612 151395 769.5MB/s lsp [ +9.5%] + BM_UFlat/8 1203174 1203007 582 816.3MB/s xls [+19.3%] + BM_UFlat/9 253869 253955 2757 571.1MB/s txt1 [+11.4%] + BM_UFlat/10 219292 219290 3194 544.4MB/s txt2 [+12.1%] + BM_UFlat/11 672135 672131 1000 605.5MB/s txt3 [+11.2%] + BM_UFlat/12 902512 902492 776 509.2MB/s txt4 [+12.5%] + BM_UFlat/13 372110 371998 1881 1.3GB/s bin [ +5.8%] + BM_UFlat/14 50407 50407 10000 723.5MB/s sum [+13.5%] + BM_UFlat/15 5699 5701 100000 707.2MB/s man [+12.4%] + BM_UFlat/16 83448 83424 8383 1.3GB/s pb [ +5.7%] + BM_UFlat/17 256958 256963 2723 684.1MB/s gaviota [ +7.9%] + BM_UValidate/0 42795 42796 16351 2.2GB/s html [+25.8%] + BM_UValidate/1 490672 490622 1427 1.3GB/s urls [+22.7%] + BM_UValidate/2 237 237 2950297 499.0GB/s jpg [+24.9%] + BM_UValidate/3 14610 14611 47901 6.0GB/s pdf [+26.8%] + BM_UValidate/4 171973 171990 4071 2.2GB/s html4 [+25.7%] + + + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@38 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit d0ee043bc50c62c5b5ff3da044f0b5567257407d +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue May 17 08:48:25 2011 +0000 + + Fix the numbering of the headlines in the Snappy format description. + + R=csilvers + DELTA=4 (0 added, 0 deleted, 4 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1906 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@37 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 6c7053871fbdb459c9c14287a138d7f82d6d84a1 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon May 16 08:59:18 2011 +0000 + + Fix public issue #32: Add compressed format documentation for Snappy. + This text is new, but an earlier version from Zeev Tarantov was used + as reference. + + R=csilvers + DELTA=112 (111 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1867 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@36 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit a1f9f9973d127992f341d442969c86fd9a0847c9 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon May 9 21:29:02 2011 +0000 + + Fix public issue #39: Pick out the median runs based on CPU time, + not real time. Also, use nth_element instead of sort, since we + only need one element. + + R=csilvers + DELTA=5 (3 added, 0 deleted, 2 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1799 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@35 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f7b105683c074cdf233740089e245e43f63e7e55 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon May 9 21:28:45 2011 +0000 + + Fix public issue #38: Make the microbenchmark framework handle + properly cases where gettimeofday() can stand return the same + result twice (as sometimes on GNU/Hurd) or go backwards + (as when the user adjusts the clock). We avoid a division-by-zero, + and put a lower bound on the number of iterations -- the same + amount as we use to calibrate. + + We should probably use CLOCK_MONOTONIC for platforms that support + it, to be robust against clock adjustments; we already use Windows' + monotonic timers. However, that's for a later changelist. + + R=csilvers + DELTA=7 (5 added, 0 deleted, 2 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1798 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@34 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit d8d481427a05b88cdb0810c29bf400153595c423 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue May 3 23:22:52 2011 +0000 + + Fix public issue #37: Only link snappy_unittest against -lz and other autodetected + libraries, not libsnappy.so (which doesn't need any such dependency). + + R=csilvers + DELTA=20 (14 added, 0 deleted, 6 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1710 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@33 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit bcecf195c0aeb2c98144d3d54b4d8d228774f50d +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue May 3 23:22:33 2011 +0000 + + Release Snappy 1.0.2, to get the license change and various other fixes into + a release. + + R=csilvers + DELTA=239 (236 added, 0 deleted, 3 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1709 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@32 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 84d9f642025cda672dda0d94a8008f094500aaa6 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Apr 26 12:34:55 2011 +0000 + + Fix public issue #30: Stop using gettimeofday() altogether on Win32, + as MSVC doesn't include it. Replace with QueryPerformanceCounter(), + which is monotonic and probably reasonably high-resolution. + (Some machines have traditionally had bugs in QPC, but they should + be relatively rare these days, and there's really no much better + alternative that I know of.) + + R=csilvers + DELTA=74 (55 added, 19 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1556 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@31 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 3d8e71df8d30f980d71d4c784ebfc5ff62d5b0cb +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Tue Apr 26 12:34:37 2011 +0000 + + Fix public issue #31: Don't reset PATH in autogen.sh; instead, do the trickery + we need for our own build system internally. + + R=csilvers + DELTA=16 (13 added, 1 deleted, 2 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1555 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@30 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 73987351de54c88e2fc3f5dcdeceb47708df3585 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Apr 15 22:55:56 2011 +0000 + + When including <windows.h>, define WIN32_LEAN_AND_MEAN first, + so we won't pull in macro definitions of things like min() and max(), + which can conflict with <algorithm>. + + R=csilvers + DELTA=1 (1 added, 0 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1485 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@29 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit fb7e0eade471a20b009720a84fea0af1552791d5 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon Apr 11 09:07:01 2011 +0000 + + Fix public issue #29: Write CPU timing code for Windows, based on GetProcessTimes() + instead of getursage(). + + I thought I'd already committed this patch, so that the 1.0.1 release already + would have a Windows-compatible snappy_unittest, but I'd seemingly deleted it + instead, so this is a reconstruction. + + R=csilvers + DELTA=43 (39 added, 3 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1295 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@28 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit c67fa0c755a329000da5546fff79089d62ac2f82 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Apr 8 09:51:53 2011 +0000 + + Include C bindings of Snappy, contributed by Martin Gieseking. + + I've made a few changes since Martin's version; mostly style nits, but also + a semantic change -- most functions that return bool in the C++ version now + return an enum, to better match typical C (and zlib) semantics. + + I've kept the copyright notice, since Martin is obviously the author here; + he has signed the contributor license agreement, though, so this should not + hinder Google's use in the future. + + We'll need to update the libtool version number to match the added interface, + but as of http://www.gnu.org/software/libtool/manual/html_node/Updating-version-info.html + I'm going to wait until public release. + + R=csilvers + DELTA=238 (233 added, 0 deleted, 5 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1294 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@27 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 56be85cb9ae06f2e92180ae2575bdd10c012ab73 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Apr 7 16:36:43 2011 +0000 + + Replace geo.protodata with a newer version. + + The data compresses/decompresses slightly faster than the old data, and has + similar density. + + R=lookingbill + DELTA=1 (0 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1288 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@26 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 3dd93f3ec74df54a37f68bffabb058ac757bbe72 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 30 20:27:53 2011 +0000 + + Fix public issue #27: Add HAVE_CONFIG_H tests around the config.h + inclusion in snappy-stubs-internal.h, which eases compiling outside the + automake/autoconf framework. + + R=csilvers + DELTA=5 (4 added, 1 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1152 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@25 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f67bcaa61006da8b325a7ed9909a782590971815 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 30 20:27:39 2011 +0000 + + Fix public issue #26: Take memory allocation and reallocation entirely out of the + Measure() loop. This gives all algorithms a small speed boost, except Snappy which + already didn't do reallocation (so the measurements were slightly biased in its + favor). + + R=csilvers + DELTA=92 (69 added, 9 deleted, 14 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1151 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@24 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit cc333c1c5cc4eabceceb9848ff3cac6c604ecbc6 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 30 20:25:09 2011 +0000 + + Renamed "namespace zippy" to "namespace snappy" to reduce + the differences from the opensource code. Will make it easier + in the future to mix-and-match third-party code that uses + snappy with google code. + + Currently, csearch shows that the only external user of + "namespace zippy" is some bigtable code that accesses + a TEST variable, which is temporarily kept in the zippy + namespace. + + R=sesse + DELTA=123 (18 added, 3 deleted, 102 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1150 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@23 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit f19fb07e6dc79d6857e37df572dba25ff30fc8f3 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Mon Mar 28 22:17:04 2011 +0000 + + Put back the final few lines of what was truncated during the + license header change. + + R=csilvers + DELTA=5 (4 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1094 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@22 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 7e8ca8f8315fc2ecb4eea19db695039ab2ca43a0 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Sat Mar 26 02:34:34 2011 +0000 + + Change on 2011-03-25 19:18:00-07:00 by sesse + + Replace the Apache 2.0 license header by the BSD-type license header; + somehow a lot of the files were missed in the last round. + + R=dannyb,csilvers + DELTA=147 (74 added, 2 deleted, 71 changed) + + Change on 2011-03-25 19:25:07-07:00 by sesse + + Unbreak the build; the relicensing removed a bit too much (only comments + were intended, but I also accidentially removed some of the top lines of + the actual source). + + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1072 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@21 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit b4bbc1041b35d844ec26fbae25f2864995361fd8 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Mar 25 16:14:41 2011 +0000 + + Change Snappy from the Apache 2.0 to a BSD-type license. + + R=dannyb + DELTA=328 (80 added, 184 deleted, 64 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1061 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@20 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit c47640c510eb11cf8913edfa34f667bceb3a4401 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Mar 25 00:39:01 2011 +0000 + + Release Snappy 1.0.1, to soup up all the various small changes + that have been made since release. + + R=csilvers + DELTA=266 (260 added, 0 deleted, 6 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1057 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@19 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit b1dc1f643eaff897a5ce135f525799b99687b118 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Mar 24 19:15:54 2011 +0000 + + Fix a microbenchmark crash on mingw32; seemingly %lld is not universally + supported on Windows, and %I64d is recommended instead. + + R=csilvers + DELTA=6 (5 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1034 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@18 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 98004ca9afc62a3279dfe9d9a359083f61db437f +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Mar 24 19:15:27 2011 +0000 + + Fix public issue #19: Fix unit test when Google Test is installed but the + gflags package isn't (Google Test is not properly initialized). + + Patch by Martin Gieseking. + + R=csilvers + DELTA=2 (1 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1033 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@17 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 444a6c5f72d6f8d8f7213a5bcc08b26606eb9934 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Mar 24 19:13:57 2011 +0000 + + Make the unit test work on systems without mmap(). This is required for, + among others, Windows support. For Windows in specific, we could have used + CreateFileMapping/MapViewOfFile, but this should at least get us a bit closer + to compiling, and is of course also relevant for embedded systems with no MMU. + + (Part 2/2) + + R=csilvers + DELTA=15 (12 added, 3 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1032 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@16 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 2e182e9bb840737f9cd8817e859dc17a82f2c16b +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Thu Mar 24 19:12:27 2011 +0000 + + Make the unit test work on systems without mmap(). This is required for, + among others, Windows support. For Windows in specific, we could have used + CreateFileMapping/MapViewOfFile, but this should at least get us a bit closer + to compiling, and is of course also relevant for embedded systems with no MMU. + + (Part 1/2) + + R=csilvers + DELTA=9 (8 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1031 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@15 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 48662cbb7f81533977334629790d346220084527 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 23:17:36 2011 +0000 + + Fix public issue #12: Don't keep autogenerated auto* files in Subversion; + it causes problems with others sending patches etc.. + + We can't get this 100% hermetic anyhow, due to files like lt~obsolete.m4, + so we can just as well go cleanly in the other direction. + + R=csilvers + DELTA=21038 (0 added, 21036 deleted, 2 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=1012 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@14 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 9e4717a586149c9538b353400312bab5ab5458c4 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 17:50:49 2011 +0000 + + Fix public issue tracker bug #3: Call AC_SUBST([LIBTOOL_DEPS]), or the rule + to rebuild libtool in Makefile.am won't work. + + R=csilvers + DELTA=1 (1 added, 0 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=997 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@13 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 519c822a34a91a0c0eb32d98e9686ee7d9cd6651 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:16:39 2011 +0000 + + Fix public issue #10: Don't add GTEST_CPPFLAGS to snappy_unittest_CXXFLAGS; + it's not needed (CPPFLAGS are always included when compiling). + + R=csilvers + DELTA=1 (0 added, 1 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=994 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@12 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit ea6b936378583cba730c33c8a53776edc1782208 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:16:18 2011 +0000 + + Fix public issue #9: Add -Wall -Werror to automake flags. + (This concerns automake itself, not the C++ compiler.) + + R=csilvers + DELTA=4 (3 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=993 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@11 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit e3ca06af253094b1c3a8eae508cd97accf077535 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:13:37 2011 +0000 + + Fix a typo in the Snappy README file. + + R=csilvers + DELTA=1 (0 added, 0 deleted, 1 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=992 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@10 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 39d27bea23873abaa663e884261386b17b058f20 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:13:13 2011 +0000 + + Fix public issue #6: Add a --with-gflags for disabling gflags autodetection + and using a manually given setting (use/don't use) instead. + + R=csilvers + DELTA=16 (13 added, 0 deleted, 3 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=991 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@9 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 60add43d99c1c31aeecd895cb555ad6f6520608e +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:12:44 2011 +0000 + + Fix public issue #5: Replace the EXTRA_LIBSNAPPY_LDFLAGS setup with something + slightly more standard, that also doesn't leak libtool command-line into + configure.ac. + + R=csilvers + DELTA=7 (0 added, 4 deleted, 3 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=990 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@8 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit a8dd1700879ad646106742aa0e9c3a48dc07b01d +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:12:22 2011 +0000 + + Fix public issue #4: Properly quote all macro arguments in configure.ac. + + R=csilvers + DELTA=16 (0 added, 0 deleted, 16 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=989 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@7 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 79752dd7033658e28dc894de55012bdf2c9afca3 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:11:54 2011 +0000 + + Fix public issue #7: Don't use internal variables named ac_*, as those belong + to autoconf's namespace. + + R=csilvers + DELTA=6 (0 added, 0 deleted, 6 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=988 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@6 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 46e39fb20c297129494b969ac4ea64fcd04b4fa0 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:11:09 2011 +0000 + + Add missing licensing headers to a few files. (Part 2/2.) + + R=csilvers + DELTA=12 (12 added, 0 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=987 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@5 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 3e764216fc8edaafca480443b90e55c14eaae2c2 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:10:39 2011 +0000 + + Add mising licensing headers to a few files. (Part 1/2.) + + R=csilvers + DELTA=24 (24 added, 0 deleted, 0 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=986 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@4 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 9a59f183c8ffec62dcdabd3499d0d515e44e4ef0 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Wed Mar 23 11:10:04 2011 +0000 + + Use the correct license file for the Apache 2.0 license; + spotted by Florian Weimer. + + R=csilvers + DELTA=202 (174 added, 0 deleted, 28 changed) + + + Revision created by MOE tool push_codebase. + MOE_MIGRATION=985 + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@3 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 28a64402392c791905d6e1384ea1b48a5cb0b281 +Author: snappy.mirrorbot@gmail.com <snappy.mirrorbot@gmail.