Mercurial > hg
view tests/test-storage.py @ 42743:8c9a6adec67a
rust-discovery: using the children cache in add_missing
The DAG range computation often needs to get back to very old
revisions, and turns out to be disproportionately long, given
that the end goal is to remove the descendents of the given
missing revisons from the undecided set.
The fast iteration capabilities available in the Rust case make
it possible to avoid the DAG range entirely, at the cost of
precomputing the children cache, and to simply iterate on
children of the given missing revisions.
This is a case where staying on the same side of the interface
between the two languages has clear benefits.
On discoveries with initial undecided sets
small enough to bypass sampling entirely, the total cost of
computing the children cache and the subsequent iteration
becomes better than the Python + C counterpart, which relies on
reachableroots2.
For example, on a repo with more than one million revisions with
an initial undecided set of 11 elements, we get these figures:
Rust version with simple iteration
addcommons: 57.287us
first undecided computation: 184.278334ms
first children cache computation: 131.056us
addmissings iteration: 42.766us
first addinfo total: 185.24 ms
Python + C version
first addcommons: 0.29 ms
addcommons 0.21 ms
first undecided computation 191.35 ms
addmissings 45.75 ms
first addinfo total: 237.77 ms
On discoveries with large undecided sets, the initial price paid
makes the first addinfo slower than the Python + C version,
but that's more than compensated by the gain in sampling and
subsequent iterations.
Here's an extreme example with an undecided set of a million revisions:
Rust version:
first undecided computation: 293.842629ms
first children cache computation: 407.911297ms
addmissings iteration: 34.312869ms
first addinfo total: 776.02 ms
taking initial sample
query 2: sampling time: 1318.38 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings: 143.062us
Python + C version:
first undecided computation 298.13 ms
addmissings 80.13 ms
first addinfo total: 399.62 ms
taking initial sample
query 2: sampling time: 3957.23 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings 52.88 ms
Differential Revision: https://phab.mercurial-scm.org/D6428
author | Georges Racinet <georges.racinet@octobus.net> |
---|---|
date | Tue, 16 Apr 2019 01:16:39 +0200 |
parents | 1bf3e6041e2c |
children | 2372284d9457 |
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__)