revset: stop serializing node when using "%ln"
Turning hundred of thousand of node from node to hex and back can be slow… what
about we stop doing it?
In many case were we are using node id we should be using revision id. However
this is not a good reason to have a stupidly slow implementation of "%ln".
This caught my attention again because the phase discovery during push make an
extensive use of "%ln" or huge set. In absolute, that phase discovery probably
should use "%ld" and need to improves its algorithmic complexity, but improving
"%ln" seems simple and long overdue. This greatly speeds up `hg push` on
repository with many drafts.
Here are some relevant poulpe benchmarks:
### 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: 44.235070
after: 20.416329 (-53.85%, -23.82)
## benchmark.variants.revs = any-100-extra-rev
before: 49.234697
after: 26.519829 (-46.14%, -22.71)
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 10.138396
after: 7.750458 (-23.55%, -2.39)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 1.263859
after: 0.700229 (-44.60%, -0.56)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 399.484481
after: 346.5089 (-13.26%, -52.98)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 4.540080
after: 3.401700 (-25.07%, -1.14)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 2.975765
after: 1.870798 (-37.13%, -1.10)
# Extension dedicated to test patch.diff() upgrade modes
from mercurial import (
error,
logcmdutil,
patch,
pycompat,
registrar,
scmutil,
)
cmdtable = {}
command = registrar.command(cmdtable)
@command(
b'autodiff',
[(b'', b'git', b'', b'git upgrade mode (yes/no/auto/warn/abort)')],
b'[OPTION]... [FILE]...',
)
def autodiff(ui, repo, *pats, **opts):
opts = pycompat.byteskwargs(opts)
diffopts = patch.difffeatureopts(ui, opts)
git = opts.get(b'git', b'no')
brokenfiles = set()
losedatafn = None
if git in (b'yes', b'no'):
diffopts.git = git == b'yes'
diffopts.upgrade = False
elif git == b'auto':
diffopts.git = False
diffopts.upgrade = True
elif git == b'warn':
diffopts.git = False
diffopts.upgrade = True
def losedatafn(fn=None, **kwargs):
brokenfiles.add(fn)
return True
elif git == b'abort':
diffopts.git = False
diffopts.upgrade = True
def losedatafn(fn=None, **kwargs):
raise error.Abort(b'losing data for %s' % fn)
else:
raise error.Abort(b'--git must be yes, no or auto')
ctx1, ctx2 = logcmdutil.revpair(repo, [])
m = scmutil.match(ctx2, pats, opts)
it = patch.diff(
repo,
ctx1.node(),
ctx2.node(),
match=m,
opts=diffopts,
losedatafn=losedatafn,
)
for chunk in it:
ui.write(chunk)
for fn in sorted(brokenfiles):
ui.write((b'data lost for: %s\n' % fn))