diff options
| author | Junio C Hamano <gitster@pobox.com> | 2022-07-14 15:03:59 -0700 |
|---|---|---|
| committer | Junio C Hamano <gitster@pobox.com> | 2022-07-14 15:03:59 -0700 |
| commit | 73b9ef6ab18fa7c9631f24eba0c67357067a1267 (patch) | |
| tree | e0f65b69d818f6725c2e3bcbbb702eb55d0134da /t/t5351-unpack-large-objects.sh | |
| parent | be733e120016a076926da3491c0c77d439686933 (diff) | |
| parent | aaf81223f48f710a3b9a64cc84fac93deed806b6 (diff) | |
| download | git-73b9ef6ab18fa7c9631f24eba0c67357067a1267.tar.gz | |
Merge branch 'hx/unpack-streaming'
Allow large objects read from a packstream to be streamed into a
loose object file straight, without having to keep it in-core as a
whole.
* hx/unpack-streaming:
unpack-objects: use stream_loose_object() to unpack large objects
core doc: modernize core.bigFileThreshold documentation
object-file.c: add "stream_loose_object()" to handle large object
object-file.c: factor out deflate part of write_loose_object()
object-file.c: refactor write_loose_object() to several steps
unpack-objects: low memory footprint for get_data() in dry_run mode
Diffstat (limited to 't/t5351-unpack-large-objects.sh')
| -rwxr-xr-x | t/t5351-unpack-large-objects.sh | 76 |
1 files changed, 76 insertions, 0 deletions
diff --git a/t/t5351-unpack-large-objects.sh b/t/t5351-unpack-large-objects.sh new file mode 100755 index 0000000000..8ce8aa3b14 --- /dev/null +++ b/t/t5351-unpack-large-objects.sh @@ -0,0 +1,76 @@ +#!/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" && + git init --bare dest.git && + git -C dest.git config core.bigFileThreshold "$1" +} + +test_expect_success "create large objects (1.5 MB) and PACK" ' + test-tool genrandom foo 1500000 >big-blob && + test_commit --append foo big-blob && + test-tool genrandom bar 1500000 >big-blob && + test_commit --append bar big-blob && + PACK=$(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 +' + +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' ' + prepare_dest 2m && + test_must_fail git -C dest.git unpack-objects <pack-$PACK.pack 2>err && + grep "fatal: attempting to allocate" err +' + +test_expect_success 'unpack-objects works with memory limitation in dry-run mode' ' + prepare_dest 2m && + git -C dest.git unpack-objects -n <pack-$PACK.pack && + test_stdout_line_count = 0 find dest.git/objects -type f && + test_dir_is_empty dest.git/objects/pack +' + +test_expect_success 'unpack big object in stream' ' + prepare_dest 1m && + git -C dest.git unpack-objects <pack-$PACK.pack && + test_dir_is_empty dest.git/objects/pack +' + +BATCH_CONFIGURATION='-c core.fsync=loose-object -c core.fsyncmethod=batch' + +test_expect_success 'unpack big object in stream (core.fsyncmethod=batch)' ' + prepare_dest 1m && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C dest.git $BATCH_CONFIGURATION unpack-objects <pack-$PACK.pack && + grep fsync/hardware-flush trace2.txt && + 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-*" +' + +test_done |