view tests/test-storage.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 2372284d9457
children 6000f5b25c9b
line wrap: on
line source

# This test verifies the conformance of various classes to various
# storage interfaces.
from __future__ import absolute_import

import silenttestrunner

from mercurial import (
    error,
    filelog,
    revlog,
    transaction,
    ui as uimod,
    vfs as vfsmod,
)

from mercurial.testing import storage as storagetesting

try:
    from hgext import sqlitestore
except ImportError:
    sqlitestore = None

try:
    import sqlite3

    if sqlite3.sqlite_version_info < (3, 8, 3):
        # WITH clause not supported
        sqlitestore = None
except ImportError:
    pass

try:
    from mercurial import zstd

    zstd.__version__
except ImportError:
    zstd = None

STATE = {
    'lastindex': 0,
    'ui': uimod.ui(),
    'vfs': vfsmod.vfs(b'.', realpath=True),
}


def makefilefn(self):
    """Factory for filelog instances."""
    fl = filelog.filelog(STATE['vfs'], b'filelog-%d' % STATE['lastindex'])
    STATE['lastindex'] += 1
    return fl


def maketransaction(self):
    vfsmap = {b'plain': STATE['vfs'], b'store': STATE['vfs']}

    return transaction.transaction(
        STATE['ui'].warn, STATE['vfs'], vfsmap, b'journal', b'undo'
    )


def addrawrevision(
    self,
    fl,
    tr,
    node,
    p1,
    p2,
    linkrev,
    rawtext=None,
    delta=None,
    censored=False,
    ellipsis=False,
    extstored=False,
):
    flags = 0

    if censored:
        flags |= revlog.REVIDX_ISCENSORED
    if ellipsis:
        flags |= revlog.REVIDX_ELLIPSIS
    if extstored:
        flags |= revlog.REVIDX_EXTSTORED

    if rawtext is not None:
        fl._revlog.addrawrevision(rawtext, tr, linkrev, p1, p2, node, flags)
    elif delta is not None:
        fl._revlog.addrawrevision(
            rawtext, tr, linkrev, p1, p2, node, flags, cachedelta=delta
        )
    else:
        raise error.Abort('must supply rawtext or delta arguments')

    # We may insert bad data. Clear caches to prevent e.g. cache hits to
    # bypass hash verification.
    fl._revlog.clearcaches()


# Assigning module-level attributes that inherit from unittest.TestCase
# is all that is needed to register tests.
filelogindextests = storagetesting.makeifileindextests(
    makefilefn, maketransaction, addrawrevision
)
filelogdatatests = storagetesting.makeifiledatatests(
    makefilefn, maketransaction, addrawrevision
)
filelogmutationtests = storagetesting.makeifilemutationtests(
    makefilefn, maketransaction, addrawrevision
)


def makesqlitefile(self):
    path = STATE['vfs'].join(b'db-%d.db' % STATE['lastindex'])
    STATE['lastindex'] += 1

    db = sqlitestore.makedb(path)

    compression = b'zstd' if zstd else b'zlib'

    return sqlitestore.sqlitefilestore(db, b'dummy-path', compression)


def addrawrevisionsqlite(
    self,
    fl,
    tr,
    node,
    p1,
    p2,
    linkrev,
    rawtext=None,
    delta=None,
    censored=False,
    ellipsis=False,
    extstored=False,
):
    flags = 0

    if censored:
        flags |= sqlitestore.FLAG_CENSORED

    if ellipsis | extstored:
        raise error.Abort(
            b'support for ellipsis and extstored flags not ' b'supported'
        )

    if rawtext is not None:
        fl._addrawrevision(node, rawtext, tr, linkrev, p1, p2, flags=flags)
    elif delta is not None:
        fl._addrawrevision(
            node, rawtext, tr, linkrev, p1, p2, storedelta=delta, flags=flags
        )
    else:
        raise error.Abort(b'must supply rawtext or delta arguments')


if sqlitestore is not None:
    sqlitefileindextests = storagetesting.makeifileindextests(
        makesqlitefile, maketransaction, addrawrevisionsqlite
    )
    sqlitefiledatatests = storagetesting.makeifiledatatests(
        makesqlitefile, maketransaction, addrawrevisionsqlite
    )
    sqlitefilemutationtests = storagetesting.makeifilemutationtests(
        makesqlitefile, maketransaction, addrawrevisionsqlite
    )

if __name__ == '__main__':
    silenttestrunner.main(__name__)