diff options
Diffstat (limited to 't/t5616-partial-clone.sh')
| -rwxr-xr-x | t/t5616-partial-clone.sh | 363 |
1 files changed, 327 insertions, 36 deletions
diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh index bbbe7537df..fea56cda6d 100755 --- a/t/t5616-partial-clone.sh +++ b/t/t5616-partial-clone.sh @@ -34,22 +34,32 @@ test_expect_success 'setup bare clone for server' ' # confirm partial clone was registered in the local config. test_expect_success 'do partial clone 1' ' git clone --no-checkout --filter=blob:none "file://$(pwd)/srv.bare" pc1 && - git -C pc1 rev-list HEAD --quiet --objects --missing=print \ - | awk -f print_1.awk \ - | sed "s/?//" \ - | sort >observed.oids && + + git -C pc1 rev-list --quiet --objects --missing=print HEAD >revs && + awk -f print_1.awk revs | + sed "s/?//" | + sort >observed.oids && + test_cmp expect_1.oids observed.oids && test "$(git -C pc1 config --local core.repositoryformatversion)" = "1" && - test "$(git -C pc1 config --local extensions.partialclone)" = "origin" && - test "$(git -C pc1 config --local core.partialclonefilter)" = "blob:none" + test "$(git -C pc1 config --local remote.origin.promisor)" = "true" && + test "$(git -C pc1 config --local remote.origin.partialclonefilter)" = "blob:none" +' + +test_expect_success 'verify that .promisor file contains refs fetched' ' + ls pc1/.git/objects/pack/pack-*.promisor >promisorlist && + test_line_count = 1 promisorlist && + git -C srv.bare rev-list HEAD >headhash && + grep "$(cat headhash) HEAD" $(cat promisorlist) && + grep "$(cat headhash) refs/heads/master" $(cat promisorlist) ' # checkout master to force dynamic object fetch of blobs at HEAD. test_expect_success 'verify checkout with dynamic object fetch' ' - git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print HEAD >observed && test_line_count = 4 observed && git -C pc1 checkout master && - git -C pc1 rev-list HEAD --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print HEAD >observed && test_line_count = 0 observed ' @@ -72,7 +82,8 @@ test_expect_success 'push new commits to server' ' # have the new blobs. test_expect_success 'partial fetch inherits filter settings' ' git -C pc1 fetch origin && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >observed && test_line_count = 5 observed ' @@ -80,7 +91,8 @@ test_expect_success 'partial fetch inherits filter settings' ' # we should only get 1 new blob (for the file in origin/master). test_expect_success 'verify diff causes dynamic object fetch' ' git -C pc1 diff master..origin/master -- file.1.txt && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >observed && test_line_count = 4 observed ' @@ -89,7 +101,8 @@ test_expect_success 'verify diff causes dynamic object fetch' ' test_expect_success 'verify blame causes dynamic object fetch' ' git -C pc1 blame origin/master -- file.1.txt >observed.blame && test_cmp expect.blame observed.blame && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >observed && test_line_count = 0 observed ' @@ -109,7 +122,8 @@ test_expect_success 'push new commits to server for file.2.txt' ' # Verify we have all the new blobs. test_expect_success 'override inherited filter-spec using --no-filter' ' git -C pc1 fetch --no-filter origin && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print >observed && + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >observed && test_line_count = 0 observed ' @@ -130,16 +144,22 @@ test_expect_success 'push new commits to server for file.3.txt' ' # perhaps combined with a command in dry-run mode. test_expect_success 'manual prefetch of missing objects' ' git -C pc1 fetch --filter=blob:none origin && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print \ - | awk -f print_1.awk \ - | sed "s/?//" \ - | sort >observed.oids && + + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >revs && + awk -f print_1.awk revs | + sed "s/?//" | + sort >observed.oids && + test_line_count = 6 observed.oids && git -C pc1 fetch-pack --stdin "file://$(pwd)/srv.bare" <observed.oids && - git -C pc1 rev-list master..origin/master --quiet --objects --missing=print \ - | awk -f print_1.awk \ - | sed "s/?//" \ - | sort >observed.oids && + + git -C pc1 rev-list --quiet --objects --missing=print \ + master..origin/master >revs && + awk -f print_1.awk revs | + sed "s/?//" | + sort >observed.oids && + test_line_count = 0 observed.oids ' @@ -154,6 +174,67 @@ test_expect_success 'partial clone with transfer.fsckobjects=1 uses index-pack - grep "git index-pack.