about summary refs log tree commit diff
path: root/third_party/git/t/perf/p5303-many-packs.sh
diff options
context:
space:
mode:
authorVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
committerVincent Ambo <Vincent Ambo>2020-01-11T23·40+0000
commit7ef0d62730840ded097b524104cc0a0904591a63 (patch)
treea670f96103667aeca4789a95d94ca0dff550c4ce /third_party/git/t/perf/p5303-many-packs.sh
parent6a2a3007077818e24a3d56fc492ada9206a10cf0 (diff)
parent1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5 (diff)
merge(third_party/git): Merge squashed git subtree at v2.23.0 r/373
Merge commit '1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5' as 'third_party/git'
Diffstat (limited to 'third_party/git/t/perf/p5303-many-packs.sh')
-rwxr-xr-xthird_party/git/t/perf/p5303-many-packs.sh87
1 files changed, 87 insertions, 0 deletions
diff --git a/third_party/git/t/perf/p5303-many-packs.sh b/third_party/git/t/perf/p5303-many-packs.sh
new file mode 100755
index 000000000000..377985194116
--- /dev/null
+++ b/third_party/git/t/perf/p5303-many-packs.sh
@@ -0,0 +1,87 @@
+#!/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 |
+	sed -n '1~5p' |
+	head -n "$1" |
+	perl -e 'print reverse <>' \
+	>pushes
+
+	# create base packfile
+	head -n 1 pushes |
+	git pack-objects --delta-base-offset --revs staging/pack
+
+	# and then incrementals between each pair of commits
+	last= &&
+	while read rev
+	do
+		if test -n "$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
+	'
+
+	# 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 pack-objects --keep-true-parents \
+		  --honor-pack-keep --non-empty --all \
+		  --reflog --indexed-objects --delta-base-offset \
+		  --stdout </dev/null >/dev/null
+	'
+done
+
+test_done