view contrib/dumprevlog @ 51977:42a116f1cdc1

branchmap-v3: introduce a "stop_rev" argument to `headsrevs` The `headsrevs` method of the revlog already have a `revs` argument to compute the headrevs of a limited set of heads. However, it disable the use of the native compiled code to compute the heads, which slows down the branchmap v3 code a lot. The branchmap v3 usage is actually quite constrained as we will always only ignores a part at the top of the graph. So we could be significantly faster. We start by making small change to the python side to improve the situation and introduce the new API. More collaboration with the native code are coming later. This massively speedup operation and close most of the remaining gaps between branchmap-v3 and branchmap-v2. especially on repository with many revs like mozilla-try. A small overhead remains mostly because the `headrevs` logic currently has some inefficiently. We will look into them from there. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.368769 (+57.79%, +0.14) branch-v3 after: 0.239857 (+2.63%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.372460 (+58.34%, +0.14) branch-v3 after: 0.240972 (+2.44%, +0.01) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.318907 (+24.78%, +0.06) branch-v3 after: 0.268560 (+5.08%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.349752 (+3.17%, +0.01) branch-v3 after: 0.349389 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.354300 (+2.24%, +0.01) branch-v3 after: 0.355661 (+2.64%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.396293 (+4.23%, +0.02) branch-v3 after: 0.408851 (+7.54%, +0.03) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.424769 (+3.06%, +0.01) branch-v3 after: 0.427782 (+3.79%, +0.02) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.421796 (+2.28%, +0.01) branch-v3 after: 0.422354 (+2.41%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.443849 (+3.34%, +0.01) branch-v3 after: 0.443197 (+3.19%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.234055 (+83.18%, +2.83) branch-v3 after: 3.819477 (+12.23%, +0.42) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.307813 (+82.58%, +2.85) branch-v3 after: 3.590284 (+3.92%, +0.14) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.176076 (+49.36%, +1.71) branch-v3 after: 3.633278 (+4.84%, +0.17)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 03 Sep 2024 11:11:17 +0200
parents 6000f5b25c9b
children
line wrap: on
line source

#!/usr/bin/env python3
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump


import sys
from mercurial.node import hex
from mercurial import (
    encoding,
    pycompat,
    revlog,
)
from mercurial.utils import procutil

from mercurial.revlogutils import (
    constants as revlog_constants,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    procutil.setbinary(fp)


def binopen(path, mode=b'rb'):
    if b'b' not in mode:
        mode = mode + b'b'
    return open(path, pycompat.sysstr(mode))


binopen.options = {}


def printb(data, end=b'\n'):
    sys.stdout.flush()
    procutil.stdout.write(data + end)


for f in sys.argv[1:]:
    localf = encoding.strtolocal(f)
    if not localf.endswith(b'.i'):
        print("file:", f, file=sys.stderr)
        print("  invalid filename", file=sys.stderr)

    r = revlog.revlog(
        binopen,
        target=(revlog_constants.KIND_OTHER, b'dump-revlog'),
        radix=localf[:-2],
    )
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        printb(b"node: %s" % hex(n))
        printb(b"linkrev: %d" % r.linkrev(i))
        printb(b"parents: %s %s" % (hex(p[0]), hex(p[1])))
        printb(b"length: %d" % len(d))
        printb(b"-start-")
        printb(d)
        printb(b"-end-")