diff mbox series

[v3,4/7] t/perf: add fsmonitor perf test for git diff

Message ID b3ad8faac43f7e499c794b4a9c106f9fcc121281.1603147657.git.gitgitgadget@gmail.com (mailing list archive)
State New, archived
Headers show
Series use fsmonitor data in git diff eliminating O(num_files) calls to lstat | expand

Commit Message

Nipunn Koorapati Oct. 19, 2020, 10:47 p.m. UTC 
From: Nipunn Koorapati <nipunn@dropbox.com>

Results for the git-diff fsmonitor optimization
in patch in the parent-rev (using a 400k file repo to test)

As you can see here - git diff with fsmonitor running is
significantly better with this patch series (80% faster on my
workload)!

GIT_PERF_LARGE_REPO=~/src/server ./run v2.29.0-rc1 . -- p7519-fsmonitor.sh

Test                                                                     v2.29.0-rc1       this tree
-----------------------------------------------------------------------------------------------------------------
7519.2: status (fsmonitor=.git/hooks/fsmonitor-watchman)                 1.46(0.82+0.64)   1.47(0.83+0.62) +0.7%
7519.3: status -uno (fsmonitor=.git/hooks/fsmonitor-watchman)            0.16(0.12+0.04)   0.17(0.12+0.05) +6.3%
7519.4: status -uall (fsmonitor=.git/hooks/fsmonitor-watchman)           1.36(0.73+0.62)   1.37(0.76+0.60) +0.7%
7519.5: diff (fsmonitor=.git/hooks/fsmonitor-watchman)                   0.85(0.22+0.63)   0.14(0.10+0.05) -83.5%
7519.6: diff -- 0_files (fsmonitor=.git/hooks/fsmonitor-watchman)        0.12(0.08+0.05)   0.13(0.11+0.02) +8.3%
7519.7: diff -- 10_files (fsmonitor=.git/hooks/fsmonitor-watchman)       0.12(0.08+0.04)   0.13(0.09+0.04) +8.3%
7519.8: diff -- 100_files (fsmonitor=.git/hooks/fsmonitor-watchman)      0.12(0.07+0.05)   0.13(0.07+0.06) +8.3%
7519.9: diff -- 1000_files (fsmonitor=.git/hooks/fsmonitor-watchman)     0.12(0.09+0.04)   0.13(0.08+0.05) +8.3%
7519.10: diff -- 10000_files (fsmonitor=.git/hooks/fsmonitor-watchman)   0.14(0.09+0.05)   0.13(0.10+0.03) -7.1%
7519.12: status (fsmonitor=)                                             1.67(0.93+1.49)   1.67(0.99+1.42) +0.0%
7519.13: status -uno (fsmonitor=)                                        0.37(0.30+0.82)   0.37(0.33+0.79) +0.0%
7519.14: status -uall (fsmonitor=)                                       1.58(0.97+1.35)   1.57(0.86+1.45) -0.6%
7519.15: diff (fsmonitor=)                                               0.34(0.28+0.83)   0.34(0.27+0.83) +0.0%
7519.16: diff -- 0_files (fsmonitor=)                                    0.09(0.06+0.04)   0.09(0.08+0.02) +0.0%
7519.17: diff -- 10_files (fsmonitor=)                                   0.09(0.07+0.03)   0.09(0.06+0.05) +0.0%
7519.18: diff -- 100_files (fsmonitor=)                                  0.09(0.06+0.04)   0.09(0.06+0.04) +0.0%
7519.19: diff -- 1000_files (fsmonitor=)                                 0.09(0.06+0.04)   0.09(0.05+0.05) +0.0%
7519.20: diff -- 10000_files (fsmonitor=)                                0.10(0.08+0.04)   0.10(0.06+0.05) +0.0%

I also added a benchmark for a tiny git diff workload w/ a pathspec.
I see an approximately .02 second overhead added w/ and w/o fsmonitor

From looking at these results, I suspected that refresh_fsmonitor
is already happening during git diff - independent of this patch
series' optimization. Confirmed that suspicion by breaking on
refresh_fsmonitor.

(gdb) bt  [simplified]
0  refresh_fsmonitor  at fsmonitor.c:176
1  ie_match_stat  at read-cache.c:375
2  match_stat_with_submodule at diff-lib.c:237
4  builtin_diff_files  at builtin/diff.c:260
5  cmd_diff  at builtin/diff.c:541
6  run_builtin  at git.c:450
7  handle_builtin  at git.c:700
8  run_argv  at git.c:767
9  cmd_main  at git.c:898
10 main  at common-main.c:52

Signed-off-by: Nipunn Koorapati <nipunn@dropbox.com>
---
 t/perf/p7519-fsmonitor.sh | 71 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
diff mbox series

Patch

diff --git a/t/perf/p7519-fsmonitor.sh b/t/perf/p7519-fsmonitor.sh
index 9313d4a51d..ef4c3c8c5c 100755
--- a/t/perf/p7519-fsmonitor.sh
+++ b/t/perf/p7519-fsmonitor.sh
@@ -115,6 +115,13 @@  test_expect_success "setup for fsmonitor" '
 
 	git config core.fsmonitor "$INTEGRATION_SCRIPT" &&
 	git update-index --fsmonitor &&
+	mkdir 1_file 10_files 100_files 1000_files 10000_files &&
+	for i in $(test_seq 1 10); do touch 10_files/$i; done &&
+	for i in $(test_seq 1 100); do touch 100_files/$i; done &&
+	for i in $(test_seq 1 1000); do touch 1000_files/$i; done &&
+	for i in $(test_seq 1 10000); do touch 10000_files/$i; done &&
+	git add 1_file 10_files 100_files 1000_files 10000_files &&
+	git commit -m "Add files" &&
 	git status  # Warm caches
 '
 
@@ -142,6 +149,38 @@  test_perf "status -uall (fsmonitor=$INTEGRATION_SCRIPT)" '
 	git status -uall
 '
 
+if test -n "$GIT_PERF_7519_DROP_CACHE"; then
+	test-tool drop-caches
+fi
+
+test_perf "diff (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff
+'
+
+if test -n "$GIT_PERF_7519_DROP_CACHE"; then
+	test-tool drop-caches
+fi
+
+test_perf "diff -- 0_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 1_file
+'
+
+test_perf "diff -- 10_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 10_files
+'
+
+test_perf "diff -- 100_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 100_files
+'
+
+test_perf "diff -- 1000_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 1000_files
+'
+
+test_perf "diff -- 10000_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 10000_files
+'
+
 test_expect_success "setup without fsmonitor" '
 	unset INTEGRATION_SCRIPT &&
 	git config --unset core.fsmonitor &&
@@ -172,6 +211,38 @@  test_perf "status -uall (fsmonitor=$INTEGRATION_SCRIPT)" '
 	git status -uall
 '
 
+if test -n "$GIT_PERF_7519_DROP_CACHE"; then
+	test-tool drop-caches
+fi
+
+test_perf "diff (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff
+'
+
+if test -n "$GIT_PERF_7519_DROP_CACHE"; then
+	test-tool drop-caches
+fi
+
+test_perf "diff -- 0_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 1_file
+'
+
+test_perf "diff -- 10_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 10_files
+'
+
+test_perf "diff -- 100_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 100_files
+'
+
+test_perf "diff -- 1000_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 1000_files
+'
+
+test_perf "diff -- 10000_files (fsmonitor=$INTEGRATION_SCRIPT)" '
+	git diff -- 10000_files
+'
+
 if test_have_prereq WATCHMAN
 then
 	watchman watch-del "$GIT_WORK_TREE" >/dev/null 2>&1 &&