*--fsck-objects" trace ' +test_expect_success 'use fsck before and after manually fetching a missing subtree' ' + # push new commit so server has a subtree + mkdir src/dir && + echo "in dir" >src/dir/file.txt && + git -C src add dir/file.txt && + git -C src commit -m "file in dir" && + git -C src push -u srv master && + SUBTREE=$(git -C src rev-parse HEAD:dir) && + + rm -rf dst && + git clone --no-checkout --filter=tree:0 "file://$(pwd)/srv.bare" dst && + git -C dst fsck && + + # Make sure we only have commits, and all trees and blobs are missing. + git -C dst rev-list --missing=allow-any --objects master \ + >fetched_objects && + awk -f print_1.awk fetched_objects | + xargs -n1 git -C dst cat-file -t >fetched_types && + + sort -u fetched_types >unique_types.observed && + echo commit >unique_types.expected && + test_cmp unique_types.expected unique_types.observed && + + # Auto-fetch a tree with cat-file. + git -C dst cat-file -p $SUBTREE >tree_contents && + grep file.txt tree_contents && + + # fsck still works after an auto-fetch of a tree. + git -C dst fsck && + + # Auto-fetch all remaining trees and blobs with --missing=error + git -C dst rev-list --missing=error --objects master >fetched_objects && + test_line_count = 70 fetched_objects && + + awk -f print_1.awk fetched_objects | + xargs -n1 git -C dst cat-file -t >fetched_types && + + sort -u fetched_types >unique_types.observed && + test_write_lines blob commit tree >unique_types.expected && + test_cmp unique_types.expected unique_types.observed +' + +test_expect_success 'implicitly construct combine: filter with repeated flags' ' + GIT_TRACE=$(pwd)/trace git clone --bare \ + --filter=blob:none --filter=tree:1 \ + "file://$(pwd)/srv.bare" pc2 && + grep "trace:.* git pack-objects .*--filter=combine:blob:none+tree:1" \ + trace && + git -C pc2 rev-list --objects --missing=allow-any HEAD >objects && + + # We should have gotten some root trees. + grep " $" objects && + # Should not have gotten any non-root trees or blobs. + ! grep " ." objects && + + xargs -n 1 git -C pc2 cat-file -t <objects >types && + sort -u types >unique_types.actual && + test_write_lines commit tree >unique_types.expected && + test_cmp unique_types.expected unique_types.actual +' + test_expect_success 'partial clone fetches blobs pointed to by refs even if normally filtered out' ' rm -rf src dst && git init src && @@ -170,14 +251,151 @@ test_expect_success 'partial clone fetches blobs pointed to by refs even if norm git -C dst fsck ' +test_expect_success 'fetch what is specified on CLI even if already promised' ' + rm -rf src dst.git && + git init src && + test_commit -C src foo && + test_config -C src uploadpack.allowfilter 1 && + test_config -C src uploadpack.allowanysha1inwant 1 && + + git hash-object --stdin <src/foo.t >blob && + + git clone --bare --filter=blob:none "file://$(pwd)/src" dst.git && + git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_before && + grep "?$(cat blob)" missing_before && + git -C dst.git fetch origin $(cat blob) && + git -C dst.git rev-list --objects --quiet --missing=print HEAD >missing_after && + ! grep "?$(cat blob)" missing_after +' + +test_expect_success 'setup src repo for sparse filter' ' + git init sparse-src && + git -C sparse-src config --local uploadpack.allowfilter 1 && + git -C sparse-src config --local uploadpack.allowanysha1inwant 1 && + test_commit -C sparse-src one && + test_commit -C sparse-src two && + echo /one.t >sparse-src/only-one && + git -C sparse-src add . && + git -C sparse-src commit -m "add sparse checkout files" +' + +test_expect_success 'partial clone with sparse filter succeeds' ' + rm -rf dst.git && + git clone --no-local --bare \ + --filter=sparse:oid=master:only-one \ + sparse-src dst.git && + ( + cd dst.git && + git rev-list --objects --missing=print HEAD >out && + grep "^$(git rev-parse HEAD:one.t)" out && + grep "^?