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Mar 18 17:14:15 2011 +0000 + + Revision created by MOE tool push_codebase. + MOE_MIGRATION= + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@2 03e5f5b5-db94-4691-08a0-1a8bf15f6143 + +commit 7c3c6077b72b4ae2237267a20f640b55e9a90569 +Author: sesse@google.com <sesse@google.com@03e5f5b5-db94-4691-08a0-1a8bf15f6143> +Date: Fri Mar 18 17:13:52 2011 +0000 + + Create trunk directory. + + + git-svn-id: https://snappy.googlecode.com/svn/trunk@1 03e5f5b5-db94-4691-08a0-1a8bf15f6143 diff --git a/src/third_party/snappy-1.1.3/INSTALL b/src/third_party/snappy-1.1.3/INSTALL new file mode 100644 index 00000000000..2099840756e --- /dev/null +++ b/src/third_party/snappy-1.1.3/INSTALL @@ -0,0 +1,370 @@ +Installation Instructions +************************* + +Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation, +Inc. + + Copying and distribution of this file, with or without modification, +are permitted in any medium without royalty provided the copyright +notice and this notice are preserved. This file is offered as-is, +without warranty of any kind. + +Basic Installation +================== + + Briefly, the shell command `./configure && make && make install' +should configure, build, and install this package. The following +more-detailed instructions are generic; see the `README' file for +instructions specific to this package. Some packages provide this +`INSTALL' file but do not implement all of the features documented +below. The lack of an optional feature in a given package is not +necessarily a bug. More recommendations for GNU packages can be found +in *note Makefile Conventions: (standards)Makefile Conventions. + + The `configure' shell script attempts to guess correct values for +various system-dependent variables used during compilation. It uses +those values to create a `Makefile' in each directory of the package. +It may also create one or more `.h' files containing system-dependent +definitions. Finally, it creates a shell script `config.status' that +you can run in the future to recreate the current configuration, and a +file `config.log' containing compiler output (useful mainly for +debugging `configure'). + + It can also use an optional file (typically called `config.cache' +and enabled with `--cache-file=config.cache' or simply `-C') that saves +the results of its tests to speed up reconfiguring. Caching is +disabled by default to prevent problems with accidental use of stale +cache files. + + If you need to do unusual things to compile the package, please try +to figure out how `configure' could check whether to do them, and mail +diffs or instructions to the address given in the `README' so they can +be considered for the next release. If you are using the cache, and at +some point `config.cache' contains results you don't want to keep, you +may remove or edit it. + + The file `configure.ac' (or `configure.in') is used to create +`configure' by a program called `autoconf'. You need `configure.ac' if +you want to change it or regenerate `configure' using a newer version +of `autoconf'. + + The simplest way to compile this package is: + + 1. `cd' to the directory containing the package's source code and type + `./configure' to configure the package for your system. + + Running `configure' might take a while. While running, it prints + some messages telling which features it is checking for. + + 2. Type `make' to compile the package. + + 3. Optionally, type `make check' to run any self-tests that come with + the package, generally using the just-built uninstalled binaries. + + 4. Type `make install' to install the programs and any data files and + documentation. When installing into a prefix owned by root, it is + recommended that the package be configured and built as a regular + user, and only the `make install' phase executed with root + privileges. + + 5. Optionally, type `make installcheck' to repeat any self-tests, but + this time using the binaries in their final installed location. + This target does not install anything. Running this target as a + regular user, particularly if the prior `make install' required + root privileges, verifies that the installation completed + correctly. + + 6. You can remove the program binaries and object files from the + source code directory by typing `make clean'. To also remove the + files that `configure' created (so you can compile the package for + a different kind of computer), type `make distclean'. There is + also a `make maintainer-clean' target, but that is intended mainly + for the package's developers. If you use it, you may have to get + all sorts of other programs in order to regenerate files that came + with the distribution. + + 7. Often, you can also type `make uninstall' to remove the installed + files again. In practice, not all packages have tested that + uninstallation works correctly, even though it is required by the + GNU Coding Standards. + + 8. Some packages, particularly those that use Automake, provide `make + distcheck', which can by used by developers to test that all other + targets like `make install' and `make uninstall' work correctly. + This target is generally not run by end users. + +Compilers and Options +===================== + + Some systems require unusual options for compilation or linking that +the `configure' script does not know about. Run `./configure --help' +for details on some of the pertinent environment variables. + + You can give `configure' initial values for configuration parameters +by setting variables in the command line or in the environment. Here +is an example: + + ./configure CC=c99 CFLAGS=-g LIBS=-lposix + + *Note Defining Variables::, for more details. + +Compiling For Multiple Architectures +==================================== + + You can compile the package for more than one kind of computer at the +same time, by placing the object files for each architecture in their +own directory. To do this, you can use GNU `make'. `cd' to the +directory where you want the object files and executables to go and run +the `configure' script. `configure' automatically checks for the +source code in the directory that `configure' is in and in `..'. This +is known as a "VPATH" build. + + With a non-GNU `make', it is safer to compile the package for one +architecture at a time in the source code directory. After you have +installed the package for one architecture, use `make distclean' before +reconfiguring for another architecture. + + On MacOS X 10.5 and later systems, you can create libraries and +executables that work on multiple system types--known as "fat" or +"universal" binaries--by specifying multiple `-arch' options to the +compiler but only a single `-arch' option to the preprocessor. Like +this: + + ./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ + CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ + CPP="gcc -E" CXXCPP="g++ -E" + + This is not guaranteed to produce working output in all cases, you +may have to build one architecture at a time and combine the results +using the `lipo' tool if you have problems. + +Installation Names +================== + + By default, `make install' installs the package's commands under +`/usr/local/bin', include files under `/usr/local/include', etc. You +can specify an installation prefix other than `/usr/local' by giving +`configure' the option `--prefix=PREFIX', where PREFIX must be an +absolute file name. + + You can specify separate installation prefixes for +architecture-specific files and architecture-independent files. If you +pass the option `--exec-prefix=PREFIX' to `configure', the package uses +PREFIX as the prefix for installing programs and libraries. +Documentation and other data files still use the regular prefix. + + In addition, if you use an unusual directory layout you can give +options like `--bindir=DIR' to specify different values for particular +kinds of files. Run `configure --help' for a list of the directories +you can set and what kinds of files go in them. In general, the +default for these options is expressed in terms of `${prefix}', so that +specifying just `--prefix' will affect all of the other directory +specifications that were not explicitly provided. + + The most portable way to affect installation locations is to pass the +correct locations to `configure'; however, many packages provide one or +both of the following shortcuts of passing variable assignments to the +`make install' command line to change installation locations without +having to reconfigure or recompile. + + The first method involves providing an override variable for each +affected directory. For example, `make install +prefix=/alternate/directory' will choose an alternate location for all +directory configuration variables that were expressed in terms of +`${prefix}'. Any directories that were specified during `configure', +but not in terms of `${prefix}', must each be overridden at install +time for the entire installation to be relocated. The approach of +makefile variable overrides for each directory variable is required by +the GNU Coding Standards, and ideally causes no recompilation. +However, some platforms have known limitations with the semantics of +shared libraries that end up requiring recompilation when using this +method, particularly noticeable in packages that use GNU Libtool. + + The second method involves providing the `DESTDIR' variable. For +example, `make install DESTDIR=/alternate/directory' will prepend +`/alternate/directory' before all installation names. The approach of +`DESTDIR' overrides is not required by the GNU Coding Standards, and +does not work on platforms that have drive letters. On the other hand, +it does better at avoiding recompilation issues, and works well even +when some directory options were not specified in terms of `${prefix}' +at `configure' time. + +Optional Features +================= + + If the package supports it, you can cause programs to be installed +with an extra prefix or suffix on their names by giving `configure' the +option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. + + Some packages pay attention to `--enable-FEATURE' options to +`configure', where FEATURE indicates an optional part of the package. +They may also pay attention to `--with-PACKAGE' options, where PACKAGE +is something like `gnu-as' or `x' (for the X Window System). The +`README' should mention any `--enable-' and `--with-' options that the +package recognizes. + + For packages that use the X Window System, `configure' can usually +find the X include and library files automatically, but if it doesn't, +you can use the `configure' options `--x-includes=DIR' and +`--x-libraries=DIR' to specify their locations. + + Some packages offer the ability to configure how verbose the +execution of `make' will be. For these packages, running `./configure +--enable-silent-rules' sets the default to minimal output, which can be +overridden with `make V=1'; while running `./configure +--disable-silent-rules' sets the default to verbose, which can be +overridden with `make V=0'. + +Particular systems +================== + + On HP-UX, the default C compiler is not ANSI C compatible. If GNU +CC is not installed, it is recommended to use the following options in +order to use an ANSI C compiler: + + ./configure CC="cc -Ae -D_XOPEN_SOURCE=500" + +and if that doesn't work, install pre-built binaries of GCC for HP-UX. + + HP-UX `make' updates targets which have the same time stamps as +their prerequisites, which makes it generally unusable when shipped +generated files such as `configure' are involved. Use GNU `make' +instead. + + On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot +parse its `<wchar.h>' header file. The option `-nodtk' can be used as +a workaround. If GNU CC is not installed, it is therefore recommended +to try + + ./configure CC="cc" + +and if that doesn't work, try + + ./configure CC="cc -nodtk" + + On Solaris, don't put `/usr/ucb' early in your `PATH'. This +directory contains several dysfunctional programs; working variants of +these programs are available in `/usr/bin'. So, if you need `/usr/ucb' +in your `PATH', put it _after_ `/usr/bin'. + + On Haiku, software installed for all users goes in `/boot/common', +not `/usr/local'. It is recommended to use the following options: + + ./configure --prefix=/boot/common + +Specifying the System Type +========================== + + There may be some features `configure' cannot figure out +automatically, but needs to determine by the type of machine the package +will run on. Usually, assuming the package is built to be run on the +_same_ architectures, `configure' can figure that out, but if it prints +a message saying it cannot guess the machine type, give it the +`--build=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name which has the form: + + CPU-COMPANY-SYSTEM + +where SYSTEM can have one of these forms: + + OS + KERNEL-OS + + See the file `config.sub' for the possible values of each field. If +`config.sub' isn't included in this package, then this package doesn't +need to know the machine type. + + If you are _building_ compiler tools for cross-compiling, you should +use the option `--target=TYPE' to select the type of system they will +produce code for. + + If you want to _use_ a cross compiler, that generates code for a +platform different from the build platform, you should specify the +"host" platform (i.e., that on which the generated programs will +eventually be run) with `--host=TYPE'. + +Sharing Defaults +================ + + If you want to set default values for `configure' scripts to share, +you can create a site shell script called `config.site' that gives +default values for variables like `CC', `cache_file', and `prefix'. +`configure' looks for `PREFIX/share/config.site' if it exists, then +`PREFIX/etc/config.site' if it exists. Or, you can set the +`CONFIG_SITE' environment variable to the location of the site script. +A warning: not all `configure' scripts look for a site script. + +Defining Variables +================== + + Variables not defined in a site shell script can be set in the +environment passed to `configure'. However, some packages may run +configure again during the build, and the customized values of these +variables may be lost. In order to avoid this problem, you should set +them in the `configure' command line, using `VAR=value'. For example: + + ./configure CC=/usr/local2/bin/gcc + +causes the specified `gcc' to be used as the C compiler (unless it is +overridden in the site shell script). + +Unfortunately, this technique does not work for `CONFIG_SHELL' due to +an Autoconf limitation. Until the limitation is lifted, you can use +this workaround: + + CONFIG_SHELL=/bin/bash ./configure CONFIG_SHELL=/bin/bash + +`configure' Invocation +====================== + + `configure' recognizes the following options to control how it +operates. + +`--help' +`-h' + Print a summary of all of the options to `configure', and exit. + +`--help=short' +`--help=recursive' + Print a summary of the options unique to this package's + `configure', and exit. The `short' variant lists options used + only in the top level, while the `recursive' variant lists options + also present in any nested packages. + +`--version' +`-V' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`--cache-file=FILE' + Enable the cache: use and save the results of the tests in FILE, + traditionally `config.cache'. FILE defaults to `/dev/null' to + disable caching. + +`--config-cache' +`-C' + Alias for `--cache-file=config.cache'. + +`--quiet' +`--silent' +`-q' + Do not print messages saying which checks are being made. To + suppress all normal output, redirect it to `/dev/null' (any error + messages will still be shown). + +`--srcdir=DIR' + Look for the package's source code in directory DIR. Usually + `configure' can determine that directory automatically. + +`--prefix=DIR' + Use DIR as the installation prefix. *note Installation Names:: + for more details, including other options available for fine-tuning + the installation locations. + +`--no-create' +`-n' + Run the configure checks, but stop before creating any output + files. + +`configure' also accepts some other, not widely useful, options. Run +`configure --help' for more details. diff --git a/src/third_party/snappy-1.1.7/NEWS b/src/third_party/snappy-1.1.3/NEWS index db70b448853..4eb7a1d1a92 100644 --- a/src/third_party/snappy-1.1.7/NEWS +++ b/src/third_party/snappy-1.1.3/NEWS @@ -1,43 +1,3 @@ -Snappy v1.1.7, August 24th 2017: - - * Improved CMake build support for 64-bit Linux distributions. - - * MSVC builds now use MSVC-specific intrinsics that map to clzll. - - * ARM64 (AArch64) builds use the code paths optimized for 64-bit processors. - -Snappy v1.1.6, July 12th 2017: - -This is a re-release of v1.1.5 with proper SONAME / SOVERSION values. - -Snappy v1.1.5, June 28th 2017: - -This release has broken SONAME / SOVERSION values. Users of snappy as a shared -library should avoid 1.1.5 and use 1.1.6 instead. SONAME / SOVERSION errors will -manifest as the dynamic library loader complaining that it cannot find snappy's -shared library file (libsnappy.so / libsnappy.dylib), or that the library it -found does not have the required version. 