tags-cache: directly perform a monimal walk for hgtagsfnodescache warming
We do something narrower than the path retrieving data. So lets use dedicated
code instead.
This provides further useful speedup:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.debug.debug-update-cache
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.pre-state = warm
before-this-series: 19.947581
skip-fnode-filter: 18.916804 (-5.17%, -1.03)
use-rev-num: 17.493725 (-12.30%, -2.45)
this-changesets: 15.919466 (-20.19%, -4.03)
--- a/mercurial/tags.py Wed Mar 13 11:51:11 2024 +0100
+++ b/mercurial/tags.py Wed Mar 13 12:02:06 2024 +0100
@@ -21,6 +21,7 @@
short,
)
from .i18n import _
+from .revlogutils.constants import ENTRY_NODE_ID
from . import (
encoding,
error,
@@ -30,6 +31,7 @@
)
from .utils import stringutil
+
# Tags computation can be expensive and caches exist to make it fast in
# the common case.
#
@@ -83,7 +85,29 @@
def warm_cache(repo):
"""ensure the cache is properly filled"""
unfi = repo.unfiltered()
- _getfnodes(repo.ui, repo, revs=unfi.changelog.revs())
+ fnodescache = hgtagsfnodescache(unfi)
+ validated_fnodes = set()
+ unknown_entries = set()
+ flog = None
+
+ entries = enumerate(repo.changelog.index)
+ node_revs = ((e[ENTRY_NODE_ID], rev) for (rev, e) in entries)
+
+ for node, rev in node_revs:
+ fnode = fnodescache.getfnode(node=node, rev=rev)
+ if fnode != repo.nullid:
+ if fnode not in validated_fnodes:
+ if flog is None:
+ flog = repo.file(b'.hgtags')
+ if flog.hasnode(fnode):
+ validated_fnodes.add(fnode)
+ else:
+ unknown_entries.add(node)
+
+ if unknown_entries:
+ fnodescache.refresh_invalid_nodes(unknown_entries)
+
+ fnodescache.write()
def fnoderevs(ui, repo, revs):