diff options
Diffstat (limited to 'commit-graph.c')
| -rw-r--r-- | commit-graph.c | 922 |
1 files changed, 532 insertions, 390 deletions
diff --git a/commit-graph.c b/commit-graph.c index e51c91dd5b..e21eeea42b 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -7,7 +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 +19,7 @@ #include "shallow.h" #include "json-writer.h" #include "trace2.h" +#include "chunk-format.h" void git_test_write_commit_graph_or_die(void) { @@ -38,11 +39,12 @@ void git_test_write_commit_graph_or_die(void) #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */ #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */ #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */ +#define GRAPH_CHUNKID_GENERATION_DATA 0x47444154 /* "GDAT" */ +#define GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW 0x47444f56 /* "GDOV" */ #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */ #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */ #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */ #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */ -#define MAX_NUM_CHUNKS 7 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16) @@ -57,13 +59,16 @@ void git_test_write_commit_graph_or_die(void) #define GRAPH_HEADER_SIZE 8 #define GRAPH_FANOUT_SIZE (4 * 256) -#define GRAPH_CHUNKLOOKUP_WIDTH 12 -#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \ +#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * CHUNK_TOC_ENTRY_SIZE \ + GRAPH_FANOUT_SIZE + the_hash_algo->rawsz) +#define CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW (1ULL << 31) + /* Remember to update object flag allocation in object.h */ #define REACHABLE (1u<<15) +define_commit_slab(topo_level_slab, uint32_t); + /* Keep track of the order in which commits are added to our list. */ define_commit_slab(commit_pos, int); static struct commit_pos commit_pos = COMMIT_SLAB_INIT(1, commit_pos); @@ -99,7 +104,7 @@ uint32_t commit_graph_position(const struct commit *c) return data ? data->graph_pos : COMMIT_NOT_FROM_GRAPH; } -uint32_t commit_graph_generation(const struct commit *c) +timestamp_t commit_graph_generation(const struct commit *c) { struct commit_graph_data *data = commit_graph_data_slab_peek(&commit_graph_data_slab, c); @@ -139,13 +144,17 @@ static struct commit_graph_data *commit_graph_data_at(const struct commit *c) return data; } +/* + * Should be used only while writing commit-graph as it compares + * generation value of commits by directly accessing commit-slab. + */ static int commit_gen_cmp(const void *va, const void *vb) { const struct commit *a = *(const struct commit **)va; const struct commit *b = *(const struct commit **)vb; - uint32_t generation_a = commit_graph_generation(a); - uint32_t generation_b = commit_graph_generation(b); + const timestamp_t generation_a = commit_graph_data_at(a)->generation; + const timestamp_t generation_b = commit_graph_data_at(b)->generation; /* lower generation commits first */ if (generation_a < generation_b) return -1; @@ -172,14 +181,21 @@ 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 +240,8 @@ 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 +257,7 @@ 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; @@ -280,14 +297,43 @@ 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) +static int graph_read_oid_lookup(const unsigned char *chunk_start, + size_t chunk_size, void *data) { - const unsigned char *data, *chunk_lookup; - uint32_t i; + struct commit_graph *g = data; + g->chunk_oid_lookup = chunk_start; + g->num_commits = chunk_size / g->hash_len; + return 0; +} + +static int graph_read_bloom_data(const unsigned char *chunk_start, + size_t chunk_size, void *data) +{ + struct commit_graph *g = data; + uint32_t hash_version; + g->chunk_bloom_data = chunk_start; + hash_version = get_be32(chunk_start); + + if (hash_version != 1) + return 0; + + g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings)); + g->bloom_filter_settings->hash_version = hash_version; + g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4); + g->bloom_filter_settings->bits_per_entry = get_be32(chunk_start + 8); + g->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES; + + return 