2022-06-11 04:44:16 +02:00
|
|
|
#!/bin/sh
|
|
|
|
|
#
|
|
|
|
|
# Copyright (c) 2022 Han Xin
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
test_description='git unpack-objects with large objects'
|
|
|
|
|
|
|
|
|
|
. ./test-lib.sh
|
|
|
|
|
|
|
|
|
|
prepare_dest () {
|
|
|
|
|
test_when_finished "rm -rf dest.git" &&
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
git init --bare dest.git &&
|
|
|
|
|
git -C dest.git config core.bigFileThreshold "$1"
|
2022-06-11 04:44:16 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
test_expect_success "create large objects (1.5 MB) and PACK" '
|
|
|
|
|
test-tool genrandom foo 1500000 >big-blob &&
|
|
|
|
|
test_commit --append foo big-blob &&
|
|
|
|
|
test-tool genrandom bar 1500000 >big-blob &&
|
|
|
|
|
test_commit --append bar big-blob &&
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
PACK=$(echo HEAD | git pack-objects --revs pack) &&
|
|
|
|
|
git verify-pack -v pack-$PACK.pack >out &&
|
|
|
|
|
sed -n -e "s/^\([0-9a-f][0-9a-f]*\).*\(commit\|tree\|blob\).*/\1/p" \
|
|
|
|
|
<out >obj-list
|
2022-06-11 04:44:16 +02:00
|
|
|
'
|
|
|
|
|
|
|
|
|
|
test_expect_success 'set memory limitation to 1MB' '
|
|
|
|
|
GIT_ALLOC_LIMIT=1m &&
|
|
|
|
|
export GIT_ALLOC_LIMIT
|
|
|
|
|
'
|
|
|
|
|
|
|
|
|
|
test_expect_success 'unpack-objects failed under memory limitation' '
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
prepare_dest 2m &&
|
2022-06-11 04:44:16 +02:00
|
|
|
test_must_fail git -C dest.git unpack-objects <pack-$PACK.pack 2>err &&
|
|
|
|
|
grep "fatal: attempting to allocate" err
|
|
|
|
|
'
|
|
|
|
|
|
|
|
|
|
test_expect_success 'unpack-objects works with memory limitation in dry-run mode' '
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
prepare_dest 2m &&
|
2022-06-11 04:44:16 +02:00
|
|
|
git -C dest.git unpack-objects -n <pack-$PACK.pack &&
|
|
|
|
|
test_stdout_line_count = 0 find dest.git/objects -type f &&
|
|
|
|
|
test_dir_is_empty dest.git/objects/pack
|
|
|
|
|
'
|
|
|
|
|
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
test_expect_success 'unpack big object in stream' '
|
|
|
|
|
prepare_dest 1m &&
|
|
|
|
|
git -C dest.git unpack-objects <pack-$PACK.pack &&
|
|
|
|
|
test_dir_is_empty dest.git/objects/pack
|
|
|
|
|
'
|
|
|
|
|
|
trace2: only include "fsync" events if we git_fsync()
Fix the overly verbose trace2 logging added in 9a4987677d3 (trace2:
add stats for fsync operations, 2022-03-30) (first released with
v2.36.0).
Since that change every single "git" command invocation has included
these "data" events, even though we'll only make use of these with
core.fsyncMethod=batch, and even then only have non-zero values if
we're writing object data to disk. See c0f4752ed2f (core.fsyncmethod:
batched disk flushes for loose-objects, 2022-04-04) for that feature.
As we're needing to indent the trace2_data_intmax() lines let's
introduce helper variables to ensure that our resulting lines (which
were already too) don't exceed the recommendations of the
CodingGuidelines. Doing that requires either wrapping them twice, or
introducing short throwaway variable names, let's do the latter.
