[PATCH 2 of 2 V6] delta: reuse _findsnapshot call from previous stage

Boris Feld boris.feld at octobus.net
Fri Jan 4 06:23:01 EST 2019


# HG changeset patch
# User Boris Feld <boris.feld at octobus.net>
# Date 1545297384 -3600
#      Thu Dec 20 10:16:24 2018 +0100
# Node ID f0e63f010a19e4c1677182df298f4d4f2f68d853
# Parent  ce19086bebe873ad5a1b62911721f2291fba766d
# EXP-Topic sparse-revlog
# Available At https://bitbucket.org/octobus/mercurial-devel/
#              hg pull https://bitbucket.org/octobus/mercurial-devel/ -r f0e63f010a19
delta: reuse _findsnapshot call from previous stage

Two different stage of the sparse-revlog logic needs the _findsnapshot data.
To avoid recomputing it twice, make it possible to reuse the first computation
in the second step.

example affected manifest write
before: 0.067141s
after:  0.064252s (-5%)

(total gain since start of series: 95%)

diff --git a/mercurial/revlogutils/deltas.py b/mercurial/revlogutils/deltas.py
--- a/mercurial/revlogutils/deltas.py
+++ b/mercurial/revlogutils/deltas.py
@@ -713,7 +713,8 @@ def _refinedgroups(revlog, p1, p2, cache
         if good is not None:
             yield None
             return
-    for candidates in _rawgroups(revlog, p1, p2, cachedelta):
+    snapshots = collections.defaultdict(list)
+    for candidates in _rawgroups(revlog, p1, p2, cachedelta, snapshots):
         good = yield candidates
         if good is not None:
             break
@@ -734,12 +735,8 @@ def _refinedgroups(revlog, p1, p2, cache
                 break
             good = yield (base,)
         # refine snapshot up
-        #
-        # XXX the _findsnapshots call can be expensive and is "duplicated" with
-        # the one done in `_rawgroups`. Once we start working on performance,
-        # we should make the two logics share this computation.
-        snapshots = collections.defaultdict(list)
-        _findsnapshots(revlog, snapshots, good + 1)
+        if not snapshots:
+            _findsnapshots(revlog, snapshots, good + 1)
         previous = None
         while good != previous:
             previous = good
@@ -749,7 +746,7 @@ def _refinedgroups(revlog, p1, p2, cache
     # we have found nothing
     yield None
 
-def _rawgroups(revlog, p1, p2, cachedelta):
+def _rawgroups(revlog, p1, p2, cachedelta, snapshots=None):
     """Provides group of revision to be tested as delta base
 
     This lower level function focus on emitting delta theorically interresting
@@ -779,7 +776,9 @@ def _rawgroups(revlog, p1, p2, cachedelt
             yield parents
 
     if sparse and parents:
-        snapshots = collections.defaultdict(list) # map: base-rev: snapshot-rev
+        if snapshots is None:
+            # map: base-rev: snapshot-rev
+            snapshots = collections.defaultdict(list)
         # See if we can use an existing snapshot in the parent chains to use as
         # a base for a new intermediate-snapshot
         #


More information about the Mercurial-devel mailing list