view contrib/fixpax.py @ 29792:58467204cac0

hgweb: tweak zlib chunking behavior

When doing streaming compression with zlib, zlib appears to emit chunks
with data after ~20-30kb on average is available. In other words, most
calls to compress() return an empty string. On the mozilla-unified repo,
only 48,433 of 921,167 (5.26%) of calls to compress() returned data.
In other words, we were sending hundreds of thousands of empty chunks
via a generator where they touched who knows how many frames (my guess
is millions). Filtering out the empty chunks from the generator
cuts down on overhead.

In addition, we were previously feeding 8kb chunks into zlib
compression. Since this function tends to emit *compressed* data after
20-30kb is available, it would take several calls before data was
produced. We increase the amount of data fed in at a time to 32kb.
This reduces the number of calls to compress() from 921,167 to
115,146. It also reduces the number of output chunks from 48,433 to
31,377. This does increase the average output chunk size by a little.
But I don't think this will matter in most scenarios.

The combination of these 2 changes appears to shave ~6s CPU time
or ~3% from a server serving the mozilla-unified repo.

#!/usr/bin/env python
# fixpax - fix ownership in bdist_mpkg output
#
# Copyright 2015 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# MIT license (http://opensource.org/licenses/MIT)

"""Set file ownership to 0 in an Archive.pax.gz.
Suitable for fixing files bdist_mpkg output:
*.mpkg/Contents/Packages/*.pkg/Contents/Archive.pax.gz
"""

from __future__ import absolute_import, print_function
import gzip
import os
import sys

def fixpax(iname, oname):
    i = gzip.GzipFile(iname)
    o = gzip.GzipFile(oname, "w")

    while True:
        magic = i.read(6)
        dev = i.read(6)
        ino = i.read(6)
        mode = i.read(6)
        i.read(6) # uid
        i.read(6) # gid
        nlink = i.read(6)
        rdev = i.read(6)
        mtime = i.read(11)
        namesize = i.read(6)
        filesize = i.read(11)
        name = i.read(int(namesize, 8))
        data = i.read(int(filesize, 8))

        o.write(magic)
        o.write(dev)
        o.write(ino)
        o.write(mode)
        o.write("000000")
        o.write("000000")
        o.write(nlink)
        o.write(rdev)
        o.write(mtime)
        o.write(namesize)
        o.write(filesize)
        o.write(name)
        o.write(data)

        if name.startswith("TRAILER!!!"):
            o.write(i.read())
            break

    o.close()
    i.close()

if __name__ == '__main__':
    for iname in sys.argv[1:]:
        print('fixing file ownership in %s' % iname)
        oname = sys.argv[1] + '.tmp'
        fixpax(iname, oname)
        os.rename(oname, iname)