23 files changed, 819 insertions, 21 deletions
diff --git a/t/perf/README b/t/perf/README
index 8848c14619..49ea4349be 100644
--- a/t/perf/README
+++ b/t/perf/README
@@ -115,8 +115,16 @@ After that you will want to use some of the following:
 
 At least one of the first two is required!
 
-You can use test_expect_success as usual.  For actual performance
-tests, use
+You can use test_expect_success as usual. In both test_expect_success
+and in test_perf, running "git" points to the version that is being
+perf-tested. The $MODERN_GIT variable points to the git wrapper for the
+currently checked-out version (i.e., the one that matches the t/perf
+scripts you are running).  This is useful if your setup uses commands
+that only work with newer versions of git than what you might want to
+test (but obviously your new commands must still create a state that can
+be used by the older version of git you are testing).
+
+For actual performance tests, use
 
 	test_perf 'descriptive string' '
 		command1 &&
diff --git a/t/perf/aggregate.perl b/t/perf/aggregate.perl
index 15f7fc1b80..1dbc85b214 100755
--- a/t/perf/aggregate.perl
+++ b/t/perf/aggregate.perl
@@ -1,5 +1,6 @@
 #!/usr/bin/perl
 
+use lib '../../perl/blib/lib';
 use strict;
 use warnings;
 use Git;
@@ -87,6 +88,7 @@ for my $t (@tests) {
 sub read_descr {
 	my $name = shift;
 	open my $fh, "<", $name or return "<error reading description>";
+	binmode $fh, ":utf8" or die "PANIC on binmode: $!";
 	my $line = <$fh>;
 	close $fh or die "cannot close $name";
 	chomp $line;
@@ -146,6 +148,8 @@ for my $t (@subtests) {
 my $totalwidth = 3*@dirs+$descrlen;
 $totalwidth += $_ for (@colwidth);
 
+binmode STDOUT, ":utf8" or die "PANIC on binmode: $!";
+
 printf "%-${descrlen}s", "Test";
 for my $i (0..$#dirs) {
 	my $d = $dirs[$i];
diff --git a/t/perf/p0000-perf-lib-sanity.sh b/t/perf/p0000-perf-lib-sanity.sh
index cf8e1efce7..002c21e52a 100755
--- a/t/perf/p0000-perf-lib-sanity.sh
+++ b/t/perf/p0000-perf-lib-sanity.sh
@@ -33,6 +33,8 @@ test_perf 'export a weird var' '
 	test_export bar
 '
 
+test_perf 'éḿíẗ ńöń-ÁŚĆÍÍ ćḧáŕáćẗéŕś' 'true'
+
 test_expect_success 'test_export works with weird vars' '
 	echo "$bar" &&
 	test "$bar" = "weird # variable"
diff --git a/t/perf/p0001-rev-list.sh b/t/perf/p0001-rev-list.sh
index 16359d51ae..ebf172401b 100755
--- a/t/perf/p0001-rev-list.sh
+++ b/t/perf/p0001-rev-list.sh
@@ -15,7 +15,8 @@ test_perf 'rev-list --all --objects' '
 '
 
 test_expect_success 'create new unreferenced commit' '
-	commit=$(git commit-tree HEAD^{tree} -p HEAD)
+	commit=$(git commit-tree HEAD^{tree} -p HEAD) &&
+	test_export commit
 '
 