$(git rev-parse HEAD:two.t)" out + ) +' + +test_expect_success 'partial clone with unresolvable sparse filter fails cleanly' ' + rm -rf dst.git && + test_must_fail git clone --no-local --bare \ + --filter=sparse:oid=master:no-such-name \ + sparse-src dst.git 2>err && + test_i18ngrep "unable to access sparse blob in .master:no-such-name" err && + test_must_fail git clone --no-local --bare \ + --filter=sparse:oid=master \ + sparse-src dst.git 2>err && + test_i18ngrep "unable to parse sparse filter data in" err +' + +setup_triangle () { + rm -rf big-blob.txt server client promisor-remote && + + printf "line %d\n" $(test_seq 1 100) >big-blob.txt && + + # Create a server with 2 commits: a commit with a big blob and a child + # commit with an incremental change. Also, create a partial clone + # client that only contains the first commit. + git init server && + git -C server config --local uploadpack.allowfilter 1 && + cp big-blob.txt server && + git -C server add big-blob.txt && + git -C server commit -m "initial" && + git clone --bare --filter=tree:0 "file://$(pwd)/server" client && + echo another line >>server/big-blob.txt && + git -C server commit -am "append line to big blob" && + + # Create a promisor remote that only contains the blob from the first + # commit, and set it as the promisor remote of client. Thus, whenever + # the client lazy fetches, the lazy fetch will succeed only if it is + # for this blob. + git init promisor-remote && + test_commit -C promisor-remote one && # so that ref advertisement is not empty + git -C promisor-remote config --local uploadpack.allowanysha1inwant 1 && + git -C promisor-remote hash-object -w --stdin <big-blob.txt && + git -C client remote set-url origin "file://$(pwd)/promisor-remote" +} + +# NEEDSWORK: The tests beginning with "fetch lazy-fetches" below only +# test that "fetch" avoid fetching trees and blobs, but not commits or +# tags. Revisit this if Git is ever taught to support partial clones +# with commits and/or tags filtered out. + +test_expect_success 'fetch lazy-fetches only to resolve deltas' ' + setup_triangle && + + # Exercise to make sure it works. Git will not fetch anything from the + # promisor remote other than for the big blob (because it needs to + # resolve the delta). + GIT_TRACE_PACKET="$(pwd)/trace" git -C client \ + fetch "file://$(pwd)/server" master && + + # Verify the assumption that the client needed to fetch the delta base + # to resolve the delta. + git hash-object big-blob.txt >hash && + grep "want $(cat hash)" trace +' + +test_expect_success 'fetch lazy-fetches only to resolve deltas, protocol v2' ' + setup_triangle && + + git -C server config --local protocol.version 2 && + git -C client config --local protocol.version 2 && + git -C promisor-remote config --local protocol.version 2 && + + # Exercise to make sure it works. Git will not fetch anything from the + # promisor remote other than for the big blob (because it needs to + # resolve the delta). + GIT_TRACE_PACKET="$(pwd)/trace" git -C client \ + fetch "file://$(pwd)/server" master && + + # Verify that protocol version 2 was used. + grep "fetch< version 2" trace && + + # Verify the assumption that the client needed to fetch the delta base + # to resolve the delta. + git hash-object big-blob.txt >hash && + grep "want $(cat hash)" trace +' + . "$TEST_DIRECTORY"/lib-httpd.sh start_httpd -# Converts bytes into a form suitable for inclusion in a sed command. For -# example, "printf 'ab\r\n' | hex_unpack" results in '\x61\x62\x0d\x0a'. -sed_escape () { - perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)' | - sed 's/\(..\)/\\x\1/g' +# Converts bytes into their hexadecimal representation. For example, +# "printf 'ab\r\n' | hex_unpack" results in '61620d0a'. +hex_unpack () { + perl -e '$/ = undef; $input = <>; print unpack("H2" x length($input), $input)' +} + +# Inserts $1 at the start of the string and every 2 characters thereafter. +intersperse () { + sed 's/\(..\)/'$1'\1/g' +} + +# Create a one-time-sed command to replace the existing packfile with $1. +replace_packfile () { + # The protocol requires that the packfile be sent in sideband 1, hence + # the extra \x01 byte at the beginning. + printf "1,/packfile/!c %04x\\\\x01%s0000" \ + "$(($(wc -c <$1) + 5))" \ + "$(hex_unpack <$1 | intersperse '\\x')" \ + >"$HTTPD_ROOT_PATH/one-time-sed" } test_expect_success 'upon cloning, check that all refs point to objects' ' @@ -194,15 +412,12 @@ test_expect_success 'upon cloning, check that all refs point to objects' ' # Craft a packfile not including that blob. git -C "$SERVER" rev-parse HEAD | - git -C "$SERVER" pack-objects --stdout >incomplete.pack && + git -C "$SERVER" pack-objects --stdout >incomplete.pack && # Replace the existing packfile with the crafted one. The protocol # requires that the packfile be sent in sideband 1, hence the extra # \x01 byte at the beginning. - printf "1,/packfile/!c %04x\\\\x01%s0000" \ - "$(($(wc -c <incomplete.pack) + 5))" \ - "$(sed_escape <incomplete.pack)" \ - >"$HTTPD_ROOT_PATH/one-time-sed" && + replace_packfile incomplete.pack && # Use protocol v2 because the sed command looks for the "packfile" # section header. @@ -210,7 +425,7 @@ test_expect_success 'upon cloning, check that all refs point to objects' ' test_must_fail git -c protocol.version=2 clone \ --filter=blob:none $HTTPD_URL/one_time_sed/server repo 2>err && - grep "did not send all necessary objects" err && + test_i18ngrep "did not send all necessary objects" err && # Ensure that the one-time-sed script was used. ! test -e "$HTTPD_ROOT_PATH/one-time-sed" @@ -242,10 +457,7 @@ test_expect_success 'when partial cloning, tolerate server not sending target of # Replace the existing packfile with the crafted one. The protocol # requires that the packfile be sent in sideband 1, hence the extra # \x01 byte at the beginning. - printf "1,/packfile/!c %04x\\\\x01%s0000" \ - "$(($(wc -c <incomplete.pack) + 5))" \ - "$(sed_escape <incomplete.pack)" \ - >"$HTTPD_ROOT_PATH/one-time-sed" && + replace_packfile incomplete.pack && # Use protocol v2 because the sed command looks for the "packfile" # section header. @@ -260,6 +472,85 @@ test_expect_success 'when partial cloning, tolerate server not sending target of ! test -e "$HTTPD_ROOT_PATH/one-time-sed" ' -stop_httpd +test_expect_success 'tolerate server sending REF_DELTA against missing promisor objects' ' + SERVER="$HTTPD_DOCUMENT_ROOT_PATH/server" && + rm -rf "$SERVER" repo && + test_create_repo "$SERVER" && + test_config -C "$SERVER" uploadpack.allowfilter 1 && + test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 && + + # Create a commit with 2 blobs to be used as delta bases. + for i in $(test_seq 10) + do + echo "this is a line" >>"$SERVER/foo.txt" && + echo "this is another line" >>"$SERVER/have.txt" + done && + git -C "$SERVER" add foo.txt have.txt && + git -C "$SERVER" commit -m bar && + git -C "$SERVER" rev-parse HEAD:foo.txt >deltabase_missing && + git -C "$SERVER" rev-parse HEAD:have.txt >deltabase_have && + + # Clone. The client has deltabase_have but not deltabase_missing. + git -c protocol.version=2 clone --no-checkout \ + --filter=blob:none $HTTPD_URL/one_time_sed/server repo && + git -C repo hash-object -w -- "$SERVER/have.txt" && + + # Sanity check to ensure that the client does not have + # deltabase_missing. + git -C repo rev-list --objects --ignore-missing \ + -- $(cat deltabase_missing) >objlist && + test_line_count = 0 objlist && + + # Another commit. This commit will be fetched by the client. + echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/foo.txt" && + echo "abcdefghijklmnopqrstuvwxyz" >>"$SERVER/have.txt" && + git -C "$SERVER" add foo.txt have.txt && + git -C "$SERVER" commit -m baz && + + # Pack a thin pack containing, among other things, HEAD:foo.txt + # delta-ed against HEAD^:foo.txt and HEAD:have.txt delta-ed against + # HEAD^:have.txt. + printf "%s\n--not\n%s\n" \ + $(git -C "$SERVER" rev-parse HEAD) \ + $(git -C "$SERVER" rev-parse HEAD^) | + git -C "$SERVER" pack-objects --thin --stdout >thin.pack && + + # Ensure that the pack contains one delta against HEAD^:foo.txt. Since + # the delta contains at least 26 novel characters, the size cannot be + # contained in 4 bits, so the object header will take up 2 bytes. The + # most significant nybble of the first byte is 0b1111 (0b1 to indicate + # that the header continues, and 0b111 to indicate REF_DELTA), followed + # by any 3 nybbles, then the OID of the delta base. + printf "f.,..%s" $(intersperse "," <deltabase_missing) >want && + hex_unpack <thin.pack | intersperse "," >have && + grep $(cat want) have && + + # Ensure that the pack contains one delta against HEAD^:have.txt, + # similar to the above. + printf "f.,..%s" $(intersperse "," <deltabase_have) >want && + hex_unpack <thin.pack | intersperse "," >have && + grep $(cat want) have && + + replace_packfile thin.pack && + + # Use protocol v2 because the sed command looks for the "packfile" + # section header. + test_config -C "$SERVER" protocol.version 2 && + + # Fetch the thin pack and ensure that index-pack is able to handle the + # REF_DELTA object with a missing promisor delta base. + GIT_TRACE_PACKET="$(pwd)/trace" git -C repo -c protocol.version=2 fetch && + + # Ensure that the missing delta base was directly fetched, but not the + # one that the client has. + grep "want $(cat deltabase_missing)" trace && + ! grep "want $(cat deltabase_have)" trace && + + # Ensure that the one-time-sed script was used. + ! test -e "$HTTPD_ROOT_PATH/one-time-sed" +' + +# DO NOT add non-httpd-specific tests here, because the last part of this +# test script is only executed when httpd is available and enabled. test_done |