git/t/t0410-partial-clone.sh

193 lines
5.6 KiB
Bash
Raw Normal View History

#!/bin/sh
test_description='partial clone'
. ./test-lib.sh
delete_object () {
rm $1/.git/objects/$(echo $2 | sed -e 's|^..|&/|')
}
pack_as_from_promisor () {
HASH=$(git -C repo pack-objects .git/objects/pack/pack) &&
>repo/.git/objects/pack/pack-$HASH.promisor
}
promise_and_delete () {
HASH=$(git -C repo rev-parse "$1") &&
git -C repo tag -a -m message my_annotated_tag "$HASH" &&
git -C repo rev-parse my_annotated_tag | pack_as_from_promisor &&
git -C repo tag -d my_annotated_tag &&
delete_object repo "$HASH"
}
test_expect_success 'missing reflog object, but promised by a commit, passes fsck' '
test_create_repo repo &&
test_commit -C repo my_commit &&
A=$(git -C repo commit-tree -m a HEAD^{tree}) &&
C=$(git -C repo commit-tree -m c -p $A HEAD^{tree}) &&
# Reference $A only from reflog, and delete it
git -C repo branch my_branch "$A" &&
git -C repo branch -f my_branch my_commit &&
delete_object repo "$A" &&
# State that we got $C, which refers to $A, from promisor
printf "$C\n" | pack_as_from_promisor &&
# Normally, it fails
test_must_fail git -C repo fsck &&
# But with the extension, it succeeds
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
git -C repo fsck
'
test_expect_success 'missing reflog object, but promised by a tag, passes fsck' '
rm -rf repo &&
test_create_repo repo &&
test_commit -C repo my_commit &&
A=$(git -C repo commit-tree -m a HEAD^{tree}) &&
git -C repo tag -a -m d my_tag_name $A &&
T=$(git -C repo rev-parse my_tag_name) &&
git -C repo tag -d my_tag_name &&
# Reference $A only from reflog, and delete it
git -C repo branch my_branch "$A" &&
git -C repo branch -f my_branch my_commit &&
delete_object repo "$A" &&
# State that we got $T, which refers to $A, from promisor
printf "$T\n" | pack_as_from_promisor &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
git -C repo fsck
'
test_expect_success 'missing reflog object alone fails fsck, even with extension set' '
rm -rf repo &&
test_create_repo repo &&
test_commit -C repo my_commit &&
A=$(git -C repo commit-tree -m a HEAD^{tree}) &&
B=$(git -C repo commit-tree -m b HEAD^{tree}) &&
# Reference $A only from reflog, and delete it
git -C repo branch my_branch "$A" &&
git -C repo branch -f my_branch my_commit &&
delete_object repo "$A" &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
test_must_fail git -C repo fsck
'
test_expect_success 'missing ref object, but promised, passes fsck' '
rm -rf repo &&
test_create_repo repo &&
test_commit -C repo my_commit &&
A=$(git -C repo commit-tree -m a HEAD^{tree}) &&
# Reference $A only from ref
git -C repo branch my_branch "$A" &&
promise_and_delete "$A" &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
git -C repo fsck
'
test_expect_success 'missing object, but promised, passes fsck' '
rm -rf repo &&
test_create_repo repo &&
test_commit -C repo 1 &&
test_commit -C repo 2 &&
test_commit -C repo 3 &&
git -C repo tag -a annotated_tag -m "annotated tag" &&
C=$(git -C repo rev-parse 1) &&
T=$(git -C repo rev-parse 2^{tree}) &&
B=$(git hash-object repo/3.t) &&
AT=$(git -C repo rev-parse annotated_tag) &&
promise_and_delete "$C" &&
promise_and_delete "$T" &&
promise_and_delete "$B" &&
promise_and_delete "$AT" &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
git -C repo fsck
'
test_expect_success 'missing CLI object, but promised, passes fsck' '
rm -rf repo &&
test_create_repo repo &&
test_commit -C repo my_commit &&
A=$(git -C repo commit-tree -m a HEAD^{tree}) &&
promise_and_delete "$A" &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "arbitrary string" &&
git -C repo fsck "$A"
'
