diff options
Diffstat (limited to 't')
| -rw-r--r-- | t/helper/test-bloom.c | 9 | ||||
| -rw-r--r-- | t/helper/test-read-graph.c | 65 | ||||
| -rwxr-xr-x | t/t0095-bloom.sh | 8 | ||||
| -rwxr-xr-x | t/t4216-log-bloom.sh | 325 |
4 files changed, 389 insertions, 18 deletions
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c index f7f9b62002..97541daf71 100644 --- a/t/helper/test-bloom.c +++ b/t/helper/test-bloom.c @@ -51,6 +51,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid) static const char *bloom_usage = "\n" " test-tool bloom get_murmur3 <string>\n" +" test-tool bloom get_murmur3_seven_highbit\n" " test-tool bloom generate_filter <string> [<string>...]\n" " test-tool bloom get_filter_for_commit <commit-hex>\n"; @@ -65,7 +66,13 @@ int cmd__bloom(int argc, const char **argv) uint32_t hashed; if (argc < 3) usage(bloom_usage); - hashed = murmur3_seeded(0, argv[2], strlen(argv[2])); + hashed = murmur3_seeded_v2(0, argv[2], strlen(argv[2])); + printf("Murmur3 Hash with seed=0:0x%08x\n", hashed); + } + + if (!strcmp(argv[1], "get_murmur3_seven_highbit")) { + uint32_t hashed; + hashed = murmur3_seeded_v2(0, "\x99\xaa\xbb\xcc\xdd\xee\xff", 7); printf("Murmur3 Hash with seed=0:0x%08x\n", hashed); } diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c index d9e980d04c..9018c9f541 100644 --- a/t/helper/test-read-graph.c +++ b/t/helper/test-read-graph.c @@ -7,20 +7,8 @@ #include "bloom.h" #include "setup.h" -int cmd__read_graph(int argc UNUSED, const char **argv UNUSED) +static void dump_graph_info(struct commit_graph *graph) { - struct commit_graph *graph = NULL; - struct object_directory *odb; - - setup_git_directory(); - odb = the_repository->objects->odb; - - prepare_repo_settings(the_repository); - - graph = read_commit_graph_one(the_repository, odb); - if (!graph) - return 1; - printf("header: %08x %d %d %d %d\n", ntohl(*(uint32_t*)graph->data), *(unsigned char*)(graph->data + 4), @@ -59,8 +47,57 @@ int cmd__read_graph(int argc UNUSED, const char **argv UNUSED) if (graph->topo_levels) printf(" topo_levels"); printf("\n"); +} + +static void dump_graph_bloom_filters(struct commit_graph *graph) +{ + uint32_t i; + + for (i = 0; i < graph->num_commits + graph->num_commits_in_base; i++) { + struct bloom_filter filter = { 0 }; + size_t j; + + if (load_bloom_filter_from_graph(graph, &filter, i) < 0) { + fprintf(stderr, "missing Bloom filter for graph " + "position %"PRIu32"\n", i); + continue; + } + + for (j = 0; j < filter.len; j++) + printf("%02x", filter.data[j]); + if (filter.len) + printf("\n"); + } +} + +int cmd__read_graph(int argc, const char **argv) +{ + struct commit_graph *graph = NULL; + struct object_directory *odb; + int ret = 0; + + setup_git_directory(); + odb = the_repository->objects->odb; + + prepare_repo_settings(the_repository); + + graph = read_commit_graph_one(the_repository, odb); + if (!graph) { + ret = 1; + goto done; + } + + if (argc <= 1) + dump_graph_info(graph); + else if (!strcmp(argv[1], "bloom-filters")) + dump_graph_bloom_filters(graph); + else { + fprintf(stderr, "unknown sub-command: '%s'\n", argv[1]); + ret = 1; + } +done: UNLEAK(graph); - return 0; + return ret; } diff --git a/t/t0095-bloom.sh b/t/t0095-bloom.sh index b567383eb8..c8d84ab606 100755 --- a/t/t0095-bloom.sh +++ b/t/t0095-bloom.sh @@ -29,6 +29,14 @@ test_expect_success 'compute unseeded murmur3 hash for test string 2' ' test_cmp expect actual ' +test_expect_success 'compute unseeded murmur3 hash for test string 3' ' + cat >expect <<-\EOF && + Murmur3 Hash with seed=0:0xa183ccfd + EOF + test-tool bloom get_murmur3_seven_highbit >actual && + test_cmp expect actual +' + test_expect_success 'compute bloom key for empty string' ' cat >expect <<-\EOF && Hashes:0x5615800c|0x5b966560|0x61174ab4|0x66983008|0x6c19155c|0x7199fab0|0x771ae004| diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh index 2ba0324a69..3f163dc396 100755 --- a/t/t4216-log-bloom.sh +++ b/t/t4216-log-bloom.sh @@ -82,7 +82,23 @@ test_bloom_filters_used () { test_bloom_filters_not_used () { log_args=$1 setup "$log_args" && - ! grep -q "statistics:{\"filter_not_present\":" "$TRASH_DIRECTORY/trace.perf" && + + if grep -q "statistics:{\"filter_not_present\":" "$TRASH_DIRECTORY/trace.perf" + then + # if the Bloom filter system is initialized, ensure that no + # filters were used + data="statistics:{" + # unusable filters (e.g., those computed with a + # different value of commitGraph.changedPathsVersion) + # are counted in the filter_not_present bucket, so any + # value is OK there. + data="$data\"filter_not_present\":[0-9][0-9]*," + data="$data\"maybe\":0," + data="$data\"definitely_not\":0," + data="$data\"false_positive\":0}" + + grep -q "$data" "$TRASH_DIRECTORY/trace.perf" + fi && test_cmp log_wo_bloom log_w_bloom } @@ -163,7 +179,7 @@ test_expect_success 'setup - add commit-graph to the chain with Bloom filters' ' test_bloom_filters_used_when_some_filters_are_missing () { log_args=$1 - bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"maybe\":6,\"definitely_not\":9" + bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"maybe\":6,\"definitely_not\":10" setup "$log_args" && grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" && test_cmp log_wo_bloom log_w_bloom @@ -206,6 +222,10 @@ test_filter_trunc_large () { grep "\"key\":\"filter-trunc-large\",\"value\":\"$1\"" $2 } +test_filter_upgraded () { + grep "\"key\":\"filter-upgraded\",\"value\":\"$1\"" $2 +} + test_expect_success 'correctly report changes over limit' ' git init limits && ( @@ -405,8 +425,307 @@ test_expect_success 'Bloom generation backfills empty commits' ' ) ' +graph=.git/objects/info/commit-graph +graphdir=.git/objects/info/commit-graphs +chain=$graphdir/commit-graph-chain + +test_expect_success 'setup for mixed Bloom setting tests' ' + repo=mixed-bloom-settings && + + git init $repo && + for i in one two three + do + test_commit -C $repo $i file || return 1 + done +' + +test_expect_success 'ensure Bloom filters with incompatible settings are ignored' ' + # Compute Bloom filters with "unusual" settings. + git -C $repo rev-parse one >in && + GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=3 git -C $repo commit-graph write \ + --stdin-commits --changed-paths --split <in && + layer=$(head -n 1 $repo/$chain) && + + # A commit-graph layer without Bloom filters "hides" the layers + # below ... + git -C $repo rev-parse two >in && + git -C $repo commit-graph write --stdin-commits --no-changed-paths \ + --split=no-merge <in && + + # Another commit-graph layer that has Bloom filters, but with + # standard settings, and is thus incompatible with the base + # layer written above. + git -C $repo rev-parse HEAD >in && + git -C $repo commit-graph write --stdin-commits --changed-paths \ + --split=no-merge <in && + + test_line_count = 3 $repo/$chain && + + # Ensure that incompatible Bloom filters are ignored. + git -C $repo -c core.commitGraph=false log --oneline --no-decorate -- file \ + >expect 2>err && + git -C $repo log --oneline --no-decorate -- file >actual 2>err && + test_cmp expect actual && + grep "disabling Bloom filters for commit-graph layer .$layer." err +' + +test_expect_success 'merge graph layers with incompatible Bloom settings' ' + # Ensure that incompatible Bloom filters are ignored when + # merging existing layers. + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C $repo commit-graph write --reachable --changed-paths 2>err && + grep "disabling Bloom filters for commit-graph layer .