1.1.6 has the same code as 1.1.5, but -carries build configuration fixes for the issues above. - - * Add CMake build support. The autoconf build support is now deprecated, and - will be removed in the next release. - - * Add AppVeyor configuration, for Windows CI coverage. - - * Small performance improvement on little-endian PowerPC. - - * Small performance improvement on LLVM with position-independent executables. - - * Fix a few issues with various build environments. - -Snappy v1.1.4, January 25th 2017: - - * Fix a 1% performance regression when snappy is used in PIE executables. - - * Improve compression performance by 5%. - - * Improve decompression performance by 20%. - Snappy v1.1.3, July 6th 2015: This is the first release to be done from GitHub, which means that diff --git a/src/third_party/snappy-1.1.7/README.md b/src/third_party/snappy-1.1.3/README index b9db833dd5b..3bc8888f991 100644 --- a/src/third_party/snappy-1.1.7/README.md +++ b/src/third_party/snappy-1.1.3/README @@ -29,12 +29,12 @@ and the like. Performance =========== - + Snappy is intended to be fast. On a single core of a Core i7 processor in 64-bit mode, it compresses at about 250 MB/sec or more and decompresses at about 500 MB/sec or more. (These numbers are for the slowest inputs in our benchmark suite; others are much faster.) In our tests, Snappy usually -is faster than algorithms in the same class (e.g. LZO, LZF, QuickLZ, +is faster than algorithms in the same class (e.g. LZO, LZF, FastLZ, QuickLZ, etc.) while achieving comparable compression ratios. Typical compression ratios (based on the benchmark suite) are about 1.5-1.7x @@ -52,7 +52,7 @@ In particular: - Snappy uses 64-bit operations in several places to process more data at once than would otherwise be possible. - Snappy assumes unaligned 32- and 64-bit loads and stores are cheap. - On some platforms, these must be emulated with single-byte loads + On some platforms, these must be emulated with single-byte loads and stores, which is much slower. - Snappy assumes little-endian throughout, and needs to byte-swap data in several places if running on a big-endian platform. @@ -62,22 +62,12 @@ Performance optimizations, whether for 64-bit x86 or other platforms, are of course most welcome; see "Contact", below. -Building -======== - -CMake is supported and autotools will soon be deprecated. -You need CMake 3.4 or above to build: - - mkdir build - cd build && cmake ../ && make - - Usage ===== Note that Snappy, both the implementation and the main interface, is written in C++. However, several third-party bindings to other languages -are available; see the home page at http://google.github.io/snappy/ +are available; see the Google Code page at http://code.google.com/p/snappy/ for more information. Also, if you want to use Snappy from C code, you can use the included C bindings in snappy-c.h. @@ -112,12 +102,12 @@ tests to verify you have not broken anything. Note that if you have the Google Test library installed, unit test behavior (especially failures) will be significantly more user-friendly. You can find Google Test at - http://github.com/google/googletest + http://code.google.com/p/googletest/ You probably also want the gflags library for handling of command-line flags; you can find it at - http://gflags.github.io/gflags/ + http://code.google.com/p/google-gflags/ In addition to the unit tests, snappy contains microbenchmarks used to tune compression and decompression performance. These are automatically run @@ -126,7 +116,7 @@ before the unit tests, but you can disable them using the flag need to edit the source). Finally, snappy can benchmark Snappy against a few other compression libraries -(zlib, LZO, LZF, and QuickLZ), if they were detected at configure time. +(zlib, LZO, LZF, FastLZ and QuickLZ), if they were detected at configure time. To benchmark using a given file, give the compression algorithm you want to test Snappy against (e.g. --zlib) and then a list of one or more file names on the command line. The testdata/ directory contains the files used by the @@ -139,11 +129,7 @@ test.) Contact ======= -Snappy is distributed through GitHub. For the latest version, a bug tracker, +Snappy is distributed through Google Code. For the latest version, a bug tracker, and other information, see - http://google.github.io/snappy/ - -or the repository at - - https://github.com/google/snappy + http://code.google.com/p/snappy/ diff --git a/src/third_party/snappy-1.1.7/SConscript b/src/third_party/snappy-1.1.3/SConscript index 7bfacecd9ba..ce0e3cd628a 100644 --- a/src/third_party/snappy-1.1.7/SConscript +++ b/src/third_party/snappy-1.1.3/SConscript @@ -14,8 +14,6 @@ elif env.TargetOSIs('windows'): env.Append(CCFLAGS=['/wd4996']) # C4018: '<': signed/unsigned mismatch env.Append(CCFLAGS=['/wd4018']) - env.Append(CPPPATH=["build_windows"]) - env.Append( CPPDEFINES=[ "HAVE_CONFIG_H", ] ) elif not env.TargetOSIs('windows'): env.Append(CPPPATH=["build_posix"]) env.Append( CPPDEFINES=[ "HAVE_CONFIG_H", ] ) diff --git a/src/third_party/snappy-1.1.3/build_linux/config.h b/src/third_party/snappy-1.1.3/build_linux/config.h new file mode 100644 index 00000000000..aaa531067ed --- /dev/null +++ b/src/third_party/snappy-1.1.3/build_linux/config.h @@ -0,0 +1,135 @@ +/* config.h. Generated from config.h.in by configure. */ +/* config.h.in. Generated from configure.ac by autoheader. */ + +/* Define if building universal (internal helper macro) */ +/* #undef AC_APPLE_UNIVERSAL_BUILD */ + +/* Define to 1 if the compiler supports __builtin_ctz and friends. */ +#define HAVE_BUILTIN_CTZ 1 + +/* Define to 1 if the compiler supports __builtin_expect. */ +#define HAVE_BUILTIN_EXPECT 1 + +/* Define to 1 if you have the <byteswap.h> header file. */ +#define HAVE_BYTESWAP_H 1 + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#define HAVE_DLFCN_H 1 + +/* Use the gflags package for command-line parsing. */ +/* #undef HAVE_GFLAGS */ + +/* Defined when Google Test is available. */ +/* #undef HAVE_GTEST */ + +/* Define to 1 if you have the <inttypes.h> header file. */ +#define HAVE_INTTYPES_H 1 + +/* Define to 1 if you have the `fastlz' library (-lfastlz). */ +/* #undef HAVE_LIBFASTLZ */ + +/* Define to 1 if you have the `lzf' library (-llzf). */ +/* #undef HAVE_LIBLZF */ + +/* Define to 1 if you have the `lzo2' library (-llzo2). */ +/* #undef HAVE_LIBLZO2 */ + +/* Define to 1 if you have the `quicklz' library (-lquicklz). */ +/* #undef HAVE_LIBQUICKLZ */ + +/* Define to 1 if you have the `z' library (-lz). */ +#define HAVE_LIBZ 1 + +/* Define to 1 if you have the <memory.h> header file. */ +#define HAVE_MEMORY_H 1 + +/* Define to 1 if you have the <stddef.h> header file. */ +#define HAVE_STDDEF_H 1 + +/* Define to 1 if you have the <stdint.h> header file. */ +#define HAVE_STDINT_H 1 + +/* Define to 1 if you have the <stdlib.h> header file. */ +#define HAVE_STDLIB_H 1 + +/* Define to 1 if you have the <strings.h> header file. */ +#define HAVE_STRINGS_H 1 + +/* Define to 1 if you have the <string.h> header file. */ +#define HAVE_STRING_H 1 + +/* Define to 1 if you have the <sys/byteswap.h> header file. */ +/* #undef HAVE_SYS_BYTESWAP_H */ + +/* Define to 1 if you have the <sys/endian.h> header file. */ +/* #undef HAVE_SYS_ENDIAN_H */ + +/* Define to 1 if you have the <sys/mman.h> header file. */ +#define HAVE_SYS_MMAN_H 1 + +/* Define to 1 if you have the <sys/resource.h> header file. */ +#define HAVE_SYS_RESOURCE_H 1 + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#define HAVE_SYS_STAT_H 1 + +/* Define to 1 if you have the <sys/time.h> header file. */ +#define HAVE_SYS_TIME_H 1 + +/* Define to 1 if you have the <sys/types.h> header file. */ +#define HAVE_SYS_TYPES_H 1 + +/* Define to 1 if you have the <unistd.h> header file. */ +#define HAVE_UNISTD_H 1 + +/* Define to 1 if you have the <windows.h> header file. */ +/* #undef HAVE_WINDOWS_H */ + +/* Define to the sub-directory in which libtool stores uninstalled libraries. + */ +#define LT_OBJDIR ".libs/" + +/* Name of package */ +#define PACKAGE "snappy" + +/* Define to the address where bug reports for this package should be sent. */ +#define PACKAGE_BUGREPORT "" + +/* Define to the full name of this package. */ +#define PACKAGE_NAME "snappy" + +/* Define to the full name and version of this package. */ +#define PACKAGE_STRING "snappy 1.1.3" + +/* Define to the one symbol short name of this package. */ +#define PACKAGE_TARNAME "snappy" + +/* Define to the home page for this package. */ +#define PACKAGE_URL "" + +/* Define to the version of this package. */ +#define PACKAGE_VERSION "1.1.3" + +/* Define to 1 if you have the ANSI C header files. */ +#define STDC_HEADERS 1 + +/* Version number of package */ +#define VERSION "1.1.3" + +/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most + significant byte first (like Motorola and SPARC, unlike Intel). */ +#if defined AC_APPLE_UNIVERSAL_BUILD +# if defined __BIG_ENDIAN__ +# define WORDS_BIGENDIAN 1 +# endif +#else +# ifndef WORDS_BIGENDIAN +/* # undef WORDS_BIGENDIAN */ +# endif +#endif + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +/* #undef size_t */ + +/* Define to `int' if <sys/types.h> does not define. */ +/* #undef ssize_t */ diff --git a/src/third_party/snappy-1.1.3/build_posix/config.h b/src/third_party/snappy-1.1.3/build_posix/config.h new file mode 100644 index 00000000000..a9b39443d09 --- /dev/null +++ b/src/third_party/snappy-1.1.3/build_posix/config.h @@ -0,0 +1,135 @@ +/* config.h. Generated from config.h.in by configure. */ +/* config.h.in. Generated from configure.ac by autoheader. */ + +/* Define if building universal (internal helper macro) */ +/* #undef AC_APPLE_UNIVERSAL_BUILD */ + +/* Define to 1 if the compiler supports __builtin_ctz and friends. */ +#define HAVE_BUILTIN_CTZ 1 + +/* Define to 1 if the compiler supports __builtin_expect. */ +#define HAVE_BUILTIN_EXPECT 1 + +/* Define to 1 if you have the <byteswap.h> header file. */ +/* #undef HAVE_BYTESWAP_H */ + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#define HAVE_DLFCN_H 1 + +/* Use the gflags package for command-line parsing. */ +/* #undef HAVE_GFLAGS */ + +/* Defined when Google Test is available. */ +/* #undef HAVE_GTEST */ + +/* Define to 1 if you have the <inttypes.h> header file. */ +#define HAVE_INTTYPES_H 1 + +/* Define to 1 if you have the `fastlz' library (-lfastlz). */ +/* #undef HAVE_LIBFASTLZ */ + +/* Define to 1 if you have the `lzf' library (-llzf). */ +/* #undef HAVE_LIBLZF */ + +/* Define to 1 if you have the `lzo2' library (-llzo2). */ +/* #undef HAVE_LIBLZO2 */ + +/* Define to 1 if you have the `quicklz' library (-lquicklz). */ +/* #undef HAVE_LIBQUICKLZ */ + +/* Define to 1 if you have the `z' library (-lz). */ +#define HAVE_LIBZ 1 + +/* Define to 1 if you have the <memory.h> header file. */ +#define HAVE_MEMORY_H 1 + +/* Define to 1 if you have the <stddef.h> header file. */ +#define HAVE_STDDEF_H 1 + +/* Define to 1 if you have the <stdint.h> header file. */ +#define HAVE_STDINT_H 1 + +/* Define to 1 if you have the <stdlib.h> header file. */ +#define HAVE_STDLIB_H 1 + +/* Define to 1 if you have the <strings.h> header file. */ +#define HAVE_STRINGS_H 1 + +/* Define to 1 if you have the <string.h> header file. */ +#define HAVE_STRING_H 1 + +/* Define to 1 if you have the <sys/byteswap.h> header file. */ +/* #undef HAVE_SYS_BYTESWAP_H */ + +/* Define to 1 if you have the <sys/endian.h> header file. */ +/* #undef HAVE_SYS_ENDIAN_H */ + +/* Define to 1 if you have the <sys/mman.h> header file. */ +#define HAVE_SYS_MMAN_H 1 + +/* Define to 1 if you have the <sys/resource.h> header file. */ +#define HAVE_SYS_RESOURCE_H 1 + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#define HAVE_SYS_STAT_H 1 + +/* Define to 1 if you have the <sys/time.h> header file. */ +#define HAVE_SYS_TIME_H 1 + +/* Define to 1 if you have the <sys/types.h> header file. */ +#define HAVE_SYS_TYPES_H 1 + +/* Define to 1 if you have the <unistd.h> header file. */ +#define HAVE_UNISTD_H 1 + +/* Define to 1 if you have the <windows.h> header file. */ +/* #undef HAVE_WINDOWS_H */ + +/* Define to the sub-directory in which libtool stores uninstalled libraries. + */ +#define LT_OBJDIR ".libs/" + +/* Name of package */ +#define PACKAGE "snappy" + +/* Define to the address where bug reports for this package should be sent. */ +#define PACKAGE_BUGREPORT "" + +/* Define to the full name of this package. */ +#define PACKAGE_NAME "snappy" + +/* Define to the full name and version of this package. */ +#define PACKAGE_STRING "snappy 1.1.3" + +/* Define to the one symbol short name of this package. */ +#define PACKAGE_TARNAME "snappy" + +/* Define to the home page for this package. */ +#define PACKAGE_URL "" + +/* Define to the version of this package. */ +#define PACKAGE_VERSION "1.1.3" + +/* Define to 1 if you have the ANSI C header files. */ +#define STDC_HEADERS 1 + +/* Version number of package */ +#define VERSION "1.1.3" + +/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most + significant byte first (like Motorola and SPARC, unlike Intel). */ +#if defined AC_APPLE_UNIVERSAL_BUILD +# if defined __BIG_ENDIAN__ +# define WORDS_BIGENDIAN 1 +# endif +#else +# ifndef WORDS_BIGENDIAN +/* # undef WORDS_BIGENDIAN */ +# endif +#endif + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +/* #undef size_t */ + +/* Define to `int' if <sys/types.h> does not define. */ +/* #undef ssize_t */ diff --git a/src/third_party/snappy-1.1.7/format_description.txt b/src/third_party/snappy-1.1.3/format_description.txt index 20db66c1f26..20db66c1f26 100644 --- a/src/third_party/snappy-1.1.7/format_description.txt +++ b/src/third_party/snappy-1.1.3/format_description.txt diff --git a/src/third_party/snappy-1.1.7/framing_format.txt b/src/third_party/snappy-1.1.3/framing_format.txt index 9764e83de66..9764e83de66 100644 --- a/src/third_party/snappy-1.1.7/framing_format.txt +++ b/src/third_party/snappy-1.1.3/framing_format.txt diff --git a/src/third_party/snappy-1.1.7/snappy-c.cc b/src/third_party/snappy-1.1.3/snappy-c.cc index 473a0b09786..473a0b09786 100644 --- a/src/third_party/snappy-1.1.7/snappy-c.cc +++ b/src/third_party/snappy-1.1.3/snappy-c.cc diff --git a/src/third_party/snappy-1.1.7/snappy-c.h b/src/third_party/snappy-1.1.3/snappy-c.h index 32aa0c6b8b5..32aa0c6b8b5 100644 --- a/src/third_party/snappy-1.1.7/snappy-c.h +++ b/src/third_party/snappy-1.1.3/snappy-c.h diff --git a/src/third_party/snappy-1.1.3/snappy-internal.h b/src/third_party/snappy-1.1.3/snappy-internal.h new file mode 100644 index 00000000000..0caeb35a850 --- /dev/null +++ b/src/third_party/snappy-1.1.3/snappy-internal.h @@ -0,0 +1,150 @@ +// Copyright 2008 Google Inc. All Rights Reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Internals shared between the Snappy implementation and its unittest. + +#ifndef THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ +#define THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ + +#include "snappy-stubs-internal.h" + +namespace snappy { +namespace internal { + +class WorkingMemory { + public: + WorkingMemory() : large_table_(NULL) { } + ~WorkingMemory() { delete[] large_table_; } + + // Allocates and clears a hash table using memory in "*this", + // stores the number of buckets in "*table_size" and returns a pointer to + // the base of the hash table. + uint16* GetHashTable(size_t input_size, int* table_size); + + private: + uint16 small_table_[1<<14]; // 32KB + uint16* large_table_; // Allocated only when needed + + DISALLOW_COPY_AND_ASSIGN(WorkingMemory); +}; + +// Flat array compression that does not emit the "uncompressed length" +// prefix. Compresses "input" string to the "*op" buffer. +// +// REQUIRES: "input_length <= kBlockSize" +// REQUIRES: "op" points to an array of memory that is at least +// "MaxCompressedLength(input_length)" in size. +// REQUIRES: All elements in "table[0..table_size-1]" are initialized to zero. +// REQUIRES: "table_size" is a power of two +// +// Returns