@matheusbsbs / matheus-bagliano / commits / 716766765c

unpack-trees: avoid quadratic index scan in next_cache_entry()

Diffing the working tree against a commit with a pathspec can take time quadratic in the size of the index when the pathspec matches a subtree whose entries are the first entries of the index. Fix it by having next_cache_entry() record how far it scanned in cache_bottom, so repeated calls no longer rescan the growing prefix of already-unpacked entries. On a Chromium checkout (~500k index entries), git diff HEAD -- .agents/OWNERS took about 8 minutes before this change and 0.07 seconds after it. The same diff without the commit, without the pathspec, or with --cached was already instant. Add p0009-diff-pathspec.sh, which builds a 10,000-entry index whose first path lives in a subtree (100,000 entries under --long-tests), to guard against the regression. Comparing v2.55.0 with this change using GIT_TEST_LONG=t: Test v2.55.0 HEAD ------------------------------------------------------------------------ 0009.2: diff pathspec subtree 7.16(7.12+0.01) 0.02(0.01+0.00) -99.7% Signed-off-by: Henrique Ferreiro <hferreiro@igalia.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Henrique Ferreiro committed Jul 8, 2026 at 21:42 UTC 716766765c945c9ca62f24f6debc3f255ff3b6a6

2 files changed +35 -1

t/perf/p0009-diff-pathspec.sh new

+32

@@ -0,0 +1,32 @@

1 +#!/bin/sh

2 +

3 +test_description='Tests performance of diffing the working tree with a pathspec'

4 +

5 +. ./perf-lib.sh

6 +

7 +test_perf_fresh_repo

8 +

9 +count=10000

10 +if test_have_prereq EXPENSIVE

11 +then

12 + count=100000

13 +fi

14 +

15 +# The entries exist only in the index, which is enough to

16 +# exercise the index scan.

17 +test_expect_success 'setup' '

18 + blob=$(echo content | git hash-object -w --stdin) &&

19 + {

20 + printf "100644 $blob\taaa/file\n" &&

21 + printf "100644 $blob\tf%s\n" $(test_seq $count)

22 + } | git update-index --index-info &&

23 + git commit -q -m initial &&

24 + mkdir -p aaa &&

25 + echo content >aaa/file

26 +'

27 +

28 +test_perf 'diff pathspec subtree' '

29 + git diff HEAD -- aaa/file

30 +'

31 +

32 +test_done

unpack-trees.c

+3 -1

@@ -671,8 +671,10 @@ static struct cache_entry *next_cache_entry(struct unpack_trees_options *o)

671

672 while (pos < index->cache_nr) {

673 struct cache_entry *ce = index->cache[pos];

674 - if (!(ce->ce_flags & CE_UNPACKED))

674 + if (!(ce->ce_flags & CE_UNPACKED)) {

675 + o->internal.cache_bottom = pos;

676 return ce;

677 + }

678 pos++;

679 }

680 return NULL;