[PATCH v3 2/4] p5413: add perf tests for connectivity check

["Kristofer Karlsson via GitGitGadget" <gitgitgadget@gmail.com>]

From: Kristofer Karlsson <krka@spotify.com>

Add benchmarks for the rev-list connectivity check.  Each fixture
varies one dimension: total tree size, incoming commit count, or
files changed per commit.

Signed-off-by: Kristofer Karlsson <krka@spotify.com>
---
 ...enerate-repo-p5413-connectivity-check.perl | 44 ++++++++++
 t/perf/p5413-connectivity-check.sh            | 85 +++++++++++++++++++
 2 files changed, 129 insertions(+)
 create mode 100644 t/perf/generate-repo-p5413-connectivity-check.perl
 create mode 100755 t/perf/p5413-connectivity-check.sh

diff --git a/t/perf/generate-repo-p5413-connectivity-check.perl b/t/perf/generate-repo-p5413-connectivity-check.perl
new file mode 100644
index 0000000000..9546996280
--- /dev/null
+++ b/t/perf/generate-repo-p5413-connectivity-check.perl
@@ -0,0 +1,44 @@
+#!/usr/bin/perl
+#
+# Generate a fast-import stream for p5412 connectivity check benchmarks.
+#
+# Usage: generate-repo-p5412-connectivity-check.perl
+#            <dirs> <files_per_dir> <commits> [<hot_dirs>] [<files_per_commit>]
+#
+# Creates one initial commit with dirs*files_per_dir files, then
+# <commits> additional commits each modifying <files_per_commit>
+# files in directories chosen round-robin from 1..<hot_dirs>.
+
+use strict;
+use warnings;
+
+my ($nd, $nf, $nc, $hot, $fpc) = @ARGV;
+$hot = $nd if !$hot || $hot > $nd;
+$fpc = 1   if !$fpc;
+
+sub data {
+	printf "data %d\n%s\n", length($_[0]), $_[0];
+}
+
+# Initial tree: one commit with nd*nf files.
+printf "commit refs/heads/main\n";
+printf "committer perf <perf\@test.com> now\n";
+data("initial");
+for my $d (1..$nd) {
+	for my $f (1..$nf) {
+		printf "M 100644 inline d-%04d/f-%03d\n", $d, $f;
+		data(sprintf "%03d%03d", $d, $f);
+	}
+}
+
+# Subsequent commits (auto-chained by fast-import).
+for my $i (1..$nc) {
+	printf "commit refs/heads/main\n";
+	printf "committer perf <perf\@test.com> now\n";
+	data(sprintf "change-%03d", $i);
+	for my $j (0..$fpc-1) {
+		my $d = (($i + $j) % $hot) + 1;
+		printf "M 100644 inline d-%04d/f-001\n", $d;
+		data(sprintf "c%d-%d", $i, $j);
+	}
+}
diff --git a/t/perf/p5413-connectivity-check.sh b/t/perf/p5413-connectivity-check.sh
new file mode 100755
index 0000000000..3fabc82a87
--- /dev/null
+++ b/t/perf/p5413-connectivity-check.sh
@@ -0,0 +1,85 @@
+#!/bin/sh
+
+test_description='performance of connectivity check
+
+Benchmark the rev-list connectivity check, avoiding pack transfer
+noise.
+
+Each repository has a flat tree of many directories with 100 files
+in each.  Three axes are scaled independently: tree size, commit
+count, and files changed per commit.'
+
+. ./perf-lib.sh
+
+test_perf_fresh_repo
+
+generate="$TEST_DIRECTORY/perf/generate-repo-p5413-connectivity-check.perl"
+
+# $1=dirs  $2=files_per_dir  $3=commits  $4=hot_dirs (optional, default=all)
+# $5=files_per_commit (optional, default=1)
+test_perf_conn () {
+	local nd="$1" nf="$2" nc="$3" hot="${4:-$1}" fpc="${5:-1}"
+	local total=$(($nd * $nf))
+	local name="repo-${nd}d-${nf}f-${nc}c-${hot}h-${fpc}fpc"
+	local label="${total} files, ${nc} commits"
+	if test "$hot" -lt "$nd"
+	then
+		label="$label (${hot} hot dirs)"
+	fi
+	if test "$fpc" -gt 1
+	then
+		label="$label (${fpc} files/commit)"
+	fi
+
+	test_expect_success "setup $label" '
+		if test -d '"$name"'
+		then
+			true
+		else
+			git init '"$name"' &&
+			"$PERL_PATH" '"$generate"' '"$nd"' '"$nf"' '"$nc"' '"$hot"' '"$fpc"' |
+			git -C '"$name"' fast-import --date-format=now --quiet &&
+			(
+				cd '"$name"' &&
+				git rev-parse main~'"$nc"' >../'"${name}"'_old &&
+				git rev-parse main >../'"${name}"'_new &&
+				git update-ref refs/heads/main \
+					$(cat ../'"${name}"'_old) &&
+				git repack -ad &&
+				git config gc.auto 0
+			)
+		fi
+	'
+
+	test_perf "$label" '
+		cat '"${name}"'_new |
+		git -C '"$name"' rev-list \
+			--objects --stdin --not --all --quiet \
+			--exclude-promisor-objects
+	'
+}
+
+# Scaling tree size (10 commits, 10 files/commit).
+test_perf_conn   50 100 10   50 10
+test_perf_conn  500 100 10  500 10
+test_perf_conn 2000 100 10 2000 10
+test_perf_conn 8000 100 10 8000 10
+
+# Scaling commit count (200K files, 10 files/commit).
+test_perf_conn 2000 100    1 2000 10
+test_perf_conn 2000 100   10 2000 10
+test_perf_conn 2000 100  100 2000 10
+test_perf_conn 2000 100   500 2000 10
+test_perf_conn 2000 100  3000 2000 10
+test_perf_conn 2000 100  5000 2000 10
+test_perf_conn 2000 100 10000 2000 10
+
+# Scaling files per commit (200K files, 10 commits).
+test_perf_conn 2000 100 10 2000   1
+test_perf_conn 2000 100 10 2000  10
+test_perf_conn 2000 100 10 2000  100
+test_perf_conn 2000 100 10 2000  500
+test_perf_conn 2000 100 10 2000 1000
+test_perf_conn 2000 100 10 2000 2000
+
+test_done
-- 
gitgitgadget