The result was that e.g. "git version" would previously emit a total
of 6 trace2 events with the GIT_TRACE2_EVENT target (version, start,
cmd_ancestry, cmd_name, exit, atexit), but afterwards would emit
8. We'd emit 2 "data" events before the "exit" event.
The reason we didn't catch this was that the trace2 unit tests added
in a15860dca3f (trace2: t/helper/test-trace2, t0210.sh, t0211.sh,
t0212.sh, 2019-02-22) would omit any "data" events that weren't the
ones it cared about. Before this change to the C code 6/7 of our
"t/t0212-trace2-event.sh" tests would fail if this change was applied
to "t/t0212/parse_events.perl".
Let's make the trace2 testing more strict, and further append any new
events types we don't know about in "t/t0212/parse_events.perl". Since
we only invoke the "test-tool trace2" there's no guarantee that we'll
catch other overly verbose events in the future, but we'll at least
notice if we start emitting new events that are issues every time we
log anything with trace2's JSON target.
We exclude the "data_json" event type, we'd otherwise would fail on
both "win test" and "win+VS test" CI due to the logging added in
353d3d77f4f (trace2: collect Windows-specific process information,
2019-02-22). It looks like that logging should really be using
trace2_cmd_ancestry() instead, which was introduced later in
2f732bf15e6 (tr2: log parent process name, 2021-07-21), but let's
leave it for now.
The fix-up to aaf81223f48 (unpack-objects: use stream_loose_object()
to unpack large objects, 2022-06-11) is needed because we're changing
the behavior of these events as discussed above. Since we'd always
emit a "hardware-flush" event the test added in aaf81223f48 wasn't
testing anything except that this trace2 data was unconditionally
logged. Even if "core.fsyncMethod" wasn't set to "batch" we'd pass the
test.
Now we'll check the expected number of "writeout" v.s. "flush" calls
under "core.fsyncMethod=batch", but note that this doesn't actually
test if we carried out the sync using that method, on a platform where
we'd have to fall back to fsync() each of those "writeout" would
really be a "flush" (i.e. a full fsync()).
But in this case what we're testing is that the logic in
"unpack-objects" behaves as expected, not the OS-specific question of
whether we actually were able to use the "bulk" method.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-18 12:31:52 +02:00
|
|
|
check_fsync_events () {
|
|
|
|
|
local trace="$1" &&
|
|
|
|
|
shift &&
|
|
|
|
|
|
|
|
|
|
cat >expect &&
|
|
|
|
|
sed -n \
|
|
|
|
|
-e '/^{"event":"data",.*"category":"fsync",/ {
|
|
|
|
|
s/.*"category":"fsync",//;
|
|
|
|
|
s/}$//;
|
|
|
|
|
p;
|
|
|
|
|
}' \
|
|
|
|
|
<"$trace" >actual &&
|
|
|
|
|
test_cmp expect actual
|
|
|
|
|
}
|
|
|
|
|
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
BATCH_CONFIGURATION='-c core.fsync=loose-object -c core.fsyncmethod=batch'
|
|
|
|
|
|
|
|
|
|
test_expect_success 'unpack big object in stream (core.fsyncmethod=batch)' '
|
|
|
|
|
prepare_dest 1m &&
|
|
|
|
|
GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \
|
trace2: only include "fsync" events if we git_fsync()
Fix the overly verbose trace2 logging added in 9a4987677d3 (trace2:
add stats for fsync operations, 2022-03-30) (first released with
v2.36.0).
Since that change every single "git" command invocation has included
these "data" events, even though we'll only make use of these with
core.fsyncMethod=batch, and even then only have non-zero values if
we're writing object data to disk. See c0f4752ed2f (core.fsyncmethod:
batched disk flushes for loose-objects, 2022-04-04) for that feature.
As we're needing to indent the trace2_data_intmax() lines let's
introduce helper variables to ensure that our resulting lines (which
were already too) don't exceed the recommendations of the
CodingGuidelines. Doing that requires either wrapping them twice, or
introducing short throwaway variable names, let's do the latter.