an "end" pointer into "op" buffer. +// "end - op" is the compressed size of "input". +char* CompressFragment(const char* input, + size_t input_length, + char* op, + uint16* table, + const int table_size); + +// Return the largest n such that +// +// s1[0,n-1] == s2[0,n-1] +// and n <= (s2_limit - s2). +// +// Does not read *s2_limit or beyond. +// Does not read *(s1 + (s2_limit - s2)) or beyond. +// Requires that s2_limit >= s2. +// +// Separate implementation for x86_64, for speed. Uses the fact that +// x86_64 is little endian. +#if defined(ARCH_K8) +static inline int FindMatchLength(const char* s1, + const char* s2, + const char* s2_limit) { + assert(s2_limit >= s2); + int matched = 0; + + // Find out how long the match is. We loop over the data 64 bits at a + // time until we find a 64-bit block that doesn't match; then we find + // the first non-matching bit and use that to calculate the total + // length of the match. + while (PREDICT_TRUE(s2 <= s2_limit - 8)) { + if (UNALIGNED_LOAD64(s2) == UNALIGNED_LOAD64(s1 + matched)) { + s2 += 8; + matched += 8; + } else { + // On current (mid-2008) Opteron models there is a 3% more + // efficient code sequence to find the first non-matching byte. + // However, what follows is ~10% better on Intel Core 2 and newer, + // and we expect AMD's bsf instruction to improve. + uint64 x = UNALIGNED_LOAD64(s2) ^ UNALIGNED_LOAD64(s1 + matched); + int matching_bits = Bits::FindLSBSetNonZero64(x); + matched += matching_bits >> 3; + return matched; + } + } + while (PREDICT_TRUE(s2 < s2_limit)) { + if (s1[matched] == *s2) { + ++s2; + ++matched; + } else { + return matched; + } + } + return matched; +} +#else +static inline int FindMatchLength(const char* s1, + const char* s2, + const char* s2_limit) { + // Implementation based on the x86-64 version, above. + assert(s2_limit >= s2); + int matched = 0; + + while (s2 <= s2_limit - 4 && + UNALIGNED_LOAD32(s2) == UNALIGNED_LOAD32(s1 + matched)) { + s2 += 4; + matched += 4; + } + if (LittleEndian::IsLittleEndian() && s2 <= s2_limit - 4) { + uint32 x = UNALIGNED_LOAD32(s2) ^ UNALIGNED_LOAD32(s1 + matched); + int matching_bits = Bits::FindLSBSetNonZero(x); + matched += matching_bits >> 3; + } else { + while ((s2 < s2_limit) && (s1[matched] == *s2)) { + ++s2; + ++matched; + } + } + return matched; +} +#endif + +} // end namespace internal +} // end namespace snappy + +#endif // THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ diff --git a/src/third_party/snappy-1.1.7/snappy-sinksource.cc b/src/third_party/snappy-1.1.3/snappy-sinksource.cc index 369a13215bc..369a13215bc 100644 --- a/src/third_party/snappy-1.1.7/snappy-sinksource.cc +++ b/src/third_party/snappy-1.1.3/snappy-sinksource.cc diff --git a/src/third_party/snappy-1.1.7/snappy-sinksource.h b/src/third_party/snappy-1.1.3/snappy-sinksource.h index 8afcdaaa2cc..8afcdaaa2cc 100644 --- a/src/third_party/snappy-1.1.7/snappy-sinksource.h +++ b/src/third_party/snappy-1.1.3/snappy-sinksource.h diff --git a/src/third_party/snappy-1.1.7/snappy-stubs-internal.cc b/src/third_party/snappy-1.1.3/snappy-stubs-internal.cc index 6ed334371f1..6ed334371f1 100644 --- a/src/third_party/snappy-1.1.7/snappy-stubs-internal.cc +++ b/src/third_party/snappy-1.1.3/snappy-stubs-internal.cc diff --git a/src/third_party/snappy-1.1.7/snappy-stubs-internal.h b/src/third_party/snappy-1.1.3/snappy-stubs-internal.h index cb605f82d0f..f81c8e35d32 100644 --- a/src/third_party/snappy-1.1.7/snappy-stubs-internal.h +++ b/src/third_party/snappy-1.1.3/snappy-stubs-internal.h @@ -45,14 +45,6 @@ #include <sys/mman.h> #endif -#ifdef HAVE_UNISTD_H -#include <unistd.h> -#endif - -#if defined(_MSC_VER) -#include <intrin.h> -#endif // defined(_MSC_VER) - #include "snappy-stubs-public.h" #if defined(__x86_64__) @@ -60,14 +52,6 @@ // Enable 64-bit optimized versions of some routines. #define ARCH_K8 1 -#elif defined(__ppc64__) - -#define ARCH_PPC 1 - -#elif defined(__aarch64__) - -#define ARCH_ARM 1 - #endif // Needed by OS X, among others. @@ -75,6 +59,10 @@ #define MAP_ANONYMOUS MAP_ANON #endif +// Pull in std::min, std::ostream, and the likes. This is safe because this +// header file is never used from any public header files. +using namespace std; + // The size of an array, if known at compile-time. // Will give unexpected results if used on a pointer. // We undefine it first, since some compilers already have a definition. @@ -85,11 +73,11 @@ // Static prediction hints. #ifdef HAVE_BUILTIN_EXPECT -#define SNAPPY_PREDICT_FALSE(x) (__builtin_expect(x, 0)) -#define SNAPPY_PREDICT_TRUE(x) (__builtin_expect(!!(x), 1)) +#define PREDICT_FALSE(x) (__builtin_expect(x, 0)) +#define PREDICT_TRUE(x) (__builtin_expect(!!(x), 1)) #else -#define SNAPPY_PREDICT_FALSE(x) x -#define SNAPPY_PREDICT_TRUE(x) x +#define PREDICT_FALSE(x) x +#define PREDICT_TRUE(x) x #endif // This is only used for recomputing the tag byte table used during @@ -108,10 +96,11 @@ static const int64 kint64max = static_cast<int64>(0x7FFFFFFFFFFFFFFFLL); // Potentially unaligned loads and stores. -// x86, PowerPC, and ARM64 can simply do these loads and stores native. +// x86 and PowerPC can simply do these loads and stores native. -#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__) || \ - defined(__aarch64__) +// MongoDB customization: Prefer memcpy on all architectures. Using reinterpret_cast is undefined +// behavior. +#if 0 && (defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)) #define UNALIGNED_LOAD16(_p) (*reinterpret_cast<const uint16 *>(_p)) #define UNALIGNED_LOAD32(_p) (*reinterpret_cast<const uint32 *>(_p)) @@ -129,17 +118,9 @@ static const int64 kint64max = static_cast<int64>(0x7FFFFFFFFFFFFFFFLL); // sub-architectures. // // This is a mess, but there's not much we can do about it. -// -// To further complicate matters, only LDR instructions (single reads) are -// allowed to be unaligned, not LDRD (two reads) or LDM (many reads). Unless we -// explicitly tell the compiler that these accesses can be unaligned, it can and -// will combine accesses. On armcc, the way to signal this is done by accessing -// through the type (uint32 __packed *), but GCC has no such attribute -// (it ignores __attribute__((packed)) on individual variables). However, -// we can tell it that a _struct_ is unaligned, which has the same effect, -// so we do that. - -#elif defined(__arm__) && \ + +// MongoDB customization: see memcpy notes above +#elif 0 && (defined(__arm__) && \ !defined(__ARM_ARCH_4__) && \ !defined(__ARM_ARCH_4T__) && \ !defined(__ARM_ARCH_5__) && \ @@ -151,41 +132,13 @@ static const int64 kint64max = static_cast<int64>(0x7FFFFFFFFFFFFFFFLL); !defined(__ARM_ARCH_6K__) && \ !defined(__ARM_ARCH_6Z__) && \ !defined(__ARM_ARCH_6ZK__) && \ - !defined(__ARM_ARCH_6T2__) + !defined(__ARM_ARCH_6T2__)) -#if __GNUC__ -#define ATTRIBUTE_PACKED __attribute__((__packed__)) -#else -#define ATTRIBUTE_PACKED -#endif - -namespace base { -namespace internal { - -struct Unaligned16Struct { - uint16 value; - uint8 dummy; // To make the size non-power-of-two. -} ATTRIBUTE_PACKED; - -struct Unaligned32Struct { - uint32 value; - uint8 dummy; // To make the size non-power-of-two. -} ATTRIBUTE_PACKED; - -} // namespace internal -} // namespace base - -#define UNALIGNED_LOAD16(_p) \ - ((reinterpret_cast<const ::snappy::base::internal::Unaligned16Struct *>(_p))->value) -#define UNALIGNED_LOAD32(_p) \ - ((reinterpret_cast<const ::snappy::base::internal::Unaligned32Struct *>(_p))->value) +#define UNALIGNED_LOAD16(_p) (*reinterpret_cast<const uint16 *>(_p)) +#define UNALIGNED_LOAD32(_p) (*reinterpret_cast<const uint32 *>(_p)) -#define UNALIGNED_STORE16(_p, _val) \ - ((reinterpret_cast< ::snappy::base::internal::Unaligned16Struct *>(_p))->value = \ - (_val)) -#define UNALIGNED_STORE32(_p, _val) \ - ((reinterpret_cast< ::snappy::base::internal::Unaligned32Struct *>(_p))->value = \ - (_val)) +#define UNALIGNED_STORE16(_p, _val) (*reinterpret_cast<uint16 *>(_p) = (_val)) +#define UNALIGNED_STORE32(_p, _val) (*reinterpret_cast<uint32 *>(_p) = (_val)) // TODO(user): NEON supports unaligned 64-bit loads and stores. // See if that would be more efficient on platforms supporting it, @@ -238,8 +191,22 @@ inline void UNALIGNED_STORE64(void *p, uint64 v) { #endif +// This can be more efficient than UNALIGNED_LOAD64 + UNALIGNED_STORE64 +// on some platforms, in particular ARM. +inline void UnalignedCopy64(const void *src, void *dst) { + if (sizeof(void *) == 8) { + UNALIGNED_STORE64(dst, UNALIGNED_LOAD64(src)); + } else { + const char *src_char = reinterpret_cast<const char *>(src); + char *dst_char = reinterpret_cast<char *>(dst); + + UNALIGNED_STORE32(dst_char, UNALIGNED_LOAD32(src_char)); + UNALIGNED_STORE32(dst_char + 4, UNALIGNED_LOAD32(src_char + 4)); + } +} + // The following guarantees declaration of the byte swap functions. -#if defined(SNAPPY_IS_BIG_ENDIAN) +#ifdef WORDS_BIGENDIAN #ifdef HAVE_SYS_BYTEORDER_H #include <sys/byteorder.h> @@ -296,7 +263,7 @@ inline uint64 bswap_64(uint64 x) { #endif -#endif // defined(SNAPPY_IS_BIG_ENDIAN) +#endif // WORDS_BIGENDIAN // Convert to little-endian storage, opposite of network format. // Convert x from host to little endian: x = LittleEndian.FromHost(x); @@ -310,7 +277,7 @@ inline uint64 bswap_64(uint64 x) { class LittleEndian { public: // Conversion functions. -#if defined(SNAPPY_IS_BIG_ENDIAN) +#ifdef WORDS_BIGENDIAN static uint16 FromHost16(uint16 x) { return bswap_16(x); } static uint16 ToHost16(uint16 x) { return bswap_16(x); } @@ -320,7 +287,7 @@ class LittleEndian { static bool IsLittleEndian() { return false; } -#else // !defined(SNAPPY_IS_BIG_ENDIAN) +#else // !defined(WORDS_BIGENDIAN) static uint16 FromHost16(uint16 x) { return x; } static uint16 ToHost16(uint16 x) { return x; } @@ -330,7 +297,7 @@ class LittleEndian { static bool IsLittleEndian() { return true; } -#endif // !defined(SNAPPY_IS_BIG_ENDIAN) +#endif // !defined(WORDS_BIGENDIAN) // Functions to do unaligned loads and stores in little-endian order. static uint16 Load16(const void *p) { @@ -360,15 +327,10 @@ class Bits { // undefined value if n == 0. FindLSBSetNonZero() is similar to ffs() except // that it's 0-indexed. static int FindLSBSetNonZero(uint32 n); - -#if defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) static int FindLSBSetNonZero64(uint64 n); -#endif // defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) private: - // No copying - Bits(const Bits&); - void operator=(const Bits&); + DISALLOW_COPY_AND_ASSIGN(Bits); }; #ifdef HAVE_BUILTIN_CTZ @@ -381,36 +343,9 @@ inline int Bits::FindLSBSetNonZero(uint32 n) { return __builtin_ctz(n); } -#if defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) inline int Bits::FindLSBSetNonZero64(uint64 n) { return __builtin_ctzll(n); } -#endif // defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) - -#elif defined(_MSC_VER) - -inline int Bits::Log2Floor(uint32 n) { - unsigned long where; - if (_BitScanReverse(&where, n)) { - return where; - } else { - return -1; - } -} - -inline int Bits::FindLSBSetNonZero(uint32 n) { - unsigned long where; - if (_BitScanForward(&where, n)) return static_cast<int>(where); - return 32; -} - -#if defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) -inline int Bits::FindLSBSetNonZero64(uint64 n) { - unsigned long where; - if (_BitScanForward64(&where, n)) return static_cast<int>(where); - return 64; -} -#endif // defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) #else // Portable versions. @@ -444,7 +379,6 @@ inline int Bits::FindLSBSetNonZero(uint32 n) { return rc; } -#if defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) // FindLSBSetNonZero64() is defined in terms of FindLSBSetNonZero(). inline int Bits::FindLSBSetNonZero64(uint64 n) { const uint32 bottombits = static_cast<uint32>(n); @@ -455,7 +389,6 @@ inline int Bits::FindLSBSetNonZero64(uint64 n) { return FindLSBSetNonZero(bottombits); } } -#endif // defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM) #endif // End portable versions. diff --git a/src/third_party/snappy-1.1.7/snappy-stubs-public.h b/src/third_party/snappy-1.1.3/snappy-stubs-public.h index 419c539fcf3..c156ba48e88 100644 --- a/src/third_party/snappy-1.1.7/snappy-stubs-public.h +++ b/src/third_party/snappy-1.1.3/snappy-stubs-public.h @@ -36,21 +36,21 @@ #ifndef THIRD_PARTY_SNAPPY_OPENSOURCE_SNAPPY_STUBS_PUBLIC_H_ #define THIRD_PARTY_SNAPPY_OPENSOURCE_SNAPPY_STUBS_PUBLIC_H_ -#if HAVE_STDINT_H // HAVE_STDINT_H +#if 1 #include <stdint.h> -#endif // HAVE_STDDEF_H +#endif -#if HAVE_STDDEF_H // HAVE_STDDEF_H +#if 1 #include <stddef.h> -#endif // HAVE_STDDEF_H +#endif -#if HAVE_SYS_UIO_H // HAVE_SYS_UIO_H +#if 0 #include <sys/uio.h> -#endif // HAVE_SYS_UIO_H +#endif -#define SNAPPY_MAJOR -#define SNAPPY_MINOR -#define SNAPPY_PATCHLEVEL +#define SNAPPY_MAJOR 1 +#define SNAPPY_MINOR 1 +#define SNAPPY_PATCHLEVEL 3 #define SNAPPY_VERSION \ ((SNAPPY_MAJOR << 16) | (SNAPPY_MINOR << 8) | SNAPPY_PATCHLEVEL) @@ -58,7 +58,7 @@ namespace snappy { -#if HAVE_STDINT_H // HAVE_STDINT_H +#if 1 typedef int8_t int8; typedef uint8_t uint8; typedef int16_t int16; @@ -76,18 +76,22 @@ typedef int int32; typedef unsigned int uint32; typedef long long int64; typedef unsigned long long uint64; -#endif // HAVE_STDINT_H +#endif typedef std::string string; -#if !HAVE_SYS_UIO_H // !HAVE_SYS_UIO_H +#define DISALLOW_COPY_AND_ASSIGN(TypeName) \ + TypeName(const TypeName&); \ + void operator=(const TypeName&) + +#if !0 // Windows does not have an iovec type, yet the concept is universally useful. // It is simple to define it ourselves, so we put it inside our own namespace. struct iovec { void* iov_base; size_t iov_len; }; -#endif // !HAVE_SYS_UIO_H +#endif } // namespace snappy diff --git a/src/third_party/snappy-1.1.7/snappy-stubs-public.h.in b/src/third_party/snappy-1.1.3/snappy-stubs-public.h.in index 3fd79bb157e..ebe676cc1d6 100644 --- a/src/third_party/snappy-1.1.7/snappy-stubs-public.h.in +++ b/src/third_party/snappy-1.1.3/snappy-stubs-public.h.in @@ -36,21 +36,21 @@ #ifndef THIRD_PARTY_SNAPPY_OPENSOURCE_SNAPPY_STUBS_PUBLIC_H_ #define THIRD_PARTY_SNAPPY_OPENSOURCE_SNAPPY_STUBS_PUBLIC_H_ -#if ${HAVE_STDINT_H_01} // HAVE_STDINT_H +#if @ac_cv_have_stdint_h@ #include <stdint.h> -#endif // HAVE_STDDEF_H +#endif -#if ${HAVE_STDDEF_H_01} // HAVE_STDDEF_H +#if @ac_cv_have_stddef_h@ #include <stddef.h> -#endif // HAVE_STDDEF_H +#endif -#if ${HAVE_SYS_UIO_H_01} // HAVE_SYS_UIO_H +#if @ac_cv_have_sys_uio_h@ #include <sys/uio.h> -#endif // HAVE_SYS_UIO_H +#endif -#define SNAPPY_MAJOR ${SNAPPY_MAJOR} -#define SNAPPY_MINOR ${SNAPPY_MINOR} -#define SNAPPY_PATCHLEVEL ${SNAPPY_PATCHLEVEL} +#define SNAPPY_MAJOR @SNAPPY_MAJOR@ +#define SNAPPY_MINOR @SNAPPY_MINOR@ +#define SNAPPY_PATCHLEVEL @SNAPPY_PATCHLEVEL@ #define SNAPPY_VERSION \ ((SNAPPY_MAJOR << 16) | (SNAPPY_MINOR << 8) | SNAPPY_PATCHLEVEL) @@ -58,7 +58,7 @@ namespace snappy { -#if ${HAVE_STDINT_H_01} // HAVE_STDINT_H +#if @ac_cv_have_stdint_h@ typedef int8_t int8; typedef uint8_t uint8; typedef int16_t int16; @@ -76,18 +76,22 @@ typedef int int32; typedef unsigned int uint32; typedef long long int64; typedef unsigned long long uint64; -#endif // HAVE_STDINT_H +#endif typedef std::string string; -#if !${HAVE_SYS_UIO_H_01} // !HAVE_SYS_UIO_H +#define DISALLOW_COPY_AND_ASSIGN(TypeName) \ + TypeName(const TypeName&); \ + void operator=(const TypeName&) + +#if !