mercurial/filelog.py
author Gregory Szorc <gregory.szorc@gmail.com>
Fri, 13 Jan 2017 19:58:00 -0800
changeset 30817 2b279126b8f5
parent 30589 be5b2098a817
child 32177 8ac7ac714e92
permissions -rw-r--r--
revlog: use compression engine APIs for decompression Now that compression engines declare their header in revlog chunks and can decompress revlog chunks, we refactor revlog.decompress() to use them. Making full use of the property that revlog compressor objects are reusable, revlog instances now maintain a dict mapping an engine's revlog header to a compressor object. This is not only a performance optimization for engines where compressor object reuse can result in better performance, but it also serves as a cache of header values so we don't need to perform redundant lookups against the compression engine manager. (Yes, I measured and the overhead of a function call versus a dict lookup was observed.) Replacing the previous inline lookup table with a dict lookup was measured to make chunk reading ~2.5% slower on changelogs and ~4.5% slower on manifests. So, the inline lookup table has been mostly preserved so we don't lose performance. This is unfortunate. But many decompression operations complete in microseconds, so Python attribute lookup, dict lookup, and function calls do matter. The impact of this change on mozilla-unified is as follows: $ hg perfrevlogchunks -c ! chunk ! wall 1.953663 comb 1.950000 user 1.920000 sys 0.030000 (best of 6) ! wall 1.946000 comb 1.940000 user 1.910000 sys 0.030000 (best of 6) ! chunk batch ! wall 1.791075 comb 1.800000 user 1.760000 sys 0.040000 (best of 6) ! wall 1.785690 comb 1.770000 user 1.750000 sys 0.020000 (best of 6) $ hg perfrevlogchunks -m ! chunk ! wall 2.587262 comb 2.580000 user 2.550000 sys 0.030000 (best of 4) ! wall 2.616330 comb 2.610000 user 2.560000 sys 0.050000 (best of 4) ! chunk batch ! wall 2.427092 comb 2.420000 user 2.400000 sys 0.020000 (best of 5) ! wall 2.462061 comb 2.460000 user 2.400000 sys 0.060000 (best of 4) Changelog chunk reading is slightly faster but manifest reading is slower. What gives? On this repo, 99.85% of changelog entries are zlib compressed (the 'x' header). On the manifest, 67.5% are zlib and 32.4% are '\0'. This patch swapped the test order of 'x' and '\0' so now 'x' is tested first. This makes changelogs faster since they almost always hit the first branch. This makes a significant percentage of manifest '\0' chunks slower because that code path now performs an extra test. Yes, I too can't believe we're able to measure the impact of an if..elif with simple string compares. I reckon this code would benefit from being written in C...

# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import re
import struct

from . import (
    error,
    mdiff,
    revlog,
)

_mdre = re.compile('\1\n')
def parsemeta(text):
    """return (metadatadict, keylist, metadatasize)"""
    # text can be buffer, so we can't use .startswith or .index
    if text[:2] != '\1\n':
        return None, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
    return meta, (s + 2)

def packmeta(meta, text):
    keys = sorted(meta.iterkeys())
    metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
    return "\1\n%s\1\n%s" % (metatext, text)

def _censoredtext(text):
    m, offs = parsemeta(text)
    return m and "censored" in m

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        super(filelog, self).__init__(opener,
                        "/".join(("data", path + ".i")))

    def read(self, node):
        t = self.revision(node)
        if not t.startswith('\1\n'):
            return t
        s = t.index('\1\n', 2)
        return t[s + 2:]

    def add(self, text, meta, transaction, link, p1=None, p2=None):
        if meta or text.startswith('\1\n'):
            text = packmeta(meta, text)
        return self.addrevision(text, transaction, link, p1, p2)

    def renamed(self, node):
        if self.parents(node)[0] != revlog.nullid:
            return False
        t = self.revision(node)
        m = parsemeta(t)[0]
        if m and "copy" in m:
            return (m["copy"], revlog.bin(m["copyrev"]))
        return False

    def size(self, rev):
        """return the size of a given revision"""

        # for revisions with renames, we have to go the slow way
        node = self.node(rev)
        if self.renamed(node):
            return len(self.read(node))
        if self.iscensored(rev):
            return 0

        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
        return super(filelog, self).size(rev)

    def cmp(self, node, text):
        """compare text with a given file revision

        returns True if text is different than what is stored.
        """

        t = text
        if text.startswith('\1\n'):
            t = '\1\n\1\n' + text

        samehashes = not super(filelog, self).cmp(node, t)
        if samehashes:
            return False

        # censored files compare against the empty file
        if self.iscensored(self.rev(node)):
            return text != ''

        # renaming a file produces a different hash, even if the data
        # remains unchanged. Check if it's the case (slow):
        if self.renamed(node):
            t2 = self.read(node)
            return t2 != text

        return True

    def checkhash(self, text, node, p1=None, p2=None, rev=None):
        try:
            super(filelog, self).checkhash(text, node, p1=p1, p2=p2, rev=rev)
        except error.RevlogError:
            if _censoredtext(text):
                raise error.CensoredNodeError(self.indexfile, node, text)
            raise

    def iscensored(self, rev):
        """Check if a file revision is censored."""
        return self.flags(rev) & revlog.REVIDX_ISCENSORED

    def _peek_iscensored(self, baserev, delta, flush):
        """Quickly check if a delta produces a censored revision."""
        # Fragile heuristic: unless new file meta keys are added alphabetically
        # preceding "censored", all censored revisions are prefixed by
        # "\1\ncensored:". A delta producing such a censored revision must be a
        # full-replacement delta, so we inspect the first and only patch in the
        # delta for this prefix.
        hlen = struct.calcsize(">lll")
        if len(delta) <= hlen:
            return False

        oldlen = self.rawsize(baserev)
        newlen = len(delta) - hlen
        if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
            return False

        add = "\1\ncensored:"
        addlen = len(add)
        return newlen >= addlen and delta[hlen:hlen + addlen] == add