# HG changeset patch # User Pierre-Yves David # Date 1447917783 28800 # Node ID f92053df8f0b892e9aff3adb9058ab0b1d8c1bef # Parent a01ecbcfaf847390660d66bfd8c9150d938f21bf revset: speed up '_matchfiles' File matching is done by applying the matcher to all elements in the 'file' field of all changesets in the repository. This requires to read/parse all changesets in the repository and do a lot of matching. However about 1/3 of the time of the function is used to create 'changectx' object and retrieve their 'file' field. This is far too much overhead so we are skipping the changectx layer and directly access the data from the changelog. This provide use significant speed up: repository: mozilla central 252524 revisions command: hg perfrevset '_matchfiles("p:browser")' Before: 15.899687s After: 10.011705s Slowdown is even more significant if you have a lot of namespace that slowdown lookup. The time is now spent with this approximate repartition: Matcher: 20% regexp matching: 10% changelog.read: 80% reading revision: 60% checking hash: 15% decompression: 15% reading chunk: 30% changelog parsing: 20% decoding to local: 10% The next easy win is probably to have more of the changelog stack implemented using the CPython api. diff -r a01ecbcfaf84 -r f92053df8f0b mercurial/revset.py --- a/mercurial/revset.py Wed Nov 18 15:46:45 2015 -0800 +++ b/mercurial/revset.py Wed Nov 18 23:23:03 2015 -0800 @@ -1164,8 +1164,16 @@ m = matchmod.match(repo.root, repo.getcwd(), pats, include=inc, exclude=exc, ctx=repo[rev], default=default) + # This directly read the changelog data as creating changectx for all + # revisions is quite expensive. + getchangeset = repo.changelog.read + wdirrev = node.wdirrev def matches(x): - for f in repo[x].files(): + if x == wdirrev: + files = repo[x].files() + else: + files = getchangeset(x)[3] + for f in files: if m(f): return True return False