0; +} + +struct commit_graph *parse_commit_graph(struct repository *r, + void *graph_map, size_t graph_size) +{ + const unsigned char *data; struct commit_graph *graph; - uint64_t next_chunk_offset; uint32_t graph_signature; unsigned char graph_version, hash_version; + struct chunkfile *cf = NULL; if (!graph_map) return NULL; @@ -318,6 +364,8 @@ 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; @@ -326,7 +374,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) graph->data_len = graph_size; if (graph_size < GRAPH_HEADER_SIZE + - (graph->num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH + + (graph->num_chunks + 1) * CHUNK_TOC_ENTRY_SIZE + GRAPH_FANOUT_SIZE + the_hash_algo->rawsz) { error(_("commit-graph file is too small to hold %u chunks"), graph->num_chunks); @@ -334,93 +382,28 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) 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 = next_chunk_offset; - int chunk_repeated = 0; - - chunk_id = get_be32(chunk_lookup + 0); - - chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH; - next_chunk_offset = get_be64(chunk_lookup + 4); + cf = init_chunkfile(NULL); - if (chunk_offset > graph_size - the_hash_algo->rawsz) { - error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32), - (uint32_t)chunk_offset); - goto free_and_return; - } - - switch (chunk_id) { - case GRAPH_CHUNKID_OIDFANOUT: - if (graph->chunk_oid_fanout) - chunk_repeated = 1; - else - graph->chunk_oid_fanout = (uint32_t*)(data + chunk_offset); - break; - - case GRAPH_CHUNKID_OIDLOOKUP: - if (graph->chunk_oid_lookup) - chunk_repeated = 1; - else { - graph->chunk_oid_lookup = data + chunk_offset; - graph->num_commits = (next_chunk_offset - chunk_offset) - / graph->hash_len; - } - break; - - case GRAPH_CHUNKID_DATA: - if (graph->chunk_commit_data) - chunk_repeated = 1; - else - graph->chunk_commit_data = data + chunk_offset; - break; - - case GRAPH_CHUNKID_EXTRAEDGES: - if (graph->chunk_extra_edges) - chunk_repeated = 1; - else - graph->chunk_extra_edges = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BASE: - if (graph->chunk_base_graphs) - chunk_repeated = 1; - else - graph->chunk_base_graphs = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BLOOMINDEXES: - if (graph->chunk_bloom_indexes) - chunk_repeated = 1; - else - graph->chunk_bloom_indexes = data + chunk_offset; - break; - - case GRAPH_CHUNKID_BLOOMDATA: - if (graph->chunk_bloom_data) - chunk_repeated = 1; - else { - uint32_t hash_version; - graph->chunk_bloom_data = data + chunk_offset; - hash_version = get_be32(data + chunk_offset); - - if (hash_version != 1) - break; + if (read_table_of_contents(cf, graph->data, graph_size, + GRAPH_HEADER_SIZE, graph->num_chunks)) + goto free_and_return; - graph->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings)); - 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); - } - break; - } + pair_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, + (const unsigned char **)&graph->chunk_oid_fanout); + read_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph); + pair_chunk(cf, GRAPH_CHUNKID_DATA, &graph->chunk_commit_data); + pair_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, &graph->chunk_extra_edges); + pair_chunk(cf, GRAPH_CHUNKID_BASE, &graph->chunk_base_graphs); + pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA, + &graph->chunk_generation_data); + pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW, + &graph->chunk_generation_data_overflow); - if (chunk_repeated) { - error(_("commit-graph chunk id %08x appears multiple times"), chunk_id); - goto free_and_return; - } + if (r->settings.commit_graph_read_changed_paths) { + pair_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES, + &graph->chunk_bloom_indexes); + read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA, + graph_read_bloom_data, graph); } if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) { @@ -437,15 +420,18 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) if (verify_commit_graph_lite(graph)) goto free_and_return; + free_chunkfile(cf); return graph; free_and_return: + free_chunkfile(cf); free(graph->bloom_filter_settings); free(graph); 