wireproto: compress data from a generator
Currently, the "getbundle" wire protocol command obtains a generator of
data, converts it to a util.chunkbuffer, then converts it back to a
generator via the protocol's groupchunks() implementation. For the SSH
protocol, groupchunks() simply reads 4kb chunks then write()s the
data to a file descriptor. For the HTTP protocol, groupchunks() reads
32kb chunks, feeds those into a zlib compressor, emits compressed data
as it is available, and that is sent to the WSGI layer, where it is
likely turned into HTTP chunked transfer chunks as is or further
buffered and turned into a larger chunk.
For both the SSH and HTTP protocols, there is inefficiency from using
util.chunkbuffer.
For SSH, emitting consistent 4kb chunks sounds nice. However, the file
descriptor it is writing to is almost certainly buffered. That means
that a Python .write() probably doesn't translate into exactly what is
written to the I/O layer.
For HTTP, we're going through an intermediate layer to zlib compress
data. So all util.chunkbuffer is doing is ensuring that the chunks we
feed into the zlib compressor are of uniform size. This means more CPU
time in Python buffering and emitting chunks in util.chunkbuffer but
fewer function calls to zlib.
This patch introduces and implements a new wire protocol abstract
method: compresschunks(). It is like groupchunks() except it operates
on a generator instead of something with a .read(). The SSH
implementation simply proxies chunks. The HTTP implementation uses
zlib compression.
To avoid duplicate code, the HTTP groupchunks() has been reimplemented
in terms of compresschunks().
To prove this all works, the "getbundle" wire protocol command has been
switched to compresschunks(). This removes the util.chunkbuffer from
that command. Now, data essentially streams straight from the
changegroup emitter to the wire, possibly through a zlib compressor.
Generators all the way, baby.
There were slim to no performance changes on the server as measured
with the mozilla-central repository. This is likely because CPU
time is dominated by reading revlogs, producing the changegroup, and
zlib compressing the output stream. Still, this brings us a little
closer to our ideal of using generators everywhere.
#!/usr/bin/env python
"""
Utility for inspecting files in various ways.
This tool is like the collection of tools found in a unix environment but are
cross platform and stable and suitable for our needs in the test suite.
This can be used instead of tools like:
[
dd
find
head
hexdump
ls
md5sum
readlink
sha1sum
stat
tail
test
readlink.py
md5sum.py
"""
from __future__ import absolute_import
import glob
import hashlib
import optparse
import os
import re
import sys
def visit(opts, filenames, outfile):
"""Process filenames in the way specified in opts, writing output to
outfile."""
for f in sorted(filenames):
isstdin = f == '-'
if not isstdin and not os.path.lexists(f):
outfile.write('%s: file not found\n' % f)
continue
quiet = opts.quiet and not opts.recurse or isstdin
isdir = os.path.isdir(f)
islink = os.path.islink(f)
isfile = os.path.isfile(f) and not islink
dirfiles = None
content = None
facts = []
if isfile:
if opts.type:
facts.append('file')
if opts.hexdump or opts.dump or opts.md5:
content = file(f, 'rb').read()
elif islink:
if opts.type:
facts.append('link')
content = os.readlink(f)
elif isstdin:
content = sys.stdin.read()
if opts.size:
facts.append('size=%s' % len(content))
elif isdir:
if opts.recurse or opts.type:
dirfiles = glob.glob(f + '/*')
facts.append('directory with %s files' % len(dirfiles))
elif opts.type:
facts.append('type unknown')
if not isstdin:
stat = os.lstat(f)
if opts.size and not isdir:
facts.append('size=%s' % stat.st_size)
if opts.mode and not islink:
facts.append('mode=%o' % (stat.st_mode & 0o777))
if opts.links:
facts.append('links=%s' % stat.st_nlink)
if opts.newer:
# mtime might be in whole seconds so newer file might be same
if stat.st_mtime >= os.stat(opts.newer).st_mtime:
facts.append('newer than %s' % opts.newer)
else:
facts.append('older than %s' % opts.newer)
if opts.md5 and content is not None:
h = hashlib.md5(content)
facts.append('md5=%s' % h.hexdigest()[:opts.bytes])
if opts.sha1 and content is not None:
h = hashlib.sha1(content)
facts.append('sha1=%s' % h.hexdigest()[:opts.bytes])
if isstdin:
outfile.write(', '.join(facts) + '\n')
elif facts:
outfile.write('%s: %s\n' % (f, ', '.join(facts)))
elif not quiet:
outfile.write('%s:\n' % f)
if content is not None:
chunk = content
if not islink:
if opts.lines:
if opts.lines >= 0:
chunk = ''.join(chunk.splitlines(True)[:opts.lines])
else:
chunk = ''.join(chunk.splitlines(True)[opts.lines:])
if opts.bytes:
if opts.bytes >= 0:
chunk = chunk[:opts.bytes]
else:
chunk = chunk[opts.bytes:]
if opts.hexdump:
for i in range(0, len(chunk), 16):
s = chunk[i:i + 16]
outfile.write('%04x: %-47s |%s|\n' %
(i, ' '.join('%02x' % ord(c) for c in s),
re.sub('[^ -~]', '.', s)))
if opts.dump:
if not quiet:
outfile.write('>>>\n')
outfile.write(chunk)
if not quiet:
if chunk.endswith('\n'):
outfile.write('<<<\n')
else:
outfile.write('\n<<< no trailing newline\n')
if opts.recurse and dirfiles:
assert not isstdin
visit(opts, dirfiles, outfile)
if __name__ == "__main__":
parser = optparse.OptionParser("%prog [options] [filenames]")
parser.add_option("-t", "--type", action="store_true",
help="show file type (file or directory)")
parser.add_option("-m", "--mode", action="store_true",
help="show file mode")
parser.add_option("-l", "--links", action="store_true",
help="show number of links")
parser.add_option("-s", "--size", action="store_true",
help="show size of file")
parser.add_option("-n", "--newer", action="store",
help="check if file is newer (or same)")
parser.add_option("-r", "--recurse", action="store_true",
help="recurse into directories")
parser.add_option("-S", "--sha1", action="store_true",
help="show sha1 hash of the content")
parser.add_option("-M", "--md5", action="store_true",
help="show md5 hash of the content")
parser.add_option("-D", "--dump", action="store_true",
help="dump file content")
parser.add_option("-H", "--hexdump", action="store_true",
help="hexdump file content")
parser.add_option("-B", "--bytes", type="int",
help="number of characters to dump")
parser.add_option("-L", "--lines", type="int",
help="number of lines to dump")
parser.add_option("-q", "--quiet", action="store_true",
help="no default output")
(opts, filenames) = parser.parse_args(sys.argv[1:])
if not filenames:
filenames = ['-']
visit(opts, filenames, sys.stdout)