The result was that e.g. "git version" would previously emit a total
of 6 trace2 events with the GIT_TRACE2_EVENT target (version, start,
cmd_ancestry, cmd_name, exit, atexit), but afterwards would emit
8. We'd emit 2 "data" events before the "exit" event.
The reason we didn't catch this was that the trace2 unit tests added
in a15860dca3f (trace2: t/helper/test-trace2, t0210.sh, t0211.sh,
t0212.sh, 2019-02-22) would omit any "data" events that weren't the
ones it cared about. Before this change to the C code 6/7 of our
"t/t0212-trace2-event.sh" tests would fail if this change was applied
to "t/t0212/parse_events.perl".
Let's make the trace2 testing more strict, and further append any new
events types we don't know about in "t/t0212/parse_events.perl". Since
we only invoke the "test-tool trace2" there's no guarantee that we'll
catch other overly verbose events in the future, but we'll at least
notice if we start emitting new events that are issues every time we
log anything with trace2's JSON target.
We exclude the "data_json" event type, we'd otherwise would fail on
both "win test" and "win+VS test" CI due to the logging added in
353d3d77f4f (trace2: collect Windows-specific process information,
2019-02-22). It looks like that logging should really be using
trace2_cmd_ancestry() instead, which was introduced later in
2f732bf15e6 (tr2: log parent process name, 2021-07-21), but let's
leave it for now.
The fix-up to aaf81223f48 (unpack-objects: use stream_loose_object()
to unpack large objects, 2022-06-11) is needed because we're changing
the behavior of these events as discussed above. Since we'd always
emit a "hardware-flush" event the test added in aaf81223f48 wasn't
testing anything except that this trace2 data was unconditionally
logged. Even if "core.fsyncMethod" wasn't set to "batch" we'd pass the
test.
Now we'll check the expected number of "writeout" v.s. "flush" calls
under "core.fsyncMethod=batch", but note that this doesn't actually
test if we carried out the sync using that method, on a platform where
we'd have to fall back to fsync() each of those "writeout" would
really be a "flush" (i.e. a full fsync()).
But in this case what we're testing is that the logic in
"unpack-objects" behaves as expected, not the OS-specific question of
whether we actually were able to use the "bulk" method.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-18 12:31:52 +02:00
|
|
|
GIT_TEST_FSYNC=true \
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
git -C dest.git $BATCH_CONFIGURATION unpack-objects <pack-$PACK.pack &&
|
2022-07-29 14:28:43 +02:00
|
|
|
if grep "core.fsyncMethod = batch is unsupported" trace2.txt
|
|
|
|
|
then
|
|
|
|
|
flush_count=7
|
|
|
|
|
else
|
|
|
|
|
flush_count=1
|
|
|
|
|
fi &&
|
|
|
|
|
check_fsync_events trace2.txt <<-EOF &&
|
trace2: only include "fsync" events if we git_fsync()
Fix the overly verbose trace2 logging added in 9a4987677d3 (trace2:
add stats for fsync operations, 2022-03-30) (first released with
v2.36.0).
Since that change every single "git" command invocation has included
these "data" events, even though we'll only make use of these with
core.fsyncMethod=batch, and even then only have non-zero values if
we're writing object data to disk. See c0f4752ed2f (core.fsyncmethod:
batched disk flushes for loose-objects, 2022-04-04) for that feature.
As we're needing to indent the trace2_data_intmax() lines let's
introduce helper variables to ensure that our resulting lines (which
were already too) don't exceed the recommendations of the
CodingGuidelines. Doing that requires either wrapping them twice, or
introducing short throwaway variable names, let's do the latter.
