##// END OF EJS Templates
util: implement zstd compression engine...
util: implement zstd compression engine Now that zstd is vendored and being built (in some configurations), we can implement a compression engine for zstd! The zstd engine is a little different from existing engines. Because it may not always be present, we have to defer load the module in case importing it fails. We facilitate this via a cached property that holds a reference to the module or None. The "available" method is implemented to reflect reality. The zstd engine declares its ability to handle bundles using the "zstd" human name and the "ZS" internal name. The latter was chosen because internal names are 2 characters (by only convention I think) and "ZS" seems reasonable. The engine, like others, supports specifying the compression level. However, there are no consumers of this API that yet pass in that argument. I have plans to change that, so stay tuned. Since all we need to do to support bundle generation with a new compression engine is implement and register the compression engine, bundle generation with zstd "just works!" Tests demonstrating this have been added. How does performance of zstd for bundle generation compare? On the mozilla-unified repo, `hg bundle --all -t <engine>-v2` yields the following on my i7-6700K on Linux: engine CPU time bundle size vs orig size throughput none 97.0s 4,054,405,584 100.0% 41.8 MB/s bzip2 (l=9) 393.6s 975,343,098 24.0% 10.3 MB/s gzip (l=6) 184.0s 1,140,533,074 28.1% 22.0 MB/s zstd (l=1) 108.2s 1,119,434,718 27.6% 37.5 MB/s zstd (l=2) 111.3s 1,078,328,002 26.6% 36.4 MB/s zstd (l=3) 113.7s 1,011,823,727 25.0% 35.7 MB/s zstd (l=4) 116.0s 1,008,965,888 24.9% 35.0 MB/s zstd (l=5) 121.0s 977,203,148 24.1% 33.5 MB/s zstd (l=6) 131.7s 927,360,198 22.9% 30.8 MB/s zstd (l=7) 139.0s 912,808,505 22.5% 29.2 MB/s zstd (l=12) 198.1s 854,527,714 21.1% 20.5 MB/s zstd (l=18) 681.6s 789,750,690 19.5% 5.9 MB/s On compression, zstd for bundle generation delivers: * better compression than gzip with significantly less CPU utilization * better than bzip2 compression ratios while still being significantly faster than gzip * ability to aggressively tune compression level to achieve significantly smaller bundles That last point is important. With clone bundles, a server can pre-generate a bundle file, upload it to a static file server, and redirect clients to transparently download it during clone. The server could choose to produce a zstd bundle with the highest compression settings possible. This would take a very long time - a magnitude longer than a typical zstd bundle generation - but the result would be hundreds of megabytes smaller! For the clone volume we do at Mozilla, this could translate to petabytes of bandwidth savings per year and faster clones (due to smaller transfer size). I don't have detailed numbers to report on decompression. However, zstd decompression is fast: >1 GB/s output throughput on this machine, even through the Python bindings. And it can do that regardless of the compression level of the input. By the time you have enough data to worry about overhead of decompression, you have plenty of other things to worry about performance wise. zstd is wins all around. I can't wait to implement support for it on the wire protocol and in revlogs.

File last commit:

r30435:b86a448a default
r30442:41a81067 default
Show More
zstd_cffi.py
152 lines | 4.8 KiB | text/x-python | PythonLexer
# Copyright (c) 2016-present, Gregory Szorc
# All rights reserved.
#
# This software may be modified and distributed under the terms
# of the BSD license. See the LICENSE file for details.
"""Python interface to the Zstandard (zstd) compression library."""
from __future__ import absolute_import, unicode_literals
import io
from _zstd_cffi import (
ffi,
lib,
)
_CSTREAM_IN_SIZE = lib.ZSTD_CStreamInSize()
_CSTREAM_OUT_SIZE = lib.ZSTD_CStreamOutSize()
class _ZstdCompressionWriter(object):
def __init__(self, cstream, writer):
self._cstream = cstream
self._writer = writer
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, exc_tb):
if not exc_type and not exc_value and not exc_tb:
out_buffer = ffi.new('ZSTD_outBuffer *')
out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE)
out_buffer.size = _CSTREAM_OUT_SIZE
out_buffer.pos = 0
while True:
res = lib.ZSTD_endStream(self._cstream, out_buffer)
if lib.ZSTD_isError(res):
raise Exception('error ending compression stream: %s' % lib.ZSTD_getErrorName)
if out_buffer.pos:
self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
out_buffer.pos = 0
if res == 0:
break
return False
def write(self, data):
out_buffer = ffi.new('ZSTD_outBuffer *')
out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE)
out_buffer.size = _CSTREAM_OUT_SIZE
out_buffer.pos = 0
# TODO can we reuse existing memory?
in_buffer = ffi.new('ZSTD_inBuffer *')
in_buffer.src = ffi.new('char[]', data)
in_buffer.size = len(data)
in_buffer.pos = 0
while in_buffer.pos < in_buffer.size:
res = lib.ZSTD_compressStream(self._cstream, out_buffer, in_buffer)
if lib.ZSTD_isError(res):
raise Exception('zstd compress error: %s' % lib.ZSTD_getErrorName(res))
if out_buffer.pos:
self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
out_buffer.pos = 0
class ZstdCompressor(object):
def __init__(self, level=3, dict_data=None, compression_params=None):
if dict_data:
raise Exception('dict_data not yet supported')
if compression_params:
raise Exception('compression_params not yet supported')
self._compression_level = level
def compress(self, data):
# Just use the stream API for now.
output = io.BytesIO()
with self.write_to(output) as compressor:
compressor.write(data)
return output.getvalue()
def copy_stream(self, ifh, ofh):
cstream = self._get_cstream()
in_buffer = ffi.new('ZSTD_inBuffer *')
out_buffer = ffi.new('ZSTD_outBuffer *')
out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE)
out_buffer.size = _CSTREAM_OUT_SIZE
out_buffer.pos = 0
total_read, total_write = 0, 0
while True:
data = ifh.read(_CSTREAM_IN_SIZE)
if not data:
break
total_read += len(data)
in_buffer.src = ffi.new('char[]', data)
in_buffer.size = len(data)
in_buffer.pos = 0
while in_buffer.pos < in_buffer.size:
res = lib.ZSTD_compressStream(cstream, out_buffer, in_buffer)
if lib.ZSTD_isError(res):
raise Exception('zstd compress error: %s' %
lib.ZSTD_getErrorName(res))
if out_buffer.pos:
ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
total_write = out_buffer.pos
out_buffer.pos = 0
# We've finished reading. Flush the compressor.
while True:
res = lib.ZSTD_endStream(cstream, out_buffer)
if lib.ZSTD_isError(res):
raise Exception('error ending compression stream: %s' %
lib.ZSTD_getErrorName(res))
if out_buffer.pos:
ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos))
total_write += out_buffer.pos
out_buffer.pos = 0
if res == 0:
break
return total_read, total_write
def write_to(self, writer):
return _ZstdCompressionWriter(self._get_cstream(), writer)
def _get_cstream(self):
cstream = lib.ZSTD_createCStream()
cstream = ffi.gc(cstream, lib.ZSTD_freeCStream)
res = lib.ZSTD_initCStream(cstream, self._compression_level)
if lib.ZSTD_isError(res):
raise Exception('cannot init CStream: %s' %
lib.ZSTD_getErrorName(res))
return cstream