diff options
Diffstat (limited to 'commit-graph.c')
| -rw-r--r-- | commit-graph.c | 2000 |
1 files changed, 1621 insertions, 379 deletions
diff --git a/commit-graph.c b/commit-graph.c index 1752341098..3860a0d847 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" @@ -9,19 +7,44 @@ #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" #include "hashmap.h" #include "replace-object.h" #include "progress.h" +#include "bloom.h" +#include "commit-slab.h" +#include "shallow.h" +#include "json-writer.h" +#include "trace2.h" +#include "chunk-format.h" + +void git_test_write_commit_graph_or_die(void) +{ + int flags = 0; + if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0)) + return; + + if (git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0)) + flags = COMMIT_GRAPH_WRITE_BLOOM_FILTERS; + + if (write_commit_graph_reachable(the_repository->objects->odb, + flags, NULL)) + die("failed to write commit-graph under GIT_TEST_COMMIT_GRAPH"); +} #define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */ #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 GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16) @@ -36,24 +59,155 @@ #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) -char *get_commit_graph_filename(const char *obj_dir) +#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); + +static void set_commit_pos(struct repository *r, const struct object_id *oid) +{ + static int32_t max_pos; + struct commit *commit = lookup_commit(r, oid); + + if (!commit) + return; /* should never happen, but be lenient */ + + *commit_pos_at(&commit_pos, commit) = max_pos++; +} + +static int commit_pos_cmp(const void *va, const void *vb) +{ + const struct commit *a = *(const struct commit **)va; + const struct commit *b = *(const struct commit **)vb; + return commit_pos_at(&commit_pos, a) - + commit_pos_at(&commit_pos, b); +} + +define_commit_slab(commit_graph_data_slab, struct commit_graph_data); +static struct commit_graph_data_slab commit_graph_data_slab = + COMMIT_SLAB_INIT(1, commit_graph_data_slab); + +static int get_configured_generation_version(struct repository *r) +{ + int version = 2; + repo_config_get_int(r, "commitgraph.generationversion", &version); + return version; +} + +uint32_t commit_graph_position(const struct commit *c) { - return xstrfmt("%s/info/commit-graph", obj_dir); + struct commit_graph_data *data = + commit_graph_data_slab_peek(&commit_graph_data_slab, c); + + return data ? data->graph_pos : COMMIT_NOT_FROM_GRAPH; +} + +timestamp_t commit_graph_generation(const struct commit *c) +{ + struct commit_graph_data *data = + commit_graph_data_slab_peek(&commit_graph_data_slab, c); + + if (!data) + return GENERATION_NUMBER_INFINITY; + else if (data->graph_pos == COMMIT_NOT_FROM_GRAPH) + return GENERATION_NUMBER_INFINITY; + + return data->generation; +} + +static struct commit_graph_data *commit_graph_data_at(const struct commit *c) +{ + unsigned int i, nth_slab; + struct commit_graph_data *data = + commit_graph_data_slab_peek(&commit_graph_data_slab, c); + + if (data) + return data; + + nth_slab = c->index / commit_graph_data_slab.slab_size; + data = commit_graph_data_slab_at(&commit_graph_data_slab, c); + + /* + * commit-slab initializes elements with zero, overwrite this with + * COMMIT_NOT_FROM_GRAPH for graph_pos. + * + * We avoid initializing generation with checking if graph position + * is not COMMIT_NOT_FROM_GRAPH. + */ + for (i = 0; i < commit_graph_data_slab.slab_size; i++) { + commit_graph_data_slab.slab[nth_slab][i].graph_pos = + COMMIT_NOT_FROM_GRAPH; + } + + 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; + + 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; + else if (generation_a > generation_b) + return 1; + + /* use date as a heuristic when generations are equal */ + if (a->date < b->date) + return -1; + else if (a->date > b->date) + return 1; + return 0; +} + +char *get_commit_graph_filename(struct object_directory *obj_dir) +{ + return xstrfmt("%s/info/commit-graph", obj_dir->path); +} + +static char *get_split_graph_filename(struct object_directory *odb, + const char *oid_hex) +{ + return xstrfmt("%s/info/commit-graphs/graph-%s.graph", odb->path, + oid_hex); +} + +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) { struct commit_graph *g = xcalloc(1, sizeof(*g)); - g->graph_fd = -1; return g; } @@ -72,7 +226,8 @@ static int commit_graph_compatible(struct repository *r) } prepare_commit_graft(r); - if (r->parsed_objects && r->parsed_objects->grafts_nr) + if (r->parsed_objects && + (r->parsed_objects->grafts_nr || r->parsed_objects->substituted_parent)) return 0; if (is_repository_shallow(r)) return 0; @@ -92,7 +247,9 @@ 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; size_t graph_size; @@ -106,12 +263,13 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st) return NULL; } graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); - ret = parse_commit_graph(graph_map, fd, graph_size); + close(fd); + ret = parse_commit_graph(r, graph_map, graph_size); - if (!ret) { + if (ret) + ret->odb = odb; + else munmap(graph_map, graph_size); - close(fd); - } return ret; } @@ -146,16 +304,43 @@ static int verify_commit_graph_lite(struct commit_graph *g) return 0; } -struct commit_graph *parse_commit_graph(void *graph_map, int fd, - 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 last_chunk_offset; - uint32_t last_chunk_id; uint32_t graph_signature; unsigned char graph_version, hash_version; + struct chunkfile *cf = NULL; if (!graph_map) return NULL; @@ -186,144 +371,281 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd, return NULL; } + prepare_repo_settings(r); + graph = alloc_commit_graph(); graph->hash_len = the_hash_algo->rawsz; graph->num_chunks = *(unsigned char*)(data + 6); - graph->graph_fd = fd; graph->data = graph_map; graph->data_len = graph_size; - last_chunk_id = 0; - last_chunk_offset = 8; - chunk_lookup = data + 8; - for (i = 0; i < graph->num_chunks; i++) { - uint32_t chunk_id; - uint64_t 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")); - free(graph); - return NULL; - } + if (graph_size < GRAPH_HEADER_SIZE + + (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); + free(graph); + return NULL; + } + + cf = init_chunkfile(NULL); - chunk_id = get_be32(chunk_lookup + 0); - chunk_offset = get_be64(chunk_lookup + 4); + if (read_table_of_contents(cf, graph->data, graph_size, + GRAPH_HEADER_SIZE, graph->num_chunks)) + goto free_and_return; + + 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); + + if (get_configured_generation_version(r) >= 2) { + 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 (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) { + init_bloom_filters(); + } else { + /* We need both the bloom chunks to exist together. Else ignore the data */ + graph->chunk_bloom_indexes = NULL; + graph->chunk_bloom_data = NULL; + FREE_AND_NULL(graph->bloom_filter_settings); + } + + oidread(&graph->oid, graph->data + graph->data_len - graph->hash_len); + + 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(struct repository *r, + const char *graph_file, + struct object_directory *odb) +{ + + struct stat st; + int fd; + struct commit_graph *g; + int open_ok = open_commit_graph(graph_file, &fd, &st); + + if (!open_ok) + return NULL; + + g = load_commit_graph_one_fd_st(r, fd, &st, odb); + + if (g) + g->filename = xstrdup(graph_file); + + return g; +} + +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(r, graph_name, odb); + free(graph_name); + + return g; +} + +static int add_graph_to_chain(struct commit_graph *g, + struct commit_graph *chain, + struct object_id *oids, + int n) +{ + struct commit_graph *cur_g = chain; + + if (n && !g->chunk_base_graphs) { + warning(_("commit-graph has no base graphs chunk")); + return 0; + } - chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH; + while (n) { + n--; - 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); - free(graph); - return NULL; + if (!cur_g || + !oideq(&oids[n], &cur_g->oid) || + !hasheq(oids[n].hash, g->chunk_base_graphs + g->hash_len * n)) { + warning(_("commit-graph chain does not match")); + return 0; } - 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; + cur_g = cur_g->base_graph; + } - case GRAPH_CHUNKID_OIDLOOKUP: - if (graph->chunk_oid_lookup) - chunk_repeated = 1; - else - graph->chunk_oid_lookup = data + chunk_offset; - break; + g->base_graph = chain; + + if (chain) + g->num_commits_in_base = chain->num_commits + chain->num_commits_in_base; - case GRAPH_CHUNKID_DATA: - if (graph->chunk_commit_data) - chunk_repeated = 1; - else - graph->chunk_commit_data = data + chunk_offset; + return 1; +} + +static struct commit_graph *load_commit_graph_chain(struct repository *r, + struct object_directory *odb) +{ + struct commit_graph *graph_chain = NULL; + struct strbuf line = STRBUF_INIT; + struct stat st; + struct object_id *oids; + int i = 0, valid = 1, count; + char *chain_name = get_commit_graph_chain_filename(odb); + FILE *fp; + int stat_res; + + fp = fopen(chain_name, "r"); + stat_res = stat(chain_name, &st); + free(chain_name); + + if (!fp || + stat_res || + st.st_size <= the_hash_algo->hexsz) + return NULL; + + count = st.st_size / (the_hash_algo->hexsz + 1); + CALLOC_ARRAY(oids, count); + + prepare_alt_odb(r); + + for (i = 0; i < count; i++) { + struct object_directory *odb; + + if (strbuf_getline_lf(&line, fp) == EOF) break; - case GRAPH_CHUNKID_EXTRAEDGES: - if (graph->chunk_extra_edges) - chunk_repeated = 1; - else - graph->chunk_extra_edges = data + chunk_offset; + if (get_oid_hex(line.buf, &oids[i])) { + warning(_("invalid commit-graph chain: line '%s' not a hash"), + line.buf); + valid = 0; break; } - if (chunk_repeated) { - error(_("commit-graph chunk id %08x appears multiple times"), chunk_id); - free(graph); - return NULL; + 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(r, graph_name, odb); + + free(graph_name); + + if (g) { + if (add_graph_to_chain(g, graph_chain, oids, i)) { + graph_chain = g; + valid = 1; + } + + break; + } } - if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP) - { - graph->num_commits = (chunk_offset - last_chunk_offset) - / graph->hash_len; + if (!valid) { + warning(_("unable to find all commit-graph files")); + break; } + } + + free(oids); + fclose(fp); + strbuf_release(&line); + + 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; - last_chunk_id = chunk_id; - last_chunk_offset = chunk_offset; + while (read_generation_data && p) { + read_generation_data = p->read_generation_data; + p = p->base_graph; } - if (verify_commit_graph_lite(graph)) { - free(graph); - return NULL; + if (read_generation_data) + return 1; + + while (g) { + g->read_generation_data = 0; + g = g->base_graph; } - return graph; + return 0; } -static struct commit_graph *load_commit_graph_one(const char *graph_file) +struct commit_graph *read_commit_graph_one(struct repository *r, + struct object_directory *odb) { + struct commit_graph *g = load_commit_graph_v1(r, odb); - struct stat st; - int fd; - int open_ok = open_commit_graph(graph_file, &fd, &st); + if (!g) + g = load_commit_graph_chain(r, odb); - if (!open_ok) - return NULL; + validate_mixed_generation_chain(g); - return load_commit_graph_one_fd_st(fd, &st); + return g; } -static void prepare_commit_graph_one(struct repository *r, const char *obj_dir) +static void prepare_commit_graph_one(struct repository *r, + struct object_directory *odb) { - char *graph_name; if (r->objects->commit_graph) return; - graph_name = get_commit_graph_filename(obj_dir); - r->objects->commit_graph = - load_commit_graph_one(graph_name); - - FREE_AND_NULL(graph_name); + r->objects->commit_graph = read_commit_graph_one(r, odb); } /* * Return 1 if commit_graph is non-NULL, and 0 otherwise. * - * On the first invocation, this function attemps to load the commit + * On the first invocation, this function attempts to load the commit * graph if the_repository is configured to have one. */ static int prepare_commit_graph(struct repository *r) { struct object_directory *odb; - int config_value; - 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); + /* + * This must come before the "already