 test_perf 'rev-list $commit --not --all' '
diff --git a/t/perf/p0003-delta-base-cache.sh b/t/perf/p0003-delta-base-cache.sh
new file mode 100755
index 0000000000..62369eaaf0
--- /dev/null
+++ b/t/perf/p0003-delta-base-cache.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+
+test_description='Test operations that emphasize the delta base cache.
+
+We look at both "log --raw", which should put only trees into the delta cache,
+and "log -Sfoo --raw", which should look at both trees and blobs.
+
+Any effects will be emphasized if the test repository is fully packed (loose
+objects obviously do not use the delta base cache at all). It is also
+emphasized if the pack has long delta chains (e.g., as produced by "gc
+--aggressive"), though cache is still quite noticeable even with the default
+depth of 50.
+
+The setting of core.deltaBaseCacheLimit in the source repository is also
+relevant (depending on the size of your test repo), so be sure it is consistent
+between runs.
+'
+. ./perf-lib.sh
+
+test_perf_large_repo
+
+# puts mostly trees into the delta base cache
+test_perf 'log --raw' '
+	git log --raw >/dev/null
+'
+
+test_perf 'log -S' '
+	git log --raw -Sfoo >/dev/null
+'
+
+test_done
diff --git a/t/perf/p0004-lazy-init-name-hash.sh b/t/perf/p0004-lazy-init-name-hash.sh
new file mode 100755
index 0000000000..8de5a98cfc
--- /dev/null
+++ b/t/perf/p0004-lazy-init-name-hash.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+
+test_description='Tests multi-threaded lazy_init_name_hash'
+. ./perf-lib.sh
+
+test_perf_large_repo
+test_checkout_worktree
+
+test_expect_success 'verify both methods build the same hashmaps' '
+	test-lazy-init-name-hash --dump --single >out.single &&
+	if test-lazy-init-name-hash --dump --multi >out.multi
+	then
+		test_set_prereq REPO_BIG_ENOUGH_FOR_MULTI &&
+		sort <out.single >sorted.single &&
+		sort <out.multi >sorted.multi &&
+		test_cmp sorted.single sorted.multi
+	fi
+'
+
+test_expect_success 'calibrate' '
+	entries=$(wc -l <out.single) &&
+
+	case $entries in
+	?) count=1000000 ;;
+	??) count=100000 ;;
+	???) count=10000 ;;
+	????) count=1000 ;;
+	?????) count=100 ;;
+	??????) count=10 ;;
+	*) count=1 ;;
+	esac &&
+	export count &&
+
+	case $entries in
+	1) entries_desc="1 entry" ;;
+	*) entries_desc="$entries entries" ;;
+	esac &&
+
+	case $count in
+	1) count_desc="1 round" ;;
+	*) count_desc="$count rounds" ;;
+	esac &&
+
+	desc="$entries_desc, $count_desc" &&
+	export desc
+'
+
+test_perf "single-threaded, $desc" "
+	test-lazy-init-name-hash --single --count=$count
+"
+
+test_perf REPO_BIG_ENOUGH_FOR_MULTI "multi-threaded, $desc" "
+	test-lazy-init-name-hash --multi --count=$count
+"
+
+test_done
diff --git a/t/perf/p0005-status.sh b/t/perf/p0005-status.sh
new file mode 100755
index 0000000000..0b0aa9858f
--- /dev/null
+++ b/t/perf/p0005-status.sh
@@ -0,0 +1,49 @@
+#!/bin/sh
+#
+# This test measures the performance of various read-tree
+# and status operations.  It is primarily interested in
+# the algorithmic costs of index operations and recursive
+# tree traversal -- and NOT disk I/O on thousands of files.
+
+test_description="Tests performance of read-tree"
+
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+# If the test repo was generated by ./repos/many-files.sh
+# then we know something about the data shape and branches,
+# so we can isolate testing to the ballast-related commits
+# and setup sparse-checkout so we don't have to populate
+# the ballast files and directories.
+#
+# Otherwise, we make some general assumptions about the
+# repo and consider the entire history of the current
+# branch to be the ballast.
+
+test_expect_success "setup repo" '
+	if git rev-parse --verify refs/heads/p0006-ballast^{commit}
+	then
+		echo Assuming synthetic repo from many-files.sh
+		git branch br_base            master
+		git branch br_ballast         p0006-ballast
+		git config --local core.sparsecheckout 1
+		cat >.git/info/sparse-checkout <<-EOF
+		/*
+		!ballast/*
+		EOF
+	else
+		echo Assuming non-synthetic repo...
+		git branch br_base            $(git rev-list HEAD | tail -n 1)
+		git branch br_ballast         HEAD
+	fi &&
+	git checkout -q br_ballast &&
+	nr_files=$(git ls-files | wc -l)
+'
+
+test_perf "read-tree status br_ballast ($nr_files)" '
+	git read-tree HEAD &&
+	git status
+'
+
+test_done
diff --git a/t/perf/p0006-read-tree-checkout.sh b/t/perf/p0006-read-tree-checkout.sh
new file mode 100755
index 0000000000..78cc23fe2f
--- /dev/null
+++ b/t/perf/p0006-read-tree-checkout.sh
@@ -0,0 +1,67 @@
+#!/bin/sh
+#
+# This test measures the performance of various read-tree
+# and checkout operations.  It is primarily interested in
+# the algorithmic costs of index operations and recursive
+# tree traversal -- and NOT disk I/O on thousands of files.
