phases: rework the logic of _pushdiscoveryphase to bound complexity This rework the various graph traversal in _pushdiscoveryphase to keep the complexity in check. This is done though a couple of things: - first, limiting the space we have to explore, for example, if we are not in publishing push, we don't need to consider remote draft roots that are also draft locally, as there is nothing to be moved there. - avoid unbounded descendant computation, and use the faster "rev between" computation. This provide a massive boost to performance when exchanging with repository with a massive amount of draft, like mozilla-try: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 20.346590 seconds after: 11.232059 seconds (-38.15%, -7.48 seconds) ## benchmark.variants.revs = any-100-extra-rev before: 24.752051 seconds after: 15.367412 seconds (-37.91%, -9.38 seconds) After this changes, the push operation is still quite too slow. Some of this can be attributed to general phases slowness (reading all the roots from disk for example) and other know slowness (not using persistent-nodemap, branchmap, tags, etc. We are also working on them, but with this series, phase discovery during push no longer showing up in profile and this is a pretty nice and bit low-hanging fruit out of the way. ### (same case as the above) # benchmark.variants.revs = any-1-extra-rev pre-%ln-change: 44.235070 this-changeset: 11.232059 seconds (-74.61%, -33.00 seconds) # benchmark.variants.revs = any-100-extra-rev pre-%ln-change: 49.234697 this-changeset: 15.367412 seconds (-68.79%, -33.87 seconds) Note that with this change, the `hg push` performance is now much closer to the `hg pull` performance, even it still lagging behind a bit. (and the overall performance are still too slow). ### data-env-vars.name = mozilla-try-2023-03-22-ds2-pnm # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.pulled-delta-reuse-policy = default # bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 6.517450 hg.command.push: 11.219888 ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 10.160991 hg.command.push: 14.251107 ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.pulled-delta-reuse-policy = default ## bin-env-vars.hg.flavor = default ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 8.577772 hg.command.push: 11.232059 ## bin-env-vars.hg.flavor = default ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 13.152976 hg.command.push: 15.367412 ## bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 8.731982 hg.command.push: 11.178751 ## bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 13.184236 hg.command.push: 15.620843

# This test verifies the conformance of various classes to various
# storage interfaces.

import silenttestrunner

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

from mercurial.testing import storage as storagetesting

try:
    from mercurial import rustext

    rustext.__name__
    # Does not pass with pure Rust index
    import sys

    sys.exit(80)
except ImportError:
    pass

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__)