Mercurial > hg-stable
view contrib/perf.py @ 15141:16dc9a32ca04
mdiff: speed up showfunc for large diffs
This addresses the following issues with showfunc:
- Silly usage of regular expressions.
- Doing str.rstrip() needlessly in an inner loop.
- Doing catastrophic backtracking when trying to find a function line.
Finding function text is now at worst O(n lines in the old file), and
at best close to O(n hunks).
Given a diff like this[1]:
src/main/antlr3/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunker.g | 4 +-
src/main/java/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunkerLexer.java | 2 +-
src/main/java/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunkerParser.java | 29189 +++++----
3 files changed, 14741 insertions(+), 14454 deletions(-)
[1]: https://bitbucket.org/wwmm/chemicaltagger/changeset/d2bfbaecd4fc/raw
Without this change, hg log --stat --config diff.showfunc=1 takes an
absurdly long time to complete:
CallCount Recursive Total(ms) Inline(ms) module:lineno(function)
32813 0 80.3546 40.6086 mercurial.mdiff:160(yieldhunk)
+65062746 0 25.7227 25.7227 +<method 'match' of '_sre.SRE_Pattern' objects>
+65062746 0 14.0221 14.0221 +<method 'rstrip' of 'str' objects>
+1809 0 0.0009 0.0009 +mercurial.mdiff:148(contextend)
+1809 0 0.0003 0.0003 +<len>
65062746 0 25.7227 25.7227 <method 'match' of '_sre.SRE_Pattern' objects>
65062763 0 14.0221 14.0221 <method 'rstrip' of 'str' objects>
543 0 0.1631 0.1631 <zlib.decompress>
3 0 0.0505 0.0505 <mercurial.bdiff.blocks>
31007 0 80.4564 0.0477 mercurial.mdiff:147(_unidiff)
+32813 0 80.3546 40.6086 +mercurial.mdiff:160(yieldhunk)
+3 0 0.0505 0.0505 +<mercurial.bdiff.blocks>
+3618 0 0.0022 0.0022 +mercurial.mdiff:154(contextstart)
+5427 0 0.0013 0.0013 +<len>
+3 0 0.0001 0.0000 +re:188(compile)
1 0 80.8381 0.0322 mercurial.patch:1777(diffstatdata)
+107499 0 0.0235 0.0235 +<method 'startswith' of 'str' objects>
+31014 0 80.7820 0.0071 +mercurial.util:1284(iterlines)
+3 0 0.0000 0.0000 +<method 'search' of '_sre.SRE_Pattern' objects>
+4 0 0.0000 0.0000 +mercurial.patch:1783(addresult)
+3 0 0.0000 0.0000 +<method 'group' of '_sre.SRE_Match' objects>
6 0 0.0444 0.0283 mercurial.mdiff:12(splitnewlines)
+6 0 0.0160 0.0160 +<method 'split' of 'str' objects>
32 0 0.0246 0.0246 <method 'update' of '_hashlib.HASH' objects>
11 0 0.0236 0.0236 <method 'read' of 'file' objects>
Time: real 80.880 secs (user 80.200+0.000 sys 0.380+0.000)
With this change, it's almost as fast as not using showfunc at all:
CallCount Recursive Total(ms) Inline(ms) module:lineno(function)
543 0 0.1699 0.1699 <zlib.decompress>
3 0 0.0501 0.0501 <mercurial.bdiff.blocks>
32813 0 0.0415 0.0348 mercurial.mdiff:161(yieldhunk)
+70837 0 0.0058 0.0058 +<method 'isalnum' of 'str' objects>
+1809 0 0.0006 0.0006 +mercurial.mdiff:148(contextend)
+1809 0 0.0002 0.0002 +<len>
1 0 0.4879 0.0310 mercurial.patch:1777(diffstatdata)
+107499 0 0.0230 0.0230 +<method 'startswith' of 'str' objects>
+31014 0 0.4335 0.0065 +mercurial.util:1284(iterlines)
+3 0 0.0000 0.0000 +<method 'search' of '_sre.SRE_Pattern' objects>
+4 0 0.0000 0.0000 +mercurial.patch:1783(addresult)
+1 0 0.0004 0.0000 +re:188(compile)
32 0 0.0293 0.0293 <method 'update' of '_hashlib.HASH' objects>
6 0 0.0427 0.0279 mercurial.mdiff:12(splitnewlines)
+6 0 0.0147 0.0147 +<method 'split' of 'str' objects>
31007 0 0.1169 0.0235 mercurial.mdiff:147(_unidiff)
+3 0 0.0501 0.0501 +<mercurial.bdiff.blocks>
+32813 0 0.0415 0.0348 +mercurial.mdiff:161(yieldhunk)
+3618 0 0.0012 0.0012 +mercurial.mdiff:154(contextstart)
+5427 0 0.0006 0.0006 +<len>
107597 0 0.0230 0.0230 <method 'startswith' of 'str' objects>
16 0 0.0213 0.0213 <mercurial.mpatch.patches>
194 0 0.0149 0.0149 <method 'split' of 'str' objects>
Time: real 0.530 secs (user 0.450+0.000 sys 0.070+0.000)
author | Brodie Rao <brodie@bitheap.org> |
---|---|
date | Mon, 19 Sep 2011 15:58:03 -0700 |
parents | 35c2cc322ba8 |
children | 33fcad3cfbbc |
line wrap: on
line source
