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
# extension to emulate invoking 'dirstate.write()' at the time
# specified by '[fakedirstatewritetime] fakenow', only when
# 'dirstate.write()' is invoked via functions below:
#
# - 'workingctx._poststatusfixup()' (= 'repo.status()')
# - 'committablectx.markcommitted()'
from mercurial import (
context,
dirstatemap as dirstatemapmod,
extensions,
policy,
registrar,
)
from mercurial.dirstateutils import timestamp
from mercurial.utils import dateutil
try:
from mercurial import rustext
rustext.__name__ # force actual import (see hgdemandimport)
except ImportError:
rustext = None
configtable = {}
configitem = registrar.configitem(configtable)
configitem(
b'fakedirstatewritetime',
b'fakenow',
default=None,
)
parsers = policy.importmod('parsers')
has_rust_dirstate = policy.importrust('dirstate') is not None
def pack_dirstate(orig, dmap, copymap, pl):
return orig(dmap, copymap, pl)
def fakewrite(ui, func):
# fake "now" of 'pack_dirstate' only if it is invoked while 'func'
fakenow = ui.config(b'fakedirstatewritetime', b'fakenow')
if not fakenow:
# Execute original one, if fakenow isn't configured. This is
# useful to prevent subrepos from executing replaced one,
# because replacing 'parsers.pack_dirstate' is also effective
# in subrepos.
return func()
# parsing 'fakenow' in YYYYmmddHHMM format makes comparison between
# 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy
fakenow = dateutil.parsedate(fakenow, [b'%Y%m%d%H%M'])[0]
fakenow = timestamp.timestamp((fakenow, 0, False))
if has_rust_dirstate:
# The Rust implementation does not use public parse/pack dirstate
# to prevent conversion round-trips
orig_dirstatemap_write = dirstatemapmod.dirstatemap.write
wrapper = lambda self, tr, st: orig_dirstatemap_write(self, tr, st)
dirstatemapmod.dirstatemap.write = wrapper
orig_get_fs_now = timestamp.get_fs_now
wrapper = lambda *args: pack_dirstate(orig_pack_dirstate, *args)
orig_module = parsers
orig_pack_dirstate = parsers.pack_dirstate
orig_module.pack_dirstate = wrapper
timestamp.get_fs_now = (
lambda *args: fakenow
) # XXX useless for this purpose now
try:
return func()
finally:
orig_module.pack_dirstate = orig_pack_dirstate
timestamp.get_fs_now = orig_get_fs_now
if has_rust_dirstate:
dirstatemapmod.dirstatemap.write = orig_dirstatemap_write
def _poststatusfixup(orig, workingctx, status, fixup):
ui = workingctx.repo().ui
return fakewrite(ui, lambda: orig(workingctx, status, fixup))
def markcommitted(orig, committablectx, node):
ui = committablectx.repo().ui
return fakewrite(ui, lambda: orig(committablectx, node))
def extsetup(ui):
extensions.wrapfunction(
context.workingctx, '_poststatusfixup', _poststatusfixup
)
extensions.wrapfunction(context.workingctx, 'markcommitted', markcommitted)