diff options
Diffstat (limited to 'commit-graph.c')
| -rw-r--r-- | commit-graph.c | 530 |
1 files changed, 297 insertions, 233 deletions
diff --git a/commit-graph.c b/commit-graph.c index 1af68c297d..e9124d4a41 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1,7 +1,5 @@ -#include "cache.h" -#include "config.h" -#include "dir.h" #include "git-compat-util.h" +#include "config.h" #include "lockfile.h" #include "pack.h" #include "packfile.h" @@ -9,7 +7,7 @@ #include "object.h" #include "refs.h" #include "revision.h" -#include "sha1-lookup.h" +#include "hash-lookup.h" #include "commit-graph.h" #include "object-store.h" #include "alloc.h" @@ -19,6 +17,8 @@ #include "bloom.h" #include "commit-slab.h" #include "shallow.h" +#include "json-writer.h" +#include "trace2.h" void git_test_write_commit_graph_or_die(void) { @@ -172,14 +172,21 @@ static char *get_split_graph_filename(struct object_directory *odb, oid_hex); } -static char *get_chain_filename(struct object_directory *odb) +char *get_commit_graph_chain_filename(struct object_directory *odb) { return xstrfmt("%s/info/commit-graphs/commit-graph-chain", odb->path); } static uint8_t oid_version(void) { - return 1; + switch (hash_algo_by_ptr(the_hash_algo)) { + case GIT_HASH_SHA1: + return 1; + case GIT_HASH_SHA256: + return 2; + default: + die(_("invalid hash version")); + } } static struct commit_graph *alloc_commit_graph(void) @@ -224,7 +231,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st) return 1; } -struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st, +struct commit_graph *load_commit_graph_one_fd_st(struct repository *r, + int fd, struct stat *st, struct object_directory *odb) { void *graph_map; @@ -240,7 +248,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st, } graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - ret = parse_commit_graph(graph_map, graph_size); + ret = parse_commit_graph(r, graph_map, graph_size); if (ret) ret->odb = odb; @@ -280,13 +288,13 @@ static int verify_commit_graph_lite(struct commit_graph *g) return 0; } -struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) +struct commit_graph *parse_commit_graph(struct repository *r, + void *graph_map, size_t graph_size) { const unsigned char *data, *chunk_lookup; uint32_t i; struct commit_graph *graph; - uint64_t last_chunk_offset; - uint32_t last_chunk_id; + uint64_t next_chunk_offset; uint32_t graph_signature; unsigned char graph_version, hash_version; @@ -319,6 +327,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) return NULL; } + prepare_repo_settings(r); + graph = alloc_commit_graph(); graph->hash_len = the_hash_algo->rawsz; @@ -326,24 +336,26 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) graph->data = graph_map; graph->data_len = graph_size; - last_chunk_id = 0; - last_chunk_offset = 8; + if (graph_size < GRAPH_HEADER_SIZE + + (graph->num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH + + GRAPH_FANOUT_SIZE + the_hash_algo->rawsz) { + error(_("commit-graph file is too small to hold %u chunks"), + graph->num_chunks); + free(graph); + return NULL; + } + chunk_lookup = data + 8; + next_chunk_offset = get_be64(chunk_lookup + 4); for (i = 0; i < graph->num_chunks; i++) { uint32_t chunk_id; - uint64_t chunk_offset; + uint64_t chunk_offset = next_chunk_offset; int chunk_repeated = 0; - if (data + graph_size - chunk_lookup < - GRAPH_CHUNKLOOKUP_WIDTH) { - error(_("commit-graph chunk lookup table entry missing; file may be incomplete")); - goto free_and_return; - } - chunk_id = get_be32(chunk_lookup + 0); - chunk_offset = get_be64(chunk_lookup + 4); chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH; + next_chunk_offset = get_be64(chunk_lookup + 4); if (chunk_offset > graph_size - the_hash_algo->rawsz) { error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32), @@ -362,8 +374,11 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) case GRAPH_CHUNKID_OIDLOOKUP: if (graph->chunk_oid_lookup) chunk_repeated = 1; - else + else { graph->chunk_oid_lookup = data + chunk_offset; + graph->num_commits = (next_chunk_offset - chunk_offset) + / graph->hash_len; + } break; case GRAPH_CHUNKID_DATA: @@ -390,14 +405,14 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) case GRAPH_CHUNKID_BLOOMINDEXES: if (graph->chunk_bloom_indexes) chunk_repeated = 1; - else + else if (r->settings.commit_graph_read_changed_paths) graph->chunk_bloom_indexes = data + chunk_offset; break; case GRAPH_CHUNKID_BLOOMDATA: if (graph->chunk_bloom_data) chunk_repeated = 1; - else { + else if (r->settings.commit_graph_read_changed_paths) { uint32_t hash_version; graph->chunk_bloom_data = data + chunk_offset; hash_version = get_be32(data + chunk_offset); @@ -409,6 +424,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) graph->bloom_filter_settings->hash_version = hash_version; graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4); graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8); + graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES; } break; } @@ -417,15 +433,6 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) error(_("commit-graph chunk id %08x appears multiple times"), chunk_id); goto free_and_return; } - - if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP) - { - graph->num_commits = (chunk_offset - last_chunk_offset) - / graph->hash_len; - } - - last_chunk_id = chunk_id; - last_chunk_offset = chunk_offset; } if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) { @@ -450,7 +457,8 @@ free_and_return: return NULL; } -static struct commit_graph *load_commit_graph_one(const char *graph_file, +static struct commit_graph *load_commit_graph_one(struct repository *r, + const char *graph_file, struct object_directory *odb) { @@ -462,7 +470,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file, if (!open_ok) return NULL; - g = load_commit_graph_one_fd_st(fd, &st, odb); + g = load_commit_graph_one_fd_st(r, fd, &st, odb); if (g) g->filename = xstrdup(graph_file); @@ -474,7 +482,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r, struct object_directory *odb) { char *graph_name = get_commit_graph_filename(odb); - struct commit_graph *g = load_commit_graph_one(graph_name, odb); + struct commit_graph *g = load_commit_graph_one(r, graph_name, odb); free(graph_name); return g; @@ -521,7 +529,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, struct stat st; struct object_id *oids; int i = 0, valid = 1, count; - char *chain_name = get_chain_filename(odb); + char *chain_name = get_commit_graph_chain_filename(odb); FILE *fp; int stat_res; @@ -555,7 +563,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, valid = 0; for (odb = r->objects->odb; odb; odb = odb->next) { char *graph_name = get_split_graph_filename(odb, line.buf); - struct commit_graph *g = load_commit_graph_one(graph_name, odb); + struct commit_graph *g = load_commit_graph_one(r, graph_name, odb); free(graph_name); @@ -624,10 +632,6 @@ static int prepare_commit_graph(struct repository *r) return !!r->objects->commit_graph; r->objects->commit_graph_attempted = 1; - if (git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD, 0)) - die("dying as requested by the '%s' variable on commit-graph load!", - GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD); - prepare_repo_settings(r); if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) && @@ -669,6 +673,17 @@ int generation_numbers_enabled(struct repository *r) return !!first_generation; } +struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r) +{ + struct commit_graph *g = r->objects->commit_graph; + while (g) { + if (g->bloom_filter_settings) + return g->bloom_filter_settings; + g = g->base_graph; + } + return NULL; +} + static void close_commit_graph_one(struct commit_graph *g) { if (!g) @@ -856,6 +871,14 @@ static int parse_commit_in_graph_one(struct repository *r, int parse_commit_in_graph(struct repository *r, struct commit *item) { + static int checked_env = 0; + + if (!checked_env && + git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE, 0)) + die("dying as requested by the '%s' variable on commit-graph