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
"""test behavior of propertycache and unfiltered propertycache
The repoview overlay is quite complex. We test the behavior of
property cache of both localrepo and repoview to prevent
regression."""
import os
import subprocess
from mercurial import (
hg,
localrepo,
pycompat,
ui as uimod,
util,
)
from mercurial.utils import procutil
# create some special property cache that trace they call
calllog = []
@util.propertycache
def testcachedfoobar(repo):
name = repo.filtername
if name is None:
name = ''
val = len(name)
calllog.append(val)
return val
unficalllog = []
@localrepo.unfilteredpropertycache
def testcachedunfifoobar(repo):
name = repo.filtername
if name is None:
name = ''
val = 100 + len(name)
unficalllog.append(val)
return val
# plug them on repo
localrepo.localrepository.testcachedfoobar = testcachedfoobar
localrepo.localrepository.testcachedunfifoobar = testcachedunfifoobar
# Create an empty repo and instantiate it. It is important to run
# these tests on the real object to detect regression.
repopath = pycompat.fsencode(os.path.join(os.environ['TESTTMP'], 'repo'))
assert (
subprocess.call(
pycompat.rapply(procutil.tonativestr, [b'hg', b'init', repopath])
)
== 0
)
ui = uimod.ui.load()
repo = hg.repository(ui, path=repopath).unfiltered()
print('')
print('=== property cache ===')
print('')
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print('')
print('= first access on unfiltered, should do a call')
print('access:', repo.testcachedfoobar)
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print('')
print('= second access on unfiltered, should not do call')
print('access', repo.testcachedfoobar)
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print('')
print('= first access on "visible" view, should do a call')
visibleview = repo.filtered('visible')
print(
'cached value ("visible" view):',
vars(visibleview).get('testcachedfoobar', 'NOCACHE'),
)
print('access:', visibleview.testcachedfoobar)
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print(
'cached value ("visible" view):',
vars(visibleview).get('testcachedfoobar', 'NOCACHE'),
)
print('')
print('= second access on "visible view", should not do call')
print('access:', visibleview.testcachedfoobar)
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print(
'cached value ("visible" view):',
vars(visibleview).get('testcachedfoobar', 'NOCACHE'),
)
print('')
print('= no effect on other view')
immutableview = repo.filtered('immutable')
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedfoobar', 'NOCACHE'),
)
print('access:', immutableview.testcachedfoobar)
print('calllog:', calllog)
print(
'cached value (unfiltered):', vars(repo).get('testcachedfoobar', 'NOCACHE')
)
print(
'cached value ("visible" view):',
vars(visibleview).get('testcachedfoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedfoobar', 'NOCACHE'),
)
# unfiltered property cache test
print('')
print('')
print('=== unfiltered property cache ===')
print('')
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)
print('')
print('= first access on unfiltered, should do a call')
print('access (unfiltered):', repo.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print('')
print('= second access on unfiltered, should not do call')
print('access (unfiltered):', repo.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print('')
print('= access on view should use the unfiltered cache')
print('access (unfiltered): ', repo.testcachedunfifoobar)
print('access ("visible" view): ', visibleview.testcachedunfifoobar)
print('access ("immutable" view):', immutableview.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)
print('')
print('= even if we clear the unfiltered cache')
del repo.__dict__['testcachedunfifoobar']
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)
print('unficalllog:', unficalllog)
print('access ("visible" view): ', visibleview.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)
print('access ("immutable" view):', immutableview.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)
print('access (unfiltered): ', repo.testcachedunfifoobar)
print('unficalllog:', unficalllog)
print(
'cached value (unfiltered): ',
vars(repo).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("visible" view): ',
vars(visibleview).get('testcachedunfifoobar', 'NOCACHE'),
)
print(
'cached value ("immutable" view):',
vars(immutableview).get('testcachedunfifoobar', 'NOCACHE'),
)