+
+test_description="Tests performance of read-tree"
+
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+# If the test repo was generated by ./repos/many-files.sh
+# then we know something about the data shape and branches,
+# so we can isolate testing to the ballast-related commits
+# and setup sparse-checkout so we don't have to populate
+# the ballast files and directories.
+#
+# Otherwise, we make some general assumptions about the
+# repo and consider the entire history of the current
+# branch to be the ballast.
+
+test_expect_success "setup repo" '
+	if git rev-parse --verify refs/heads/p0006-ballast^{commit}
+	then
+		echo Assuming synthetic repo from many-files.sh
+		git branch br_base            master
+		git branch br_ballast         p0006-ballast^
+		git branch br_ballast_alias   p0006-ballast^
+		git branch br_ballast_plus_1  p0006-ballast
+		git config --local core.sparsecheckout 1
+		cat >.git/info/sparse-checkout <<-EOF
+		/*
+		!ballast/*
+		EOF
+	else
+		echo Assuming non-synthetic repo...
+		git branch br_base            $(git rev-list HEAD | tail -n 1)
+		git branch br_ballast         HEAD^ || error "no ancestor commit from current head"
+		git branch br_ballast_alias   HEAD^
+		git branch br_ballast_plus_1  HEAD
+	fi &&
+	git checkout -q br_ballast &&
+	nr_files=$(git ls-files | wc -l)
+'
+
+test_perf "read-tree br_base br_ballast ($nr_files)" '
+	git read-tree -m br_base br_ballast -n
+'
+
+test_perf "switch between br_base br_ballast ($nr_files)" '
+	git checkout -q br_base &&
+	git checkout -q br_ballast
+'
+
+test_perf "switch between br_ballast br_ballast_plus_1 ($nr_files)" '
+	git checkout -q br_ballast_plus_1 &&
+	git checkout -q br_ballast
+'
+
+test_perf "switch between aliases ($nr_files)" '
+	git checkout -q br_ballast_alias &&
+	git checkout -q br_ballast
+'
+
+test_done
diff --git a/t/perf/p0071-sort.sh b/t/perf/p0071-sort.sh
new file mode 100755
index 0000000000..7c9a35a646
--- /dev/null
+++ b/t/perf/p0071-sort.sh
@@ -0,0 +1,26 @@
+#!/bin/sh
+
+test_description='Basic sort performance tests'
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+test_expect_success 'setup' '
+	git ls-files --stage "*.[ch]" "*.sh" |
+	cut -f2 -d" " |
+	git cat-file --batch >unsorted
+'
+
+test_perf 'sort(1)' '
+	sort <unsorted >expect
+'
+
+test_perf 'string_list_sort()' '
+	test-string-list sort <unsorted >actual
+'
+
+test_expect_success 'string_list_sort() sorts like sort(1)' '
+	test_cmp_bin expect actual
+'
+
+test_done
diff --git a/t/perf/p3400-rebase.sh b/t/perf/p3400-rebase.sh
new file mode 100755
index 0000000000..b3e7d525d2
--- /dev/null
+++ b/t/perf/p3400-rebase.sh
@@ -0,0 +1,36 @@
+#!/bin/sh
+
+test_description='Tests rebase performance'
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+test_expect_success 'setup' '
+	git checkout -f -b base &&
+	git checkout -b to-rebase &&
+	git checkout -b upstream &&
+	for i in $(seq 100)
+	do
+		# simulate huge diffs
+		echo change$i >unrelated-file$i &&
+		seq 1000 >>unrelated-file$i &&
+		git add unrelated-file$i &&
+		test_tick &&
+		git commit -m commit$i unrelated-file$i &&
+		echo change$i >unrelated-file$i &&
+		seq 1000 | tac >>unrelated-file$i &&
+		git add unrelated-file$i &&
+		test_tick &&
+		git commit -m commit$i-reverse unrelated-file$i ||
+		break
+	done &&
+	git checkout to-rebase &&
+	test_commit our-patch interesting-file
+'
+
+test_perf 'rebase on top of a lot of unrelated changes' '
+	git rebase --onto upstream HEAD^ &&
+	git rebase --onto base HEAD^
+'
+
+test_done
diff --git a/t/perf/p3404-rebase-interactive.sh b/t/perf/p3404-rebase-interactive.sh
new file mode 100755
index 0000000000..88f47de282
--- /dev/null
+++ b/t/perf/p3404-rebase-interactive.sh
@@ -0,0 +1,36 @@
+#!/bin/sh
+
+test_description='Tests rebase -i performance'
+. ./perf-lib.sh
+
+test_perf_default_repo
+
+# This commit merges a sufficiently long topic branch for reasonable
+# performance testing
+branch_merge=ba5312da19c6fdb6c6747d479f58932aae6e900c^{commit}
+export branch_merge
+
+git rev-parse --verify $branch_merge >/dev/null 2>&1 || {
+	skip_all='skipping because $branch_merge was not found'
+	test_done
+}
+
+write_script swap-first-two.sh <<\EOF
+case "$1" in
+*/COMMIT_EDITMSG)
+	mv "$1" "$1".bak &&
+	sed -e '1{h;d}' -e 2G <"$1".bak >"$1"
+	;;
+esac
+EOF
+
+test_expect_success 'setup' '
+	git config core.editor "\"$PWD"/swap-first-two.sh\" &&
+	git checkout -f $branch_merge^2
+'
+
+test_perf 'rebase -i' '
+	git rebase -i $branch_merge^
+'
+
+test_done
diff --git a/t/perf/p4211-line-log.sh b/t/perf/p4211-line-log.sh
index 3d074b0e41..b7ff68d4fa 100755
--- a/t/perf/p4211-line-log.sh
+++ b/t/perf/p4211-line-log.sh
@@ -23,11 +23,11 @@ test_perf 'git log --follow (baseline for -M)' '
 	git log --oneline --follow -- "$file" >/dev/null
 '
 