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) { @@ -457,7 +443,7 @@ 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); @@ -469,7 +455,7 @@ 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; @@ -516,7 +502,7 @@ 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; @@ -530,7 +516,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, return NULL; count = st.st_size / (the_hash_algo->hexsz + 1); - oids = xcalloc(count, sizeof(struct object_id)); + CALLOC_ARRAY(oids, count); prepare_alt_odb(r); @@ -550,7 +536,7 @@ 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); @@ -577,6 +563,31 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, return graph_chain; } +/* + * returns 1 if and only if all graphs in the chain have + * corrected commit dates stored in the generation_data chunk. + */ +static int validate_mixed_generation_chain(struct commit_graph *g) +{ + int read_generation_data = 1; + struct commit_graph *p = g; + + while (read_generation_data && p) { + read_generation_data = p->read_generation_data; + p = p->base_graph; + } + + if (read_generation_data) + return 1; + + while (g) { + g->read_generation_data = 0; + g = g->base_graph; + } + + return 0; +} + struct commit_graph *read_commit_graph_one(struct repository *r, struct object_directory *odb) { @@ -585,6 +596,8 @@ struct commit_graph *read_commit_graph_one(struct repository *r, if (!g) g = load_commit_graph_chain(r, odb); + validate_mixed_generation_chain(g); + return g; } @@ -660,6 +673,31 @@ int generation_numbers_enabled(struct repository *r) return !!first_generation; } +int corrected_commit_dates_enabled(struct repository *r) +{ + struct commit_graph *g; + if (!prepare_commit_graph(r)) + return 0; + + g = r->objects->commit_graph; + + if (!g->num_commits) + return 0; + + return g->read_generation_data; +} + +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) @@ -724,17 +762,41 @@ static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, { const unsigned char *commit_data; struct commit_graph_data *graph_data; - uint32_t lex_index; + uint32_t lex_index, offset_pos; + uint64_t date_high, date_low, offset; while (pos < g->num_commits_in_base) g = g->base_graph; + if (pos >= g->num_commits + g->num_commits_in_base) + die(_("invalid commit position. commit-graph is likely corrupt")); + lex_index = pos - g->num_commits_in_base; commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * lex_index; graph_data = commit_graph_data_at(item); graph_data->graph_pos = pos; - graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2; + + date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; + date_low = get_be32(commit_data + g->hash_len + 12); + item->date = (timestamp_t)((date_high << 32) | date_low); + + if (g->read_generation_data) { + offset = (timestamp_t)get_be32(g->chunk_generation_data + sizeof(uint32_t) * lex_index); + + if (offset & CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW) { + if (!g->chunk_generation_data_overflow) + die(_("commit-graph requires overflow generation data but has none")); + + offset_pos = offset ^ CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW; + graph_data->generation = get_be64(g->chunk_generation_data_overflow + 8 * offset_pos); + } else + graph_data->generation = item->date + offset; + } else + graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2; + + if (g->topo_levels) + *topo_level_slab_at(g->topo_levels, item) = get_be32(commit_data + g->hash_len + 8) >> 2; } static inline void set_commit_tree(struct commit *c, struct tree *t) @@ -748,38 +810,22 @@ static int fill_commit_in_graph(struct repository *r, { uint32_t edge_value; uint32_t *parent_data_ptr; - uint64_t date_low, date_high; struct commit_list **pptr; - struct commit_graph_data *graph_data; const unsigned char *commit_data; uint32_t lex_index; while (pos < g->num_commits_in_base) g = g->base_graph; - if (pos >= g->num_commits + g->num_commits_in_base) - die(_("invalid commit position. commit-graph is likely corrupt")); + fill_commit_graph_info(item, g, pos); - /* - * Store the "full" position, but then use the - * "local" position for the rest of the calculation. - */ - graph_data = commit_graph_data_at(item); - graph_data->graph_pos = pos; lex_index = pos - g->num_commits_in_base; - commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index; item->object.parsed = 1; set_commit_tree(item, NULL); - date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; - date_low = get_be32(commit_data + g->hash_len + 12); - item->date = (timestamp_t)((date_high << 32) | date_low); - - graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2; - pptr = &item->parents; edge_value = get_be32(commit_data + g->hash_len); @@ -908,23 +954,18 @@ 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; + int num_generation_data_overflows; unsigned long approx_nr_objects; struct progress *progress; int progress_done; @@ -943,16 +984,25 @@ struct write_commit_graph_context { report_progress:1, split:1, changed_paths:1, - order_by_pack:1; + order_by_pack:1, + write_generation_data:1, + trust_generation_numbers:1; - const struct split_commit_graph_opts *split_opts; + struct topo_level_slab *topo_levels; + 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 int write_graph_chunk_fanout(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; int i, count = 0; struct commit **list = ctx->commits.list; @@ -977,8 +1027,9 @@ static int write_graph_chunk_fanout(struct hashfile *f, } static int write_graph_chunk_oids(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; struct commit **list = ctx->commits.list; int count; for (count = 0; count < ctx->commits.nr; count++, list++) { @@ -989,15 +1040,16 @@ static int write_graph_chunk_oids(struct hashfile *f, return 0; } -static const unsigned char *commit_to_sha1(size_t index, void *table) +static const struct object_id *commit_to_oid(size_t index, const void *table) { - struct commit **commits = table; - return commits[index]->object.oid.hash; + const struct commit * const *commits = table; + return &commits[index]->object.oid; } static int write_graph_chunk_data(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; uint32_t num_extra_edges = 0; @@ -1009,7 +1061,7 @@ static int write_graph_chunk_data(struct hashfile *f, uint32_t packedDate[2]; display_progress(ctx->progress, ++ctx->progress_cnt); - if (parse_commit_no_graph(*list)) + if (repo_parse_commit_no_graph(ctx->r, *list)) die(_("unable to parse commit %s"), oid_to_hex(&(*list)->object.oid)); tree = get_commit_tree_oid(*list); @@ -1020,10 +1072,10 @@ static int write_graph_chunk_data(struct hashfile *f, if (!parent) edge_value = GRAPH_PARENT_NONE; else { - edge_value = sha1_pos(parent->item->object.oid.hash, - ctx->commits.list, - ctx->commits.nr, - commit_to_sha1); + edge_value = oid_pos(&parent->item->object.oid, + ctx->commits.list, + ctx->commits.nr, + commit_to_oid); if (edge_value >= 0) edge_value += ctx->new_num_commits_in_base; @@ -1051,10 +1103,10 @@ static int write_graph_chunk_data(struct hashfile *f, else if (parent->next) edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges; else { - edge_value = sha1_pos(parent->item->object.oid.hash, - ctx->commits.list, - ctx->commits.nr, - commit_to_sha1); + edge_value = oid_pos(&parent->item->object.oid, + ctx->commits.list, + ctx->commits.nr, + commit_to_oid); if (edge_value >= 0) edge_value += ctx->new_num_commits_in_base; @@ -1086,7 +1138,7 @@ static int write_graph_chunk_data(struct hashfile *f, else packedDate[0] = 0; - packedDate[0] |= htonl(commit_graph_data_at(*list)->generation << 2); + packedDate[0] |= htonl(*topo_level_slab_at(ctx->topo_levels, *list) << 2); packedDate[1] = htonl((*list)->date); hashwrite(f, packedDate, 8); @@ -1097,9 +1149,53 @@ static int write_graph_chunk_data(struct hashfile *f, return 0; } +static int write_graph_chunk_generation_data(struct hashfile *f, + void *data) +{ + struct write_commit_graph_context *ctx = data; + int i, num_generation_data_overflows = 0; + + for (i = 0; i < ctx->commits.nr; i++) { + struct commit *c = ctx->commits.list[i]; + timestamp_t offset; + repo_parse_commit(ctx->r, c); + offset = commit_graph_data_at(c)->generation - c->date; + display_progress(ctx->progress, ++ctx->progress_cnt); + + if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) { + offset = CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW | num_generation_data_overflows; + num_generation_data_overflows++; + } + + hashwrite_be32(f, offset); + } + + return 0; +} + +static int write_graph_chunk_generation_data_overflow(struct hashfile *f, + void *data) +{ + struct write_commit_graph_context *ctx = data; + int i; + for (i = 0; i < ctx->commits.nr; i++) { + struct commit *c = ctx->commits.list[i]; + timestamp_t offset = commit_graph_data_at(c)->generation - c->date; + display_progress(ctx->progress, ++ctx->progress_cnt); + + if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) { + hashwrite_be32(f, offset >> 32); + hashwrite_be32(f, (uint32_t) offset); + } + } + + return 0; +} + static int write_graph_chunk_extra_edges(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; struct commit_list *parent; @@ -1120,10 +1216,10 @@ static int 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, - ctx->commits.list, - ctx->commits.nr, - commit_to_sha1); + int edge_value = oid_pos(&parent->item->object.oid, + ctx->commits.list, + ctx->commits.nr, + commit_to_oid); if (edge_value >= 0) edge_value += ctx->new_num_commits_in_base; @@ -1152,14 +1248,15 @@ static int write_graph_chunk_extra_edges(struct hashfile *f, } static int write_graph_chunk_bloom_indexes(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; 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); + 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); @@ -1178,6 +1275,7 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx) 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); @@ -1186,8 +1284,9 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx) } static int write_graph_chunk_bloom_data(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; struct commit **list = ctx->commits.list; struct commit **last = ctx->commits.list + ctx->commits.nr; @@ -1198,7 +1297,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f, 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); @@ -1210,13 +1309,6 @@ static int write_graph_chunk_bloom_data(struct hashfile *f, return 0; } -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); -} - static int add_packed_commits(const struct object_id *oid, struct packed_git *pack, uint32_t pos, @@ -1237,10 +1329,7 @@ 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; @@ -1251,9 +1340,7 @@ 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; } } @@ -1263,8 +1350,8 @@ 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( @@ -1272,7 +1359,7 @@ 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; } @@ -1289,16 +1376,16 @@ 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; if (ctx->split) { - if ((!parse_commit(commit) && + if ((!repo_parse_commit(ctx->r, commit) && commit_graph_position(commit) == COMMIT_NOT_FROM_GRAPH) || flags == COMMIT_GRAPH_SPLIT_REPLACE) add_missing_parents(ctx, commit); - } else if (!parse_commit_no_graph(commit)) + } else if (!repo_parse_commit_no_graph(ctx->r, commit)) add_missing_parents(ctx, commit); } stop_progress(&ctx->progress); @@ -1309,7 +1396,7 @@ 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; @@ -1317,6 +1404,59 @@ static void close_reachable(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } +static void compute_topological_levels(struct write_commit_graph_context *ctx) +{ + int i; + struct commit_list *list = NULL; + + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Computing commit graph topological levels"), + ctx->commits.nr); + for (i = 0; i < ctx->commits.nr; i++) { + struct commit *c = ctx->commits.list[i]; + uint32_t level; + + repo_parse_commit(ctx->r, c); + level = *topo_level_slab_at(ctx->topo_levels, c); + + display_progress(ctx->progress, i + 1); + if (level != GENERATION_NUMBER_ZERO) + continue; + + commit_list_insert(c, &list); + while (list) { + struct commit *current = list->item; + struct commit_list *parent; + int all_parents_computed = 1; + uint32_t max_level = 0; + + for (parent = current->parents; parent; parent = parent->next) { + repo_parse_commit(ctx->r, parent->item); + level = *topo_level_slab_at(ctx->topo_levels, parent->item); + + if (level == GENERATION_NUMBER_ZERO) { + all_parents_computed = 0; + commit_list_insert(parent->item, &list); + break; + } + + if (level > max_level) + max_level = level; + } + + if (all_parents_computed) { + pop_commit(&list); + + if (max_level > GENERATION_NUMBER_V1_MAX - 1) + max_level = GENERATION_NUMBER_V1_MAX - 1; + *topo_level_slab_at(ctx->topo_levels, current) = max_level + 1; + } + } + } + stop_progress(&ctx->progress); +} + static void compute_generation_numbers(struct write_commit_graph_context *ctx) { int i; @@ -1326,53 +1466,80 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx) ctx->progress = start_delayed_progress( _("Computing commit graph generation numbers"), ctx->commits.nr); + + if (!ctx->trust_generation_numbers) { + for (i = 0; i < ctx->commits.nr; i++) { + struct commit *c = ctx->commits.list[i]; + repo_parse_commit(ctx->r, c); + commit_graph_data_at(c)->generation = GENERATION_NUMBER_ZERO; + } + } + for (i = 0; i < ctx->commits.nr; i++) { - uint32_t generation = commit_graph_data_at(ctx->commits.list[i])->generation; + struct commit *c = ctx->commits.list[i]; + timestamp_t corrected_commit_date; + + repo_parse_commit(ctx->r, c); + corrected_commit_date = commit_graph_data_at(c)->generation; display_progress(ctx->progress, i + 1); - if (generation != GENERATION_NUMBER_INFINITY && - generation != GENERATION_NUMBER_ZERO) + if (corrected_commit_date != GENERATION_NUMBER_ZERO) continue; - commit_list_insert(ctx->commits.list[i], &list); + commit_list_insert(c, &list); while (list) { struct commit *current = list->item; struct commit_list *parent; int all_parents_computed = 1; - uint32_t max_generation = 0; + timestamp_t max_corrected_commit_date = 0; for (parent = current->parents; parent; parent = parent->next) { - generation = commit_graph_data_at(parent->item)->generation; + repo_parse_commit(ctx->r, parent->item); + corrected_commit_date = commit_graph_data_at(parent->item)->generation; - if (generation == GENERATION_NUMBER_INFINITY || - generation == GENERATION_NUMBER_ZERO) { + if (corrected_commit_date == GENERATION_NUMBER_ZERO) { all_parents_computed = 0; commit_list_insert(parent->item, &list); break; - } else if (generation > max_generation) { - max_generation = generation; } + + if (corrected_commit_date > max_corrected_commit_date) + max_corrected_commit_date = corrected_commit_date; } if (all_parents_computed) { - struct commit_graph_data *data = commit_graph_data_at(current); - - data->generation = max_generation + 1; pop_commit(&list); - if (data->generation > GENERATION_NUMBER_MAX) - data->generation = GENERATION_NUMBER_MAX; + if (current->date && current->date > max_corrected_commit_date) + max_corrected_commit_date = current->date - 1; + commit_graph_data_at(current)->generation = max_corrected_commit_date + 1; + + if (commit_graph_data_at(current)->generation - current->date > GENERATION_NUMBER_V2_OFFSET_MAX) + ctx->num_generation_data_overflows++; } } } 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(); @@ -1389,13 +1556,34 @@ 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); } @@ -1412,7 +1600,7 @@ static int add_ref_to_set(const char *refname, struct object_id peeled; struct refs_cb_data *data = (struct refs_cb_data *)cb_data; - if (!peel_ref(refname, &peeled)) + if (!peel_iterated_oid(oid, &peeled)) oid = &peeled; if (oid_object_info(the_repository, oid, NULL) == OBJ_COMMIT) oidset_insert(data->commits, oid); @@ -1424,7 +1612,7 @@ 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; @@ -1441,7 +1629,7 @@ 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; @@ -1503,9 +1691,7 @@ 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; @@ -1524,64 +1710,34 @@ 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) continue; if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE) - parse_commit(ctx->commits.list[ctx->commits.nr]); + repo_parse_commit(ctx->r, ctx->commits.list[ctx->commits.nr]); else - parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]); + repo_parse_commit_no_graph(ctx->r, ctx->commits.list[ctx->commits.nr]); num_parents = commit_list_count(ctx->commits.list[ctx->commits.nr]->parents); if (num_parents > 2) @@ -1606,8 +1762,9 @@ static int write_graph_chunk_base_1(struct hashfile *f, } static int write_graph_chunk_base(struct hashfile *f, - struct write_commit_graph_context *ctx) + void *data) { + struct write_commit_graph_context *ctx = data; int num = write_graph_chunk_base_1(f, ctx->new_base_graph); if (num != ctx->num_commit_graphs_after - 1) { @@ -1618,36 +1775,16 @@ 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; - 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; - struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_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; - } + struct chunkfile *cf; if (ctx->split) { struct strbuf tmp_file = STRBUF_INIT; @@ -1668,7 +1805,7 @@ 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); @@ -1689,87 +1826,66 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) } else { hold_lock_file_for_update_mode(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR, 0444); - fd = lk.tempfile->fd; - f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); - } - - 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) { - 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++; - } + fd = get_lock_file_fd(&lk); + f = hashfd(fd, get_lock_file_path(&lk)); + } + + cf = init_chunkfile(f); + + add_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, GRAPH_FANOUT_SIZE, + write_graph_chunk_fanout); + add_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, hashsz * ctx->commits.nr, + write_graph_chunk_oids); + add_chunk(cf, GRAPH_CHUNKID_DATA, (hashsz + 16) * ctx->commits.nr, + write_graph_chunk_data); + + if (git_env_bool(GIT_TEST_COMMIT_GRAPH_NO_GDAT, 0)) + ctx->write_generation_data = 0; + if (ctx->write_generation_data) + add_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA, + sizeof(uint32_t) * ctx->commits.nr, + write_graph_chunk_generation_data); + if (ctx->num_generation_data_overflows) + add_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW, + sizeof(timestamp_t) * ctx->num_generation_data_overflows, + write_graph_chunk_generation_data_overflow); + if (ctx->num_extra_edges) + add_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, + 4 * ctx->num_extra_edges, + write_graph_chunk_extra_edges); if (ctx->changed_paths) { - 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++; - 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) { - 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++; - } - - chunks[num_chunks].id = 0; - chunks[num_chunks].size = 0; + add_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES, + sizeof(uint32_t) * ctx->commits.nr, + write_graph_chunk_bloom_indexes); + add_chunk(cf, GRAPH_CHUNKID_BLOOMDATA, + sizeof(uint32_t) * 3 + + ctx->total_bloom_filter_data_size, + write_graph_chunk_bloom_data); + } + if (ctx->num_commit_graphs_after > 1) + add_chunk(cf, GRAPH_CHUNKID_BASE, + hashsz * (ctx->num_commit_graphs_after - 1), + write_graph_chunk_base); hashwrite_be32(f, GRAPH_SIGNATURE); hashwrite_u8(f, GRAPH_VERSION); hashwrite_u8(f, oid_version()); - hashwrite_u8(f, num_chunks); + hashwrite_u8(f, get_num_chunks(cf)); 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(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) { strbuf_addf(&progress_title, Q_("Writing out commit graph in %d pass", "Writing out commit graph in %d passes", - num_chunks), - num_chunks); + get_num_chunks(cf)), + get_num_chunks(cf)); ctx->progress = start_delayed_progress( progress_title.buf, - num_chunks * ctx->commits.nr); + get_num_chunks(cf) * ctx->commits.nr); } - 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); - } + write_chunkfile(cf, ctx); stop_progress(&ctx->progress); strbuf_release(&progress_title); @@ -1786,6 +1902,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) close_commit_graph(ctx->r->objects); finalize_hashfile(f, file_hash.