From 7b671f8c2b6b7de511fd2f6587e4540c25764b61 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 23 Jun 2020 17:47:01 +0000 Subject: commit-graph: change test to die on parse, not load 43d3561 (commit-graph write: don't die if the existing graph is corrupt, 2019-03-25) introduced the GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD environment variable. This was created to verify that commit-graph was not loaded when writing a new non-incremental commit-graph. An upcoming change wants to load a commit-graph in some valuable cases, but we want to maintain that we don't trust the commit-graph data when writing our new file. Instead of dying on load, instead die if we ever try to parse a commit from the commit-graph. This functionally verifies the same intended behavior, but allows a more advanced feature in the next change. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- commit-graph.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'commit-graph.h') diff --git a/commit-graph.h b/commit-graph.h index 881c9b46e5..f0fb13e3f2 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -5,7 +5,7 @@ #include "object-store.h" #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH" -#define GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD "GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD" +#define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE" #define GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS "GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS" /* -- cgit v1.3 From 0087a87ba8fc69b27dde0183ec24ade367a4aa5b Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 1 Jul 2020 13:27:24 +0000 Subject: commit-graph: persist existence of changed-paths The changed-path Bloom filters were released in v2.27.0, but have a significant drawback. A user can opt-in to writing the changed-path filters using the "--changed-paths" option to "git commit-graph write" but the next write will drop the filters unless that option is specified. This becomes even more important when considering the interaction with gc.writeCommitGraph (on by default) or fetch.writeCommitGraph (part of features.experimental). These config options trigger commit-graph writes that the user did not signal, and hence there is no --changed-paths option available. Allow a user that opts-in to the changed-path filters to persist the property of "my commit-graph has changed-path filters" automatically. A user can drop filters using the --no-changed-paths option. In the process, we need to be extremely careful to match the Bloom filter settings as specified by the commit-graph. This will allow future versions of Git to customize these settings, and the version with this change will persist those settings as commit-graphs are rewritten on top. Use the trace2 API to signal the settings used during the write, and check that output in a test after manually adjusting the correct bytes in the commit-graph file. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 5 ++++- builtin/commit-graph.c | 5 ++++- commit-graph.c | 45 +++++++++++++++++++++++++++++++++++--- commit-graph.h | 1 + t/t4216-log-bloom.sh | 17 +++++++++++++- 5 files changed, 67 insertions(+), 6 deletions(-) (limited to 'commit-graph.h') diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index f4b13c005b..369b222b08 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -60,7 +60,10 @@ existing commit-graph file. With the `--changed-paths` option, compute and write information about the paths changed between a commit and it's first parent. This operation can take a while on large repositories. It provides significant performance gains -for getting history of a directory or a file with `git log -- `. +for getting history of a directory or a file with `git log -- `. If +this option is given, future commit-graph writes will automatically assume +that this option was intended. Use `--no-changed-paths` to stop storing this +data. + With the `--split` option, write the commit-graph as a chain of multiple commit-graph files stored in `/info/commit-graphs`. The new commits diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 59009837dc..ff7b177c33 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -151,6 +151,7 @@ static int graph_write(int argc, const char **argv) }; opts.progress = isatty(2); + opts.enable_changed_paths = -1; split_opts.size_multiple = 2; split_opts.max_commits = 0; split_opts.expire_time = 0; @@ -171,7 +172,9 @@ static int graph_write(int argc, const char **argv) flags |= COMMIT_GRAPH_WRITE_SPLIT; if (opts.progress) flags |= COMMIT_GRAPH_WRITE_PROGRESS; - if (opts.enable_changed_paths || + if (!opts.enable_changed_paths) + flags |= COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS; + if (opts.enable_changed_paths == 1 || git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0)) flags |= COMMIT_GRAPH_WRITE_BLOOM_FILTERS; diff --git a/commit-graph.c b/commit-graph.c index 50ce039a53..6762704324 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -16,6 +16,8 @@ #include "progress.h" #include "bloom.h" #include "commit-slab.h" +#include "json-writer.h" +#include "trace2.h" void git_test_write_commit_graph_or_die(void) { @@ -1108,6 +1110,21 @@ static void write_graph_chunk_bloom_indexes(struct hashfile *f, stop_progress(&progress); } +static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx) +{ + struct json_writer jw = JSON_WRITER_INIT; + + jw_object_begin(&jw, 0); + jw_object_intmax(&jw, "hash_version", ctx->bloom_settings->hash_version); + jw_object_intmax(&jw, "num_hashes", ctx->bloom_settings->num_hashes); + jw_object_intmax(&jw, "bits_per_entry", ctx->bloom_settings->bits_per_entry); + jw_end(&jw); + + trace2_data_json("bloom", ctx->r, "settings", &jw); + + jw_release(&jw); +} + static void write_graph_chunk_bloom_data(struct hashfile *f, struct write_commit_graph_context *ctx) { @@ -1116,6 +1133,8 @@ static void write_graph_chunk_bloom_data(struct hashfile *f, struct progress *progress = NULL; int i = 0; + trace2_bloom_filter_settings(ctx); + if (ctx->report_progress) progress = start_delayed_progress( _("Writing changed paths Bloom filters data"), @@ -1547,9 +1566,15 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) int num_chunks = 3; uint64_t chunk_offset; struct object_id file_hash; - const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; + struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; - ctx->bloom_settings = &bloom_settings; + if (!ctx->bloom_settings) { + bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY", + bloom_settings.bits_per_entry); + bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES", + bloom_settings.num_hashes); + ctx->bloom_settings = &bloom_settings; + } if (ctx->split) { struct strbuf tmp_file = STRBUF_INIT; @@ -1974,9 +1999,23 @@ int write_commit_graph(struct object_directory *odb, ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0; ctx->check_oids = flags & COMMIT_GRAPH_WRITE_CHECK_OIDS ? 1 : 0; ctx->split_opts = split_opts; - ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0; ctx->total_bloom_filter_data_size = 0; + if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS) + ctx->changed_paths = 1; + if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) { + struct commit_graph *g; + prepare_commit_graph_one(ctx->r, ctx->odb); + + g = ctx->r->objects->commit_graph; + + /* We have changed-paths already. Keep them in the next graph */ + if (g && g->chunk_bloom_data) { + ctx->changed_paths = 1; + ctx->bloom_settings = g->bloom_filter_settings; + } + } + if (ctx->split) { struct commit_graph *g; prepare_commit_graph(ctx->r); diff --git a/commit-graph.h b/commit-graph.h index f0fb13e3f2..45b1e5bca3 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -96,6 +96,7 @@ enum commit_graph_write_flags { /* Make sure that each OID in the input is a valid commit OID. */ COMMIT_GRAPH_WRITE_CHECK_OIDS = (1 << 3), COMMIT_GRAPH_WRITE_BLOOM_FILTERS = (1 << 4), + COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS = (1 << 5), }; struct split_commit_graph_opts { diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh index 2761208e74..52ad998f9e 100755 --- a/t/t4216-log-bloom.sh +++ b/t/t4216-log-bloom.sh @@ -126,7 +126,7 @@ test_expect_success 'setup - add commit-graph to the chain without Bloom filters test_commit c14 A/anotherFile2 && test_commit c15 A/B/anotherFile2 && test_commit c16 A/B/C/anotherFile2 && - GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=0 git commit-graph write --reachable --split && + git commit-graph write --reachable --split --no-changed-paths && test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain ' @@ -152,6 +152,21 @@ test_expect_success 'Use Bloom filters if they exist in the latest but not all c test_bloom_filters_used_when_some_filters_are_missing "-- A/B" ' +test_expect_success 'persist filter settings' ' + test_when_finished rm -rf .git/objects/info/commit-graph* && + rm -rf .git/objects/info/commit-graph* && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ + GIT_TRACE2_EVENT_NESTING=5 \ + GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=9 \ + GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY=15 \ + git commit-graph write --reachable --changed-paths && + grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2-auto.txt" \ + GIT_TRACE2_EVENT_NESTING=5 \ + git commit-graph write --reachable --changed-paths && + grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt +' + test_expect_success 'correctly report changes over limit' ' git init 513changes && ( -- cgit v1.3