-test_perf 'git log -L' '
-	git log -L 1:"$file" >/dev/null
+test_perf 'git log -L (renames off)' '
+	git log --no-renames -L 1:"$file" >/dev/null
 '
 
-test_perf 'git log -M -L' '
+test_perf 'git log -L (renames on)' '
 	git log -M -L 1:"$file" >/dev/null
 '
 
diff --git a/t/perf/p5302-pack-index.sh b/t/perf/p5302-pack-index.sh
index 5ee9211f98..99bdb16c85 100755
--- a/t/perf/p5302-pack-index.sh
+++ b/t/perf/p5302-pack-index.sh
@@ -13,6 +13,13 @@ test_expect_success 'repack' '
 	export PACK
 '
 
+test_expect_success 'create target repositories' '
+	for repo in t1 t2 t3 t4 t5 t6
+	do
+		git init --bare $repo
+	done
+'
+
 test_perf 'index-pack 0 threads' '
 	GIT_DIR=t1 git index-pack --threads=1 --stdin < $PACK
 '
diff --git a/t/perf/p5303-many-packs.sh b/t/perf/p5303-many-packs.sh
new file mode 100755
index 0000000000..3779851941
--- /dev/null
+++ b/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
diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh
index f8ed8573b7..bb91dbb173 100755
--- a/t/perf/p5310-pack-bitmaps.sh
+++ b/t/perf/p5310-pack-bitmaps.sh
@@ -32,6 +32,14 @@ test_perf 'simulated fetch' '
 	} | git pack-objects --revs --stdout >/dev/null
 '
 
+test_perf 'pack to file' '
+	git pack-objects --all pack1 </dev/null >/dev/null
+'
+
+test_perf 'pack to file (bitmap)' '
+	git pack-objects --use-bitmap-index --all pack1b </dev/null >/dev/null
+'
+
 test_expect_success 'create partial bitmap state' '
 	# pick a commit to represent the repo tip in the past
 	cutoff=$(git rev-list HEAD~100 -1) &&
@@ -39,22 +47,26 @@ test_expect_success 'create partial bitmap state' '
 
 	# now kill off all of the refs and pretend we had
 	# just the one tip
-	rm -rf .git/logs .git/refs/* .git/packed-refs
-	git update-ref HEAD $cutoff
+	rm -rf .git/logs .git/refs/* .git/packed-refs &&
+	git update-ref HEAD $cutoff &&
 
