view mercurial/repocache.py @ 52245:d57d1606049c stable

clone: properly exclude rev-branch-cache from post clone cache warming When adding "CACHE_REV_BRANCH" to "CACHES_ALL" in e51161b12c7e, I did not expected it to impact the clone steps. However the "CACHES_POST_CLONE" set is created rather creatively. (we should fix that, but not on stable) The benchmark caught a quite significant slowdown one hardlink and ssh-stream clones. Such slow down can be reduced to around ~5% by fully warming the cache before the clone. However keeping this expensive step away from the clone operation fully fix the slowdown and preserve the initial intend. Example slowdow for hardlink clone ### benchmark.name = hg.command.clone # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = none # benchmark.variants.issue6528 = default # benchmark.variants.protocol = local-hardlink # benchmark.variants.pulled-delta-reuse-policy = default # benchmark.variants.resource-usage = default # benchmark.variants.validate = default ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog 6.8.2: 19.799752 6.9rc0: 29.017493 (+46.55%, +9.22) after: 19.929341 ## data-env-vars.name = mercurial-public-2018-08-01-zstd-sparse-revlog 6.8.2: 0.468020 6.9rc0: 1.701294 (+263.51%, +1.23) after: 0.471934 ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog 6.8.2: 2.397564 6.9rc0: 5.666641 (+137.41%, +3.28) after: 2.428085
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 13 Nov 2024 13:33:36 +0100
parents f4733654f144
children
line wrap: on
line source

# repocache.py - in-memory repository cache for long-running services
#
# Copyright 2018 Yuya Nishihara <yuya@tcha.org>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import annotations

import collections
import gc
import threading

from . import (
    error,
    hg,
    obsolete,
    scmutil,
    util,
)


class repoloader:
    """Load repositories in background thread

    This is designed for a forking server. A cached repo cannot be obtained
    until the server fork()s a worker and the loader thread stops.
    """

    def __init__(self, ui, maxlen):
        self._ui = ui.copy()
        self._cache = util.lrucachedict(max=maxlen)
        # use deque and Event instead of Queue since deque can discard
        # old items to keep at most maxlen items.
        self._inqueue = collections.deque(maxlen=maxlen)
        self._accepting = False
        self._newentry = threading.Event()
        self._thread = None

    def start(self):
        assert not self._thread
        if self._inqueue.maxlen == 0:
            # no need to spawn loader thread as the cache is disabled
            return
        self._accepting = True
        self._thread = threading.Thread(target=self._mainloop)
        self._thread.start()

    def stop(self):
        if not self._thread:
            return
        self._accepting = False
        self._newentry.set()
        self._thread.join()
        self._thread = None
        self._cache.clear()
        self._inqueue.clear()

    def load(self, path):
        """Request to load the specified repository in background"""
        self._inqueue.append(path)
        self._newentry.set()

    def get(self, path):
        """Return a cached repo if available

        This function must be called after fork(), where the loader thread
        is stopped. Otherwise, the returned repo might be updated by the
        loader thread.
        """
        if self._thread and self._thread.is_alive():
            raise error.ProgrammingError(
                b'cannot obtain cached repo while loader is active'
            )
        return self._cache.peek(path, None)

    def _mainloop(self):
        while self._accepting:
            # Avoid heavy GC after fork(), which would cancel the benefit of
            # COW. We assume that GIL is acquired while GC is underway in the
            # loader thread. If that isn't true, we might have to move
            # gc.collect() to the main thread so that fork() would never stop
            # the thread where GC is in progress.
            gc.collect()

            self._newentry.wait()
            while self._accepting:
                self._newentry.clear()
                try:
                    path = self._inqueue.popleft()
                except IndexError:
                    break
                scmutil.callcatch(self._ui, lambda: self._load(path))

    def _load(self, path):
        start = util.timer()
        # TODO: repo should be recreated if storage configuration changed
        try:
            # pop before loading so inconsistent state wouldn't be exposed
            repo = self._cache.pop(path)
        except KeyError:
            repo = hg.repository(self._ui, path).unfiltered()
        _warmupcache(repo)
        repo.ui.log(
            b'repocache',
            b'loaded repo into cache: %s (in %.3fs)\n',
            path,
            util.timer() - start,
        )
        self._cache.insert(path, repo)


# TODO: think about proper API of preloading cache
def _warmupcache(repo):
    repo.invalidateall()
    repo.changelog
    repo.obsstore._all
    repo.obsstore.successors
    repo.obsstore.predecessors
    repo.obsstore.children
    for name in obsolete.cachefuncs:
        obsolete.getrevs(repo, name)
    # ensure the phase cache is fully initialized
    repo._phasecache.phase(repo, repo.changelog.tiprev())


# TODO: think about proper API of attaching preloaded attributes
def copycache(srcrepo, destrepo):
    """Copy cached attributes from srcrepo to destrepo"""
    destfilecache = destrepo._filecache
    srcfilecache = srcrepo._filecache
    if b'changelog' in srcfilecache:
        destfilecache[b'changelog'] = ce = srcfilecache[b'changelog']
        ce.obj.opener = ce.obj._inner.opener = destrepo.svfs
    if b'obsstore' in srcfilecache:
        destfilecache[b'obsstore'] = ce = srcfilecache[b'obsstore']
        ce.obj.svfs = destrepo.svfs
    if b'_phasecache' in srcfilecache:
        destfilecache[b'_phasecache'] = ce = srcfilecache[b'_phasecache']
        ce.obj.opener = destrepo.svfs