summaryrefslogtreecommitdiff
path: root/t/perf/p5303-many-packs.sh
blob: ce0c42cc9f72d6ff610c5fa0608353beb64fa3df (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
#!/bin/sh

test_description='performance with large numbers of packs'
. ./perf-lib.sh

test_perf_large_repo

# A real many-pack situation would probably come from having a lot of pushes
# over time. We don't know how big each push would be, but we can fake it by
# just walking the first-parent chain and having every 5 commits be their own
# "push". This isn't _entirely_ accurate, as real pushes would have some
# duplicate objects due to thin-pack fixing, but it's a reasonable
# approximation.
#
# And then all of the rest of the objects can go in a single packfile that
# represents the state before any of those pushes (actually, we'll generate
# that first because in such a setup it would be the oldest pack, and we sort
# the packs by reverse mtime inside git).
repack_into_n () {
	rm -rf staging &&
	mkdir staging &&

	git rev-list --first-parent HEAD |
	perl -e '
		my $n = shift;
		while (<>) {
			last unless @commits < $n;
			push @commits, $_ if $. % 5 == 1;
		}
		print reverse @commits;
	' "$1" >pushes

	# create base packfile
	head -n 1 pushes |
	git pack-objects --delta-base-offset --revs staging/pack

	# and then incrementals between each pair of commits
	last= &&
	while read rev
	do
		if test -n "$last"; then
			{
				echo "$rev" &&
				echo "^$last"
			} |
			git pack-objects --delta-base-offset --revs \
				staging/pack || return 1
		fi
		last=$rev
	done <pushes &&

	# and install the whole thing
	rm -f .git/objects/pack/* &&
	mv staging/* .git/objects/pack/
}

# Pretend we just have a single branch and no reflogs, and that everything is
# in objects/pack; that makes our fake pack-building via repack_into_n()
# much simpler.
test_expect_success 'simplify reachability' '
	tip=$(git rev-parse --verify HEAD) &&
	git for-each-ref --format="option no-deref%0adelete %(refname)" |
	git update-ref --stdin &&
	rm -rf .git/logs &&
	git update-ref refs/heads/master $tip &&
	git symbolic-ref HEAD refs/heads/master &&
	git repack -ad
'

for nr_packs in 1 50 1000
do
	test_expect_success "create $nr_packs-pack scenario" '
		repack_into_n $nr_packs
	'

	test_perf "rev-list ($nr_packs)" '
		git rev-list --objects --all >/dev/null
	'

	test_perf "abbrev-commit ($nr_packs)" '
		git rev-list --abbrev-commit HEAD >/dev/null
	'

	# This simulates the interesting part of the repack, which is the
	# actual pack generation, without smudging the on-disk setup
	# between trials.
	test_perf "repack ($nr_packs)" '
		GIT_TEST_FULL_IN_PACK_ARRAY=1 \
		git pack-objects --keep-true-parents \
		  --honor-pack-keep --non-empty --all \
		  --reflog --indexed-objects --delta-base-offset \
		  --stdout </dev/null >/dev/null
	'
done

# Measure pack loading with 10,000 packs.
test_expect_success 'generate lots of packs' '
	for i in $(test_seq 10000); do
		echo "blob"
		echo "data <<EOF"
		echo "blob $i"
		echo "EOF"
		echo "checkpoint"
	done |
	git -c fastimport.unpackLimit=0 fast-import
'

# The purpose of this test is to evaluate load time for a large number
# of packs while doing as little other work as possible.
test_perf "load 10,000 packs" '
	git rev-parse --verify "HEAD^{commit}"
'

test_done