1
0
mirror of https://github.com/lz4/lz4.git synced 2026-10-24 01:48:57 +03:00
Yann Collet 84507cb3d6 MT: synchronous signals remain deliverable in workers ; CLI reports SIGBUS on memory-mapped input (checkpoint)
Prototype, not intended for a PR as is.

A memory-mapped file truncated during its compression, or unreadable (I/O error),
raises SIGBUS in the thread reading it. Worker threads were blocking all signals,
so a fault in a worker killed the process, bypassing any handler.

- lz4frame.c : worker threads still block signals intended for the application,
  but not synchronous ones (SIGBUS, SIGSEGV, SIGFPE, SIGILL) : the application's
  handlers are invoked on faults (documented in lz4frame.h, nbWorkers).
- lz4 CLI : while a file is memory-mapped, a SIGBUS handler reports
  "Error 53 : <file> : file truncated or unreadable during compression (memory-mapped) ;
  retry with --no-mmap", then terminates the process (async-signal-safe : write, _exit).
  The message is prepared beforehand ; when several threads fault simultaneously,
  only the first one reports. Previous handler restored once unmapped.
- -H help, man page (--[no-]mmap) and lz4io.h updated.

Truncation test (silesia x4 truncated during -9 -T4) : error 53 with one message,
including --no-frame-crc (workers read the mapping first) ; with the former signal
mask, the process was killed by SIGBUS. --no-mmap : unchanged.
Output and speed unchanged. Validated : full tests MT / no-MT, ASAN+UBSAN, TSAN,
make test, wine (frameMT, lz4.exe == Linux CLI), CLI == dev CLI.
2026-10-22 04:26:50 -07:00
2026-01-22 15:27:42 -08:00
2018-01-14 00:21:43 -08:00
2025-04-30 21:26:16 -07:00
2026-02-13 15:32:22 -08:00
2024-07-16 12:37:32 -07:00
2017-08-30 15:02:04 -07:00
2024-07-10 07:26:20 +02:00
2023-06-07 18:00:38 +00:00

LZ4 - Extremely fast compression

LZ4 is a lossless compression algorithm, providing compression speed > 500 MB/s per core, scalable with multi-core CPUs. It features an extremely fast decoder, with speed in multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.

Compression speed can be tuned dynamically, by selecting an "acceleration" factor which trades compression ratio for faster speed. On the other end, a high compression derivative, LZ4_HC, is also provided, trading CPU time for improved compression ratio. All versions feature the same decompression speed.

LZ4 is also compatible with dictionary compression, both at API and CLI (-D) levels. It can ingest any input file as dictionary, though only the final 64 KB are used. This capability can be combined with the Zstandard Dictionary Builder, in order to drastically improve compression performance on small files.

The LZ4 library is provided as open-source software using the BSD 2-Clause license. The lz4 command line utility is provided under the GPL-2.0-or-later license.

Benchmarks

The benchmark uses lzbench, from @inikep compiled with GCC v8.2.0 on Linux 64-bits (Ubuntu 4.18.0-17). The reference system uses a Core i7-9700K CPU @ 4.9GHz (w/ turbo boost). Benchmark evaluates the compression of reference Silesia Corpus in single-thread mode.

Compressor Factor Compression Decompression
memcpy 1.000 13700 MB/s 13700 MB/s
LZ4 default (v1.9.0) 2.101 780 MB/s 4970 MB/s
LZO 2.09 2.108 670 MB/s 860 MB/s
QuickLZ 1.5.0 2.238 575 MB/s 780 MB/s
Snappy 1.1.4 2.091 565 MB/s 1950 MB/s
Zstandard 1.4.0 -1 2.883 515 MB/s 1380 MB/s
LZF v3.6 2.073 415 MB/s 910 MB/s
zlib deflate 1.2.11 -1 2.730 100 MB/s 415 MB/s
LZ4 HC -9 (v1.9.0) 2.721 41 MB/s 4900 MB/s
zlib deflate 1.2.11 -6 3.099 36 MB/s 445 MB/s

Installation

make
make install     # this command may require root permissions

LZ4's Makefile supports standard Makefile conventions, including staged installs, redirection, or command redefinition. It is compatible with parallel builds (-j#).

Alternative build systems (CMake, Meson, Visual Studio) are provided in build/.

Building LZ4 - Using vcpkg

You can download and install LZ4 using the vcpkg dependency manager:

git clone https://github.com/Microsoft/vcpkg.git
cd vcpkg
./bootstrap-vcpkg.sh
./vcpkg integrate install
./vcpkg install lz4

The LZ4 port in vcpkg is kept up to date by Microsoft team members and community contributors. If the version is out of date, please create an issue or pull request on the vcpkg repository.

Documentation

The raw LZ4 block compression format is detailed within lz4_Block_format.

Arbitrarily long files or data streams are compressed using multiple blocks, for streaming requirements. These blocks are organized into a frame, defined in lz4_Frame_format. Interoperable versions of LZ4 must also respect the frame format.

The library API is documented in its headers: lz4.h (block API), lz4hc.h (high compression) and lz4frame.h (frame API).

Other source versions

Beyond the C reference source, many contributors have created versions of lz4 in multiple languages (Java, C#, Python, Perl, Ruby, etc.). A list of known source ports is maintained on the LZ4 Homepage.

Packaging status

Most distributions are bundled with a package manager which allows easy installation of both the liblz4 library and the lz4 command line interface.

Packaging status

Special Thanks

  • Takayuki Matsuoka, aka @t-mat, for exceptional first-class support throughout the lifetime of this project
Description
Чрезвычайно быстрый алгоритм сжатия
Readme 14 MiB
Languages
C 86.1%
Makefile 4.4%
Python 2.6%
Shell 2.4%
Meson 1.5%
Other 3%