The result was that e.g. "git version" would previously emit a total
of 6 trace2 events with the GIT_TRACE2_EVENT target (version, start,
cmd_ancestry, cmd_name, exit, atexit), but afterwards would emit
8. We'd emit 2 "data" events before the "exit" event.
The reason we didn't catch this was that the trace2 unit tests added
in a15860dca3f (trace2: t/helper/test-trace2, t0210.sh, t0211.sh,
t0212.sh, 2019-02-22) would omit any "data" events that weren't the
ones it cared about. Before this change to the C code 6/7 of our
"t/t0212-trace2-event.sh" tests would fail if this change was applied
to "t/t0212/parse_events.perl".
Let's make the trace2 testing more strict, and further append any new
events types we don't know about in "t/t0212/parse_events.perl". Since
we only invoke the "test-tool trace2" there's no guarantee that we'll
catch other overly verbose events in the future, but we'll at least
notice if we start emitting new events that are issues every time we
log anything with trace2's JSON target.
We exclude the "data_json" event type, we'd otherwise would fail on
both "win test" and "win+VS test" CI due to the logging added in
353d3d77f4f (trace2: collect Windows-specific process information,
2019-02-22). It looks like that logging should really be using
trace2_cmd_ancestry() instead, which was introduced later in
2f732bf15e6 (tr2: log parent process name, 2021-07-21), but let's
leave it for now.
The fix-up to aaf81223f48 (unpack-objects: use stream_loose_object()
to unpack large objects, 2022-06-11) is needed because we're changing
the behavior of these events as discussed above. Since we'd always
emit a "hardware-flush" event the test added in aaf81223f48 wasn't
testing anything except that this trace2 data was unconditionally
logged. Even if "core.fsyncMethod" wasn't set to "batch" we'd pass the
test.
Now we'll check the expected number of "writeout" v.s. "flush" calls
under "core.fsyncMethod=batch", but note that this doesn't actually
test if we carried out the sync using that method, on a platform where
we'd have to fall back to fsync() each of those "writeout" would
really be a "flush" (i.e. a full fsync()).
But in this case what we're testing is that the logic in
"unpack-objects" behaves as expected, not the OS-specific question of
whether we actually were able to use the "bulk" method.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-18 12:31:52 +02:00
|
|
|
"key":"fsync/writeout-only","value":"6"
|
2022-07-29 14:28:43 +02:00
|
|
|
"key":"fsync/hardware-flush","value":"$flush_count"
|
trace2: only include "fsync" events if we git_fsync()
Fix the overly verbose trace2 logging added in 9a4987677d3 (trace2:
add stats for fsync operations, 2022-03-30) (first released with
v2.36.0).
Since that change every single "git" command invocation has included
these "data" events, even though we'll only make use of these with
core.fsyncMethod=batch, and even then only have non-zero values if
we're writing object data to disk. See c0f4752ed2f (core.fsyncmethod:
batched disk flushes for loose-objects, 2022-04-04) for that feature.
As we're needing to indent the trace2_data_intmax() lines let's
introduce helper variables to ensure that our resulting lines (which
were already too) don't exceed the recommendations of the
CodingGuidelines. Doing that requires either wrapping them twice, or
introducing short throwaway variable names, let's do the latter.
The result was that e.g. "git version" would previously emit a total
of 6 trace2 events with the GIT_TRACE2_EVENT target (version, start,
cmd_ancestry, cmd_name, exit, atexit), but afterwards would emit
8. We'd emit 2 "data" events before the "exit" event.
The reason we didn't catch this was that the trace2 unit tests added
in a15860dca3f (trace2: t/helper/test-trace2, t0210.sh, t0211.sh,
t0212.sh, 2019-02-22) would omit any "data" events that weren't the
ones it cared about. Before this change to the C code 6/7 of our
"t/t0212-trace2-event.sh" tests would fail if this change was applied
to "t/t0212/parse_events.perl".