attempted?" check below, because + * we want to disable even an already-loaded graph file. + */ + if (r->commit_graph_disabled) + return 0; if (r->objects->commit_graph_attempted) return !!r->objects->commit_graph; r->objects->commit_graph_attempted = 1; + prepare_repo_settings(r); + if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) && - (repo_config_get_bool(r, "core.commitgraph", &config_value) || - !config_value)) + r->settings.core_commit_graph != 1) /* * This repository is not configured to use commit graphs, so * do not load one. (But report commit_graph_attempted anyway @@ -339,7 +661,7 @@ static int prepare_commit_graph(struct repository *r) for (odb = r->objects->odb; !r->objects->commit_graph && odb; odb = odb->next) - prepare_commit_graph_one(r, odb->path); + prepare_commit_graph_one(r, odb); return !!r->objects->commit_graph; } @@ -361,9 +683,43 @@ 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) + return; + + close_commit_graph_one(g->base_graph); + free_commit_graph(g); +} + void close_commit_graph(struct raw_object_store *o) { - free_commit_graph(o->commit_graph); + close_commit_graph_one(o->commit_graph); o->commit_graph = NULL; } @@ -373,30 +729,84 @@ static int bsearch_graph(struct commit_graph *g, struct object_id *oid, uint32_t g->chunk_oid_lookup, g->hash_len, pos); } +static void load_oid_from_graph(struct commit_graph *g, + uint32_t pos, + struct object_id *oid) +{ + uint32_t lex_index; + + while (g && pos < g->num_commits_in_base) + g = g->base_graph; + + if (!g) + BUG("NULL commit-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; + + oidread(oid, g->chunk_oid_lookup + g->hash_len * lex_index); +} + static struct commit_list **insert_parent_or_die(struct repository *r, struct commit_graph *g, - uint64_t pos, + uint32_t pos, struct commit_list **pptr) { struct commit *c; struct object_id oid; - if (pos >= g->num_commits) - die("invalid parent position %"PRIu64, pos); + if (pos >= g->num_commits + g->num_commits_in_base) + die("invalid parent position %"PRIu32, pos); - hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos); + load_oid_from_graph(g, pos, &oid); c = lookup_commit(r, &oid); if (!c) die(_("could not find commit %s"), oid_to_hex(&oid)); - c->graph_pos = pos; + commit_graph_data_at(c)->graph_pos = pos; return &commit_list_insert(c, pptr)->next; } static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, uint32_t pos) { - const unsigned char *commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * pos; - item->graph_pos = pos; - item->generation = get_be32(commit_data + g->hash_len + 8) >> 2; + const unsigned char *commit_data; + struct commit_graph_data *graph_data; + 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; + + 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) @@ -410,20 +820,21 @@ 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; - const unsigned char *commit_data = g->chunk_commit_data + (g->hash_len + 16) * pos; + const unsigned char *commit_data; + uint32_t lex_index; - item->object.parsed = 1; - item->graph_pos = pos; + while (pos < g->num_commits_in_base) + g = g->base_graph; - set_commit_tree(item, NULL); + fill_commit_graph_info(item, g, pos); - 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); + lex_index = pos - g->num_commits_in_base; + commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index; - item->generation = get_be32(commit_data + g->hash_len + 8) >> 2; + item->object.parsed = 1; + + set_commit_tree(item, NULL); pptr = &item->parents; @@ -455,11 +866,23 @@ static int fill_commit_in_graph(struct repository *r, static int find_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t *pos) { - if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) { - *pos = item->graph_pos; + uint32_t graph_pos = commit_graph_position(item); + if (graph_pos != COMMIT_NOT_FROM_GRAPH) { + *pos = graph_pos; return 1; } else { - return bsearch_graph(g, &(item->object.oid), pos); + struct commit_graph *cur_g = g; + uint32_t lex_index; + + while (cur_g && !bsearch_graph(cur_g, &(item->object.oid), &lex_index)) + cur_g = cur_g->base_graph; + + if (cur_g) { + *pos = lex_index + cur_g->num_commits_in_base; + return 1; + } + + return 0; } } @@ -480,6 +903,14 @@ 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); @@ -499,10 +930,16 @@ static struct tree *load_tree_for_commit(struct repository *r, struct commit *c) { struct object_id oid; - const unsigned char *commit_data = g->chunk_commit_data + - GRAPH_DATA_WIDTH * (c->graph_pos); + const unsigned char *commit_data; + uint32_t graph_pos = commit_graph_position(c); + + while (graph_pos < g->num_commits_in_base) + g = g->base_graph; + + commit_data = g->chunk_commit_data + + GRAPH_DATA_WIDTH * (graph_pos - g->num_commits_in_base); - hashcpy(oid.hash, commit_data); + oidread(&oid, commit_data); set_commit_tree(c, lookup_tree(r, &oid)); return c->maybe_tree; @@ -514,7 +951,7 @@ static struct tree *get_commit_tree_in_graph_one(struct repository *r, { if (c->maybe_tree) return c->maybe_tree; - if (c->graph_pos == COMMIT_NOT_FROM_GRAPH) + if (commit_graph_position(c) == COMMIT_NOT_FROM_GRAPH) BUG("get_commit_tree_in_graph_one called from non-commit-graph commit"); return load_tree_for_commit(r, g, (struct commit *)c); @@ -527,34 +964,55 @@ 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; - const char *obj_dir; + 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; uint64_t progress_cnt; + + char *base_graph_name; + int num_commit_graphs_before; + int num_commit_graphs_after; + char **commit_graph_filenames_before; + char **commit_graph_filenames_after; + char **commit_graph_hash_after; + uint32_t new_num_commits_in_base; + struct commit_graph *new_base_graph; + unsigned append:1, - report_progress:1; + report_progress:1, + split:1, + changed_paths:1, + order_by_pack:1, + write_generation_data:1, + trust_generation_numbers:1; + + 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 void write_graph_chunk_fanout(struct hashfile *f, - struct write_commit_graph_context *ctx) +static int write_graph_chunk_fanout(struct hashfile *f, + void *data) { + struct write_commit_graph_context *ctx = data; int i, count = 0; struct commit **list = ctx->commits.list; @@ -574,50 +1032,70 @@ 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, + 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++) { 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) +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 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, + 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; while (list < last) { struct commit_list *parent; + struct object_id *tree; int edge_value; uint32_t packedDate[2]; display_progress(ctx->progress, ++ctx->progress_cnt); - parse_commit_no_graph(*list); - hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len); + 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); + 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, - 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; + else if (ctx->new_base_graph) { + uint32_t pos; + if (find_commit_in_graph(parent->item, + ctx->new_base_graph, + &pos)) + edge_value = pos; + } if (edge_value < 0) BUG("missing parent %s for commit %s", @@ -635,10 +1113,21 @@ 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, - 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; + else if (ctx->new_base_graph) { + uint32_t pos; + if (find_commit_in_graph(parent->item, + ctx->new_base_graph, + &pos)) + edge_value = pos; + } + if (edge_value < 0) BUG("missing parent %s for commit %s", oid_to_hex(&parent->item->object.oid), @@ -659,18 +1148,64 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, else packedDate[0] = 0; - packedDate[0] |= htonl((*list)->generation << 2); + packedDate[0] |= htonl(*topo_level_slab_at(ctx->topo_levels, *list) << 2); packedDate[1] = htonl((*list)->date); hashwrite(f, packedDate, 8); list++; } + + return 0; } -static void write_graph_chunk_extra_edges(struct hashfile *f, - struct write_commit_graph_context *ctx) +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, + 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; @@ -691,10 +1226,20 @@ 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, - 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; + else if (ctx->new_base_graph) { + uint32_t pos; + if (find_commit_in_graph(parent->item, + ctx->new_base_graph, + &pos)) + edge_value = pos; + } if (edge_value < 0) BUG("missing parent %s for commit %s", @@ -708,13 +1253,70 @@ static void write_graph_chunk_extra_edges(struct hashfile *f, list++; } + + return 0; } -static int commit_compare(const void *_a, const void *_b) +static int write_graph_chunk_bloom_indexes(struct hashfile *f, + 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); + 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) { - const struct object_id *a = (const struct object_id *)_a; - const struct object_id *b = (const struct object_id *)_b; - return oidcmp(a, b); + 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 int write_graph_chunk_bloom_data(struct hashfile *f, + void *data) +{ + struct write_commit_graph_context *ctx = data; + struct commit **list = ctx->commits.list; + struct commit **last = ctx->commits.list + ctx->commits.nr; + + 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); + size_t len = filter ? filter->len : 0; + + display_progress(ctx->progress, ++ctx->progress_cnt); + if (len) + hashwrite(f, filter->data, len * sizeof(unsigned char)); + list++; + } + + return 0; } static int add_packed_commits(const struct object_id *oid, @@ -737,9 +1339,8 @@ 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; } @@ -748,11 +1349,9 @@ 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 & UNINTERESTING)) { - 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++; - parent->item->object.flags |= UNINTERESTING; + if (!(parent->item->object.flags & REACHABLE)) { + oid_array_append(&ctx->oids, &parent->item->object.oid); + parent->item->object.flags |= REACHABLE; } } } @@ -761,6 +1360,8 @@ static void close_reachable(struct write_commit_graph_context *ctx) { int i; struct commit *commit; + 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( @@ -768,9 +1369,9 @@ 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 |= UNINTERESTING; + commit->object.flags |= REACHABLE; } stop_progress(&ctx->progress); @@ -782,12 +1383,19 @@ static void close_reachable(struct write_commit_graph_context *ctx) if (ctx->report_progress) ctx->progress = start_delayed_progress( _("Expanding reachable commits in commit graph"), - ctx->oids.nr); + 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 && !parse_commit_no_graph(commit)) + if (!commit) + continue; + if (ctx->split) { + 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 (!repo_parse_commit_no_graph(ctx->r, commit)) add_missing_parents(ctx, commit); } stop_progress(&ctx->progress); @@ -798,10 +1406,63 @@ 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 &= ~UNINTERESTING; + commit->object.flags &= ~REACHABLE; + } + 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); } @@ -812,65 +1473,175 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx) struct commit_list *list = NULL; if (ctx->report_progress) - ctx->progress = start_progress( + 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++) { + 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 (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY && - ctx->commits.list[i]->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) { - if (parent->item->generation == GENERATION_NUMBER_INFINITY || - parent->item->generation == GENERATION_NUMBER_ZERO) { + repo_parse_commit(ctx->r, parent->item); + corrected_commit_date = commit_graph_data_at(parent->item)->generation; + + if (corrected_commit_date == GENERATION_NUMBER_ZERO) { all_parents_computed = 0; commit_list_insert(parent->item, &list); break; - } else if (parent->item->generation > max_generation) { - max_generation = parent->item->generation; } + + if (corrected_commit_date > max_corrected_commit_date) + max_corrected_commit_date = corrected_commit_date; } if (all_parents_computed) { - current->generation = max_generation + 