# perf.py - performance test routines '''helper extension to measure performance''' from mercurial import cmdutil, scmutil, match, commands import time, os, sys def timer(func, title=None): results = [] begin = time.time() count = 0 while True: ostart = os.times() cstart = time.time() r = func() cstop = time.time() ostop = os.times() count += 1 a, b = ostart, ostop results.append((cstop - cstart, b[0] - a[0], b[1]-a[1])) if cstop - begin > 3 and count >= 100: break if cstop - begin > 10 and count >= 3: break if title: sys.stderr.write("! %s\n" % title) if r: sys.stderr.write("! result: %s\n" % r) m = min(results) sys.stderr.write("! wall %f comb %f user %f sys %f (best of %d)\n" % (m[0], m[1] + m[2], m[1], m[2], count)) def perfwalk(ui, repo, *pats): try: m = scmutil.match(repo[None], pats, {}) timer(lambda: len(list(repo.dirstate.walk(m, [], True, False)))) except: try: m = scmutil.match(repo[None], pats, {}) timer(lambda: len([b for a, b, c in repo.dirstate.statwalk([], m)])) except: timer(lambda: len(list(cmdutil.walk(repo, pats, {})))) def perfstatus(ui, repo, *pats): #m = match.always(repo.root, repo.getcwd()) #timer(lambda: sum(map(len, repo.dirstate.status(m, [], False, False, False)))) timer(lambda: sum(map(len, repo.status()))) def perfheads(ui, repo): timer(lambda: len(repo.changelog.heads())) def perftags(ui, repo): import mercurial.changelog, mercurial.manifest def t(): repo.changelog = mercurial.changelog.changelog(repo.sopener) repo.manifest = mercurial.manifest.manifest(repo.sopener) repo._tags = None return len(repo.tags()) timer(t) def perfdirstate(ui, repo): "a" in repo.dirstate def d(): repo.dirstate.invalidate() "a" in repo.dirstate timer(d) def perfdirstatedirs(ui, repo): "a" in repo.dirstate def d(): "a" in repo.dirstate._dirs del repo.dirstate._dirs timer(d) def perfmanifest(ui, repo): def d(): t = repo.manifest.tip() m = repo.manifest.read(t) repo.manifest.mapcache = None repo.manifest._cache = None timer(d) def perfindex(ui, repo): import mercurial.revlog mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg n = repo["tip"].node() def d(): repo.invalidate() repo[n] timer(d) def perfstartup(ui, repo): cmd = sys.argv[0] def d(): os.system("HGRCPATH= %s version -q > /dev/null" % cmd) timer(d) def perfparents(ui, repo): nl = [repo.changelog.node(i) for i in xrange(1000)] def d(): for n in nl: repo.changelog.parents(n) timer(d) def perflookup(ui, repo, rev): timer(lambda: len(repo.lookup(rev))) def perflog(ui, repo, **opts): ui.pushbuffer() timer(lambda: commands.log(ui, repo, rev=[], date='', user='', copies=opts.get('rename'))) ui.popbuffer() def perftemplating(ui, repo): ui.pushbuffer() timer(lambda: commands.log(ui, repo, rev=[], date='', user='', template='{date|shortdate} [{rev}:{node|short}]' ' {author|person}: {desc|firstline}\n')) ui.popbuffer() def perfdiffwd(ui, repo): """Profile diff of working directory changes""" options = { 'w': 'ignore_all_space', 'b': 'ignore_space_change', 'B': 'ignore_blank_lines', } for diffopt in ('', 'w', 'b', 'B', 'wB'): opts = dict((options[c], '1') for c in diffopt) def d(): ui.pushbuffer() commands.diff(ui, repo, **opts) ui.popbuffer() title = 'diffopts: %s' % (diffopt and ('-' + diffopt) or 'none') timer(d, title) def perfrevlog(ui, repo, file_, **opts): from mercurial import revlog dist = opts['dist'] def d(): r = revlog.revlog(lambda fn: open(fn, 'rb'), file_) for x in xrange(0, len(r), dist): r.revision(r.node(x)) timer(d) cmdtable = { 'perflookup': (perflookup, []), 'perfparents': (perfparents, []), 'perfstartup': (perfstartup, []), 'perfstatus': (perfstatus, []), 'perfwalk': (perfwalk, []), 'perfmanifest': (perfmanifest, []), 'perfindex': (perfindex, []), 'perfheads': (perfheads, []), 'perftags': (perftags, []), 'perfdirstate': (perfdirstate, []), 'perfdirstatedirs': (perfdirstate, []), 'perflog': (perflog, [('', 'rename', False, 'ask log to follow renames')]), 'perftemplating': (perftemplating, []), 'perfdiffwd': (perfdiffwd, []), 'perfrevlog': (perfrevlog, [('d', 'dist', 100, 'distance between the revisions')], "[INDEXFILE]"), }