tests/f
author Gregory Szorc <gregory.szorc@gmail.com>
Sat, 26 Sep 2015 21:43:13 -0700
changeset 26380 56a640b0f656
parent 23912 7d0aa6269ece
child 26950 6686ae524f94
permissions -rwxr-xr-x
revlog: don't flush data file after every added revision The current behavior of revlogs is to flush the data file when writing data to it. Tracing system calls revealed that changegroup processing incurred numerous write(2) calls for values much smaller than the default buffer size (Python defaults to 4096, but it can be adjusted based on detected block size at run time by CPython). The reason we flush revlogs is so readers have all data available. For example, the current code in revlog.py will re-open the revlog file (instead of seeking an existing file handle) to read the text of a revision. This happens when starting a new delta chain when adding several revisions from changegroups, for example. Yes, this is likely sub-optimal (we should probably be sharing file descriptors between readers and writers to avoid the flushing and associated overhead of re-opening files). While flushing revlogs is necessary, it appears all callers are diligent about flushing files before a read is performed (see buildtext() in _addrevision()), making the flush in _writeentry() redundant and unncessary. So, we remove it. In practice, this means we incur a write(2) a) when the buffer is full (typically 4096 bytes) b) when a new delta chain is created rather than after every added revision. This applies to every revlog, but by volume it mostly impacts filelogs. Removing the redundant flush from _writeentry() significantly reduces the number of write(2) calls during changegroup processing on my Linux machine. When applying a changegroup of the hg repo based on my local repo, the total number of write(2) calls during application of the mercurial/localrepo.py revlogs dropped from 1,320 to 217 with this patch applied. Total I/O related system calls dropped from 1,577 to 474. When unbundling a mozilla-central gzipped bundle (264,403 changesets with 1,492,215 changes to 222,507 files), total write(2) calls dropped from 1,252,881 to 827,106 and total system calls dropped from 3,601,259 to 3,178,636 - a reduction of 425,775! While the system call reduction is significant, it appears to have no impact on wall time on my Linux and Windows machines. Still, fewer syscalls is fewer syscalls. Surely this can't hurt. If nothing else, it makes examining remaining system call usage simpler and opens the door to experimenting with the performance impact of different buffer sizes.

#!/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
"""

import sys, os, errno, re, glob, optparse

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).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 & 0777))
            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:
            try:
                from hashlib import md5
            except ImportError:
                from md5 import md5
            facts.append('md5=%s' % md5(content).hexdigest()[:opts.bytes])
        if opts.sha1 and content is not None:
            try:
                from hashlib import sha1
            except ImportError:
                from sha import sha as sha1
            facts.append('sha1=%s' % sha1(content).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)