$layer." err && + grep "{\"hash_version\":1,\"num_hashes\":7,\"bits_per_entry\":10,\"max_changed_paths\":512" trace2.txt && + + test_path_is_file $repo/$graph && + test_dir_is_empty $repo/$graphdir && + + git -C $repo -c core.commitGraph=false log --oneline --no-decorate -- \ + file >expect && + trace_out="$(pwd)/trace.perf" && + GIT_TRACE2_PERF="$trace_out" \ + git -C $repo log --oneline --no-decorate -- file >actual 2>err && + + test_cmp expect actual && + grep "statistics:{\"filter_not_present\":0," trace.perf && + test_must_be_empty err +' + +# chosen to be the same under all Unicode normalization forms +CENT=$(printf "\302\242") + +test_expect_success 'ensure Bloom filter with incompatible versions are ignored' ' + rm "$repo/$graph" && + + git -C $repo log --oneline --no-decorate -- $CENT >expect && + + # Compute v1 Bloom filters for commits at the bottom. + git -C $repo rev-parse HEAD^ >in && + git -C $repo commit-graph write --stdin-commits --changed-paths \ + --split <in && + + # Compute v2 Bloomfilters for the rest of the commits at the top. + git -C $repo rev-parse HEAD >in && + git -C $repo -c commitGraph.changedPathsVersion=2 commit-graph write \ + --stdin-commits --changed-paths --split=no-merge <in && + + test_line_count = 2 $repo/$chain && + + git -C $repo log --oneline --no-decorate -- $CENT >actual 2>err && + test_cmp expect actual && + + layer="$(head -n 1 $repo/$chain)" && + cat >expect.err <<-EOF && + warning: disabling Bloom filters for commit-graph layer $SQ$layer$SQ due to incompatible settings + EOF + test_cmp expect.err err && + + # Merge the two layers with incompatible bloom filter versions, + # ensuring that the v2 filters are used. + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C $repo -c commitGraph.changedPathsVersion=2 commit-graph write --reachable --changed-paths 2>err && + grep "disabling Bloom filters for commit-graph layer .$layer." err && + grep "{\"hash_version\":2,\"num_hashes\":7,\"bits_per_entry\":10,\"max_changed_paths\":512" trace2.txt +' + +get_first_changed_path_filter () { + test-tool read-graph bloom-filters >filters.dat && + head -n 1 filters.dat +} + +test_expect_success 'set up repo with high bit path, version 1 changed-path' ' + git init highbit1 && + test_commit -C highbit1 c1 "$CENT" && + git -C highbit1 commit-graph write --reachable --changed-paths +' + +test_expect_success 'setup check value of version 1 changed-path' ' + ( + cd highbit1 && + echo "52a9" >expect && + get_first_changed_path_filter >actual + ) +' + +# expect will not match actual if char is unsigned by default. Write the test +# in this way, so that a user running this test script can still see if the two +# files match. (It will appear as an ordinary success if they match, and a skip +# if not.) +if test_cmp highbit1/expect highbit1/actual +then + test_set_prereq SIGNED_CHAR_BY_DEFAULT +fi +test_expect_success SIGNED_CHAR_BY_DEFAULT 'check value of version 1 changed-path' ' + # Only the prereq matters for this test. + true +' + +test_expect_success 'setup make another commit' ' + # "git log" does not use Bloom filters for root commits - see how, in + # revision.c, rev_compare_tree() (the only code path that eventually calls + # get_bloom_filter()) is only called by try_to_simplify_commit() when the commit + # has one parent. Therefore, make another commit so that we perform the tests on + # a non-root commit. + test_commit -C highbit1 anotherc1 "another$CENT" +' + +test_expect_success 'version 1 changed-path used when version 1 requested' ' + ( + cd highbit1 && + test_bloom_filters_used "-- another$CENT" + ) +' + +test_expect_success 'version 1 changed-path not used when version 2 requested' ' + ( + cd highbit1 && + git config --add commitGraph.changedPathsVersion 2 && + test_bloom_filters_not_used "-- another$CENT" + ) +' + +test_expect_success 'version 1 changed-path used when autodetect requested' ' + ( + cd highbit1 && + git config --add commitGraph.changedPathsVersion -1 && + test_bloom_filters_used "-- another$CENT" + ) +' + +test_expect_success 'when writing another commit graph, preserve existing version 1 of changed-path' ' + test_commit -C highbit1 c1double "$CENT$CENT" && + git -C highbit1 commit-graph write --reachable --changed-paths && + ( + cd highbit1 && + git config --add commitGraph.changedPathsVersion -1 && + echo "options: bloom(1,10,7) read_generation_data" >expect && + test-tool read-graph >full && + grep options full >actual && + test_cmp expect actual + ) +' + +test_expect_success 'set up repo with high bit path, version 2 changed-path' ' + git