contrib/check-commit

perf: add command to benchmark bundle reading

Upcoming commits will be refactoring bundle2 I/O code.

This commit establishes a `hg perfbundleread` command that measures
how long it takes to read a bundle using various mechanisms.

As a baseline, here's output from an uncompressed bundle1
bundle of my Firefox repo (7,098,622,890 bytes):

! read(8k)
! wall 0.763481 comb 0.760000 user 0.160000 sys 0.600000 (best of 6)
! read(16k)
! wall 0.644512 comb 0.640000 user 0.110000 sys 0.530000 (best of 16)
! read(32k)
! wall 0.581172 comb 0.590000 user 0.060000 sys 0.530000 (best of 18)
! read(128k)
! wall 0.535183 comb 0.530000 user 0.010000 sys 0.520000 (best of 19)
! cg1 deltaiter()
! wall 0.873500 comb 0.880000 user 0.840000 sys 0.040000 (best of 12)
! cg1 getchunks()
! wall 6.283797 comb 6.270000 user 5.570000 sys 0.700000 (best of 3)
! cg1 read(8k)
! wall 1.097173 comb 1.100000 user 0.400000 sys 0.700000 (best of 10)
! cg1 read(16k)
! wall 0.810750 comb 0.800000 user 0.200000 sys 0.600000 (best of 13)
! cg1 read(32k)
! wall 0.671215 comb 0.670000 user 0.110000 sys 0.560000 (best of 15)
! cg1 read(128k)
! wall 0.597857 comb 0.600000 user 0.020000 sys 0.580000 (best of 15)

And from an uncompressed bundle2 bundle (6,070,036,163 bytes):

! read(8k)
! wall 0.676997 comb 0.680000 user 0.160000 sys 0.520000 (best of 15)
! read(16k)
! wall 0.592706 comb 0.590000 user 0.080000 sys 0.510000 (best of 17)
! read(32k)
! wall 0.529395 comb 0.530000 user 0.050000 sys 0.480000 (best of 16)
! read(128k)
! wall 0.491270 comb 0.490000 user 0.010000 sys 0.480000 (best of 19)
! bundle2 forwardchunks()
! wall 2.997131 comb 2.990000 user 2.270000 sys 0.720000 (best of 4)
! bundle2 iterparts()
! wall 12.247197 comb 10.670000 user 8.170000 sys 2.500000 (best of 3)
! bundle2 part seek()
! wall 11.761675 comb 10.500000 user 8.240000 sys 2.260000 (best of 3)
! bundle2 part read(8k)
! wall 9.116163 comb 9.110000 user 8.240000 sys 0.870000 (best of 3)
! bundle2 part read(16k)
! wall 8.984362 comb 8.970000 user 8.110000 sys 0.860000 (best of 3)
! bundle2 part read(32k)
! wall 8.758364 comb 8.740000 user 7.860000 sys 0.880000 (best of 3)
! bundle2 part read(128k)
! wall 8.749040 comb 8.730000 user 7.830000 sys 0.900000 (best of 3)

We already see some interesting data. Notably that bundle2 has
significant overhead compared to bundle1. This matters for e.g. stream
clone bundles, which can be applied at >1Gbps.

Differential Revision: https://phab.mercurial-scm.org/D1385

#!/usr/bin/env python
#
# Copyright 2014 Matt Mackall <[e-mail]>
#
# A tool/hook to run basic sanity checks on commits/patches for
# submission to Mercurial. Install by adding the following to your
# .hg/hgrc:
#
# [hooks]
# pretxncommit = contrib/check-commit
#
# The hook can be temporarily bypassed with:
#
# $ BYPASS= hg commit
#
# See also: https://mercurial-scm.org/wiki/ContributingChanges

from __future__ import absolute_import, print_function

import os
import re
import sys

commitheader = r"^(?:# [^\n]*\n)*"
afterheader = commitheader + r"(?!#)"
beforepatch = afterheader + r"(?!\n(?!@@))"

errors = [
    (beforepatch + r".*[(]bc[)]", "(BC) needs to be uppercase"),
    (beforepatch + r".*[(]issue \d\d\d",
     "no space allowed between issue and number"),
    (beforepatch + r".*[(]bug(\d|\s)", "use (issueDDDD) instead of bug"),
    (commitheader + r"# User [^@\n]+\n", "username is not an email address"),
    (commitheader + r"(?!merge with )[^#]\S+[^:] ",
     "summary line doesn't start with 'topic: '"),
    (afterheader + r"[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (afterheader + r"[^\n]*: *[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (afterheader + r"\S*[^A-Za-z0-9-_]\S*: ",
     "summary keyword should be most user-relevant one-word command or topic"),
    (afterheader + r".*\.\s*\n", "don't add trailing period on summary line"),
    (afterheader + r".{79,}", "summary line too long (limit is 78)"),
    (r"\n\+\n( |\+)\n", "adds double empty line"),
    (r"\n \n\+\n", "adds double empty line"),
    # Forbid "_" in function name.
    #
    # We skip the check for cffi related functions. They use names mapping the
    # name of the C function. C function names may contain "_".
    (r"\n\+[ \t]+def (?!cffi)[a-z]+_[a-z]",
     "adds a function with foo_bar naming"),
]

word = re.compile('\S')
def nonempty(first, second):
    if word.search(first):
        return first
    return second

def checkcommit(commit, node=None):
    exitcode = 0
    printed = node is None
    hits = []
    signtag = (afterheader +
          r'Added (tag [^ ]+|signature) for changeset [a-f0-9]{12}')
    if re.search(signtag, commit):
        return 0
    for exp, msg in errors:
        for m in re.finditer(exp, commit):
            end = m.end()
            trailing = re.search(r'(\\n)+$', exp)
            if trailing:
                end -= len(trailing.group()) / 2
            hits.append((end, exp, msg))
    if hits:
        hits.sort()
        pos = 0
        last = ''
        for n, l in enumerate(commit.splitlines(True)):
            pos += len(l)
            while len(hits):
                end, exp, msg = hits[0]
                if pos < end:
                    break
                if not printed:
                    printed = True
                    print("node: %s" % node)
                print("%d: %s" % (n, msg))
                print(" %s" % nonempty(l, last)[:-1])
                if "BYPASS" not in os.environ:
                    exitcode = 1
                del hits[0]
            last = nonempty(l, last)

    return exitcode

def readcommit(node):
    return os.popen("hg export %s" % node).read()

if __name__ == "__main__":
    exitcode = 0
    node = os.environ.get("HG_NODE")

    if node:
        commit = readcommit(node)
        exitcode = checkcommit(commit)
    elif sys.argv[1:]:
        for node in sys.argv[1:]:
            exitcode |= checkcommit(readcommit(node), node)
    else:
        commit = sys.stdin.read()
        exitcode = checkcommit(commit)
    sys.exit(exitcode)