1; pop_commit(&list); - if (current->generation > GENERATION_NUMBER_MAX) - current->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 int add_ref_to_list(const char *refname, - const struct object_id *oid, - int flags, void *cb_data) +static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx) { - struct string_list *list = (struct string_list *)cb_data; + 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(); + + if (ctx->report_progress) + progress = start_delayed_progress( + _("Computing commit changed paths Bloom filters"), + ctx->commits.nr); + + ALLOC_ARRAY(sorted_commits, ctx->commits.nr); + COPY_ARRAY(sorted_commits, ctx->commits.list, ctx->commits.nr); + + if (ctx->order_by_pack) + QSORT(sorted_commits, ctx->commits.nr, commit_pos_cmp); + 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_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); +} + +struct refs_cb_data { + struct oidset *commits; + struct progress *progress; +}; + +static int add_ref_to_set(const char *refname, + const struct object_id *oid, + int flags, void *cb_data) +{ + struct object_id peeled; + struct refs_cb_data *data = (struct refs_cb_data *)cb_data; + + if (!peel_iterated_oid(oid, &peeled)) + oid = &peeled; + if (oid_object_info(the_repository, oid, NULL) == OBJ_COMMIT) + oidset_insert(data->commits, oid); + + display_progress(data->progress, oidset_size(data->commits)); - string_list_append(list, oid_to_hex(oid)); return 0; } -int write_commit_graph_reachable(const char *obj_dir, unsigned int flags) +int write_commit_graph_reachable(struct object_directory *odb, + enum commit_graph_write_flags flags, + const struct commit_graph_opts *opts) { - struct string_list list = STRING_LIST_INIT_DUP; + struct oidset commits = OIDSET_INIT; + struct refs_cb_data data; int result; - for_each_ref(add_ref_to_list, &list); - result = write_commit_graph(obj_dir, NULL, &list, - flags); + memset(&data, 0, sizeof(data)); + data.commits = &commits; + if (flags & COMMIT_GRAPH_WRITE_PROGRESS) + data.progress = start_delayed_progress( + _("Collecting referenced commits"), 0); + + for_each_ref(add_ref_to_set, &data); - string_list_clear(&list, 0); + stop_progress(&data.progress); + + result = write_commit_graph(odb, NULL, &commits, + flags, opts); + + oidset_clear(&commits); return result; } @@ -882,7 +1653,7 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx, struct strbuf packname = STRBUF_INIT; int dirlen; - strbuf_addf(&packname, "%s/pack/", ctx->obj_dir); + strbuf_addf(&packname, "%s/pack/", ctx->odb->path); dirlen = packname.len; if (ctx->report_progress) { strbuf_addf(&progress_title, @@ -913,48 +1684,27 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx, } stop_progress(&ctx->progress); - strbuf_reset(&progress_title); + strbuf_release(&progress_title); strbuf_release(&packname); return 0; } -static void fill_oids_from_commit_hex(struct write_commit_graph_context *ctx, - struct string_list *commit_hex) +static int fill_oids_from_commits(struct write_commit_graph_context *ctx, + struct oidset *commits) { - uint32_t i; - struct strbuf progress_title = STRBUF_INIT; + struct oidset_iter iter; + struct object_id *oid; - if (ctx->report_progress) { - strbuf_addf(&progress_title, - Q_("Finding commits for commit graph from %d ref", - "Finding commits for commit graph from %d refs", - commit_hex->nr), - commit_hex->nr); - ctx->progress = start_delayed_progress( - progress_title.buf, - commit_hex->nr); - } - for (i = 0; i < commit_hex->nr; i++) { - const char *end; - struct object_id oid; - struct commit *result; - - display_progress(ctx->progress, i + 1); - if (commit_hex->items[i].string && - parse_oid_hex(commit_hex->items[i].string, &oid, &end)) - continue; - - result = lookup_commit_reference_gently(ctx->r, &oid, 1); + if (!oidset_size(commits)) + return 0; - if (result) { - ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); - oidcpy(&ctx->oids.list[ctx->oids.nr], &(result->object.oid)); - ctx->oids.nr++; - } + oidset_iter_init(commits, &iter); + while ((oid = oidset_iter_next(&iter))) { + oid_array_append(&ctx->oids, oid); } - stop_progress(&ctx->progress); - strbuf_release(&progress_title); + + return 0; } static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx) @@ -970,50 +1720,36 @@ 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, commit_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])) - count_distinct++; - } - stop_progress(&ctx->progress); - - return count_distinct; -} - static void copy_oids_to_commits(struct write_commit_graph_context *ctx) { uint32_t i; - struct commit_list *parent; + 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++) { - int num_parents = 0; + 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; - ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]); - parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]); + ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc); + ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.oid[i]); - for (parent = ctx->commits.list[ctx->commits.nr]->parents; - parent; parent = parent->next) - num_parents++; + 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) + repo_parse_commit(ctx->r, ctx->commits.list[ctx->commits.nr]); + else + 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) ctx->num_extra_edges += num_parents - 1; @@ -1022,18 +1758,55 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } +static int write_graph_chunk_base_1(struct hashfile *f, + struct commit_graph *g) +{ + int num = 0; + + if (!g) + return 0; + + num = write_graph_chunk_base_1(f, g->base_graph); + hashwrite(f, g->oid.hash, the_hash_algo->rawsz); + return num + 1; +} + +static int write_graph_chunk_base(struct hashfile *f, + 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) { + error(_("failed to write correct number of base graph ids")); + return -1; + } + + return 0; +} + 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[5]; - uint64_t chunk_offsets[5]; const unsigned hashsz = the_hash_algo->rawsz; struct strbuf progress_title = STRBUF_INIT; - int num_chunks = ctx->num_extra_edges ? 