init highbit2 && + git -C highbit2 config --add commitGraph.changedPathsVersion 2 && + test_commit -C highbit2 c2 "$CENT" && + git -C highbit2 commit-graph write --reachable --changed-paths +' + +test_expect_success 'check value of version 2 changed-path' ' + ( + cd highbit2 && + echo "c01f" >expect && + get_first_changed_path_filter >actual && + test_cmp expect actual + ) +' + +test_expect_success 'setup make another commit' ' + # "git log" does not use Bloom filters for root commits - see how, in + # revision.c, rev_compare_tree() (the only code path that eventually calls + # get_bloom_filter()) is only called by try_to_simplify_commit() when the commit + # has one parent. Therefore, make another commit so that we perform the tests on + # a non-root commit. + test_commit -C highbit2 anotherc2 "another$CENT" +' + +test_expect_success 'version 2 changed-path used when version 2 requested' ' + ( + cd highbit2 && + test_bloom_filters_used "-- another$CENT" + ) +' + +test_expect_success 'version 2 changed-path not used when version 1 requested' ' + ( + cd highbit2 && + git config --add commitGraph.changedPathsVersion 1 && + test_bloom_filters_not_used "-- another$CENT" + ) +' + +test_expect_success 'version 2 changed-path used when autodetect requested' ' + ( + cd highbit2 && + git config --add commitGraph.changedPathsVersion -1 && + test_bloom_filters_used "-- another$CENT" + ) +' + +test_expect_success 'when writing another commit graph, preserve existing version 2 of changed-path' ' + test_commit -C highbit2 c2double "$CENT$CENT" && + git -C highbit2 commit-graph write --reachable --changed-paths && + ( + cd highbit2 && + git config --add commitGraph.changedPathsVersion -1 && + echo "options: bloom(2,10,7) read_generation_data" >expect && + test-tool read-graph >full && + grep options full >actual && + test_cmp expect actual + ) +' + +test_expect_success 'when writing commit graph, do not reuse changed-path of another version' ' + git init doublewrite && + test_commit -C doublewrite c "$CENT" && + + git -C doublewrite config --add commitGraph.changedPathsVersion 1 && + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C doublewrite commit-graph write --reachable --changed-paths && + test_filter_computed 1 trace2.txt && + test_filter_upgraded 0 trace2.txt && + + git -C doublewrite commit-graph write --reachable --changed-paths && + for v in -2 3 + do + git -C doublewrite config --add commitGraph.changedPathsVersion $v && + git -C doublewrite commit-graph write --reachable --changed-paths 2>err && + cat >expect <<-EOF && + warning: attempting to write a commit-graph, but ${SQ}commitGraph.changedPathsVersion${SQ} ($v) is not supported + EOF + test_cmp expect err || return 1 + done && + + git -C doublewrite config --add commitGraph.changedPathsVersion 2 && + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C doublewrite commit-graph write --reachable --changed-paths && + test_filter_computed 1 trace2.txt && + test_filter_upgraded 0 trace2.txt && + + ( + cd doublewrite && + echo "c01f" >expect && + get_first_changed_path_filter >actual && + test_cmp expect actual + ) +' + +test_expect_success 'when writing commit graph, reuse changed-path of another version where possible' ' + git init upgrade && + + test_commit -C upgrade base no-high-bits && + + git -C upgrade config --add commitGraph.changedPathsVersion 1 && + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C upgrade commit-graph write --reachable --changed-paths && + test_filter_computed 1 trace2.txt && + test_filter_upgraded 0 trace2.txt && + + git -C upgrade config --add commitGraph.changedPathsVersion 2 && + >trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + git -C upgrade commit-graph write --reachable --changed-paths && + test_filter_computed 0 trace2.txt && + test_filter_upgraded 1 trace2.txt +' + corrupt_graph () { - graph=.git/objects/info/commit-graph && test_when_finished "rm -rf $graph" && git commit-graph write --reachable --changed-paths && corrupt_chunk_file $graph "$@" |