# HG changeset patch # User Pierre-Yves David # Date 1552263020 -3600 # Node ID 9f45d3d526f9ebaae1a98ca0e4a01a9f63b2e7bb # Parent 2930b31383af4e24a5afeacd67c5a213db46de4f hgtagsfnodescache: inherit fnode from parent when possible If a changeset does not update the content of `.hgtags`, it means it will use the same file-node (for `.hgtags`) as its parents. In this case we can directly reuse the parent's file-node. We use this property when updating the `hgtagsfnodescache` taking a faster path if we already have a cached value for the parents of the node we are looking at. Doing so provides a large performance boost when looking at a lot of fnodes, especially on repository with very large manifest: timing for `tagsmod.fnoderevs(ui, repo, repo.changelog.revs())` mercurial: (41907 revisions, 1923 files) before: 6.9 seconds after: 2.7 seconds (-54%) pypy: (96266 revisions, 5198 files) before: 80 seconds after: 20 seconds (-75%) mozilla-central: (463411 revisions, 272080 files) before: 7166.4 seconds after: 47.8 seconds (-99%, x150 speedup) On a copy of mozilla-try with about 35K heads ans 1.7M changesets, this moves the computation from many hours to a couple of minutes, making it more interesting to do a full warm up of this cache before computing tags (from a cold cache). There seems to be other performance low hanging fruits, like avoiding the use of changectx or a more revision centric logic. However, the new code is fast enough for my needs right now. diff -r 2930b31383af -r 9f45d3d526f9 mercurial/tags.py --- a/mercurial/tags.py Mon Mar 11 01:09:38 2019 +0100 +++ b/mercurial/tags.py Mon Mar 11 01:10:20 2019 +0100 @@ -18,6 +18,7 @@ bin, hex, nullid, + nullrev, short, ) from .i18n import _ @@ -718,12 +719,33 @@ if not computemissing: return None - # Populate missing entry. - try: - fnode = ctx.filenode('.hgtags') - except error.LookupError: - # No .hgtags file on this revision. - fnode = nullid + fnode = None + cl = self._repo.changelog + p1rev, p2rev = cl._uncheckedparentrevs(rev) + p1node = cl.node(p1rev) + p1fnode = self.getfnode(p1node, computemissing=False) + if p2rev != nullrev: + # There is some no-merge changeset where p1 is null and p2 is set + # Processing them as merge is just slower, but still gives a good + # result. + p2node = cl.node(p1rev) + p2fnode = self.getfnode(p2node, computemissing=False) + if p1fnode != p2fnode: + # we cannot rely on readfast because we don't know against what + # parent the readfast delta is computed + p1fnode = None + if p1fnode is not None: + mctx = ctx.manifestctx() + fnode = mctx.readfast().get('.hgtags') + if fnode is None: + fnode = p1fnode + if fnode is None: + # Populate missing entry. + try: + fnode = ctx.filenode('.hgtags') + except error.LookupError: + # No .hgtags file on this revision. + fnode = nullid self._writeentry(offset, properprefix, fnode) return fnode diff -r 2930b31383af -r 9f45d3d526f9 tests/test-tags.t --- a/tests/test-tags.t Mon Mar 11 01:09:38 2019 +0100 +++ b/tests/test-tags.t Mon Mar 11 01:10:20 2019 +0100 @@ -145,7 +145,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing 48 bytes to cache/hgtagsfnodes1 - 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/1 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/2 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> blackbox -l 6 @@ -159,7 +159,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> not writing .hg/cache/hgtagsfnodes1 because lock cannot be acquired - 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/1 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> 0/2 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> identify exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @b9154636be938d3d431e75a7c906504a079bfe07 (5000)> blackbox -l 6 @@ -363,7 +363,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> tags 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> writing 24 bytes to cache/hgtagsfnodes1 - 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> 2/3 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> 3/4 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> tags exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @8dbfe60eff306a54259cfe007db9e330e7ecf866 (5000)> blackbox -l 6 @@ -384,7 +384,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> couldn't write cache/hgtagsfnodes1: [Errno *] * (glob) - 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 2/3 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 3/4 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> blackbox -l 6 @@ -399,7 +399,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing 24 bytes to cache/hgtagsfnodes1 - 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 2/3 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> 3/4 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> tags exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @b968051b5cf3f624b771779c6d5f84f1d4c3fb5d (5000)> blackbox -l 6 @@ -427,7 +427,7 @@ $ hg blackbox -l 5 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> writing 24 bytes to cache/hgtagsfnodes1 - 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> 2/3 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> 2/4 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> tags exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @0c192d7d5e6b78a714de54a2e9627952a877e25a (5000)> blackbox -l 5 @@ -445,7 +445,7 @@ $ hg blackbox -l 6 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> tags 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> writing 24 bytes to cache/hgtagsfnodes1 - 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> 2/3 cache hits/lookups in * seconds (glob) + 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> 3/4 cache hits/lookups in * seconds (glob) 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> writing .hg/cache/tags2-visible with 1 tags 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> tags exited 0 after * seconds (glob) 1970/01/01 00:00:00 bob @035f65efb448350f4772141702a81ab1df48c465 (5000)> blackbox -l 6