sha1_file: support lazily fetching missing objects Teach sha1_file to fetch objects from the remote configured in extensions.partialclone whenever an object is requested but missing. The fetching of objects can be suppressed through a global variable. This is used by fsck and index-pack. However, by default, such fetching is not suppressed. This is meant as a temporary measure to ensure that all Git commands work in such a situation. Future patches will update some commands to either tolerate missing objects (without fetching them) or be more efficient in fetching them. In order to determine the code changes in sha1_file.c necessary, I investigated the following: (1) functions in sha1_file.c that take in a hash, without the user regarding how the object is stored (loose or packed) (2) functions in packfile.c (because I need to check callers that know about the loose/packed distinction and operate on both differently, and ensure that they can handle the concept of objects that are neither loose nor packed) (1) is handled by the modification to sha1_object_info_extended(). For (2), I looked at for_each_packed_object and others. For for_each_packed_object, the callers either already work or are fixed in this patch: - reachable - only to find recent objects - builtin/fsck - already knows about missing objects - builtin/cat-file - warning message added in this commit Callers of the other functions do not need to be changed: - parse_pack_index - http - indirectly from http_get_info_packs - find_pack_entry_one - this searches a single pack that is provided as an argument; the caller already knows (through other means) that the sought object is in a specific pack - find_sha1_pack - fast-import - appears to be an optimization to not store a file if it is already in a pack - http-walker - to search through a struct alt_base - http-push - to search through remote packs - has_sha1_pack - builtin/fsck - already knows about promisor objects - builtin/count-objects - informational purposes only (check if loose object is also packed) - builtin/prune-packed - check if object to be pruned is packed (if not, don't prune it) - revision - used to exclude packed objects if requested by user - diff - just for optimization Signed-off-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-12-08 15:27:14 +00:00
test_expect_success 'fetching of missing objects' '
rm -rf repo &&
test_create_repo server &&
test_commit -C server foo &&
git -C server repack -a -d --write-bitmap-index &&
git clone "file://$(pwd)/server" repo &&
HASH=$(git -C repo rev-parse foo) &&
rm -rf repo/.git/objects/* &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "origin" &&
git -C repo cat-file -p "$HASH" &&
# Ensure that the .promisor file is written, and check that its
# associated packfile contains the object
ls repo/.git/objects/pack/pack-*.promisor >promisorlist &&
test_line_count = 1 promisorlist &&
IDX=$(cat promisorlist | sed "s/promisor$/idx/") &&
git verify-pack --verbose "$IDX" | grep "$HASH"
'
LIB_HTTPD_PORT=12345 # default port, 410, cannot be used as non-root
. "$TEST_DIRECTORY"/lib-httpd.sh
start_httpd
test_expect_success 'fetching of missing objects from an HTTP server' '
rm -rf repo &&
SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" &&
test_create_repo "$SERVER" &&
test_commit -C "$SERVER" foo &&
git -C "$SERVER" repack -a -d --write-bitmap-index &&
git clone $HTTPD_URL/smart/server repo &&
HASH=$(git -C repo rev-parse foo) &&
rm -rf repo/.git/objects/* &&
git -C repo config core.repositoryformatversion 1 &&
git -C repo config extensions.partialclone "origin" &&
git -C repo cat-file -p "$HASH" &&
# Ensure that the .promisor file is written, and check that its
# associated packfile contains the object
ls repo/.git/objects/pack/pack-*.promisor >promisorlist &&
test_line_count = 1 promisorlist &&
IDX=$(cat promisorlist | sed "s/promisor$/idx/") &&
git verify-pack --verbose "$IDX" | grep "$HASH"
'
stop_httpd
test_done