 	# and then repack, which will leave us with a nice
 	# big bitmap pack of the "old" history, and all of
 	# the new history will be loose, as if it had been pushed
 	# up incrementally and exploded via unpack-objects
-	git repack -Ad
+	git repack -Ad &&
 
 	# and now restore our original tip, as if the pushes
 	# had happened
 	git update-ref HEAD $orig_tip
 '
 
-test_perf 'partial bitmap' '
+test_perf 'clone (partial bitmap)' '
 	git pack-objects --stdout --all </dev/null >/dev/null
 '
 
+test_perf 'pack to file (partial bitmap)' '
+	git pack-objects --use-bitmap-index --all pack2b </dev/null >/dev/null
+'
+
 test_done
diff --git a/t/perf/p5550-fetch-tags.sh b/t/perf/p5550-fetch-tags.sh
new file mode 100755
index 0000000000..a5dc39f86a
--- /dev/null
+++ b/t/perf/p5550-fetch-tags.sh
@@ -0,0 +1,99 @@
+#!/bin/sh
+
+test_description='performance of tag-following with many tags
+
+This tests a fairly pathological case, so rather than rely on a real-world
+case, we will construct our own repository. The situation is roughly as
+follows.
+
+The parent repository has a large number of tags which are disconnected from
+the rest of history. That makes them candidates for tag-following, but we never
+actually grab them (and thus they will impact each subsequent fetch).
+
+The child repository is a clone of parent, without the tags, and is at least
+one commit behind the parent (meaning that we will fetch one object and then
+examine the tags to see if they need followed). Furthermore, it has a large
+number of packs.
+
+The exact values of "large" here are somewhat arbitrary; I picked values that
+start to show a noticeable performance problem on my machine, but without
+taking too long to set up and run the tests.
+'
+. ./perf-lib.sh
+
+# make a long nonsense history on branch $1, consisting of $2 commits, each
+# with a unique file pointing to the blob at $2.
+create_history () {
+	perl -le '
+		my ($branch, $n, $blob) = @ARGV;
+		for (1..$n) {
+			print "commit refs/heads/$branch";
+			print "committer nobody <nobody@example.com> now";
+			print "data 4";
+			print "foo";
+			print "M 100644 $blob $_";
+		}
+	' "$@" |
+	git fast-import --date-format=now
+}
+
+# make a series of tags, one per commit in the revision range given by $@
+create_tags () {
+	git rev-list "$@" |
+	perl -lne 'print "create refs/tags/$. $_"' |
+	git update-ref --stdin
+}
+
+# create $1 nonsense packs, each with a single blob
+create_packs () {
+	perl -le '
+		my ($n) = @ARGV;
+		for (1..$n) {
+			print "blob";
+			print "data <<EOF";
+			print "$_";
+			print "EOF";
+		}
+	' "$@" |
+	git fast-import &&
+
+	git cat-file --batch-all-objects --batch-check='%(objectname)' |
+	while read sha1
+	do
+		echo $sha1 | git pack-objects .git/objects/pack/pack
+	done
+}
+
+test_expect_success 'create parent and child' '
+	git init parent &&
+	git -C parent commit --allow-empty -m base &&
+	git clone parent child &&
+	git -C parent commit --allow-empty -m trigger-fetch
+'
+
+test_expect_success 'populate parent tags' '
+	(
+		cd parent &&
+		blob=$(echo content | git hash-object -w --stdin) &&
+		create_history cruft 3000 $blob &&
+		create_tags cruft &&
+		git branch -D cruft
+	)
+'
+
+test_expect_success 'create child packs' '
+	(
+		cd child &&
+		git config gc.auto 0 &&
+		git config gc.autopacklimit 0 &&
+		create_packs 500
+	)
+'
+
+test_perf 'fetch' '
+	# make sure there is something to fetch on each iteration
+	git -C child update-ref -d refs/remotes/origin/master &&
+	git -C child fetch
+'
+
+test_done
diff --git a/t/perf/p7000-filter-branch.sh b/t/perf/p7000-filter-branch.sh
new file mode 100755
index 0000000000..b029586ccb
--- /dev/null
+++ b/t/perf/p7000-filter-branch.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+
+test_description='performance of filter-branch'
+. ./perf-lib.sh
+
+test_perf_default_repo
+test_checkout_worktree
+
+test_expect_success 'mark bases for tests' '
+	git tag -f tip &&
+	git tag -f base HEAD~100
+'
+
+test_perf 'noop filter' '
+	git checkout --detach tip &&
+	git filter-branch -f base..HEAD
+'
+
+test_perf 'noop prune-empty' '
+	git checkout --detach tip &&
+	git filter-branch -f --prune-empty base..HEAD
+'
+
+test_done
diff --git a/t/perf/p7300-clean.sh b/t/perf/p7300-clean.sh
new file mode 100755
index 0000000000..7c1888a27e
--- /dev/null
+++ b/t/perf/p7300-clean.sh
@@ -0,0 +1,35 @@
+#!/bin/sh
+
+test_description="Test git-clean performance"
+
+. ./perf-lib.sh
+
+test_perf_default_repo
+test_checkout_worktree
+
+test_expect_success 'setup untracked directory with many sub dirs' '
+	rm -rf 500_sub_dirs 100000_sub_dirs clean_test_dir &&
+	mkdir 500_sub_dirs 100000_sub_dirs clean_test_dir &&
+	for i in $(test_seq 1 500)
+	do
+		mkdir 500_sub_dirs/dir$i || return $?
+	done &&
+	for i in $(test_seq 1 200)
+	do
+		cp -r 500_sub_dirs 100000_sub_dirs/dir$i || return $?
+	done
+'
+
+test_perf 'clean many untracked sub dirs, check for nested git' '
+	git clean -n -q -f -d 100000_sub_dirs/
+'
+
+test_perf 'clean many untracked sub dirs, ignore nested git' '
+	git clean -n -q -f -f -d 100000_sub_dirs/
+'
+
+test_perf 'ls-files -o' '
+	git ls-files -o
+'
+
+test_done
diff --git a/t/perf/perf-lib.sh b/t/perf/perf-lib.sh
index 5cf74eddec..ab4b8b06ae 100644
--- a/t/perf/perf-lib.sh
+++ b/t/perf/perf-lib.sh
@@ -52,6 +52,9 @@ TEST_NO_MALLOC_CHECK=t
 # need to export them for test_perf subshells
 export TEST_DIRECTORY TRASH_DIRECTORY GIT_BUILD_DIR GIT_TEST_CMP
 