Let's make the trace2 testing more strict, and further append any new
events types we don't know about in "t/t0212/parse_events.perl". Since
we only invoke the "test-tool trace2" there's no guarantee that we'll
catch other overly verbose events in the future, but we'll at least
notice if we start emitting new events that are issues every time we
log anything with trace2's JSON target.
We exclude the "data_json" event type, we'd otherwise would fail on
both "win test" and "win+VS test" CI due to the logging added in
353d3d77f4f (trace2: collect Windows-specific process information,
2019-02-22). It looks like that logging should really be using
trace2_cmd_ancestry() instead, which was introduced later in
2f732bf15e6 (tr2: log parent process name, 2021-07-21), but let's
leave it for now.
The fix-up to aaf81223f48 (unpack-objects: use stream_loose_object()
to unpack large objects, 2022-06-11) is needed because we're changing
the behavior of these events as discussed above. Since we'd always
emit a "hardware-flush" event the test added in aaf81223f48 wasn't
testing anything except that this trace2 data was unconditionally
logged. Even if "core.fsyncMethod" wasn't set to "batch" we'd pass the
test.
Now we'll check the expected number of "writeout" v.s. "flush" calls
under "core.fsyncMethod=batch", but note that this doesn't actually
test if we carried out the sync using that method, on a platform where
we'd have to fall back to fsync() each of those "writeout" would
really be a "flush" (i.e. a full fsync()).
But in this case what we're testing is that the logic in
"unpack-objects" behaves as expected, not the OS-specific question of
whether we actually were able to use the "bulk" method.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-07-18 12:31:52 +02:00
|
|
|
EOF
|
|
|
|
|
|
unpack-objects: use stream_loose_object() to unpack large objects
Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.
We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:
rm -rf /tmp/scalar.git &&
git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
git hyperfine \
-r 2 --warmup 1 \
-L rev origin/master,HEAD -L v "10,512,1k,1m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'
Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:
Summary
'./git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:
rm -rf /tmp/repo &&
git init /tmp/repo &&
(
cd /tmp/repo &&
for i in 1 25 50 75 100
do
dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
done &&
git add blob.* &&
git commit -mblobs &&
git gc &&
PACK=$(echo .git/objects/pack/pack-*.pack) &&
cp "$PACK" my.pack
) &&
git hyperfine \
--show-output \
-L rev origin/master,HEAD -L v "512,50m,100m" \
-s 'make' \
-p 'git init --bare dest.git' \
-c 'rm -rf dest.git' \
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'
Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.
The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:
'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
Maximum resident set size (kbytes): 107080
1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 106968
1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
Maximum resident set size (kbytes): 107032
1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 107072
1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 55704
2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
Maximum resident set size (kbytes): 4564
This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.
An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.
Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.
0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/
Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-11 04:44:21 +02:00
|
|
|
test_dir_is_empty dest.git/objects/pack &&
|
|
|
|
|
git -C dest.git cat-file --batch-check="%(objectname)" <obj-list >current &&
|
|
|
|
|
cmp obj-list current
|
|
|
|
|
'
|
|
|
|
|
|
|
|
|
|
test_expect_success 'do not unpack existing large objects' '
|
|
|
|
|
prepare_dest 1m &&
|
|
|
|
|
git -C dest.git index-pack --stdin <pack-$PACK.pack &&
|
|
|
|
|
git -C dest.git unpack-objects <pack-$PACK.pack &&
|
|
|
|
|
|
|
|
|
|
# The destination came up with the exact same pack...
|
|
|
|
|
DEST_PACK=$(echo dest.git/objects/pack/pack-*.pack) &&
|
|
|
|
|
test_cmp pack-$PACK.pack $DEST_PACK &&
|
|
|
|
|
|
|
|
|
|
# ...and wrote no loose objects
|
|
|
|
|
test_stdout_line_count = 0 find dest.git/objects -type f ! -name "pack-*"
|
|
|
|
|
'
|
|
|
|
|
|
2022-06-11 04:44:16 +02:00
|
|
|
test_done
|