parse!", + GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE); + checked_env = 1; + if (!prepare_commit_graph(r)) return 0; return parse_commit_in_graph_one(r, r->objects->commit_graph, item); @@ -909,21 +932,15 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit struct packed_commit_list { struct commit **list; - int nr; - int alloc; -}; - -struct packed_oid_list { - struct object_id *list; - int nr; - int alloc; + size_t nr; + size_t alloc; }; struct write_commit_graph_context { struct repository *r; struct object_directory *odb; char *graph_name; - struct packed_oid_list oids; + struct oid_array oids; struct packed_commit_list commits; int num_extra_edges; unsigned long approx_nr_objects; @@ -946,12 +963,18 @@ struct write_commit_graph_context { changed_paths:1, order_by_pack:1; - const struct split_commit_graph_opts *split_opts; + const struct commit_graph_opts *opts; size_t total_bloom_filter_data_size; + const struct bloom_filter_settings *bloom_settings; + + int count_bloom_filter_computed; + int count_bloom_filter_not_computed; + int count_bloom_filter_trunc_empty; + int count_bloom_filter_trunc_large; }; -static void write_graph_chunk_fanout(struct hashfile *f, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_fanout(struct hashfile *f, + struct write_commit_graph_context *ctx) { int i, count = 0; struct commit **list = ctx->commits.list; @@ -972,17 +995,21 @@ static void write_graph_chunk_fanout(struct hashfile *f, hashwrite_be32(f, count); } + + return 0; } -static void write_graph_chunk_oids(struct hashfile *f, int hash_len, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_oids(struct hashfile *f, + struct write_commit_graph_context *ctx) { struct commit **list = ctx->commits.list; int count; for (count = 0; count < ctx->commits.nr; count++, list++) { display_progress(ctx->progress, ++ctx->progress_cnt); - hashwrite(f, (*list)->object.oid.hash, (int)hash_len); + hashwrite(f, (*list)->object.oid.hash, the_hash_algo->rawsz); } + + return 0; } static const unsigned char *commit_to_sha1(size_t index, void *table) @@ -991,8 +1018,8 @@ static const unsigned char *commit_to_sha1(size_t index, void *table) return commits[index]->object.oid.hash; } -static void write_graph_chunk_data(struct hashfile *f, int hash_len, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_data(struct hashfile *f, + struct write_commit_graph_context *ctx) { struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; @@ -1009,14 +1036,14 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, die(_("unable to parse commit %s"), oid_to_hex(&(*list)->object.oid)); tree = get_commit_tree_oid(*list); - hashwrite(f, tree->hash, hash_len); + hashwrite(f, tree->hash, the_hash_algo->rawsz); parent = (*list)->parents; if (!parent) edge_value = GRAPH_PARENT_NONE; else { - edge_value = sha1_pos(parent->item->object.oid.hash, + edge_value = hash_pos(parent->item->object.oid.hash, ctx->commits.list, ctx->commits.nr, commit_to_sha1); @@ -1047,7 +1074,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, else if (parent->next) edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges; else { - edge_value = sha1_pos(parent->item->object.oid.hash, + edge_value = hash_pos(parent->item->object.oid.hash, ctx->commits.list, ctx->commits.nr, commit_to_sha1); @@ -1089,10 +1116,12 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, list++; } + + return 0; } -static void write_graph_chunk_extra_edges(struct hashfile *f, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_extra_edges(struct hashfile *f, + struct write_commit_graph_context *ctx) { struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; @@ -1114,7 +1143,7 @@ static void write_graph_chunk_extra_edges(struct hashfile *f, /* Since num_parents > 2, this initializer is safe. */ for (parent = (*list)->parents->next; parent; parent = parent->next) { - int edge_value = sha1_pos(parent->item->object.oid.hash, + int edge_value = hash_pos(parent->item->object.oid.hash, ctx->commits.list, ctx->commits.nr, commit_to_sha1); @@ -1141,48 +1170,68 @@ static void write_graph_chunk_extra_edges(struct hashfile *f, list++; } + + return 0; } -static void write_graph_chunk_bloom_indexes(struct hashfile *f, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_bloom_indexes(struct hashfile *f, + struct write_commit_graph_context *ctx) { struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; uint32_t cur_pos = 0; while (list < last) { - struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0); - cur_pos += filter->len; + struct bloom_filter *filter = get_bloom_filter(ctx->r, *list); + size_t len = filter ? filter->len : 0; + cur_pos += len; display_progress(ctx->progress, ++ctx->progress_cnt); hashwrite_be32(f, cur_pos); list++; } + + return 0; +} + +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_object_intmax(&jw, "max_changed_paths", ctx->bloom_settings->max_changed_paths); + 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, - const struct bloom_filter_settings *settings) +static int write_graph_chunk_bloom_data(struct hashfile *f, + struct write_commit_graph_context *ctx) { struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; - hashwrite_be32(f, settings->hash_version); - hashwrite_be32(f, settings->num_hashes); - hashwrite_be32(f, settings->bits_per_entry); + trace2_bloom_filter_settings(ctx); + + hashwrite_be32(f, ctx->bloom_settings->hash_version); + hashwrite_be32(f, ctx->bloom_settings->num_hashes); + hashwrite_be32(f, ctx->bloom_settings->bits_per_entry); while (list < last) { - struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0); + struct bloom_filter *filter = get_bloom_filter(ctx->r, *list); + size_t len = filter ? filter->len : 0; + display_progress(ctx->progress, ++ctx->progress_cnt); - hashwrite(f, filter->data, filter->len * sizeof(unsigned char)); + if (len) + hashwrite(f, filter->data, len * sizeof(unsigned char)); list++; } -} -static int oid_compare(const void *_a, const void *_b) -{ - const struct object_id *a = (const struct object_id *)_a; - const struct object_id *b = (const struct object_id *)_b; - return oidcmp(a, b); + return 0; } static int add_packed_commits(const struct object_id *oid, @@ -1205,10 +1254,7 @@ static int add_packed_commits(const struct object_id *oid, if (type != OBJ_COMMIT) return 0; - ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); - oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid); - ctx->oids.nr++; - + oid_array_append(&ctx->oids, oid); set_commit_pos(ctx->r, oid); return 0; @@ -1219,9 +1265,7 @@ static void add_missing_parents(struct write_commit_graph_context *ctx, struct c struct commit_list *parent; for (parent = commit->parents; parent; parent = parent->next) { if (!(parent->item->object.flags & REACHABLE)) { - ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); - oidcpy(&ctx->oids.list[ctx->oids.nr], &(parent->item->object.oid)); - ctx->oids.nr++; + oid_array_append(&ctx->oids, &parent->item->object.oid); parent->item->object.flags |= REACHABLE; } } @@ -1231,8 +1275,8 @@ static void close_reachable(struct write_commit_graph_context *ctx) { int i; struct commit *commit; - enum commit_graph_split_flags flags = ctx->split_opts ? - ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED; + enum commit_graph_split_flags flags = ctx->opts ? + ctx->opts->split_flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED; if (ctx->report_progress) ctx->progress = start_delayed_progress( @@ -1240,7 +1284,7 @@ static void close_reachable(struct write_commit_graph_context *ctx) ctx->oids.nr); for (i = 0; i < ctx->oids.nr; i++) { display_progress(ctx->progress, i + 1); - commit = lookup_commit(ctx->r, &ctx->oids.list[i]); + commit = lookup_commit(ctx->r, &ctx->oids.oid[i]); if (commit) commit->object.flags |= REACHABLE; } @@ -1257,7 +1301,7 @@ static void close_reachable(struct write_commit_graph_context *ctx) 0); for (i = 0; i < ctx->oids.nr; i++) { display_progress(ctx->progress, i + 1); - commit = lookup_commit(ctx->r, &ctx->oids.list[i]); + commit = lookup_commit(ctx->r, &ctx->oids.oid[i]); if (!commit) continue; @@ -1277,7 +1321,7 @@ static void close_reachable(struct write_commit_graph_context *ctx) ctx->oids.nr); for (i = 0; i < ctx->oids.nr; i++) { display_progress(ctx->progress, i + 1); - commit = lookup_commit(ctx->r, &ctx->oids.list[i]); + commit = lookup_commit(ctx->r, &ctx->oids.oid[i]); if (commit) commit->object.flags &= ~REACHABLE; @@ -1336,11 +1380,24 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } +static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx) +{ + trace2_data_intmax("commit-graph", ctx->r, "filter-computed", + ctx->count_bloom_filter_computed); + trace2_data_intmax("commit-graph", ctx->r, "filter-not-computed", + ctx->count_bloom_filter_not_computed); + trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-empty", + ctx->count_bloom_filter_trunc_empty); + trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large", + ctx->count_bloom_filter_trunc_large); +} + static void compute_bloom_filters(struct write_commit_graph_context *ctx) { int i; struct progress *progress = NULL; struct commit **sorted_commits; + int max_new_filters; init_bloom_filters(); @@ -1357,13 +1414,34 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx) else QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp); + max_new_filters = ctx->opts && ctx->opts->max_new_filters >= 0 ? + ctx->opts->max_new_filters : ctx->commits.nr; + for (i = 0; i < ctx->commits.nr; i++) { + enum bloom_filter_computed computed = 0; struct commit *c = sorted_commits[i]; - struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1); - ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len; + struct bloom_filter *filter = get_or_compute_bloom_filter( + ctx->r, + c, + ctx->count_bloom_filter_computed < max_new_filters, + ctx->bloom_settings, + &computed); + if (computed & BLOOM_COMPUTED) { + ctx->count_bloom_filter_computed++; + if (computed & BLOOM_TRUNC_EMPTY) + ctx->count_bloom_filter_trunc_empty++; + if (computed & BLOOM_TRUNC_LARGE) + ctx->count_bloom_filter_trunc_large++; + } else if (computed & BLOOM_NOT_COMPUTED) + ctx->count_bloom_filter_not_computed++; + ctx->total_bloom_filter_data_size += filter + ? sizeof(unsigned char) * filter->len : 0; display_progress(progress, i + 1); } + if (trace2_is_enabled()) + trace2_bloom_filter_write_statistics(ctx); + free(sorted_commits); stop_progress(&progress); } @@ -1392,7 +1470,7 @@ static int add_ref_to_set(const char *refname, int write_commit_graph_reachable(struct object_directory *odb, enum commit_graph_write_flags flags, - const struct split_commit_graph_opts *split_opts) + const struct commit_graph_opts *opts) { struct oidset commits = OIDSET_INIT; struct refs_cb_data data; @@ -1409,7 +1487,7 @@ int write_commit_graph_reachable(struct object_directory *odb, stop_progress(&data.progress); result = write_commit_graph(odb, NULL, &commits, - flags, split_opts); + flags, opts); oidset_clear(&commits); return result; @@ -1471,9 +1549,7 @@ static int fill_oids_from_commits(struct write_commit_graph_context *ctx, oidset_iter_init(commits, &iter); while ((oid = oidset_iter_next(&iter))) { - ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); - oidcpy(&ctx->oids.list[ctx->oids.nr], oid); - ctx->oids.nr++; + oid_array_append(&ctx->oids, oid); } return 0; @@ -1492,55 +1568,25 @@ static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } -static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx) -{ - uint32_t i, count_distinct = 1; - - if (ctx->report_progress) - ctx->progress = start_delayed_progress( - _("Counting distinct commits in commit graph"), - ctx->oids.nr); - display_progress(ctx->progress, 0); /* TODO: Measure QSORT() progress */ - QSORT(ctx->oids.list, ctx->oids.nr, oid_compare); - - for (i = 1; i < ctx->oids.nr; i++) { - display_progress(ctx->progress, i + 1); - if (!oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i])) { - if (ctx->split) { - struct commit *c = lookup_commit(ctx->r, &ctx->oids.list[i]); - - if (!c || commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH) - continue; - } - - count_distinct++; - } - } - stop_progress(&ctx->progress); - - return