+MODERN_GIT=$GIT_BUILD_DIR/bin-wrappers/git
+export MODERN_GIT
+
 perf_results_dir=$TEST_OUTPUT_DIRECTORY/test-results
 mkdir -p "$perf_results_dir"
 rm -f "$perf_results_dir"/$(basename "$0" .sh).subtests
@@ -80,23 +83,29 @@ test_perf_create_repo_from () {
 	error "bug in the test script: not 2 parameters to test-create-repo"
 	repo="$1"
 	source="$2"
-	source_git=$source/$(cd "$source" && git rev-parse --git-dir)
+	source_git="$("$MODERN_GIT" -C "$source" rev-parse --git-dir)"
+	objects_dir="$("$MODERN_GIT" -C "$source" rev-parse --git-path objects)"
 	mkdir -p "$repo/.git"
 	(
-		cd "$repo/.git" &&
-		{ cp -Rl "$source_git/objects" . 2>/dev/null ||
-			cp -R "$source_git/objects" .; } &&
+		cd "$source" &&
+		{ cp -Rl "$objects_dir" "$repo/.git/" 2>/dev/null ||
+			cp -R "$objects_dir" "$repo/.git/"; } &&
 		for stuff in "$source_git"/*; do
 			case "$stuff" in
-				*/objects|*/hooks|*/config)
+				*/objects|*/hooks|*/config|*/commondir)
 					;;
 				*)
-					cp -R "$stuff" . || exit 1
+					cp -R "$stuff" "$repo/.git/" || exit 1
 					;;
 			esac
-		done &&
-		cd .. &&
-		git init -q &&
+		done
+	) &&
+	(
+		cd "$repo" &&
+		"$MODERN_GIT" init -q && {
+			test_have_prereq SYMLINKS ||
+			git config core.symlinks false
+		} &&
 		mv .git/hooks .git/hooks-disabled 2>/dev/null
 	) || error "failed to copy repository '$source' to '$repo'"
 }
@@ -121,11 +130,15 @@ test_checkout_worktree () {
 # Performance tests should never fail.  If they do, stop immediately
 immediate=t
 
