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
# Mercurial extension to provide 'hg relink' command
#
# Copyright (C) 2007 Brendan Cully <brendan@kublai.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""recreates hardlinks between repository clones"""
import os
import stat
from mercurial.i18n import _
from mercurial.pycompat import open
from mercurial import (
error,
hg,
registrar,
util,
)
from mercurial.utils import (
stringutil,
urlutil,
)
cmdtable = {}
command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'
@command(
b'relink', [], _(b'[ORIGIN]'), helpcategory=command.CATEGORY_MAINTENANCE
)
def relink(ui, repo, origin=None, **opts):
"""recreate hardlinks between two repositories
When repositories are cloned locally, their data files will be
hardlinked so that they only use the space of a single repository.
Unfortunately, subsequent pulls into either repository will break
hardlinks for any files touched by the new changesets, even if
both repositories end up pulling the same changes.
Similarly, passing --rev to "hg clone" will fail to use any
hardlinks, falling back to a complete copy of the source
repository.
This command lets you recreate those hardlinks and reclaim that
wasted space.
This repository will be relinked to share space with ORIGIN, which
must be on the same local disk. If ORIGIN is omitted, looks for
"default-relink", then "default", in [paths].
Do not attempt any read operations on this repository while the
command is running. (Both repositories will be locked against
writes.)
"""
if not hasattr(util, 'samefile') or not hasattr(util, 'samedevice'):
raise error.Abort(_(b'hardlinks are not supported on this system'))
if origin is None and b'default-relink' in ui.paths:
origin = b'default-relink'
path = urlutil.get_unique_pull_path_obj(b'relink', ui, origin)
src = hg.repository(repo.baseui, path.loc)
ui.status(_(b'relinking %s to %s\n') % (src.store.path, repo.store.path))
if repo.root == src.root:
ui.status(_(b'there is nothing to relink\n'))
return
if not util.samedevice(src.store.path, repo.store.path):
# No point in continuing
raise error.Abort(_(b'source and destination are on different devices'))
with repo.lock(), src.lock():
candidates = sorted(collect(src, ui))
targets = prune(candidates, src.store.path, repo.store.path, ui)
do_relink(src.store.path, repo.store.path, targets, ui)
def collect(src, ui):
seplen = len(os.path.sep)
candidates = []
live = len(src[b'tip'].manifest())
# Your average repository has some files which were deleted before
# the tip revision. We account for that by assuming that there are
# 3 tracked files for every 2 live files as of the tip version of
# the repository.
#
# mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
total = live * 3 // 2
src = src.store.path
progress = ui.makeprogress(_(b'collecting'), unit=_(b'files'), total=total)
pos = 0
ui.status(
_(b"tip has %d files, estimated total number of files: %d\n")
% (live, total)
)
for dirpath, dirnames, filenames in os.walk(src):
dirnames.sort()
relpath = dirpath[len(src) + seplen :]
for filename in sorted(filenames):
if filename[-2:] not in (b'.d', b'.i'):
continue
st = os.stat(os.path.join(dirpath, filename))
if not stat.S_ISREG(st.st_mode):
continue
pos += 1
candidates.append((os.path.join(relpath, filename), st))
progress.update(pos, item=filename)
progress.complete()
ui.status(_(b'collected %d candidate storage files\n') % len(candidates))
return candidates
def prune(candidates, src, dst, ui):
def linkfilter(src, dst, st):
try:
ts = os.stat(dst)
except OSError:
# Destination doesn't have this file?
return False
if util.samefile(src, dst):
return False
if not util.samedevice(src, dst):
# No point in continuing
raise error.Abort(
_(b'source and destination are on different devices')
)
if st.st_size != ts.st_size:
return False
return st
targets = []
progress = ui.makeprogress(
_(b'pruning'), unit=_(b'files'), total=len(candidates)
)
pos = 0
for fn, st in candidates:
pos += 1
srcpath = os.path.join(src, fn)
tgt = os.path.join(dst, fn)
ts = linkfilter(srcpath, tgt, st)
if not ts:
ui.debug(b'not linkable: %s\n' % fn)
continue
targets.append((fn, ts.st_size))
progress.update(pos, item=fn)
progress.complete()
ui.status(
_(b'pruned down to %d probably relinkable files\n') % len(targets)
)
return targets
def do_relink(src, dst, files, ui):
def relinkfile(src, dst):
bak = dst + b'.bak'
os.rename(dst, bak)
try:
util.oslink(src, dst)
except OSError:
os.rename(bak, dst)
raise
os.remove(bak)
CHUNKLEN = 65536
relinked = 0
savedbytes = 0
progress = ui.makeprogress(
_(b'relinking'), unit=_(b'files'), total=len(files)
)
pos = 0
for f, sz in files:
pos += 1
source = os.path.join(src, f)
tgt = os.path.join(dst, f)
# Binary mode, so that read() works correctly, especially on Windows
sfp = open(source, b'rb')
dfp = open(tgt, b'rb')
sin = sfp.read(CHUNKLEN)
while sin:
din = dfp.read(CHUNKLEN)
if sin != din:
break
sin = sfp.read(CHUNKLEN)
sfp.close()
dfp.close()
if sin:
ui.debug(b'not linkable: %s\n' % f)
continue
try:
relinkfile(source, tgt)
progress.update(pos, item=f)
relinked += 1
savedbytes += sz
except OSError as inst:
ui.warn(b'%s: %s\n' % (tgt, stringutil.forcebytestr(inst)))
progress.complete()
ui.status(
_(b'relinked %d files (%s reclaimed)\n')
% (relinked, util.bytecount(savedbytes))
)