Teach git-commit-graph to read commits from stdin when the --stdin-commits flag is specified. Commits reachable from these commits are added to the graph. This is a much faster way to construct the graph than inspecting all packed objects, but is restricted to known tips. For the Linux repository, 700,000+ commits were added to the graph file starting from 'master' in 7-9 seconds, depending on the number of packfiles in the repo (1, 24, or 120). Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx> --- Documentation/git-commit-graph.txt | 7 ++++++- builtin/commit-graph.c | 34 +++++++++++++++++++++++++--------- commit-graph.c | 26 +++++++++++++++++++++++--- commit-graph.h | 4 +++- t/t5318-commit-graph.sh | 18 ++++++++++++++++++ 5 files changed, 75 insertions(+), 14 deletions(-) diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index d0571cd896..3357c0cf8f 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -46,7 +46,12 @@ OPTIONS --stdin-packs:: When used with --write, generate the new graph by walking objects only in the specified packfiles and any commits in the - existing graph-head. + existing graph-head. (Cannot be combined with --stdin-commits.) + +--stdin-commits:: + When used with --write, generate the new graph by walking commits + starting at the commits specified in stdin as a list of OIDs in + hex, one OID per line. (Cannot be combined with --stdin-packs.) EXAMPLES -------- diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 80a409e784..adc05f0582 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -12,7 +12,7 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--pack-dir <packdir>]"), N_("git commit-graph --clear [--pack-dir <packdir>]"), N_("git commit-graph --read [--graph-hash=<hash>]"), - N_("git commit-graph --write [--pack-dir <packdir>] [--update-head] [--delete-expired] [--stdin-packs]"), + N_("git commit-graph --write [--pack-dir <packdir>] [--update-head] [--delete-expired] [--stdin-packs|--stdin-commits]"), NULL }; @@ -25,6 +25,7 @@ static struct opts_commit_graph { int update_head; int delete_expired; int stdin_packs; + int stdin_commits; int has_existing; struct object_id old_graph_hash; } opts; @@ -117,23 +118,36 @@ static int graph_write(void) { struct object_id *graph_hash; char **pack_indexes = NULL; + char **commits = NULL; int num_packs = 0; - int size_packs = 0; + int num_commits = 0; + char **lines = NULL; + int num_lines = 0; + int size_lines = 0; - if (opts.stdin_packs) { + if (opts.stdin_packs || opts.stdin_commits) { struct strbuf buf = STRBUF_INIT; - size_packs = 128; - ALLOC_ARRAY(pack_indexes, size_packs); + size_lines = 128; + ALLOC_ARRAY(lines, size_lines); while (strbuf_getline(&buf, stdin) != EOF) { - ALLOC_GROW(pack_indexes, num_packs + 1, size_packs); - pack_indexes[num_packs++] = buf.buf; + ALLOC_GROW(lines, num_lines + 1, size_lines); + lines[num_lines++] = buf.buf; strbuf_detach(&buf, NULL); } - } - graph_hash = construct_commit_graph(opts.pack_dir, pack_indexes, num_packs); + if (opts.stdin_packs) { + pack_indexes = lines; + num_packs = num_lines; + } + if (opts.stdin_commits) { + commits = lines; + num_commits = num_lines; + } + } + graph_hash = construct_commit_graph(opts.pack_dir, pack_indexes, num_packs, + commits, num_commits); if (opts.update_head) update_head_file(opts.pack_dir, graph_hash); @@ -172,6 +186,8 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix) N_("delete expired head graph file")), OPT_BOOL('s', "stdin-packs", &opts.stdin_packs, N_("only scan packfiles listed by stdin")), + OPT_BOOL('C', "stdin-commits", &opts.stdin_commits, + N_("start walk at commits listed by stdin")), { OPTION_STRING, 'H', "graph-hash", &opts.graph_hash, N_("hash"), N_("A hash for a specific graph file in the pack-dir."), diff --git a/commit-graph.c b/commit-graph.c index cfa0415a21..7f31a6c795 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -664,7 +664,9 @@ static void close_reachable(struct packed_oid_list *oids) struct object_id *construct_commit_graph(const char *pack_dir, char **pack_indexes, - int nr_packs) + int nr_packs, + char **commit_hex, + int nr_commits) { struct packed_oid_list oids; struct packed_commit_list commits; @@ -717,10 +719,28 @@ struct object_id *construct_commit_graph(const char *pack_dir, for_each_object_in_pack(p, if_packed_commit_add_to_list, &oids); close_pack(p); } - } else { - for_each_packed_object(if_packed_commit_add_to_list, &oids, 0); } + if (commit_hex) { + for (i = 0; i < nr_commits; i++) { + const char *end; + ALLOC_GROW(oids.list, oids.num + 1, oids.size); + + oids.list[oids.num] = malloc(sizeof(struct object_id)); + + if (parse_oid_hex(commit_hex[i], oids.list[oids.num], &end)) { + free(oids.list[oids.num]); + continue; + } + + if (lookup_commit(oids.list[oids.num])) + oids.num++; + } + } + + if (!pack_indexes && !commit_hex) + for_each_packed_object(if_packed_commit_add_to_list, &oids, 0); + close_reachable(&oids); QSORT(oids.list, oids.num, commit_compare); diff --git a/commit-graph.h b/commit-graph.h index 3ae1eadce0..619b1f6def 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -62,6 +62,8 @@ extern struct object_id *get_nth_commit_oid(struct commit_graph *g, extern struct object_id *construct_commit_graph(const char *pack_dir, char **pack_indexes, - int nr_packs); + int nr_packs, + char **commits, + int nr_commits); #endif diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 2001b0b5b5..0bf27a2e7c 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -227,6 +227,24 @@ test_expect_success 'build graph from latest pack with closure' \ _graph_git_behavior commits/20 merge/1 _graph_git_behavior commits/20 merge/2 +test_expect_success 'build graph from commits with closure' \ + 'git rev-parse commits/20 >commits-in && + git rev-parse merge/1 >>commits-in && + git rev-parse merge/2 >>commits-in && + graph6=$(cat commits-in | git commit-graph --write --update-head --delete-expired --stdin-commits) && + test_path_is_file ${packdir}/graph-${graph6}.graph && + test_path_is_missing ${packdir}/graph-${graph5}.graph && + test_path_is_file ${packdir}/graph-${graph1}.graph && + test_path_is_file ${packdir}/graph-head && + echo ${graph6} >expect && + cmp -n 40 expect ${packdir}/graph-head && + git commit-graph --read --graph-hash=${graph6} >output && + _graph_read_expect "23" "${packdir}" && + cmp expect output' + +_graph_git_behavior commits/20 merge/1 +_graph_git_behavior commits/20 merge/2 + test_expect_success 'setup bare repo' \ 'cd .. && git clone --bare full bare && -- 2.16.0.15.g9c3cf44.dirty