+# Perf tests require GNU time
+case "$(uname -s)" in Darwin) GTIME="${GTIME:-gtime}";; esac
+GTIME="${GTIME:-/usr/bin/time}"
+
 test_run_perf_ () {
 	test_cleanup=:
 	test_export_="test_cleanup"
 	export test_cleanup test_export_
-	/usr/bin/time -f "%E %U %S" -o test_time.$i "$SHELL" -c '
+	"$GTIME" -f "%E %U %S" -o test_time.$i "$SHELL" -c '
 . '"$TEST_DIRECTORY"/test-lib-functions.sh'
 test_export () {
 	[ $# != 0 ] || return 0
diff --git a/t/perf/repos/.gitignore b/t/perf/repos/.gitignore
new file mode 100644
index 0000000000..72e3dc3e19
--- /dev/null
+++ b/t/perf/repos/.gitignore
@@ -0,0 +1 @@
+gen-*/
diff --git a/t/perf/repos/inflate-repo.sh b/t/perf/repos/inflate-repo.sh
new file mode 100755
index 0000000000..fcfc992b5b
--- /dev/null
+++ b/t/perf/repos/inflate-repo.sh
@@ -0,0 +1,85 @@
+#!/bin/sh
+# Inflate the size of an EXISTING repo.
+#
+# This script should be run inside the worktree of a TEST repo.
+# It will use the contents of the current HEAD to generate a
+# commit containing copies of the current worktree such that the
+# total size of the commit has at least <target_size> files.
+#
+# Usage: [-t target_size] [-b branch_name]
+
+set -e
+
+target_size=10000
+branch_name=p0006-ballast
+ballast=ballast
+
+while test "$#" -ne 0
+do
+    case "$1" in
+	-b)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -b requires an argument' >&2; exit 1; }
+	    branch_name=$1;
+	    shift ;;
+	-t)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -t requires an argument' >&2; exit 1; }
+	    target_size=$1;
+	    shift ;;
+	*)
+	    echo "error: unknown option '$1'" >&2; exit 1 ;;
+    esac
+done
+
+git ls-tree -r HEAD >GEN_src_list
+nr_src_files=$(cat GEN_src_list | wc -l)
+
+src_branch=$(git symbolic-ref --short HEAD)
+
+echo "Branch $src_branch initially has $nr_src_files files."
+
+if test $target_size -le $nr_src_files
+then
+    echo "Repository already exceeds target size $target_size."
+    rm GEN_src_list
+    exit 1
+fi
+
+# Create well-known branch and add 1 file change to start
+# if off before the ballast.
+git checkout -b $branch_name HEAD
+echo "$target_size" > inflate-repo.params
+git add inflate-repo.params
+git commit -q -m params
+
+# Create ballast for in our branch.
+copy=1
+nr_files=$nr_src_files
+while test $nr_files -lt $target_size
+do
+    sed -e "s|	|	$ballast/$copy/|" <GEN_src_list |
+	git update-index --index-info
+
+    nr_files=$(expr $nr_files + $nr_src_files)
+    copy=$(expr $copy + 1)
+done
+rm GEN_src_list
+git commit -q -m "ballast"
+
+# Modify 1 file and commit.
+echo "$target_size" >> inflate-repo.params
+git add inflate-repo.params
+git commit -q -m "ballast plus 1"
+
+nr_files=$(git ls-files | wc -l)
+
+# Checkout master to put repo in canonical state (because
+# the perf test may need to clone and enable sparse-checkout
+# before attempting to checkout a commit with the ballast
+# (because it may contain 100K directories and 1M files)).
+git checkout $src_branch
+
+echo "Repository inflated. Branch $branch_name has $nr_files files."
+
+exit 0
diff --git a/t/perf/repos/many-files.sh b/t/perf/repos/many-files.sh
new file mode 100755
index 0000000000..28720e4e10
--- /dev/null
+++ b/t/perf/repos/many-files.sh
@@ -0,0 +1,110 @@
+#!/bin/sh
+# Generate test data repository using the given parameters.
+# When omitted, we create "gen-many-files-d-w-f.git".
+#
+# Usage: [-r repo] [-d depth] [-w width] [-f files]
+#
+# -r repo: path to the new repo to be generated
+# -d depth: the depth of sub-directories
+# -w width: the number of sub-directories at each level