@ac_cv_have_sys_uio_h@ // Windows does not have an iovec type, yet the concept is universally useful. // It is simple to define it ourselves, so we put it inside our own namespace. struct iovec { void* iov_base; size_t iov_len; }; -#endif // !HAVE_SYS_UIO_H +#endif } // namespace snappy diff --git a/src/third_party/snappy-1.1.7/snappy-test.cc b/src/third_party/snappy-1.1.3/snappy-test.cc index 01d5541fd2c..7f1d0a8d1a7 100644 --- a/src/third_party/snappy-1.1.7/snappy-test.cc +++ b/src/third_party/snappy-1.1.3/snappy-test.cc @@ -33,9 +33,6 @@ #endif #ifdef HAVE_WINDOWS_H -// Needed to be able to use std::max without workarounds in the source code. -// https://support.microsoft.com/en-us/help/143208/prb-using-stl-in-windows-program-can-cause-min-max-conflicts -#define NOMINMAX #include <windows.h> #endif @@ -204,7 +201,7 @@ void Benchmark::Run() { if (benchmark_real_time_us > 0) { num_iterations = 200000 * kCalibrateIterations / benchmark_real_time_us; } - num_iterations = std::max(num_iterations, kCalibrateIterations); + num_iterations = max(num_iterations, kCalibrateIterations); BenchmarkRun benchmark_runs[kNumRuns]; for (int run = 0; run < kNumRuns; ++run) { @@ -220,10 +217,10 @@ void Benchmark::Run() { string heading = StringPrintf("%s/%d", name_.c_str(), test_case_num); string human_readable_speed; - std::nth_element(benchmark_runs, - benchmark_runs + kMedianPos, - benchmark_runs + kNumRuns, - BenchmarkCompareCPUTime()); + nth_element(benchmark_runs, + benchmark_runs + kMedianPos, + benchmark_runs + kNumRuns, + BenchmarkCompareCPUTime()); int64 real_time_us = benchmark_runs[kMedianPos].real_time_us; int64 cpu_time_us = benchmark_runs[kMedianPos].cpu_time_us; if (cpu_time_us <= 0) { @@ -526,8 +523,8 @@ int ZLib::UncompressAtMostOrAll(Bytef *dest, uLongf *destLen, LOG(WARNING) << "UncompressChunkOrAll: Received some extra data, bytes total: " << uncomp_stream_.avail_in << " bytes: " - << std::string(reinterpret_cast<const char *>(uncomp_stream_.next_in), - std::min(int(uncomp_stream_.avail_in), 20)); + << string(reinterpret_cast<const char *>(uncomp_stream_.next_in), + min(int(uncomp_stream_.avail_in), 20)); UncompressErrorInit(); return Z_DATA_ERROR; // what's the extra data for? } else if (err != Z_OK && err != Z_STREAM_END && err != Z_BUF_ERROR) { diff --git a/src/third_party/snappy-1.1.7/snappy-test.h b/src/third_party/snappy-1.1.3/snappy-test.h index 078f3211046..dbc55b9819d 100644 --- a/src/third_party/snappy-1.1.7/snappy-test.h +++ b/src/third_party/snappy-1.1.3/snappy-test.h @@ -110,8 +110,26 @@ #include "lzo/lzo1x.h" #endif +#ifdef HAVE_LIBLZF +extern "C" { +#include "lzf.h" +} +#endif + +#ifdef HAVE_LIBFASTLZ +#include "fastlz.h" +#endif + +#ifdef HAVE_LIBQUICKLZ +#include "quicklz.h" +#endif + namespace { +namespace File { + void Init() { } +} // namespace File + namespace file { int Defaults() { return 0; } @@ -120,8 +138,7 @@ namespace file { void CheckSuccess() { } }; - DummyStatus GetContents( - const std::string& filename, std::string* data, int unused) { + DummyStatus GetContents(const string& filename, string* data, int unused) { FILE* fp = fopen(filename.c_str(), "rb"); if (fp == NULL) { perror(filename.c_str()); @@ -136,7 +153,7 @@ namespace file { perror("fread"); exit(1); } - data->append(std::string(buf, ret)); + data->append(string(buf, ret)); } fclose(fp); @@ -144,8 +161,9 @@ namespace file { return DummyStatus(); } - inline DummyStatus SetContents( - const std::string& filename, const std::string& str, int unused) { + DummyStatus SetContents(const string& filename, + const string& str, + int unused) { FILE* fp = fopen(filename.c_str(), "wb"); if (fp == NULL) { perror(filename.c_str()); @@ -178,7 +196,6 @@ void Test_Snappy_RandomData(); void Test_Snappy_FourByteOffset(); void Test_SnappyCorruption_TruncatedVarint(); void Test_SnappyCorruption_UnterminatedVarint(); -void Test_SnappyCorruption_OverflowingVarint(); void Test_Snappy_ReadPastEndOfBuffer(); void Test_Snappy_FindMatchLength(); void Test_Snappy_FindMatchLengthRandom(); @@ -449,7 +466,7 @@ class ZLib { DECLARE_bool(run_microbenchmarks); -static inline void RunSpecifiedBenchmarks() { +static void RunSpecifiedBenchmarks() { if (!FLAGS_run_microbenchmarks) { return; } @@ -483,7 +500,6 @@ static inline int RUN_ALL_TESTS() { snappy::Test_Snappy_FourByteOffset(); snappy::Test_SnappyCorruption_TruncatedVarint(); snappy::Test_SnappyCorruption_UnterminatedVarint(); - snappy::Test_SnappyCorruption_OverflowingVarint(); snappy::Test_Snappy_ReadPastEndOfBuffer(); snappy::Test_Snappy_FindMatchLength(); snappy::Test_Snappy_FindMatchLengthRandom(); @@ -497,6 +513,10 @@ static inline int RUN_ALL_TESTS() { // For main(). namespace snappy { +static void CompressFile(const char* fname); +static void UncompressFile(const char* fname); +static void MeasureFile(const char* fname); + // Logging. #define LOG(level) LogMessage() @@ -507,15 +527,15 @@ class LogMessage { public: LogMessage() { } ~LogMessage() { - std::cerr << std::endl; + cerr << endl; } LogMessage& operator<<(const std::string& msg) { - std::cerr << msg; + cerr << msg; return *this; } LogMessage& operator<<(int x) { - std::cerr << x; + cerr << x; return *this; } }; @@ -524,7 +544,7 @@ class LogMessage { // and ones that are always active. #define CRASH_UNLESS(condition) \ - SNAPPY_PREDICT_TRUE(condition) ? (void)0 : \ + PREDICT_TRUE(condition) ? (void)0 : \ snappy::LogMessageVoidify() & snappy::LogMessageCrash() #ifdef _MSC_VER @@ -538,7 +558,7 @@ class LogMessageCrash : public LogMessage { public: LogMessageCrash() { } ~LogMessageCrash() { - std::cerr << std::endl; + cerr << endl; abort(); } }; @@ -568,6 +588,10 @@ class LogMessageVoidify { #define CHECK_GT(a, b) CRASH_UNLESS((a) > (b)) #define CHECK_OK(cond) (cond).CheckSuccess() -} // namespace snappy +} // namespace + +using snappy::CompressFile; +using snappy::UncompressFile; +using snappy::MeasureFile; #endif // THIRD_PARTY_SNAPPY_OPENSOURCE_SNAPPY_TEST_H_ diff --git a/src/third_party/snappy-1.1.7/snappy.cc b/src/third_party/snappy-1.1.3/snappy.cc index fd519e5a068..a50a4acd522 100644 --- a/src/third_party/snappy-1.1.7/snappy.cc +++ b/src/third_party/snappy-1.1.3/snappy.cc @@ -26,22 +26,13 @@ // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// MongoDB customization: includes basetsd.h under Windows where SSIZE_T is declared. +#include "mongo/platform/basic.h" + #include "snappy.h" #include "snappy-internal.h" #include "snappy-sinksource.h" -#ifndef SNAPPY_HAVE_SSE2 -#if defined(__SSE2__) || defined(_M_X64) || \ - (defined(_M_IX86_FP) && _M_IX86_FP >= 2) -#define SNAPPY_HAVE_SSE2 1 -#else -#define SNAPPY_HAVE_SSE2 0 -#endif -#endif - -#if SNAPPY_HAVE_SSE2 -#include <emmintrin.h> -#endif #include <stdio.h> #include <algorithm> @@ -49,13 +40,17 @@ #include <vector> -namespace snappy { +// Fixes missing ssize_t under Windows. +// Used in IncrementalCopy and IncrementalCopyFastPath. +// See: +// https://code.google.com/p/snappy/issues/detail?id=79 +// http://msdn.microsoft.com/en-us/library/windows/desktop/aa383751(v=vs.85).aspx#SSIZE_T +// http://src.chromium.org/viewvc/chrome/trunk/src/third_party/snappy/win32/snappy-stubs-public.h +#if defined(_WIN32) +typedef SSIZE_T ssize_t; +#endif // _WIN32 -using internal::COPY_1_BYTE_OFFSET; -using internal::COPY_2_BYTE_OFFSET; -using internal::LITERAL; -using internal::char_table; -using internal::kMaximumTagLength; +namespace snappy { // Any hash function will produce a valid compressed bitstream, but a good // hash function reduces the number of collisions and thus yields better @@ -94,129 +89,79 @@ size_t MaxCompressedLength(size_t source_len) { return 32 + source_len + source_len/6; } -namespace { - -void UnalignedCopy64(const void* src, void* dst) { - char tmp[8]; - memcpy(tmp, src, 8); - memcpy(dst, tmp, 8); -} - -void UnalignedCopy128(const void* src, void* dst) { - // TODO(alkis): Remove this when we upgrade to a recent compiler that emits - // SSE2 moves for memcpy(dst, src, 16). -#if SNAPPY_HAVE_SSE2 - __m128i x = _mm_loadu_si128(static_cast<const __m128i*>(src)); - _mm_storeu_si128(static_cast<__m128i*>(dst), x); -#else - char tmp[16]; - memcpy(tmp, src, 16); - memcpy(dst, tmp, 16); -#endif -} - -// Copy [src, src+(op_limit-op)) to [op, (op_limit-op)) a byte at a time. Used -// for handling COPY operations where the input and output regions may overlap. -// For example, suppose: -// src == "ab" -// op == src + 2 -// op_limit == op + 20 -// After IncrementalCopySlow(src, op, op_limit), the result will have eleven -// copies of "ab" +enum { + LITERAL = 0, + COPY_1_BYTE_OFFSET = 1, // 3 bit length + 3 bits of offset in opcode + COPY_2_BYTE_OFFSET = 2, + COPY_4_BYTE_OFFSET = 3 +}; +static const int kMaximumTagLength = 5; // COPY_4_BYTE_OFFSET plus the actual offset. + +// Copy "len" bytes from "src" to "op", one byte at a time. Used for +// handling COPY operations where the input and output regions may +// overlap. For example, suppose: +// src == "ab" +// op == src + 2 +// len == 20 +// After IncrementalCopy(src, op, len), the result will have +// eleven copies of "ab" // ababababababababababab -// Note that this does not match the semantics of either memcpy() or memmove(). -inline char* IncrementalCopySlow(const char* src, char* op, - char* const op_limit) { - while (op < op_limit) { +// Note that this does not match the semantics of either memcpy() +// or memmove(). +static inline void IncrementalCopy(const char* src, char* op, ssize_t len) { + assert(len > 0); + do { *op++ = *src++; - } - return op_limit; + } while (--len > 0); } -// Copy [src, src+(op_limit-op)) to [op, (op_limit-op)) but faster than -// IncrementalCopySlow. buf_limit is the address past the end of the writable -// region of the buffer. -inline char* IncrementalCopy(const char* src, char* op, char* const op_limit, - char* const buf_limit) { - // Terminology: - // - // slop = buf_limit - op - // pat = op - src - // len = limit - op - assert(src < op); - assert(op_limit <= buf_limit); - // NOTE: The compressor always emits 4 <= len <= 64. It is ok to assume that - // to optimize this function but we have to also handle these cases in case - // the input does not satisfy these conditions. - - size_t pattern_size = op - src; - // The cases are split into different branches to allow the branch predictor, - // FDO, and static prediction hints to work better. For each input we list the - // ratio of invocations that match each condition. - // - // input slop < 16 pat < 8 len > 16 - // ------------------------------------------ - // html|html4|cp 0% 1.01% 27.73% - // urls 0% 0.88% 14.79% - // jpg 0% 64.29% 7.14% - // pdf 0% 2.56% 58.06% - // txt[1-4] 0% 0.23% 0.97% - // pb 0% 0.96% 13.88% - // bin 0.01% 22.27% 41.17% - // - // It is very rare that we don't have enough slop for doing block copies. It - // is also rare that we need to expand a pattern. Small patterns are common - // for incompressible formats and for those we are plenty fast already. - // Lengths are normally not greater than 16 but they vary depending on the - // input. In general if we always predict len <= 16 it would be an ok - // prediction. - // - // In order to be fast we want a pattern >= 8 bytes and an unrolled loop - // copying 2x 8 bytes at a time. - - // Handle the uncommon case where pattern is less than 8 bytes. - if (SNAPPY_PREDICT_FALSE(pattern_size < 8)) { - // Expand pattern to at least 8 bytes. The worse case scenario in terms of - // buffer usage is when the pattern is size 3. ^ is the original position - // of op. x are irrelevant bytes copied by the last UnalignedCopy64. - // - // abc - // abcabcxxxxx - // abcabcabcabcxxxxx - // ^ - // The last x is 14 bytes after ^. - if (SNAPPY_PREDICT_TRUE(op <= buf_limit - 14)) { - while (pattern_size < 8) { - UnalignedCopy64(src, op); - op += pattern_size; - pattern_size *= 2; - } - if (SNAPPY_PREDICT_TRUE(op >= op_limit)) return op_limit; - } else { - return IncrementalCopySlow(src, op, op_limit); - } - } - assert(pattern_size >= 8); +// Equivalent to IncrementalCopy except that it can write up to ten extra +// bytes after the end of the copy, and that it is faster. +// +// The main part of this loop is a simple copy of eight bytes at a time until +// we've copied (at least) the requested amount of bytes. However, if op and +// src are less than eight bytes apart (indicating a repeating pattern of +// length < 8), we first need to expand the pattern in order to get the correct +// results. For instance, if the buffer looks like this, with the eight-byte +// <src> and <op> patterns marked as intervals: +// +// abxxxxxxxxxxxx +// [------] src +// [------] op +// +// a single eight-byte copy from <src> to <op> will repeat the pattern once, +// after which we can move <op> two bytes without moving <src>: +// +// ababxxxxxxxxxx +// [------] src +// [------] op +// +// and repeat the exercise until the two no longer overlap. +// +// This allows us to do very well in the special case of one single byte +// repeated many times, without taking a big hit for more general cases. +// +// The worst case of extra writing past the end of the match occurs when +// op - src == 1 and len == 1; the last copy will read from byte positions +// [0..7] and write to [4..11], whereas it was only supposed to write to +// position 1. Thus, ten excess bytes. + +namespace { + +const int kMaxIncrementCopyOverflow = 10; - // Copy 2x 8 bytes at a time. Because op - src can be < 16, a single - // UnalignedCopy128 might overwrite data in op. UnalignedCopy64 is safe - // because expanding the pattern to at least 8 bytes guarantees that - // op - src >= 8. - while (op <= buf_limit - 16) { +inline void IncrementalCopyFastPath(const char* src, char* op, ssize_t len) { + while (PREDICT_FALSE(op - src < 8)) { UnalignedCopy64(src, op); - UnalignedCopy64(src + 8, op + 8); - src += 16; - op += 16; - if (SNAPPY_PREDICT_TRUE(op >= op_limit)) return op_limit; - } - // We only take this branch if we didn't have enough slop and we can do a - // single 8 byte copy. - if (SNAPPY_PREDICT_FALSE(op <= buf_limit - 8)) { + len -= op - src; + op += op - src; + } + while (len > 0) { UnalignedCopy64(src, op); src += 8; op += 8; + len -= 8; } - return IncrementalCopySlow(src, op, op_limit); } } // namespace @@ -225,29 +170,26 @@ static inline char* EmitLiteral(char* op, const char* literal, int len, bool allow_fast_path) { - // The vast majority of copies are below 16 bytes, for which a - // call to memcpy is overkill. This fast path can sometimes - // copy up to 15 bytes too much, but that is okay in the - // main loop, since we have a bit to go on for both sides: - // - // - The input will always have kInputMarginBytes = 15 extra - // available bytes, as long as we're in the main loop, and - // if not, allow_fast_path = false. - // - The output will always have 32 spare bytes (see - // MaxCompressedLength). - assert(len > 0); // Zero-length literals are disallowed - int n = len - 1; - if (allow_fast_path && len <= 16) { - // Fits in tag byte - *op++ = LITERAL | (n << 2); - - UnalignedCopy128(literal, op); - return op + len; - } - + int n = len - 1; // Zero-length literals are disallowed if (n < 60) { // Fits in tag byte *op++ = LITERAL | (n << 2); + + // The vast majority of copies are below 16 bytes, for which a + // call to memcpy is overkill. This fast path can sometimes + // copy up to 15 bytes too much, but that is okay in the + // main loop, since we have a bit to go on for both sides: + // + // - The input will always have kInputMarginBytes = 15 extra + // available bytes, as long as we're in the main loop, and + // if not, allow_fast_path = false. + // - The output will always have 32 spare bytes (see + // MaxCompressedLength). + if (allow_fast_path && len <= 16) { + UnalignedCopy64(literal, op); + UnalignedCopy64(literal + 8, op + 8); + return op + len; + } } else { // Encode in upcoming bytes char* base = op; @@ -266,55 +208,43 @@ static inline char* EmitLiteral(char* op, return op + len; } -static inline char* EmitCopyAtMost64(char* op, size_t offset, size_t len, - bool len_less_than_12) { +static inline char* EmitCopyLessThan64(char* op, size_t offset, int len) { assert(len <= 64); assert(len >= 4); assert(offset < 65536); - assert(len_less_than_12 == (len < 12)); - if (len_less_than_12 && SNAPPY_PREDICT_TRUE(offset < 2048)) { - // offset fits in 11 bits. The 3 highest go in the top of the first byte, - // and the rest go in the second byte. - *op++ = COPY_1_BYTE_OFFSET + ((len - 4) << 2) + ((offset >> 3) & 0xe0); + if ((len < 12) && (offset < 2048)) { + size_t len_minus_4 = len - 4; + assert(len_minus_4 < 8); // Must fit in 3 bits + *op++ = COPY_1_BYTE_OFFSET + ((len_minus_4) << 2) + ((offset >> 8) << 5); *op++ = offset & 0xff; } else { - // Write 4 bytes, though we only care about 3 of them. The output buffer - // is required to have some slack, so the extra byte won't overrun it. - uint32 u = COPY_2_BYTE_OFFSET + ((len - 1) << 2) + (offset << 8); - LittleEndian::Store32(op, u); - op += 3; + *op++ = COPY_2_BYTE_OFFSET + ((len-1) << 2); + LittleEndian::Store16(op, offset); + op += 2; } return op; } -static inline char* EmitCopy(char* op, size_t offset, size_t len, - bool len_less_than_12) { - assert(len_less_than_12 == (len < 12)); - if (len_less_than_12) { - return EmitCopyAtMost64(op, offset, len, true); - } else { - // A special case for len <= 64 might help, but so far measurements suggest - // it's in the noise. - - // Emit 64 byte copies but make sure to keep at least four bytes reserved. - while (SNAPPY_PREDICT_FALSE(len >= 68)) { - op = EmitCopyAtMost64(op, offset, 64, false); - len -= 64; - } - - // One or two copies will now finish the job. - if (len > 64) { - op = EmitCopyAtMost64(op, offset, 60, false); - len -= 60; - } +static inline char* EmitCopy(char* op, size_t offset, int len) { + // Emit 64 byte copies but make sure to keep at least four bytes reserved + while (PREDICT_FALSE(len >= 68)) { + op = EmitCopyLessThan64(op, offset, 64); + len -= 64; + } - // Emit remainder. - op = EmitCopyAtMost64(op, offset, len, len < 12); - return op; + // Emit an extra 60 byte copy if have too much data to fit in one copy + if (len > 64) { + op = EmitCopyLessThan64(op, offset, 60); + len -= 60; } + + // Emit remainder + op = EmitCopyLessThan64(op, offset, len); + return op; } + bool GetUncompressedLength(const char* start, size_t n, size_t* result) { uint32 v = 0; const char* limit = start + n; @@ -427,7 +357,7 @@ char* CompressFragment(const char* input, const char* next_emit = ip; const size_t kInputMarginBytes = 15; - if (SNAPPY_PREDICT_TRUE(input_size >= kInputMarginBytes)) { + if (PREDICT_TRUE(input_size >= kInputMarginBytes)) { const char* ip_limit = input + input_size - kInputMarginBytes; for (uint32 next_hash = Hash(++ip, shift); ; ) { @@ -447,9 +377,9 @@ char* CompressFragment(const char* input, // // Heuristic match skipping: If 32 bytes are scanned with no matches // found, start looking only at every other byte. If 32 more bytes are - // scanned (or skipped), look at every third byte, etc.. When a match is - // found, immediately go back to looking at every byte. This is a small - // loss (~5% performance, ~0.1% density) for compressible data due to more + // scanned, look at every third byte, etc.. When a match is found, + // immediately go back to looking at every byte. This is a small loss + // (~5% performance, ~0.1% density) for compressible data due to more // bookkeeping, but for non-compressible data (such as JPEG) it's a huge // win since the compressor quickly "realizes" the data is incompressible // and doesn't bother looking for matches everywhere. @@ -465,10 +395,9 @@ char* CompressFragment(const char* input, ip = next_ip; uint32 hash = next_hash; assert(hash == Hash(ip, shift)); - uint32 bytes_between_hash_lookups = skip >> 5; - skip += bytes_between_hash_lookups; + uint32 bytes_between_hash_lookups = skip++ >> 5; next_ip = ip + bytes_between_hash_lookups; - if (SNAPPY_PREDICT_FALSE(next_ip > ip_limit)) { + if (PREDICT_FALSE(next_ip > ip_limit)) { goto emit_remainder; } next_hash = Hash(next_ip, shift); @@ -477,8 +406,8 @@ char* CompressFragment(const char* input, assert(candidate < ip); table[hash] = ip - base_ip; - } while (SNAPPY_PREDICT_TRUE(UNALIGNED_LOAD32(ip) != - UNALIGNED_LOAD32(candidate))); + } while (PREDICT_TRUE(UNALIGNED_LOAD32(ip) != + UNALIGNED_LOAD32(candidate))); // Step 2: A 4-byte match has been found. We'll later see if more // than 4 bytes match. But, prior to the match, input @@ -501,21 +430,19 @@ char* CompressFragment(const char* input, // We have a 4-byte match at ip, and no need to emit any // "literal bytes" prior to ip. const char* base = ip; - std::pair<size_t, bool> p = - FindMatchLength(candidate + 4, ip + 4, ip_end); - size_t matched = 4 + p.first; + int matched = 4 + FindMatchLength(candidate + 4, ip + 4, ip_end); ip += matched; size_t offset = base - candidate; assert(0 == memcmp(base, candidate, matched)); - op = EmitCopy(op, offset, matched, p.second); + op = EmitCopy(op, offset, matched); + // We could immediately start working at ip now, but to improve + // compression we first update table[Hash(ip - 1, ...)]