count_distinct; -} - static void copy_oids_to_commits(struct write_commit_graph_context *ctx) { uint32_t i; - enum commit_graph_split_flags flags = ctx->split_opts ? - ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED; + enum commit_graph_split_flags flags = ctx->opts ? + ctx->opts->split_flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED; ctx->num_extra_edges = 0; if (ctx->report_progress) ctx->progress = start_delayed_progress( _("Finding extra edges in commit graph"), ctx->oids.nr); - for (i = 0; i < ctx->oids.nr; i++) { + oid_array_sort(&ctx->oids); + for (i = 0; i < ctx->oids.nr; i = oid_array_next_unique(&ctx->oids, i)) { unsigned int num_parents; display_progress(ctx->progress, i + 1); - if (i > 0 && oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i])) - continue; ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc); - ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]); + ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.oid[i]); if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE && commit_graph_position(ctx->commits.list[ctx->commits.nr]) != COMMIT_NOT_FROM_GRAPH) @@ -1586,19 +1632,27 @@ static int write_graph_chunk_base(struct hashfile *f, return 0; } +typedef int (*chunk_write_fn)(struct hashfile *f, + struct write_commit_graph_context *ctx); + +struct chunk_info { + uint32_t id; + uint64_t size; + chunk_write_fn write_fn; +}; + static int write_commit_graph_file(struct write_commit_graph_context *ctx) { uint32_t i; int fd; struct hashfile *f; struct lock_file lk = LOCK_INIT; - uint32_t chunk_ids[MAX_NUM_CHUNKS + 1]; - uint64_t chunk_offsets[MAX_NUM_CHUNKS + 1]; + struct chunk_info chunks[MAX_NUM_CHUNKS + 1]; const unsigned hashsz = the_hash_algo->rawsz; struct strbuf progress_title = STRBUF_INIT; int num_chunks = 3; + uint64_t chunk_offset; struct object_id file_hash; - const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; if (ctx->split) { struct strbuf tmp_file = STRBUF_INIT; @@ -1619,7 +1673,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) } if (ctx->split) { - char *lock_name = get_chain_filename(ctx->odb); + char *lock_name = get_commit_graph_chain_filename(ctx->odb); hold_lock_file_for_update_mode(&lk, lock_name, LOCK_DIE_ON_ERROR, 0444); @@ -1644,51 +1698,41 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); } - chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT; - chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP; - chunk_ids[2] = GRAPH_CHUNKID_DATA; + chunks[0].id = GRAPH_CHUNKID_OIDFANOUT; + chunks[0].size = GRAPH_FANOUT_SIZE; + chunks[0].write_fn = write_graph_chunk_fanout; + chunks[1].id = GRAPH_CHUNKID_OIDLOOKUP; + chunks[1].size = hashsz * ctx->commits.nr; + chunks[1].write_fn = write_graph_chunk_oids; + chunks[2].id = GRAPH_CHUNKID_DATA; + chunks[2].size = (hashsz + 16) * ctx->commits.nr; + chunks[2].write_fn = write_graph_chunk_data; if (ctx->num_extra_edges) { - chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES; + chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES; + chunks[num_chunks].size = 4 * ctx->num_extra_edges; + chunks[num_chunks].write_fn = write_graph_chunk_extra_edges; num_chunks++; } if (ctx->changed_paths) { - chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMINDEXES; + chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMINDEXES; + chunks[num_chunks].size = sizeof(uint32_t) * ctx->commits.nr; + chunks[num_chunks].write_fn = write_graph_chunk_bloom_indexes; num_chunks++; - chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMDATA; + chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMDATA; + chunks[num_chunks].size = sizeof(uint32_t) * 3 + + ctx->total_bloom_filter_data_size; + chunks[num_chunks].write_fn = write_graph_chunk_bloom_data; num_chunks++; } if (ctx->num_commit_graphs_after > 1) { - chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE; - num_chunks++; - } - - chunk_ids[num_chunks] = 0; - - chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH; - chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE; - chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr; - chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr; - - num_chunks = 3; - if (ctx->num_extra_edges) { - chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + - 4 * ctx->num_extra_edges; + chunks[num_chunks].id = GRAPH_CHUNKID_BASE; + chunks[num_chunks].size = hashsz * (ctx->num_commit_graphs_after - 1); + chunks[num_chunks].write_fn = write_graph_chunk_base; num_chunks++; } - if (ctx->changed_paths) { - chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + - sizeof(uint32_t) * ctx->commits.nr; - num_chunks++; - chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + - sizeof(uint32_t) * 3 + ctx->total_bloom_filter_data_size; - num_chunks++; - } - if (ctx->num_commit_graphs_after > 1) { - chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + - hashsz * (ctx->num_commit_graphs_after - 1); - num_chunks++; - } + chunks[num_chunks].id = 0; + chunks[num_chunks].size = 0; hashwrite_be32(f, GRAPH_SIGNATURE); @@ -1697,13 +1741,16 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) hashwrite_u8(f, num_chunks); hashwrite_u8(f, ctx->num_commit_graphs_after - 1); + chunk_offset = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH; for (i = 0; i <= num_chunks; i++) { uint32_t chunk_write[3]; - chunk_write[0] = htonl(chunk_ids[i]); - chunk_write[1] = htonl(chunk_offsets[i] >> 32); - chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff); + chunk_write[0] = htonl(chunks[i].id); + chunk_write[1] = htonl(chunk_offset >> 32); + chunk_write[2] = htonl(chunk_offset & 0xffffffff); hashwrite(f, chunk_write, 12); + + chunk_offset += chunks[i].size; } if (ctx->report_progress) { @@ -1716,19 +1763,19 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) progress_title.buf, num_chunks * ctx->commits.nr); } - write_graph_chunk_fanout(f, ctx); - write_graph_chunk_oids(f, hashsz, ctx); - write_graph_chunk_data(f, hashsz, ctx); - if (ctx->num_extra_edges) - write_graph_chunk_extra_edges(f, ctx); - if (ctx->changed_paths) { - write_graph_chunk_bloom_indexes(f, ctx); - write_graph_chunk_bloom_data(f, ctx, &bloom_settings); - } - if (ctx->num_commit_graphs_after > 1 && - write_graph_chunk_base(f, ctx)) { - return -1; + + for (i = 0; i < num_chunks; i++) { + uint64_t start_offset = f->total + f->offset; + + if (chunks[i].write_fn(f, ctx)) + return -1; + + if (f->total + f->offset != start_offset + chunks[i].size) + BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead", + chunks[i].size, chunks[i].id, + f->total + f->offset - start_offset); } + stop_progress(&ctx->progress); strbuf_release(&progress_title); @@ -1809,13 +1856,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) int max_commits = 0; int size_mult = 2; - if (ctx->split_opts) { - max_commits = ctx->split_opts->max_commits; + if (ctx->opts) { + max_commits = ctx->opts->max_commits; - if (ctx->split_opts->size_multiple) - size_mult = ctx->split_opts->size_multiple; + if (ctx->opts->size_multiple) + size_mult = ctx->opts->size_multiple; - flags = ctx->split_opts->flags; + flags = ctx->opts->split_flags; } g = ctx->r->objects->commit_graph; @@ -1911,7 +1958,7 @@ static int commit_compare(const void *_a, const void *_b) static void sort_and_scan_merged_commits(struct write_commit_graph_context *ctx) { - uint32_t i; + uint32_t i, dedup_i = 0; if (ctx->report_progress) ctx->progress = start_delayed_progress( @@ -1926,17 +1973,27 @@ static void sort_and_scan_merged_commits(struct write_commit_graph_context *ctx) if (i && oideq(&ctx->commits.list[i - 1]->object.oid, &ctx->commits.list[i]->object.oid)) { - die(_("unexpected duplicate commit id %s"), - oid_to_hex(&ctx->commits.list[i]->object.oid)); + /* + * Silently ignore duplicates. These were likely + * created due to a commit appearing in multiple + * layers of the chain, which is unexpected but + * not invalid. We should make sure there is a + * unique copy in the new layer. + */ } else { unsigned int num_parents; + ctx->commits.list[dedup_i] = ctx->commits.list[i]; + dedup_i++; + num_parents = commit_list_count(ctx->commits.list[i]->parents); if (num_parents > 2) ctx->num_extra_edges += num_parents - 1; } } + ctx->commits.nr = dedup_i; + stop_progress(&ctx->progress); } @@ -1993,10 +2050,10 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx) size_t dirnamelen; timestamp_t expire_time = time(NULL); - if (ctx->split_opts && ctx->split_opts->expire_time) - expire_time = ctx->split_opts->expire_time; + if (ctx->opts && ctx->opts->expire_time) + expire_time = ctx->opts->expire_time; if (!ctx->split) { - char *chain_file_name = get_chain_filename(ctx->odb); + char *chain_file_name = get_commit_graph_chain_filename(ctx->odb); unlink(chain_file_name); free(chain_file_name); ctx->num_commit_graphs_after = 0; @@ -2045,13 +2102,19 @@ int write_commit_graph(struct object_directory *odb, struct string_list *pack_indexes, struct oidset *commits, enum commit_graph_write_flags flags, - const struct split_commit_graph_opts *split_opts) + const struct commit_graph_opts *opts) { struct write_commit_graph_context *ctx; - uint32_t i, count_distinct = 0; + uint32_t i; int res = 0; int replace = 0; + struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; + prepare_repo_settings(the_repository); + if (!the_repository->settings.core_commit_graph) { + warning(_("attempting to write a commit-graph, but 'core.commitGraph' is disabled")); + return 0; + } if (!commit_graph_compatible(the_repository)) return 0; @@ -2061,10 +2124,32 @@ int write_commit_graph(struct object_directory *odb, ctx->append = flags & COMMIT_GRAPH_WRITE_APPEND ? 1 : 0; ctx->report_progress = flags & COMMIT_GRAPH_WRITE_PROGRESS ? 1 : 0; ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0; - ctx->split_opts = split_opts; - ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0; + ctx->opts = opts; ctx->total_bloom_filter_data_size = 0; + 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); + bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS", + bloom_settings.max_changed_paths); + ctx->bloom_settings = &bloom_settings; + + 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); @@ -2087,31 +2172,21 @@ int write_commit_graph(struct object_directory *odb, } } - if (ctx->split_opts) - replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE; + if (ctx->opts) + replace = ctx->opts->split_flags & COMMIT_GRAPH_SPLIT_REPLACE; } ctx->approx_nr_objects = approximate_object_count(); - ctx->oids.alloc = ctx->approx_nr_objects / 32; - - if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits) - ctx->oids.alloc = split_opts->max_commits; - if (ctx->append) { + if (ctx->append) prepare_commit_graph_one(ctx->r, ctx->odb); - if (ctx->r->objects->commit_graph) - ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits; - } - - if (ctx->oids.alloc < 1024) - ctx->oids.alloc = 1024; - ALLOC_ARRAY(ctx->oids.list, ctx->oids.alloc); if (ctx->append && ctx->r->objects->commit_graph) { struct commit_graph *g = ctx->r->objects->commit_graph; for (i = 0; i < g->num_commits; i++) { - const unsigned char *hash = g->chunk_oid_lookup + g->hash_len * i; - hashcpy(ctx->oids.list[ctx->oids.nr++].hash, hash); + struct object_id oid; + hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * i); + oid_array_append(&ctx->oids, &oid); } } @@ -2133,17 +2208,6 @@ int write_commit_graph(struct object_directory *odb, close_reachable(ctx); - count_distinct = count_distinct_commits(ctx); - - if (count_distinct >= GRAPH_EDGE_LAST_MASK) { - error(_("the commit graph format cannot write %d commits"), count_distinct); - res = -1; - goto cleanup; - } - - ctx->commits.alloc = count_distinct; - ALLOC_ARRAY(ctx->commits.list, ctx->commits.alloc); - copy_oids_to_commits(ctx); if (ctx->commits.nr >= GRAPH_EDGE_LAST_MASK) { @@ -2178,7 +2242,7 @@ int write_commit_graph(struct object_directory *odb, cleanup: free(ctx->graph_name); free(ctx->commits.list); - free(ctx->oids.list); + oid_array_clear(&ctx->oids); if (ctx->commit_graph_filenames_after) { for (i = 0; i < ctx->num_commit_graphs_after; i++) { |