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC); + free_chunkfile(cf); if (ctx->split) { FILE *chainf = fdopen_lock_file(&lk, "w"); @@ -1828,7 +1945,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) result = rename(ctx->graph_name, final_graph_name); for (i = 0; i < ctx->num_commit_graphs_after; i++) - fprintf(lk.tempfile->fp, "%s\n", ctx->commit_graph_hash_after[i]); + fprintf(get_lock_file_fp(&lk), "%s\n", ctx->commit_graph_hash_after[i]); if (result) { error(_("failed to rename temporary commit-graph file")); @@ -1851,13 +1968,13 @@ 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; @@ -1913,6 +2030,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) if (i < ctx->num_commit_graphs_after) ctx->commit_graph_hash_after[i] = xstrdup(oid_to_hex(&g->oid)); + /* + * If the topmost remaining layer has generation data chunk, the + * resultant layer also has generation data chunk. + */ + if (i == ctx->num_commit_graphs_after - 2) + ctx->write_generation_data = !!g->chunk_generation_data; + i--; g = g->base_graph; } @@ -1953,7 +2077,7 @@ 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( @@ -1968,17 +2092,27 @@ 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); } @@ -2035,10 +2169,10 @@ 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; @@ -2087,30 +2221,59 @@ 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; + struct topo_level_slab topo_levels; + 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; - ctx = xcalloc(1, sizeof(struct write_commit_graph_context)); + CALLOC_ARRAY(ctx, 1); ctx->r = the_repository; ctx->odb = 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->opts = opts; ctx->total_bloom_filter_data_size = 0; + ctx->write_generation_data = 1; + ctx->num_generation_data_overflows = 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; + + init_topo_level_slab(&topo_levels); + ctx->topo_levels = &topo_levels; + + prepare_commit_graph(ctx->r); + if (ctx->r->objects->commit_graph) { + struct commit_graph *g = ctx->r->objects->commit_graph; + + while (g) { + g->topo_levels = &topo_levels; + g = g->base_graph; + } + } 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; @@ -2122,10 +2285,7 @@ int write_commit_graph(struct object_directory *odb, } if (ctx->split) { - struct commit_graph *g; - prepare_commit_graph(ctx->r); - - g = ctx->r->objects->commit_graph; + struct commit_graph *g = ctx->r->objects->commit_graph; while (g) { ctx->num_commit_graphs_before++; @@ -2143,31 +2303,18 @@ 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) { - 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); } } @@ -2189,17 +2336,6 @@ 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) { @@ -2219,7 +2355,11 @@ int write_commit_graph(struct object_directory *odb, } else ctx->num_commit_graphs_after = 1; - compute_generation_numbers(ctx); + ctx->trust_generation_numbers = validate_mixed_generation_chain(ctx->r->objects->commit_graph); + + compute_topological_levels(ctx); + if (ctx->write_generation_data) + compute_generation_numbers(ctx); if (ctx->changed_paths) compute_bloom_filters(ctx); @@ -2234,7 +2374,8 @@ 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); + clear_topo_level_slab(&topo_levels); if (ctx->commit_graph_filenames_after) { for (i = 0; i < ctx->num_commit_graphs_after; i++) { @@ -2347,8 +2488,8 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags) for (i = 0; i < g->num_commits; i++) { struct commit *graph_commit, *odb_commit; struct commit_list *graph_parents, *odb_parents; - uint32_t max_generation = 0; - uint32_t generation; + timestamp_t max_generation = 0; + timestamp_t generation; display_progress(progress, i + 1); hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i); @@ -2412,16 +2553,17 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags) continue; /* - * If one of our parents has generation GENERATION_NUMBER_MAX, then - * our generation is also GENERATION_NUMBER_MAX. Decrement to avoid - * extra logic in the following condition. + * If we are using topological level and one of our parents has + * generation GENERATION_NUMBER_V1_MAX, then our generation is + * also GENERATION_NUMBER_V1_MAX. Decrement to avoid extra logic + * in the following condition. */ - if (max_generation == GENERATION_NUMBER_MAX) + if (!g->read_generation_data && max_generation == GENERATION_NUMBER_V1_MAX) max_generation--; generation = commit_graph_generation(graph_commit); - if (generation != max_generation + 1) - graph_report(_("commit-graph generation for commit %s is %u != %u"), + if (generation < max_generation + 1) + graph_report(_("commit-graph generation for commit %s is %"PRItime" < %"PRItime), oid_to_hex(&cur_oid), generation, max_generation + 1); |