. + const char* insert_tail = ip - 1; next_emit = ip; - if (SNAPPY_PREDICT_FALSE(ip >= ip_limit)) { + if (PREDICT_FALSE(ip >= ip_limit)) { goto emit_remainder; } - // We are now looking for a 4-byte match again. We read - // table[Hash(ip, shift)] for that. To improve compression, - // we also update table[Hash(ip - 1, shift)] and table[Hash(ip, shift)]. - input_bytes = GetEightBytesAt(ip - 1); + input_bytes = GetEightBytesAt(insert_tail); uint32 prev_hash = HashBytes(GetUint32AtOffset(input_bytes, 0), shift); table[prev_hash] = ip - base_ip - 1; uint32 cur_hash = HashBytes(GetUint32AtOffset(input_bytes, 1), shift); @@ -539,10 +466,6 @@ char* CompressFragment(const char* input, } } // end namespace internal -// Called back at avery compression call to trace parameters and sizes. -static inline void Report(const char *algorithm, size_t compressed_size, - size_t uncompressed_size) {} - // Signature of output types needed by decompression code. // The decompression code is templatized on a type that obeys this // signature so that we do not pay virtual function call overhead in @@ -583,14 +506,162 @@ static inline void Report(const char *algorithm, size_t compressed_size, // bool TryFastAppend(const char* ip, size_t available, size_t length); // }; -namespace internal { +// ----------------------------------------------------------------------- +// Lookup table for decompression code. Generated by ComputeTable() below. +// ----------------------------------------------------------------------- // Mapping from i in range [0,4] to a mask to extract the bottom 8*i bits static const uint32 wordmask[] = { 0u, 0xffu, 0xffffu, 0xffffffu, 0xffffffffu }; -} // end namespace internal +// Data stored per entry in lookup table: +// Range Bits-used Description +// ------------------------------------ +// 1..64 0..7 Literal/copy length encoded in opcode byte +// 0..7 8..10 Copy offset encoded in opcode byte / 256 +// 0..4 11..13 Extra bytes after opcode +// +// We use eight bits for the length even though 7 would have sufficed +// because of efficiency reasons: +// (1) Extracting a byte is faster than a bit-field +// (2) It properly aligns copy offset so we do not need a <<8 +static const uint16 char_table[256] = { + 0x0001, 0x0804, 0x1001, 0x2001, 0x0002, 0x0805, 0x1002, 0x2002, + 0x0003, 0x0806, 0x1003, 0x2003, 0x0004, 0x0807, 0x1004, 0x2004, + 0x0005, 0x0808, 0x1005, 0x2005, 0x0006, 0x0809, 0x1006, 0x2006, + 0x0007, 0x080a, 0x1007, 0x2007, 0x0008, 0x080b, 0x1008, 0x2008, + 0x0009, 0x0904, 0x1009, 0x2009, 0x000a, 0x0905, 0x100a, 0x200a, + 0x000b, 0x0906, 0x100b, 0x200b, 0x000c, 0x0907, 0x100c, 0x200c, + 0x000d, 0x0908, 0x100d, 0x200d, 0x000e, 0x0909, 0x100e, 0x200e, + 0x000f, 0x090a, 0x100f, 0x200f, 0x0010, 0x090b, 0x1010, 0x2010, + 0x0011, 0x0a04, 0x1011, 0x2011, 0x0012, 0x0a05, 0x1012, 0x2012, + 0x0013, 0x0a06, 0x1013, 0x2013, 0x0014, 0x0a07, 0x1014, 0x2014, + 0x0015, 0x0a08, 0x1015, 0x2015, 0x0016, 0x0a09, 0x1016, 0x2016, + 0x0017, 0x0a0a, 0x1017, 0x2017, 0x0018, 0x0a0b, 0x1018, 0x2018, + 0x0019, 0x0b04, 0x1019, 0x2019, 0x001a, 0x0b05, 0x101a, 0x201a, + 0x001b, 0x0b06, 0x101b, 0x201b, 0x001c, 0x0b07, 0x101c, 0x201c, + 0x001d, 0x0b08, 0x101d, 0x201d, 0x001e, 0x0b09, 0x101e, 0x201e, + 0x001f, 0x0b0a, 0x101f, 0x201f, 0x0020, 0x0b0b, 0x1020, 0x2020, + 0x0021, 0x0c04, 0x1021, 0x2021, 0x0022, 0x0c05, 0x1022, 0x2022, + 0x0023, 0x0c06, 0x1023, 0x2023, 0x0024, 0x0c07, 0x1024, 0x2024, + 0x0025, 0x0c08, 0x1025, 0x2025, 0x0026, 0x0c09, 0x1026, 0x2026, + 0x0027, 0x0c0a, 0x1027, 0x2027, 0x0028, 0x0c0b, 0x1028, 0x2028, + 0x0029, 0x0d04, 0x1029, 0x2029, 0x002a, 0x0d05, 0x102a, 0x202a, + 0x002b, 0x0d06, 0x102b, 0x202b, 0x002c, 0x0d07, 0x102c, 0x202c, + 0x002d, 0x0d08, 0x102d, 0x202d, 0x002e, 0x0d09, 0x102e, 0x202e, + 0x002f, 0x0d0a, 0x102f, 0x202f, 0x0030, 0x0d0b, 0x1030, 0x2030, + 0x0031, 0x0e04, 0x1031, 0x2031, 0x0032, 0x0e05, 0x1032, 0x2032, + 0x0033, 0x0e06, 0x1033, 0x2033, 0x0034, 0x0e07, 0x1034, 0x2034, + 0x0035, 0x0e08, 0x1035, 0x2035, 0x0036, 0x0e09, 0x1036, 0x2036, + 0x0037, 0x0e0a, 0x1037, 0x2037, 0x0038, 0x0e0b, 0x1038, 0x2038, + 0x0039, 0x0f04, 0x1039, 0x2039, 0x003a, 0x0f05, 0x103a, 0x203a, + 0x003b, 0x0f06, 0x103b, 0x203b, 0x003c, 0x0f07, 0x103c, 0x203c, + 0x0801, 0x0f08, 0x103d, 0x203d, 0x1001, 0x0f09, 0x103e, 0x203e, + 0x1801, 0x0f0a, 0x103f, 0x203f, 0x2001, 0x0f0b, 0x1040, 0x2040 +}; + +// In debug mode, allow optional computation of the table at startup. +// Also, check that the decompression table is correct. +#ifndef NDEBUG +DEFINE_bool(snappy_dump_decompression_table, false, + "If true, we print the decompression table at startup."); + +static uint16 MakeEntry(unsigned int extra, + unsigned int len, + unsigned int copy_offset) { + // Check that all of the fields fit within the allocated space + assert(extra == (extra & 0x7)); // At most 3 bits + assert(copy_offset == (copy_offset & 0x7)); // At most 3 bits + assert(len == (len & 0x7f)); // At most 7 bits + return len | (copy_offset << 8) | (extra << 11); +} + +static void ComputeTable() { + uint16 dst[256]; + + // Place invalid entries in all places to detect missing initialization + int assigned = 0; + for (int i = 0; i < 256; i++) { + dst[i] = 0xffff; + } + + // Small LITERAL entries. We store (len-1) in the top 6 bits. + for (unsigned int len = 1; len <= 60; len++) { + dst[LITERAL | ((len-1) << 2)] = MakeEntry(0, len, 0); + assigned++; + } + + // Large LITERAL entries. We use 60..63 in the high 6 bits to + // encode the number of bytes of length info that follow the opcode. + for (unsigned int extra_bytes = 1; extra_bytes <= 4; extra_bytes++) { + // We set the length field in the lookup table to 1 because extra + // bytes encode len-1. + dst[LITERAL | ((extra_bytes+59) << 2)] = MakeEntry(extra_bytes, 1, 0); + assigned++; + } + + // COPY_1_BYTE_OFFSET. + // + // The tag byte in the compressed data stores len-4 in 3 bits, and + // offset/256 in 5 bits. offset%256 is stored in the next byte. + // + // This format is used for length in range [4..11] and offset in + // range [0..2047] + for (unsigned int len = 4; len < 12; len++) { + for (unsigned int offset = 0; offset < 2048; offset += 256) { + dst[COPY_1_BYTE_OFFSET | ((len-4)<<2) | ((offset>>8)<<5)] = + MakeEntry(1, len, offset>>8); + assigned++; + } + } + + // COPY_2_BYTE_OFFSET. + // Tag contains len-1 in top 6 bits, and offset in next two bytes. + for (unsigned int len = 1; len <= 64; len++) { + dst[COPY_2_BYTE_OFFSET | ((len-1)<<2)] = MakeEntry(2, len, 0); + assigned++; + } + + // COPY_4_BYTE_OFFSET. + // Tag contents len-1 in top 6 bits, and offset in next four bytes. + for (unsigned int len = 1; len <= 64; len++) { + dst[COPY_4_BYTE_OFFSET | ((len-1)<<2)] = MakeEntry(4, len, 0); + assigned++; + } + + // Check that each entry was initialized exactly once. + if (assigned != 256) { + fprintf(stderr, "ComputeTable: assigned only %d of 256\n", assigned); + abort(); + } + for (int i = 0; i < 256; i++) { + if (dst[i] == 0xffff) { + fprintf(stderr, "ComputeTable: did not assign byte %d\n", i); + abort(); + } + } + + if (FLAGS_snappy_dump_decompression_table) { + printf("static const uint16 char_table[256] = {\n "); + for (int i = 0; i < 256; i++) { + printf("0x%04x%s", + dst[i], + ((i == 255) ? "\n" : (((i%8) == 7) ? ",\n " : ", "))); + } + printf("};\n"); + } + + // Check that computed table matched recorded table + for (int i = 0; i < 256; i++) { + if (dst[i] != char_table[i]) { + fprintf(stderr, "ComputeTable: byte %d: computed (%x), expect (%x)\n", + i, static_cast<int>(dst[i]), static_cast<int>(char_table[i])); + abort(); + } + } +} +#endif /* !NDEBUG */ // Helper class for decompression class SnappyDecompressor { @@ -643,9 +714,7 @@ class SnappyDecompressor { if (n == 0) return false; const unsigned char c = *(reinterpret_cast<const unsigned char*>(ip)); reader_->Skip(1); - uint32 val = c & 0x7f; - if (((val << shift) >> shift) != val) return false; - *result |= val << shift; + *result |= static_cast<uint32>(c & 0x7f) << shift; if (c < 128) { break; } @@ -659,19 +728,6 @@ class SnappyDecompressor { template <class Writer> void DecompressAllTags(Writer* writer) { const char* ip = ip_; - // For position-independent executables, accessing global arrays can be - // slow. Move wordmask array onto the stack to mitigate this. - uint32 wordmask[sizeof(internal::wordmask)/sizeof(uint32)]; - // Do not use memcpy to copy internal::wordmask to - // wordmask. LLVM converts stack arrays to global arrays if it detects - // const stack arrays and this hurts the performance of position - // independent code. This change is temporary and can be reverted when - // https://reviews.llvm.org/D30759 is approved. - wordmask[0] = internal::wordmask[0]; - wordmask[1] = internal::wordmask[1]; - wordmask[2] = internal::wordmask[2]; - wordmask[3] = internal::wordmask[3]; - wordmask[4] = internal::wordmask[4]; // We could have put this refill fragment only at the beginning of the loop. // However, duplicating it at the end of each branch gives the compiler more @@ -685,29 +741,10 @@ class SnappyDecompressor { } MAYBE_REFILL(); - // Add loop alignment directive. Without this directive, we observed - // significant performance degradation on several intel architectures - // in snappy benchmark built with LLVM. The degradation was caused by - // increased branch miss prediction. -#if defined(__clang__) && defined(__x86_64__) - asm volatile (".p2align 5"); -#endif for ( ;; ) { const unsigned char c = *(reinterpret_cast<const unsigned char*>(ip++)); - // Ratio of iterations that have LITERAL vs non-LITERAL for different - // inputs. - // - // input LITERAL NON_LITERAL - // ----------------------------------- - // html|html4|cp 23% 77% - // urls 36% 64% - // jpg 47% 53% - // pdf 19% 81% - // txt[1-4] 25% 75% - // pb 24% 76% - // bin 24% 76% - if (SNAPPY_PREDICT_FALSE((c & 0x3) == LITERAL)) { + if ((c & 0x3) == LITERAL) { size_t literal_length = (c >> 2) + 1u; if (writer->TryFastAppend(ip, ip_limit_ - ip, literal_length)) { assert(literal_length < 61); @@ -717,7 +754,7 @@ class SnappyDecompressor { // bytes in addition to the literal. continue; } - if (SNAPPY_PREDICT_FALSE(literal_length >= 61)) { + if (PREDICT_FALSE(literal_length >= 61)) { // Long literal. const size_t literal_length_length = literal_length - 60; literal_length = @@ -743,15 +780,15 @@ class SnappyDecompressor { ip += literal_length; MAYBE_REFILL(); } else { - const size_t entry = char_table[c]; - const size_t trailer = LittleEndian::Load32(ip) & wordmask[entry >> 11]; - const size_t length = entry & 0xff; + const uint32 entry = char_table[c]; + const uint32 trailer = LittleEndian::Load32(ip) & wordmask[entry >> 11]; + const uint32 length = entry & 0xff; ip += entry >> 11; // copy_offset/256 is encoded in bits 8..10. By just fetching // those bits, we get copy_offset (since the bit-field starts at // bit 8). - const size_t copy_offset = entry & 0x700; + const uint32 copy_offset = entry & 0x700; if (!writer->AppendFromSelf(copy_offset + trailer, length)) { return; } @@ -771,8 +808,10 @@ bool SnappyDecompressor::RefillTag() { size_t n; ip = reader_->Peek(&n); peeked_ = n; - eof_ = (n == 0); - if (eof_) return false; + if (n == 0) { + eof_ = true; + return false; + } ip_limit_ = ip + n; } @@ -797,7 +836,7 @@ bool SnappyDecompressor::RefillTag() { size_t length; const char* src = reader_->Peek(&length); if (length == 0) return false; - uint32 to_add = std::min<uint32>(needed - nbuf, length); + uint32 to_add = min<uint32>(needed - nbuf, length); memcpy(scratch_ + nbuf, src, to_add); nbuf += to_add; reader_->Skip(to_add); @@ -826,18 +865,13 @@ static bool InternalUncompress(Source* r, Writer* writer) { SnappyDecompressor decompressor(r); uint32 uncompressed_len = 0; if (!decompressor.ReadUncompressedLength(&uncompressed_len)) return false; - - return InternalUncompressAllTags(&decompressor, writer, r->Available(), - uncompressed_len); + return InternalUncompressAllTags(&decompressor, writer, uncompressed_len); } template <typename Writer> static bool InternalUncompressAllTags(SnappyDecompressor* decompressor, Writer* writer, - uint32 compressed_len, uint32 uncompressed_len) { - Report("snappy_uncompress", compressed_len, uncompressed_len); - writer->SetExpectedLength(uncompressed_len); // Process the entire input @@ -854,7 +888,6 @@ bool GetUncompressedLength(Source* source, uint32* result) { size_t Compress(Source* reader, Sink* writer) { size_t written = 0; size_t N = reader->Available(); - const size_t uncompressed_size = N; char ulength[Varint::kMax32]; char* p = Varint::Encode32(ulength, N); writer->Append(ulength, p-ulength); @@ -869,7 +902,7 @@ size_t Compress(Source* reader, Sink* writer) { size_t fragment_size; const char* fragment = reader->Peek(&fragment_size); assert(fragment_size != 0); // premature end of input - const size_t num_to_read = std::min(N, kBlockSize); + const size_t num_to_read = min(N, kBlockSize); size_t bytes_read = fragment_size; size_t pending_advance = 0; @@ -890,7 +923,7 @@ size_t Compress(Source* reader, Sink* writer) { while (bytes_read < num_to_read) { fragment = reader->Peek(&fragment_size); - size_t n = std::min<size_t>(fragment_size, num_to_read - bytes_read); + size_t n = min<size_t>(fragment_size, num_to_read - bytes_read); memcpy(scratch + bytes_read, fragment, n); bytes_read += n; reader->Skip(n); @@ -908,16 +941,16 @@ size_t Compress(Source* reader, Sink* writer) { // Compress input_fragment and append to dest const int max_output = MaxCompressedLength(num_to_read); - // Need a scratch buffer for the output, in case the byte sink doesn't - // have room for us directly. - if (scratch_output == NULL) { - scratch_output = new char[max_output]; - } else { - // Since we encode kBlockSize regions followed by a region - // which is <= kBlockSize in length, a previously allocated - // scratch_output[] region is big enough for this iteration. - } + // If the byte sink doesn't have room for us directly, allocate a scratch + // buffer. + // + // Since we encode kBlockSize regions followed by a region + // which is <= kBlockSize in length, a previously allocated + // scratch_output[] region is big enough for this iteration. char* dest = writer->GetAppendBuffer(max_output, scratch_output); + if (dest == NULL) { + dest = scratch_output = new char[max_output]; + } char* end = internal::CompressFragment(fragment, fragment_size, dest, table, table_size); writer->Append(dest, end - dest); @@ -927,8 +960,6 @@ size_t Compress(Source* reader, Sink* writer) { reader->Skip(pending_advance); } - Report("snappy_compress", written, uncompressed_size); - delete[] scratch; delete[] scratch_output; @@ -948,7 +979,7 @@ class SnappyIOVecWriter { const size_t output_iov_count_; // We are currently writing into output_iov_[curr_iov_index_]. - size_t curr_iov_index_; + int curr_iov_index_; // Bytes written to output_iov_[curr_iov_index_] so far. size_t curr_iov_written_; @@ -959,7 +990,7 @@ class SnappyIOVecWriter { // Maximum number of bytes that will be decompressed into output_iov_. size_t output_limit_; - inline char* GetIOVecPointer(size_t index, size_t offset) { + inline char* GetIOVecPointer(int index, size_t offset) { return reinterpret_cast<char*>(output_iov_[index].iov_base) + offset; } @@ -1020,7 +1051,8 @@ class SnappyIOVecWriter { output_iov_[curr_iov_index_].iov_len - curr_iov_written_ >= 16) { // Fast path, used for the majority (about 95%) of invocations. char* ptr = GetIOVecPointer(curr_iov_index_, curr_iov_written_); - UnalignedCopy128(ip, ptr); + UnalignedCopy64(ip, ptr); + UnalignedCopy64(ip + 8, ptr + 8); curr_iov_written_ += len; total_written_ += len; return true; @@ -1039,7 +1071,7 @@ class SnappyIOVecWriter { } // Locate the iovec from which we need to start the copy. - size_t from_iov_index = curr_iov_index_; + int from_iov_index = curr_iov_index_; size_t from_iov_offset = curr_iov_written_; while (offset > 0) { if (from_iov_offset >= offset) { @@ -1048,8 +1080,8 @@ class SnappyIOVecWriter { } offset -= from_iov_offset; - assert(from_iov_index > 0); --from_iov_index; + assert(from_iov_index >= 0); from_iov_offset = output_iov_[from_iov_index].iov_len; } @@ -1084,10 +1116,9 @@ class SnappyIOVecWriter { if (to_copy > len) { to_copy = len; } - IncrementalCopySlow( - GetIOVecPointer(from_iov_index, from_iov_offset), - GetIOVecPointer(curr_iov_index_, curr_iov_written_), - GetIOVecPointer(curr_iov_index_, curr_iov_written_) + to_copy); + IncrementalCopy(GetIOVecPointer(from_iov_index, from_iov_offset), + GetIOVecPointer(curr_iov_index_, curr_iov_written_), + to_copy); curr_iov_written_ += to_copy; from_iov_offset += to_copy; total_written_ += to_copy; @@ -1157,7 +1188,8 @@ class SnappyArrayWriter { const size_t space_left = op_limit_ - op; if (len <= 16 && available >= 16 + kMaximumTagLength && space_left >= 16) { // Fast path, used for the majority (about 95%) of invocations. - UnalignedCopy128(ip, op); + UnalignedCopy64(ip, op); + UnalignedCopy64(ip + 8, op + 8); op_ = op + len; return true; } else { @@ -1166,7 +1198,8 @@ class SnappyArrayWriter { } inline bool AppendFromSelf(size_t offset, size_t len) { - char* const op_end = op_ + len; + char* op = op_; + const size_t space_left = op_limit_ - op; // Check if we try to append from before the start of the buffer. // Normally this would just be a check for "produced < offset", @@ -1175,13 +1208,30 @@ class SnappyArrayWriter { // to a very big number. This is convenient, as offset==0 is another // invalid case that we also want to catch, so that we do not go // into an infinite loop. - if (Produced() <= offset - 1u || op_end > op_limit_) return false; - op_ = IncrementalCopy(op_ - offset, op_, op_end, op_limit_); + assert(op >= base_); + size_t produced = op - base_; + if (produced <= offset - 1u) { + return false; + } + if (len <= 16 && offset >= 8 && space_left >= 16) { + // Fast path, used for the majority (70-80%) of dynamic invocations. + UnalignedCopy64(op - offset, op); + UnalignedCopy64(op - offset + 8, op + 8); + } else { + if (space_left >= len + kMaxIncrementCopyOverflow) { + IncrementalCopyFastPath(op - offset, op, len); + } else { + if (space_left < len) { + return false; + } + IncrementalCopy(op - offset, op, len); + } + } + op_ = op + len; return true; } inline size_t Produced() const { - assert(op_ >= base_); return op_ - base_; } inline void Flush() {} @@ -1267,7 +1317,7 @@ void RawCompress(const char* input, size_t Compress(const char* input, size_t input_length, string* compressed) { // Pre-grow the buffer to the max length of the compressed output - STLStringResizeUninitialized(compressed, MaxCompressedLength(input_length)); + compressed->resize(MaxCompressedLength(input_length)); size_t compressed_length; RawCompress(input, input_length, string_as_array(compressed), @@ -1290,7 +1340,7 @@ class SnappyScatteredWriter { // We need random access into the data generated so far. Therefore // we keep track of all of the generated data as an array of blocks. // All of the blocks except the last have length kBlockSize. - std::vector<char*> blocks_; + vector<char*> blocks_; size_t expected_; // Total size of all fully generated blocks so far @@ -1349,7 +1399,8 @@ class SnappyScatteredWriter { if (length <= 16 && available >= 16 + kMaximumTagLength && space_left >= 16) { // Fast path, used for the majority (about 95%) of invocations. - UnalignedCopy128(ip, op); + UNALIGNED_STORE64(op, UNALIGNED_LOAD64(ip)); + UNALIGNED_STORE64(op + 8, UNALIGNED_LOAD64(ip + 8)); op_ptr_ = op + length; return true; } else { @@ -1358,14 +1409,16 @@ class SnappyScatteredWriter { } inline bool AppendFromSelf(size_t offset, size_t len) { - char* const op_end = op_ptr_ + len; // See SnappyArrayWriter::AppendFromSelf for an explanation of // the "offset - 1u" trick. - if (SNAPPY_PREDICT_TRUE(offset - 1u < op_ptr_ - op_base_ && - op_end <= op_limit_)) { - // Fast path: src and dst in current block. - op_ptr_ = IncrementalCopy(op_ptr_ - offset, op_ptr_, op_end, op_limit_); - return true; + if (offset - 1u < op_ptr_ - op_base_) { + const size_t space_left = op_limit_ - op_ptr_; + if (space_left >= len + kMaxIncrementCopyOverflow) { + // Fast path: src and dst in current block. + IncrementalCopyFastPath(op_ptr_ - offset, op_ptr_, len); + op_ptr_ += len; + return true; + } } return SlowAppendFromSelf(offset, len); } @@ -1393,7 +1446,7 @@ bool SnappyScatteredWriter<Allocator>::SlowAppend(const char* ip, size_t len) { } // Make new block - size_t bsize = std::min<size_t>(kBlockSize, expected_ - full_size_); + size_t bsize = min<size_t>(kBlockSize, expected_ - full_size_); op_base_ = allocator_.Allocate(bsize); op_ptr_ = op_base_; op_limit_ = op_base_ + bsize; @@ -1450,7 +1503,7 @@ class SnappySinkAllocator { size_t size_written = 0; size_t block_size; for (int i = 0; i < blocks_.size(); ++i) { - block_size = std::min<size_t>(blocks_[i].size, size - size_written); + block_size = min<size_t>(blocks_[i].size, size - size_written); dest_->AppendAndTakeOwnership(blocks_[i].data, block_size, &SnappySinkAllocator::Deleter, NULL); size_written += block_size; @@ -1470,7 +1523,7 @@ class SnappySinkAllocator { } Sink* dest_; - std::vector<Datablock> blocks_; + vector<Datablock> blocks_; // Note: copying this object is allowed }; @@ -1495,20 +1548,18 @@ bool Uncompress(Source* compressed, Sink* uncompressed) { char* buf = uncompressed->GetAppendBufferVariable( 1, uncompressed_len, &c, 1, &allocated_size); - const size_t compressed_len = compressed->Available(); // If we can get a flat buffer, then use it, otherwise do block by block // uncompression if (allocated_size >= uncompressed_len) { SnappyArrayWriter writer(buf); - bool result = InternalUncompressAllTags(&decompressor, &writer, - compressed_len, uncompressed_len); + bool result = InternalUncompressAllTags( + &decompressor, &writer, uncompressed_len); uncompressed->Append(buf, writer.Produced()); return result; } else { SnappySinkAllocator allocator(uncompressed); SnappyScatteredWriter<SnappySinkAllocator> writer(allocator); - return InternalUncompressAllTags(&decompressor, &writer, compressed_len, - uncompressed_len); + return InternalUncompressAllTags(&decompressor, &writer, uncompressed_len); } } diff --git a/src/third_party/snappy-1.1.7/snappy.h b/src/third_party/snappy-1.1.3/snappy.h index 4568db890d6..4568db890d6 100644 --- a/src/third_party/snappy-1.1.7/snappy.h +++ b/src/third_party/snappy-1.1.3/snappy.h diff --git a/src/third_party/snappy-1.1.7/snappy_unittest.cc b/src/third_party/snappy-1.1.3/snappy_unittest.cc index fcb3261d20a..4a80f2ad6d4 100644 --- a/src/third_party/snappy-1.1.7/snappy_unittest.cc +++ b/src/third_party/snappy-1.1.3/snappy_unittest.cc @@ -32,7 +32,6 @@ #include <algorithm> #include <string> -#include <utility> #include <vector> #include "snappy.h" @@ -51,6 +50,13 @@ DEFINE_bool(zlib, false, "Run zlib compression (http://www.zlib.net)"); DEFINE_bool(lzo, false, "Run LZO compression (http://www.oberhumer.com/opensource/lzo/)"); +DEFINE_bool(quicklz, false, + "Run quickLZ compression (http://www.quicklz.com/)"); +DEFINE_bool(liblzf, false, + "Run libLZF compression " + "(http://www.goof.com/pcg/marc/liblzf.html)"); +DEFINE_bool(fastlz, false, + "Run FastLZ compression (http://www.fastlz.org/"); DEFINE_bool(snappy, true, "Run snappy compression"); DEFINE_bool(write_compressed, false, @@ -58,12 +64,10 @@ DEFINE_bool(write_compressed, false, DEFINE_bool(write_uncompressed, false, "Write uncompressed versions of each file to <file>.uncomp"); -DEFINE_bool(snappy_dump_decompression_table, false, - "If true, we print the decompression table during tests."); - namespace snappy { -#if defined(HAVE_FUNC_MMAP) && defined(HAVE_FUNC_SYSCONF) + +#ifdef HAVE_FUNC_MMAP // To test against code that reads beyond its input, this class copies a // string to a newly allocated group of pages, the last of which @@ -74,7 +78,7 @@ namespace snappy { class DataEndingAtUnreadablePage { public: explicit DataEndingAtUnreadablePage(const string& s) { - const size_t page_size = sysconf(_SC_PAGESIZE); + const size_t page_size = getpagesize(); const size_t size = s.size(); // Round up space for string to a multiple of page_size. size_t space_for_string = (size + page_size - 1) & ~(page_size - 1); @@ -92,9 +96,8 @@ class DataEndingAtUnreadablePage { } ~DataEndingAtUnreadablePage() { - const size_t page_size = sysconf(_SC_PAGESIZE); // Undo the mprotect. - CHECK_EQ(0, mprotect(protected_page_, page_size, PROT_READ|PROT_WRITE)); + CHECK_EQ(0, mprotect(protected_page_, getpagesize(), PROT_READ|PROT_WRITE)); CHECK_EQ(0, munmap(mem_, alloc_size_)); } @@ -109,7 +112,7 @@ class DataEndingAtUnreadablePage { size_t size_; }; -#else // defined(HAVE_FUNC_MMAP) && defined(HAVE_FUNC_SYSCONF) +#else // HAVE_FUNC_MMAP // Fallback for systems without mmap. typedef string DataEndingAtUnreadablePage; @@ -117,11 +120,11 @@ typedef string DataEndingAtUnreadablePage; #endif enum CompressorType { - ZLIB, LZO, SNAPPY + ZLIB, LZO, LIBLZF, QUICKLZ, FASTLZ, SNAPPY }; const char* names[] = { - "ZLIB", "LZO", "SNAPPY" + "ZLIB", "LZO", "LIBLZF", "QUICKLZ", "FASTLZ", "SNAPPY" }; static size_t MinimumRequiredOutputSpace(size_t input_size, @@ -137,6 +140,21 @@ static size_t MinimumRequiredOutputSpace(size_t input_size, return input_size + input_size/64 + 16 + 3; #endif // LZO_VERSION +#ifdef LZF_VERSION + case LIBLZF: + return input_size; +#endif // LZF_VERSION + +#ifdef QLZ_VERSION_MAJOR + case QUICKLZ: + return input_size + 36000; // 36000 is used for scratch. +#endif // QLZ_VERSION_MAJOR + +#ifdef FASTLZ_VERSION + case FASTLZ: + return max(static_cast<int>(ceil(input_size * 1.05)), 66); +#endif // FASTLZ_VERSION + case SNAPPY: return snappy::MaxCompressedLength(input_size); @@ -196,6 +214,58 @@ static bool Compress(const char* input, size_t input_size, CompressorType comp, } #endif // LZO_VERSION +#ifdef LZF_VERSION + case LIBLZF: { + int destlen = lzf_compress(input, + input_size, + string_as_array(compressed), + input_size); + if (destlen == 0) { + // lzf *can* cause lots of blowup when compressing, so they + // recommend to limit outsize to insize, and just not compress + // if it's bigger. Ideally, we'd just swap input and output. + compressed->assign(input, input_size); + destlen = input_size; + } + if (!compressed_is_preallocated) { + compressed->resize(destlen); + } + break; + } +#endif // LZF_VERSION + +#ifdef QLZ_VERSION_MAJOR + case QUICKLZ: { + qlz_state_compress *state_compress = new qlz_state_compress; + int destlen = qlz_compress(input, + string_as_array(compressed), + input_size, + state_compress); + delete state_compress; + CHECK_NE(0, destlen); + if (!compressed_is_preallocated) { + compressed->resize(destlen); + } + break; + } +#endif // QLZ_VERSION_MAJOR + +#ifdef FASTLZ_VERSION + case FASTLZ: { + // Use level 1 compression since we mostly care about speed. + int destlen = fastlz_compress_level( + 1, + input, + input_size, + string_as_array(compressed)); + if (!compressed_is_preallocated) { + compressed->resize(destlen); + } + CHECK_NE(destlen, 0); + break; + } +#endif // FASTLZ_VERSION + case SNAPPY: { size_t destlen; snappy::RawCompress(input, input_size, @@ -250,6 +320,49 @@ static bool Uncompress(const string& compressed, CompressorType comp, } #endif // LZO_VERSION +#ifdef LZF_VERSION + case LIBLZF: { + output->resize(size); + int destlen = lzf_decompress(compressed.data(), + compressed.size(), + string_as_array(output), + output->size()); + if (destlen == 0) { + // This error probably means we had decided not to compress, + // and thus have stored input in output directly. + output->assign(compressed.data(), compressed.size()); + destlen = compressed.size(); + } + CHECK_EQ(destlen, size); + break; + } +#endif // LZF_VERSION + +#ifdef QLZ_VERSION_MAJOR + case QUICKLZ: { + output->resize(size); + qlz_state_decompress *state_decompress = new qlz_state_decompress; + int destlen = qlz_decompress(compressed.data(), + string_as_array(output), + state_decompress); + delete state_decompress; + CHECK_EQ(destlen, size); + break; + } +#endif // QLZ_VERSION_MAJOR + +#ifdef FASTLZ_VERSION + case FASTLZ: { + output->resize(size); + int destlen = fastlz_decompress(compressed.data(), + compressed.length(), + string_as_array(output), + size); + CHECK_EQ(destlen, size); + break; + } +#endif // FASTLZ_VERSION + case SNAPPY: { snappy::RawUncompress(compressed.data(), compressed.size(), string_as_array(output)); @@ -277,13 +390,13 @@ static void Measure(const char* data, { // Chop the input into blocks int num_blocks = (length + block_size - 1) / block_size; - std::vector<const char*> input(num_blocks); - std::vector<size_t> input_length(num_blocks); - std::vector<string> compressed(num_blocks); - std::vector<string> output(num_blocks); + vector<const char*> input(num_blocks); + vector<size_t> input_length(num_blocks); + vector<string> compressed(num_blocks); + vector<string> output(num_blocks); for (int b = 0; b < num_blocks; b++) { int input_start = b * block_size; - int input_limit = std::min<int>((b+1)*block_size, length); + int input_limit = min<int>((b+1)*block_size, length); input[b] = data+input_start; input_length[b] = input_limit-input_start; @@ -338,8 +451,8 @@ static void Measure(const char* data, } } - std::sort(ctime, ctime + kRuns); - std::sort(utime, utime + kRuns); + sort(ctime, ctime + kRuns); + sort(utime, utime + kRuns); const int med = kRuns/2; float comp_rate = (length / ctime[med]) * repeats / 1048576.0; @@ -354,7 +467,7 @@ static void Measure(const char* data, x.c_str(), block_size/(1<<20), static_cast<int>(length), static_cast<uint32>(compressed_size), - (compressed_size * 100.0) / std::max<int>(1, length), + (compressed_size * 100.0) / max<int>(1, length), comp_rate, urate.c_str()); } @@ -891,20 +1004,6 @@ TEST(SnappyCorruption, UnterminatedVarint) { &uncompressed)); } -TEST(SnappyCorruption, OverflowingVarint) { - string compressed, uncompressed; - size_t ulength; - compressed.push_back('\xfb'); - compressed.push_back('\xff'); - compressed.push_back('\xff'); - compressed.push_back('\xff'); - compressed.push_back('\x7f'); - CHECK(!CheckUncompressedLength(compressed, &ulength)); - CHECK(!snappy::IsValidCompressedBuffer(compressed.data(), compressed.size())); - CHECK(!snappy::Uncompress(compressed.data(), compressed.size(), - &uncompressed)); -} - TEST(Snappy, ReadPastEndOfBuffer) { // Check that we do not read past end of input @@ -938,10 +1037,7 @@ TEST(Snappy, ZeroOffsetCopyValidation) { namespace { int TestFindMatchLength(const char* s1, const char *s2, unsigned length) { - std::pair<size_t, bool> p = - snappy::internal::FindMatchLength(s1, s2, s2 + length); - CHECK_EQ(p.first < 8, p.second); - return p.first; + return snappy::internal::FindMatchLength(s1, s2, s2 + length); } } // namespace @@ -1051,7 +1147,8 @@ TEST(Snappy, FindMatchLengthRandom) { } DataEndingAtUnreadablePage u(s); DataEndingAtUnreadablePage v(t); - int matched = TestFindMatchLength(u.data(), v.data(), t.size()); + int matched = snappy::internal::FindMatchLength( + u.data(), v.data(), v.data() + t.size()); if (matched == t.size()) { EXPECT_EQ(s, t); } else { @@ -1063,99 +1160,6 @@ TEST(Snappy, FindMatchLengthRandom) { } } -static uint16 MakeEntry(unsigned int extra, - unsigned int len, - unsigned int copy_offset) { - // Check that all of the fields fit within the allocated space - assert(extra == (extra & 0x7)); // At most 3 bits - assert(copy_offset == (copy_offset & 0x7)); // At most 3 bits - assert(len == (len & 0x7f)); // At most 7 bits - return len | (copy_offset << 8) | (extra << 11); -} - -// Check that the decompression table is correct, and optionally print out -// the computed one. -TEST(Snappy, VerifyCharTable) { - using snappy::internal::LITERAL; - using snappy::internal::COPY_1_BYTE_OFFSET; - using snappy::internal::COPY_2_BYTE_OFFSET; - using snappy::internal::COPY_4_BYTE_OFFSET; - using snappy::internal::char_table; - - uint16 dst[256]; - - // Place invalid entries in all places to detect missing initialization - int assigned = 0; - for (int i = 0; i < 256; i++) { - dst[i] = 0xffff; - } - - // Small LITERAL entries. We store (len-1) in the top 6 bits. - for (unsigned int len = 1; len <= 60; len++) { - dst[LITERAL | ((len-1) << 2)] = MakeEntry(0, len, 0); - assigned++; - } - - // Large LITERAL entries. We use 60..63 in the high 6 bits to - // encode the number of bytes of length info that follow the opcode. - for (unsigned int extra_bytes = 1; extra_bytes <= 4; extra_bytes++) { - // We set the length field in the lookup table to 1 because extra - // bytes encode len-1. - dst[LITERAL | ((extra_bytes+59) << 2)] = MakeEntry(extra_bytes, 1, 0); - assigned++; - } - - // COPY_1_BYTE_OFFSET. - // - // The tag byte in the compressed data stores len-4 in 3 bits, and - // offset/256 in 5 bits. offset%256 is stored in the next byte. - // - // This format is used for length in range [4..11] and offset in - // range [0..2047] - for (unsigned int len = 4; len < 12; len++) { - for (unsigned int offset = 0; offset < 2048; offset += 256) { - dst[COPY_1_BYTE_OFFSET | ((len-4)<<2) | ((offset>>8)<<5)] = - MakeEntry(1, len, offset>>8); - assigned++; - } - } - - // COPY_2_BYTE_OFFSET. - // Tag contains len-1 in top 6 bits, and offset in next two bytes. - for (unsigned int len = 1; len <= 64; len++) { - dst[COPY_2_BYTE_OFFSET | ((len-1)<<2)] = MakeEntry(2, len, 0); - assigned++; - } - - // COPY_4_BYTE_OFFSET. - // Tag contents len-1 in top 6 bits, and offset in next four bytes. - for (unsigned int len = 1; len <= 64; len++) { - dst[COPY_4_BYTE_OFFSET | ((len-1)<<2)] = MakeEntry(4, len, 0); - assigned++; - } - - // Check that each entry was initialized exactly once. - EXPECT_EQ(256, assigned) << "Assigned only " << assigned << " of 256"; - for (int i = 0; i < 256; i++) { - EXPECT_NE(0xffff, dst[i]) << "Did not assign byte " << i; - } - - if (FLAGS_snappy_dump_decompression_table) { - printf("static const uint16 char_table[256] = {\n "); - for (int i = 0; i < 256; i++) { - printf("0x%04x%s", - dst[i], - ((i == 255) ? "\n" : (((i%8) == 7) ? ",\n " : ", "))); - } - printf("};\n"); - } - - // Check that computed table matched recorded table. - for (int i = 0; i < 256; i++) { - EXPECT_EQ(dst[i], char_table[i]) << "Mismatch