+# -f files: the number of files created in each directory
+#
+# Note that all files will have the same SHA-1 and each
+# directory at a level will have the same SHA-1, so we
+# will potentially have a large index, but not a large
+# ODB.
+#
+# Ballast will be created under "ballast/".
+
+EMPTY_BLOB=e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+
+set -e
+
+# (5, 10, 9) will create 999,999 ballast files.
+# (4, 10, 9) will create  99,999 ballast files.
+depth=5
+width=10
+files=9
+
+while test "$#" -ne 0
+do
+    case "$1" in
+	-r)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -r requires an argument' >&2; exit 1; }
+	    repo=$1;
+	    shift ;;
+	-d)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -d requires an argument' >&2; exit 1; }
+	    depth=$1;
+	    shift ;;
+	-w)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -w requires an argument' >&2; exit 1; }
+	    width=$1;
+	    shift ;;
+	-f)
+	    shift;
+	    test "$#" -ne 0 || { echo 'error: -f requires an argument' >&2; exit 1; }
+	    files=$1;
+	    shift ;;
+	*)
+	    echo "error: unknown option '$1'" >&2; exit 1 ;;
+	esac
+done
+
+# Inflate the index with thousands of empty files.
+# usage: dir depth width files
+fill_index() {
+	awk -v arg_dir=$1 -v arg_depth=$2 -v arg_width=$3 -v arg_files=$4 '
+		function make_paths(dir, depth, width, files, f, w) {
+			for (f = 1; f <= files; f++) {
+				print dir "/file" f
+			}
+			if (depth > 0) {
+				for (w = 1; w <= width; w++) {
+					make_paths(dir "/dir" w, depth - 1, width, files)
+				}
+			}
+		}
+		END { make_paths(arg_dir, arg_depth, arg_width, arg_files) }
+		' </dev/null |
+	sed "s/^/100644 $EMPTY_BLOB	/" |
+	git update-index --index-info
+	return 0
+}
+
+[ -z "$repo" ] && repo=gen-many-files-$depth.$width.$files.git
+
+mkdir $repo
+cd $repo
+git init .
+
+# Create an initial commit just to define master.
+touch many-files.empty
+echo "$depth $width $files" >many-files.params
+git add many-files.*
+git commit -q -m params
+
+# Create ballast for p0006 based upon the given params and
+# inflate the index with thousands of empty files and commit.
+git checkout -b p0006-ballast
+fill_index "ballast" $depth $width $files
+git commit -q -m "ballast"
+
+nr_files=$(git ls-files | wc -l)
+
+# Modify 1 file and commit.
+echo "$depth $width $files" >>many-files.params
+git add many-files.params
+git commit -q -m "ballast plus 1"
+
+# Checkout master to put repo in canonical state (because
+# the perf test may need to clone and enable sparse-checkout
+# before attempting to checkout a commit with the ballast
+# (because it may contain 100K directories and 1M files)).
+git checkout master
+
+echo "Repository "$repo" ($depth, $width, $files) created.  Ballast $nr_files."
+exit 0
diff --git a/t/perf/run b/t/perf/run
index cfd70129bb..c788d713ae 100755
--- a/t/perf/run
+++ b/t/perf/run
@@ -30,7 +30,13 @@ unpack_git_rev () {
 }
 build_git_rev () {
 	rev=$1
-	cp ../../config.mak build/$rev/config.mak
+	for config in config.mak config.mak.autogen config.status
+	do
+		if test -e "../../$config"
+		then
+			cp "../../$config" "build/$rev/"
+		fi
+	done
 	(cd build/$rev && make $GIT_PERF_MAKE_OPTS) ||
 	die "failed to build revision '$mydir'"
 }
@@ -57,6 +63,9 @@ run_dirs_helper () {
 		unset GIT_TEST_INSTALLED
 	else
 		GIT_TEST_INSTALLED="$mydir/bin-wrappers"
+		# Older versions of git lacked bin-wrappers; fallback to the
+		# files in the root.
+		test -d "$GIT_TEST_INSTALLED" || GIT_TEST_INSTALLED=$mydir
 		export GIT_TEST_INSTALLED
 	fi
 	run_one_dir "$@"