in byte " << i; - } -} - static void CompressFile(const char* fname) { string fullinput; CHECK_OK(file::GetContents(fname, &fullinput, file::Defaults())); @@ -1190,13 +1194,16 @@ static void MeasureFile(const char* fname) { int start_len = (FLAGS_start_len < 0) ? fullinput.size() : FLAGS_start_len; int end_len = fullinput.size(); if (FLAGS_end_len >= 0) { - end_len = std::min<int>(fullinput.size(), FLAGS_end_len); + end_len = min<int>(fullinput.size(), FLAGS_end_len); } for (int len = start_len; len <= end_len; len++) { const char* const input = fullinput.data(); int repeats = (FLAGS_bytes + len) / (len + 1); if (FLAGS_zlib) Measure(input, len, ZLIB, repeats, 1024<<10); if (FLAGS_lzo) Measure(input, len, LZO, repeats, 1024<<10); + if (FLAGS_liblzf) Measure(input, len, LIBLZF, repeats, 1024<<10); + if (FLAGS_quicklz) Measure(input, len, QUICKLZ, repeats, 1024<<10); + if (FLAGS_fastlz) Measure(input, len, FASTLZ, repeats, 1024<<10); if (FLAGS_snappy) Measure(input, len, SNAPPY, repeats, 4096<<10); // For block-size based measurements @@ -1389,6 +1396,7 @@ BENCHMARK(BM_ZFlat)->DenseRange(0, ARRAYSIZE(files) - 1); } // namespace snappy + int main(int argc, char** argv) { InitGoogle(argv[0], &argc, &argv, true); RunSpecifiedBenchmarks(); @@ -1396,11 +1404,11 @@ int main(int argc, char** argv) { if (argc >= 2) { for (int arg = 1; arg < argc; arg++) { if (FLAGS_write_compressed) { - snappy::CompressFile(argv[arg]); + CompressFile(argv[arg]); } else if (FLAGS_write_uncompressed) { - snappy::UncompressFile(argv[arg]); + UncompressFile(argv[arg]); } else { - snappy::MeasureFile(argv[arg]); + MeasureFile(argv[arg]); } } return 0; diff --git a/src/third_party/snappy-1.1.7/CONTRIBUTING.md b/src/third_party/snappy-1.1.7/CONTRIBUTING.md deleted file mode 100644 index c7b84516c2f..00000000000 --- a/src/third_party/snappy-1.1.7/CONTRIBUTING.md +++ /dev/null @@ -1,26 +0,0 @@ -# How to Contribute - -We'd love to accept your patches and contributions to this project. There are -just a few small guidelines you need to follow. - -## Contributor License Agreement - -Contributions to this project must be accompanied by a Contributor License -Agreement. You (or your employer) retain the copyright to your contribution, -this simply gives us permission to use and redistribute your contributions as -part of the project. Head over to <https://cla.developers.google.com/> to see -your current agreements on file or to sign a new one. - -You generally only need to submit a CLA once, so if you've already submitted one -(even if it was for a different project), you probably don't need to do it -again. - -## Code reviews - -All submissions, including submissions by project members, require review. We -use GitHub pull requests for this purpose. Consult -[GitHub Help](https://help.github.com/articles/about-pull-requests/) for more -information on using pull requests. - -Please make sure that all the automated checks (CLA, AppVeyor, Travis) pass for -your pull requests. Pull requests whose checks fail may be ignored. diff --git a/src/third_party/snappy-1.1.7/build_linux/config.h b/src/third_party/snappy-1.1.7/build_linux/config.h deleted file mode 100644 index 2595d0e0caa..00000000000 --- a/src/third_party/snappy-1.1.7/build_linux/config.h +++ /dev/null @@ -1,62 +0,0 @@ -#ifndef THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ -#define THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ - -/* Define to 1 if the compiler supports __builtin_ctz and friends. */ -#define HAVE_BUILTIN_CTZ 1 - -/* Define to 1 if the compiler supports __builtin_expect. */ -#define HAVE_BUILTIN_EXPECT 1 - -/* Define to 1 if you have the <byteswap.h> header file. */ -#define HAVE_BYTESWAP_H 1 - -/* Define to 1 if you have a definition for mmap() in <sys/mman.h>. */ -#define HAVE_FUNC_MMAP 1 - -/* Define to 1 if you have a definition for sysconf() in <unistd.h>. */ -#define HAVE_FUNC_SYSCONF 1 - -/* Define to 1 to use the gflags package for command-line parsing. */ -/* #undef HAVE_GFLAGS */ - -/* Define to 1 if you have Google Test. */ -/* #undef HAVE_GTEST */ - -/* Define to 1 if you have the `lzo2' library (-llzo2). */ -/* #undef HAVE_LIBLZO2 */ - -/* Define to 1 if you have the `z' library (-lz). */ -#define HAVE_LIBZ 1 - -/* Define to 1 if you have the <stddef.h> header file. */ -#define HAVE_STDDEF_H 1 - -/* Define to 1 if you have the <stdint.h> header file. */ -#define HAVE_STDINT_H 1 - -/* Define to 1 if you have the <sys/endian.h> header file. */ -/* #undef HAVE_SYS_ENDIAN_H */ - -/* Define to 1 if you have the <sys/mman.h> header file. */ -#define HAVE_SYS_MMAN_H 1 - -/* Define to 1 if you have the <sys/resource.h> header file. */ -#define HAVE_SYS_RESOURCE_H 1 - -/* Define to 1 if you have the <sys/time.h> header file. */ -#define HAVE_SYS_TIME_H 1 - -/* Define to 1 if you have the <sys/uio.h> header file. */ -#define HAVE_SYS_UIO_H 1 - -/* Define to 1 if you have the <unistd.h> header file. */ -#define HAVE_UNISTD_H 1 - -/* Define to 1 if you have the <windows.h> header file. */ -/* #undef HAVE_WINDOWS_H */ - -/* Define to 1 if your processor stores words with the most significant byte - first (like Motorola and SPARC, unlike Intel and VAX). */ -/* #undef SNAPPY_IS_BIG_ENDIAN */ - -#endif // THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ diff --git a/src/third_party/snappy-1.1.7/build_posix/config.h b/src/third_party/snappy-1.1.7/build_posix/config.h deleted file mode 100644 index 16bb03153f2..00000000000 --- a/src/third_party/snappy-1.1.7/build_posix/config.h +++ /dev/null @@ -1,62 +0,0 @@ -#ifndef THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ -#define THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ - -/* Define to 1 if the compiler supports __builtin_ctz and friends. */ -#define HAVE_BUILTIN_CTZ 1 - -/* Define to 1 if the compiler supports __builtin_expect. */ -#define HAVE_BUILTIN_EXPECT 1 - -/* Define to 1 if you have the <byteswap.h> header file. */ -/* #undef HAVE_BYTESWAP_H */ - -/* Define to 1 if you have a definition for mmap() in <sys/mman.h>. */ -#define HAVE_FUNC_MMAP 1 - -/* Define to 1 if you have a definition for sysconf() in <unistd.h>. */ -#define HAVE_FUNC_SYSCONF 1 - -/* Define to 1 to use the gflags package for command-line parsing. */ -/* #undef HAVE_GFLAGS */ - -/* Define to 1 if you have Google Test. */ -/* #undef HAVE_GTEST */ - -/* Define to 1 if you have the `lzo2' library (-llzo2). */ -/* #undef HAVE_LIBLZO2 */ - -/* Define to 1 if you have the `z' library (-lz). */ -#define HAVE_LIBZ 1 - -/* Define to 1 if you have the <stddef.h> header file. */ -#define HAVE_STDDEF_H 1 - -/* Define to 1 if you have the <stdint.h> header file. */ -#define HAVE_STDINT_H 1 - -/* Define to 1 if you have the <sys/endian.h> header file. */ -/* #undef HAVE_SYS_ENDIAN_H */ - -/* Define to 1 if you have the <sys/mman.h> header file. */ -#define HAVE_SYS_MMAN_H 1 - -/* Define to 1 if you have the <sys/resource.h> header file. */ -#define HAVE_SYS_RESOURCE_H 1 - -/* Define to 1 if you have the <sys/time.h> header file. */ -#define HAVE_SYS_TIME_H 1 - -/* Define to 1 if you have the <sys/uio.h> header file. */ -#define HAVE_SYS_UIO_H 1 - -/* Define to 1 if you have the <unistd.h> header file. */ -#define HAVE_UNISTD_H 1 - -/* Define to 1 if you have the <windows.h> header file. */ -/* #undef HAVE_WINDOWS_H */ - -/* Define to 1 if your processor stores words with the most significant byte - first (like Motorola and SPARC, unlike Intel and VAX). */ -/* #undef SNAPPY_IS_BIG_ENDIAN */ - -#endif // THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_ diff --git a/src/third_party/snappy-1.1.7/build_windows/config.h b/src/third_party/snappy-1.1.7/build_windows/config.h deleted file mode 100644 index 8bb6650dce8..00000000000 --- a/src/third_party/snappy-1.1.7/build_windows/config.h +++ /dev/null @@ -1,62 +0,0 @@ -#ifndef THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_
-#define THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_
-
-/* Define to 1 if the compiler supports __builtin_ctz and friends. */
-/* #undef HAVE_BUILTIN_CTZ */
-
-/* Define to 1 if the compiler supports __builtin_expect. */
-/* #undef HAVE_BUILTIN_EXPECT */
-
-/* Define to 1 if you have the <byteswap.h> header file. */
-/* #undef HAVE_BYTESWAP_H */
-
-/* Define to 1 if you have a definition for mmap() in <sys/mman.h>. */
-/* #undef HAVE_FUNC_MMAP */
-
-/* Define to 1 if you have a definition for sysconf() in <unistd.h>. */
-/* #undef HAVE_FUNC_SYSCONF */
-
-/* Define to 1 to use the gflags package for command-line parsing. */
-/* #undef HAVE_GFLAGS */
-
-/* Define to 1 if you have Google Test. */
-/* #undef HAVE_GTEST */
-
-/* Define to 1 if you have the `lzo2' library (-llzo2). */
-/* #undef HAVE_LIBLZO2 */
-
-/* Define to 1 if you have the `z' library (-lz). */
-/* #undef HAVE_LIBZ */
-
-/* Define to 1 if you have the <stddef.h> header file. */
-#define HAVE_STDDEF_H 1
-
-/* Define to 1 if you have the <stdint.h> header file. */
-#define HAVE_STDINT_H 1
-
-/* Define to 1 if you have the <sys/endian.h> header file. */
-/* #undef HAVE_SYS_ENDIAN_H */
-
-/* Define to 1 if you have the <sys/mman.h> header file. */
-/* #undef HAVE_SYS_MMAN_H */
-
-/* Define to 1 if you have the <sys/resource.h> header file. */
-/* #undef HAVE_SYS_RESOURCE_H */
-
-/* Define to 1 if you have the <sys/time.h> header file. */
-/* #undef HAVE_SYS_TIME_H */
-
-/* Define to 1 if you have the <sys/uio.h> header file. */
-/* #undef HAVE_SYS_UIO_H */
-
-/* Define to 1 if you have the <unistd.h> header file. */
-/* #undef HAVE_UNISTD_H */
-
-/* Define to 1 if you have the <windows.h> header file. */
-#define HAVE_WINDOWS_H 1
-
-/* Define to 1 if your processor stores words with the most significant byte
- first (like Motorola and SPARC, unlike Intel and VAX). */
-/* #undef SNAPPY_IS_BIG_ENDIAN */
-
-#endif // THIRD_PARTY_SNAPPY_OPENSOURCE_CMAKE_CONFIG_H_
diff --git a/src/third_party/snappy-1.1.7/snappy-internal.h b/src/third_party/snappy-1.1.7/snappy-internal.h deleted file mode 100644 index 4b53d596f49..00000000000 --- a/src/third_party/snappy-1.1.7/snappy-internal.h +++ /dev/null @@ -1,224 +0,0 @@ -// Copyright 2008 Google Inc. All Rights Reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Internals shared between the Snappy implementation and its unittest. - -#ifndef THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ -#define THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ - -#include "snappy-stubs-internal.h" - -namespace snappy { -namespace internal { - -class WorkingMemory { - public: - WorkingMemory() : large_table_(NULL) { } - ~WorkingMemory() { delete[] large_table_; } - - // Allocates and clears a hash table using memory in "*this", - // stores the number of buckets in "*table_size" and returns a pointer to - // the base of the hash table. - uint16* GetHashTable(size_t input_size, int* table_size); - - private: - uint16 small_table_[1<<10]; // 2KB - uint16* large_table_; // Allocated only when needed - - // No copying - WorkingMemory(const WorkingMemory&); - void operator=(const WorkingMemory&); -}; - -// Flat array compression that does not emit the "uncompressed length" -// prefix. Compresses "input" string to the "*op" buffer. -// -// REQUIRES: "input_length <= kBlockSize" -// REQUIRES: "op" points to an array of memory that is at least -// "MaxCompressedLength(input_length)" in size. -// REQUIRES: All elements in "table[0..table_size-1]" are initialized to zero. -// REQUIRES: "table_size" is a power of two -// -// Returns an "end" pointer into "op" buffer. -// "end - op" is the compressed size of "input". -char* CompressFragment(const char* input, - size_t input_length, - char* op, - uint16* table, - const int table_size); - -// Find the largest n such that -// -// s1[0,n-1] == s2[0,n-1] -// and n <= (s2_limit - s2). -// -// Return make_pair(n, n < 8). -// Does not read *s2_limit or beyond. -// Does not read *(s1 + (s2_limit - s2)) or beyond. -// Requires that s2_limit >= s2. -// -// Separate implementation for 64-bit, little-endian cpus. -#if !defined(SNAPPY_IS_BIG_ENDIAN) && \ - (defined(ARCH_K8) || defined(ARCH_PPC) || defined(ARCH_ARM)) -static inline std::pair<size_t, bool> FindMatchLength(const char* s1, - const char* s2, - const char* s2_limit) { - assert(s2_limit >= s2); - size_t matched = 0; - - // This block isn't necessary for correctness; we could just start looping - // immediately. As an optimization though, it is useful. It creates some not - // uncommon code paths that determine, without extra effort, whether the match - // length is less than 8. In short, we are hoping to avoid a conditional - // branch, and perhaps get better code layout from the C++ compiler. - if (SNAPPY_PREDICT_TRUE(s2 <= s2_limit - 8)) { - uint64 a1 = UNALIGNED_LOAD64(s1); - uint64 a2 = UNALIGNED_LOAD64(s2); - if (a1 != a2) { - return std::pair<size_t, bool>(Bits::FindLSBSetNonZero64(a1 ^ a2) >> 3, - true); - } else { - matched = 8; - s2 += 8; - } - } - - // Find out how long the match is. We loop over the data 64 bits at a - // time until we find a 64-bit block that doesn't match; then we find - // the first non-matching bit and use that to calculate the total - // length of the match. - while (SNAPPY_PREDICT_TRUE(s2 <= s2_limit - 8)) { - if (UNALIGNED_LOAD64(s2) == UNALIGNED_LOAD64(s1 + matched)) { - s2 += 8; - matched += 8; - } else { - uint64 x = UNALIGNED_LOAD64(s2) ^ UNALIGNED_LOAD64(s1 + matched); - int matching_bits = Bits::FindLSBSetNonZero64(x); - matched += matching_bits >> 3; - assert(matched >= 8); - return std::pair<size_t, bool>(matched, false); - } - } - while (SNAPPY_PREDICT_TRUE(s2 < s2_limit)) { - if (s1[matched] == *s2) { - ++s2; - ++matched; - } else { - return std::pair<size_t, bool>(matched, matched < 8); - } - } - return std::pair<size_t, bool>(matched, matched < 8); -} -#else -static inline std::pair<size_t, bool> FindMatchLength(const char* s1, - const char* s2, - const char* s2_limit) { - // Implementation based on the x86-64 version, above. - assert(s2_limit >= s2); - int matched = 0; - - while (s2 <= s2_limit - 4 && - UNALIGNED_LOAD32(s2) == UNALIGNED_LOAD32(s1 + matched)) { - s2 += 4; - matched += 4; - } - if (LittleEndian::IsLittleEndian() && s2 <= s2_limit - 4) { - uint32 x = UNALIGNED_LOAD32(s2) ^ UNALIGNED_LOAD32(s1 + matched); - int matching_bits = Bits::FindLSBSetNonZero(x); - matched += matching_bits >> 3; - } else { - while ((s2 < s2_limit) && (s1[matched] == *s2)) { - ++s2; - ++matched; - } - } - return std::pair<size_t, bool>(matched, matched < 8); -} -#endif - -// Lookup tables for decompression code. Give --snappy_dump_decompression_table -// to the unit test to recompute char_table. - -enum { - LITERAL = 0, - COPY_1_BYTE_OFFSET = 1, // 3 bit length + 3 bits of offset in opcode - COPY_2_BYTE_OFFSET = 2, - COPY_4_BYTE_OFFSET = 3 -}; -static const int kMaximumTagLength = 5; // COPY_4_BYTE_OFFSET plus the actual offset. - -// Data stored per entry in lookup table: -// Range Bits-used Description -// ------------------------------------ -// 1..64 0..7 Literal/copy length encoded in opcode byte -// 0..7 8..10 Copy offset encoded in opcode byte / 256 -// 0..4 11..13 Extra bytes after opcode -// -// We use eight bits for the length even though 7 would have sufficed -// because of efficiency reasons: -// (1) Extracting a byte is faster than a bit-field -// (2) It properly aligns copy offset so we do not need a <<8 -static const uint16 char_table[256] = { - 0x0001, 0x0804, 0x1001, 0x2001, 0x0002, 0x0805, 0x1002, 0x2002, - 0x0003, 0x0806, 0x1003, 0x2003, 0x0004, 0x0807, 0x1004, 0x2004, - 0x0005, 0x0808, 0x1005, 0x2005, 0x0006, 0x0809, 0x1006, 0x2006, - 0x0007, 0x080a, 0x1007, 0x2007, 0x0008, 0x080b, 0x1008, 0x2008, - 0x0009, 0x0904, 0x1009, 0x2009, 0x000a, 0x0905, 0x100a, 0x200a, - 0x000b, 0x0906, 0x100b, 0x200b, 0x000c, 0x0907, 0x100c, 0x200c, - 0x000d, 0x0908, 0x100d, 0x200d, 0x000e, 0x0909, 0x100e, 0x200e, - 0x000f, 0x090a, 0x100f, 0x200f, 0x0010, 0x090b, 0x1010, 0x2010, - 0x0011, 0x0a04, 0x1011, 0x2011, 0x0012, 0x0a05, 0x1012, 0x2012, - 0x0013, 0x0a06, 0x1013, 0x2013, 0x0014, 0x0a07, 0x1014, 0x2014, - 0x0015, 0x0a08, 0x1015, 0x2015, 0x0016, 0x0a09, 0x1016, 0x2016, - 0x0017, 0x0a0a, 0x1017, 0x2017, 0x0018, 0x0a0b, 0x1018, 0x2018, - 0x0019, 0x0b04, 0x1019, 0x2019, 0x001a, 0x0b05, 0x101a, 0x201a, - 0x001b, 0x0b06, 0x101b, 0x201b, 0x001c, 0x0b07, 0x101c, 0x201c, - 0x001d, 0x0b08, 0x101d, 0x201d, 0x001e, 0x0b09, 0x101e, 0x201e, - 0x001f, 0x0b0a, 0x101f, 0x201f, 0x0020, 0x0b0b, 0x1020, 0x2020, - 0x0021, 0x0c04, 0x1021, 0x2021, 0x0022, 0x0c05, 0x1022, 0x2022, - 0x0023, 0x0c06, 0x1023, 0x2023, 0x0024, 0x0c07, 0x1024, 0x2024, - 0x0025, 0x0c08, 0x1025, 0x2025, 0x0026, 0x0c09, 0x1026, 0x2026, - 0x0027, 0x0c0a, 0x1027, 0x2027, 0x0028, 0x0c0b, 0x1028, 0x2028, - 0x0029, 0x0d04, 0x1029, 0x2029, 0x002a, 0x0d05, 0x102a, 0x202a, - 0x002b, 0x0d06, 0x102b, 0x202b, 0x002c, 0x0d07, 0x102c, 0x202c, - 0x002d, 0x0d08, 0x102d, 0x202d, 0x002e, 0x0d09, 0x102e, 0x202e, - 0x002f, 0x0d0a, 0x102f, 0x202f, 0x0030, 0x0d0b, 0x1030, 0x2030, - 0x0031, 0x0e04, 0x1031, 0x2031, 0x0032, 0x0e05, 0x1032, 0x2032, - 0x0033, 0x0e06, 0x1033, 0x2033, 0x0034, 0x0e07, 0x1034, 0x2034, - 0x0035, 0x0e08, 0x1035, 0x2035, 0x0036, 0x0e09, 0x1036, 0x2036, - 0x0037, 0x0e0a, 0x1037, 0x2037, 0x0038, 0x0e0b, 0x1038, 0x2038, - 0x0039, 0x0f04, 0x1039, 0x2039, 0x003a, 0x0f05, 0x103a, 0x203a, - 0x003b, 0x0f06, 0x103b, 0x203b, 0x003c, 0x0f07, 0x103c, 0x203c, - 0x0801, 0x0f08, 0x103d, 0x203d, 0x1001, 0x0f09, 0x103e, 0x203e, - 0x1801, 0x0f0a, 0x103f, 0x203f, 0x2001, 0x0f0b, 0x1040, 0x2040 -}; - -} // end namespace internal -} // end namespace snappy - -#endif // THIRD_PARTY_SNAPPY_SNAPPY_INTERNAL_H_ |