4 : 3; + struct chunkfile *cf; + unsigned char file_hash[GIT_MAX_RAWSZ]; + + if (ctx->split) { + struct strbuf tmp_file = STRBUF_INIT; + + strbuf_addf(&tmp_file, + "%s/info/commit-graphs/tmp_graph_XXXXXX", + ctx->odb->path); + ctx->graph_name = strbuf_detach(&tmp_file, NULL); + } else { + ctx->graph_name = get_commit_graph_filename(ctx->odb); + } - ctx->graph_name = get_commit_graph_filename(ctx->obj_dir); if (safe_create_leading_directories(ctx->graph_name)) { UNLEAK(ctx->graph_name); error(_("unable to create leading directories of %s"), @@ -1041,127 +1814,536 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) return -1; } - hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR); - f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); - - hashwrite_be32(f, GRAPH_SIGNATURE); + if (ctx->split) { + char *lock_name = get_commit_graph_chain_filename(ctx->odb); - hashwrite_u8(f, GRAPH_VERSION); - hashwrite_u8(f, oid_version()); - hashwrite_u8(f, num_chunks); - hashwrite_u8(f, 0); /* unused padding byte */ + hold_lock_file_for_update_mode(&lk, lock_name, + LOCK_DIE_ON_ERROR, 0444); - chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT; - chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP; - chunk_ids[2] = GRAPH_CHUNKID_DATA; - if (ctx->num_extra_edges) - chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES; - else - chunk_ids[3] = 0; - chunk_ids[4] = 0; + fd = git_mkstemp_mode(ctx->graph_name, 0444); + if (fd < 0) { + error(_("unable to create temporary graph layer")); + return -1; + } - 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; - chunk_offsets[4] = chunk_offsets[3] + 4 * ctx->num_extra_edges; + if (adjust_shared_perm(ctx->graph_name)) { + error(_("unable to adjust shared permissions for '%s'"), + ctx->graph_name); + return -1; + } - for (i = 0; i <= num_chunks; i++) { - uint32_t chunk_write[3]; + f = hashfd(fd, ctx->graph_name); + } else { + hold_lock_file_for_update_mode(&lk, ctx->graph_name, + LOCK_DIE_ON_ERROR, 0444); + fd = get_lock_file_fd(&lk); + f = hashfd(fd, get_lock_file_path(&lk)); + } - chunk_write[0] = htonl(chunk_ids[i]); - chunk_write[1] = htonl(chunk_offsets[i] >> 32); - chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff); - hashwrite(f, chunk_write, 12); + 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 (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) { + 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, get_num_chunks(cf)); + hashwrite_u8(f, ctx->num_commit_graphs_after - 1); 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); } - 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); + + write_chunkfile(cf, ctx); + stop_progress(&ctx->progress); strbuf_release(&progress_title); + if (ctx->split && ctx->base_graph_name && ctx->num_commit_graphs_after > 1) { + char *new_base_hash = xstrdup(oid_to_hex(&ctx->new_base_graph->oid)); + char *new_base_name = get_split_graph_filename(ctx->new_base_graph->odb, new_base_hash); + + free(ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2]); + free(ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2]); + ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2] = new_base_name; + ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2] = new_base_hash; + } + close_commit_graph(ctx->r->objects); - finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC); + finalize_hashfile(f, file_hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC); + free_chunkfile(cf); + + if (ctx->split) { + FILE *chainf = fdopen_lock_file(&lk, "w"); + char *final_graph_name; + int result; + + close(fd); + + if (!chainf) { + error(_("unable to open commit-graph chain file")); + return -1; + } + + if (ctx->base_graph_name) { + const char *dest; + int idx = ctx->num_commit_graphs_after - 1; + if (ctx->num_commit_graphs_after > 1) + idx--; + + dest = ctx->commit_graph_filenames_after[idx]; + + if (strcmp(ctx->base_graph_name, dest)) { + result = rename(ctx->base_graph_name, dest); + + if (result) { + error(_("failed to rename base commit-graph file")); + return -1; + } + } + } else { + char *graph_name = get_commit_graph_filename(ctx->odb); + unlink(graph_name); + } + + ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1] = xstrdup(hash_to_hex(file_hash)); + final_graph_name = get_split_graph_filename(ctx->odb, + ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1]); + ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 1] = final_graph_name; + + result = rename(ctx->graph_name, final_graph_name); + + for (i = 0; i < ctx->num_commit_graphs_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")); + return -1; + } + } + commit_lock_file(&lk); return 0; } -int write_commit_graph(const char *obj_dir, +static void split_graph_merge_strategy(struct write_commit_graph_context *ctx) +{ + struct commit_graph *g; + uint32_t num_commits; + enum commit_graph_split_flags flags = COMMIT_GRAPH_SPLIT_UNSPECIFIED; + uint32_t i; + + int max_commits = 0; + int size_mult = 2; + + if (ctx->opts) { + max_commits = ctx->opts->max_commits; + + if (ctx->opts->size_multiple) + size_mult = ctx->opts->size_multiple; + + flags = ctx->opts->split_flags; + } + + g = ctx->r->objects->commit_graph; + num_commits = ctx->commits.nr; + if (flags == COMMIT_GRAPH_SPLIT_REPLACE) + ctx->num_commit_graphs_after = 1; + else + ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1; + + if (flags != COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED && + flags != COMMIT_GRAPH_SPLIT_REPLACE) { + while (g && (g->num_commits <= size_mult * num_commits || + (max_commits && num_commits > max_commits))) { + if (g->odb != ctx->odb) + break; + + num_commits += g->num_commits; + g = g->base_graph; + + ctx->num_commit_graphs_after--; + } + } + + if (flags != COMMIT_GRAPH_SPLIT_REPLACE) + ctx->new_base_graph = g; + else if (ctx->num_commit_graphs_after != 1) + BUG("split_graph_merge_strategy: num_commit_graphs_after " + "should be 1 with --split=replace"); + + if (ctx->num_commit_graphs_after == 2) { + char *old_graph_name = get_commit_graph_filename(g->odb); + + if (!strcmp(g->filename, old_graph_name) && + g->odb != ctx->odb) { + ctx->num_commit_graphs_after = 1; + ctx->new_base_graph = NULL; + } + + free(old_graph_name); + } + + CALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after); + CALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after); + + for (i = 0; i < ctx->num_commit_graphs_after && + i < ctx->num_commit_graphs_before; i++) + ctx->commit_graph_filenames_after[i] = xstrdup(ctx->commit_graph_filenames_before[i]); + + i = ctx->num_commit_graphs_before - 1; + g = ctx->r->objects->commit_graph; + + while (g) { + 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; + } +} + +static void merge_commit_graph(struct write_commit_graph_context *ctx, + struct commit_graph *g) +{ + uint32_t i; + uint32_t offset = g->num_commits_in_base; + + ALLOC_GROW(ctx->commits.list, ctx->commits.nr + g->num_commits, ctx->commits.alloc); + + for (i = 0; i < g->num_commits; i++) { + struct object_id oid; + struct commit *result; + + display_progress(ctx->progress, i + 1); + + load_oid_from_graph(g, i + offset, &oid); + + /* only add commits if they still exist in the repo */ + result = lookup_commit_reference_gently(ctx->r, &oid, 1); + + if (result) { + ctx->commits.list[ctx->commits.nr] = result; + ctx->commits.nr++; + } + } +} + +static int commit_compare(const void *_a, const void *_b) +{ + const struct commit *a = *(const struct commit **)_a; + const struct commit *b = *(const struct commit **)_b; + return oidcmp(&a->object.oid, &b->object.oid); +} + +static void sort_and_scan_merged_commits(struct write_commit_graph_context *ctx) +{ + uint32_t i, dedup_i = 0; + + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Scanning merged commits"), + ctx->commits.nr); + + QSORT(ctx->commits.list, ctx->commits.nr, commit_compare); + + ctx->num_extra_edges = 0; + for (i = 0; i < ctx->commits.nr; i++) { + display_progress(ctx->progress, i); + + if (i && oideq(&ctx->commits.list[i - 1]->object.oid, + &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); +} + +static void merge_commit_graphs(struct write_commit_graph_context *ctx) +{ + struct commit_graph *g = ctx->r->objects->commit_graph; + uint32_t current_graph_number = ctx->num_commit_graphs_before; + + while (g && current_graph_number >= ctx->num_commit_graphs_after) { + current_graph_number--; + + if (ctx->report_progress) + ctx->progress = start_delayed_progress(_("Merging commit-graph"), 0); + + merge_commit_graph(ctx, g); + stop_progress(&ctx->progress); + + g = g->base_graph; + } + + if (g) { + ctx->new_base_graph = g; + ctx->new_num_commits_in_base = g->num_commits + g->num_commits_in_base; + } + + if (ctx->new_base_graph) + ctx->base_graph_name = xstrdup(ctx->new_base_graph->filename); + + sort_and_scan_merged_commits(ctx); +} + +static void mark_commit_graphs(struct write_commit_graph_context *ctx) +{ + uint32_t i; + time_t now = time(NULL); + + for (i = ctx->num_commit_graphs_after - 1; i < ctx->num_commit_graphs_before; i++) { + struct stat st; + struct utimbuf updated_time; + + stat(ctx->commit_graph_filenames_before[i], &st); + + updated_time.actime = st.st_atime; + updated_time.modtime = now; + utime(ctx->commit_graph_filenames_before[i], &updated_time); + } +} + +static void expire_commit_graphs(struct write_commit_graph_context *ctx) +{ + struct strbuf path = STRBUF_INIT; + DIR *dir; + struct dirent *de; + size_t dirnamelen; + timestamp_t expire_time = time(NULL); + + if (ctx->opts && ctx->opts->expire_time) + expire_time = ctx->opts->expire_time; + if (!ctx->split) { + 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; + } + + strbuf_addstr(&path, ctx->odb->path); + strbuf_addstr(&path, "/info/commit-graphs"); + dir = opendir(path.buf); + + if (!dir) + goto out; + + strbuf_addch(&path, '/'); + dirnamelen = path.len; + while ((de = readdir(dir)) != NULL) { + struct stat st; + uint32_t i, found = 0; + + strbuf_setlen(&path, dirnamelen); + strbuf_addstr(&path, de->d_name); + + stat(path.buf, &st); + + if (st.st_mtime > expire_time) + continue; + if (path.len < 6 || strcmp(path.buf + path.len - 6, ".graph")) + continue; + + for (i = 0; i < ctx->num_commit_graphs_after; i++) { + if (!strcmp(ctx->commit_graph_filenames_after[i], + path.buf)) { + found = 1; + break; + } + } + + if (!found) + unlink(path.buf); + } + +out: + strbuf_release(&path); +} + +int write_commit_graph(struct object_directory *odb, struct string_list *pack_indexes, - struct string_list *commit_hex, - unsigned int flags) + struct oidset *commits, + enum commit_graph_write_flags flags, + const struct commit_graph_opts *opts) { + struct repository *r = the_repository; 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; - if (!commit_graph_compatible(the_repository)) + prepare_repo_settings(r); + if (!r->settings.core_commit_graph) { + warning(_("attempting to write a commit-graph, but 'core.commitGraph' is disabled")); return 0; + } + if (!commit_graph_compatible(r)) + return 0; + + CALLOC_ARRAY(ctx, 1); + ctx->r = r; + 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->opts = opts; + ctx->total_bloom_filter_data_size = 0; + ctx->write_generation_data = (get_configured_generation_version(r) == 2); + 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; - ctx = xcalloc(1, sizeof(struct write_commit_graph_context)); - ctx->r = the_repository; - ctx->obj_dir = obj_dir; - ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0; - ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0; + while (g) { + g->topo_levels = &topo_levels; + g = g->base_graph; + } + } - ctx->approx_nr_objects = approximate_object_count(); - ctx->oids.alloc = ctx->approx_nr_objects / 32; + if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS) + ctx->changed_paths = 1; + if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) { + struct commit_graph *g; + + 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 = ctx->r->objects->commit_graph; - if (ctx->append) { - prepare_commit_graph_one(ctx->r, ctx->obj_dir); - if (ctx->r->objects->commit_graph) - ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits; + while (g) { + ctx->num_commit_graphs_before++; + g = g->base_graph; + } + + if (ctx->num_commit_graphs_before) { + ALLOC_ARRAY(ctx->commit_graph_filenames_before, ctx->num_commit_graphs_before); + i = ctx->num_commit_graphs_before; + g = ctx->r->objects->commit_graph; + + while (g) { + ctx->commit_graph_filenames_before[--i] = xstrdup(g->filename); + g = g->base_graph; + } + } + + if (ctx->opts) + replace = ctx->opts->split_flags & COMMIT_GRAPH_SPLIT_REPLACE; } - if (ctx->oids.alloc < 1024) - ctx->oids.alloc = 1024; - ALLOC_ARRAY(ctx->oids.list, ctx->oids.alloc); + ctx->approx_nr_objects = approximate_object_count(); 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; + oidread(&oid, g->chunk_oid_lookup + g->hash_len * i); + oid_array_append(&ctx->oids, &oid); } } if (pack_indexes) { + ctx->order_by_pack = 1; if ((res = fill_oids_from_packs(ctx, pack_indexes))) goto cleanup; } - if (commit_hex) - fill_oids_from_commit_hex(ctx, commit_hex); + if (commits) { + if ((res = fill_oids_from_commits(ctx, commits))) + goto cleanup; + } - if (!pack_indexes && !commit_hex) + if (!pack_indexes && !commits) { + ctx->order_by_pack = 1; fill_oids_from_all_packs(ctx); - - 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); + close_reachable(ctx); copy_oids_to_commits(ctx); @@ -1171,14 +2353,53 @@ int write_commit_graph(const char *obj_dir, goto cleanup; } - compute_generation_numbers(ctx); + if (!ctx->commits.nr && !replace) + goto cleanup; + + if (ctx->split) { + split_graph_merge_strategy(ctx); + + if (!replace) + merge_commit_graphs(ctx); + } else + ctx->num_commit_graphs_after = 1; + + 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); res = write_commit_graph_file(ctx); + if (ctx->split) + mark_commit_graphs(ctx); + + expire_commit_graphs(ctx); + 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++) { + free(ctx->commit_graph_filenames_after[i]); + free(ctx->commit_graph_hash_after[i]); + } + + for (i = 0; i < ctx->num_commit_graphs_before; i++) + free(ctx->commit_graph_filenames_before[i]); + + free(ctx->commit_graph_filenames_after); + free(ctx->commit_graph_filenames_before); + free(ctx->commit_graph_hash_after); + } + free(ctx); return res; @@ -1187,6 +2408,7 @@ cleanup: #define VERIFY_COMMIT_GRAPH_ERROR_HASH 2 static int verify_commit_graph_error; +__attribute__((format (printf, 1, 2))) static void graph_report(const char *fmt, ...) { va_list ap; @@ -1201,14 +2423,18 @@ static void graph_report(const char *fmt, ...) #define GENERATION_ZERO_EXISTS 1 #define GENERATION_NUMBER_EXISTS 2 -int verify_commit_graph(struct repository *r, struct commit_graph *g) +static int commit_graph_checksum_valid(struct commit_graph *g) +{ + return hashfile_checksum_valid(g->data, g->data_len); +} + +int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags) { uint32_t i, cur_fanout_pos = 0; - struct object_id prev_oid, cur_oid, checksum; + struct object_id prev_oid, cur_oid; int generation_zero = 0; - struct hashfile *f; - int devnull; struct progress *progress = NULL; + int local_error = 0; if (!g) { graph_report("no commit-graph file loaded"); @@ -1219,11 +2445,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) if (verify_commit_graph_error) return verify_commit_graph_error; - devnull = open("/dev/null", O_WRONLY); - f = hashfd(devnull, NULL); - hashwrite(f, g->data, g->data_len - g->hash_len); - finalize_hashfile(f, checksum.hash, CSUM_CLOSE); - if (!hasheq(checksum.hash, g->data + g->data_len - g->hash_len)) { + if (!commit_graph_checksum_valid(g)) { graph_report(_("the commit-graph file has incorrect checksum and is likely corrupt")); verify_commit_graph_error = VERIFY_COMMIT_GRAPH_ERROR_HASH; } @@ -1231,7 +2453,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) for (i = 0; i < g->num_commits; i++) { struct commit *graph_commit; - hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i); + oidread(&cur_oid, g->chunk_oid_lookup + g->hash_len * i); if (i && oidcmp(&prev_oid, &cur_oid) >= 0) graph_report(_("commit-graph has incorrect OID order: %s then %s"), @@ -1268,18 +2490,21 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) if (verify_commit_graph_error & ~VERIFY_COMMIT_GRAPH_ERROR_HASH) return verify_commit_graph_error; - progress = start_progress(_("Verifying commits in commit graph"), - g->num_commits); + if (flags & COMMIT_GRAPH_WRITE_PROGRESS) + progress = start_progress(_("Verifying commits in commit graph"), + g->num_commits); + 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; + 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); + oidread(&cur_oid, g->chunk_oid_lookup + g->hash_len * i); graph_commit = lookup_commit(r, &cur_oid); - odb_commit = (struct commit *)create_object(r, cur_oid.hash, alloc_commit_node(r)); + odb_commit = (struct commit *)create_object(r, &cur_oid, alloc_commit_node(r)); if (parse_commit_internal(odb_commit, 0, 0)) { graph_report(_("failed to parse commit %s from object database for commit-graph"), oid_to_hex(&cur_oid)); @@ -1303,14 +2528,18 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) break; } + /* parse parent in case it is in a base graph */ + parse_commit_in_graph_one(r, g, graph_parents->item); + if (!oideq(&graph_parents->item->object.oid, &odb_parents->item->object.oid)) graph_report(_("commit-graph parent for %s is %s != %s"), oid_to_hex(&cur_oid), oid_to_hex(&graph_parents->item->object.oid), oid_to_hex(&odb_parents->item->object.oid)); - if (graph_parents->item->generation > max_generation) - max_generation = graph_parents->item->generation; + generation = commit_graph_generation(graph_parents->item); + if (generation > max_generation) + max_generation = generation; graph_parents = graph_parents->next; odb_parents = odb_parents->next; @@ -1320,7 +2549,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) graph_report(_("commit-graph parent list for commit %s terminates early"), oid_to_hex(&cur_oid)); - if (!graph_commit->generation) { + if (!commit_graph_generation(graph_commit)) { if (generation_zero == GENERATION_NUMBER_EXISTS) graph_report(_("commit-graph has generation number zero for commit %s, but non-zero elsewhere"), oid_to_hex(&cur_oid)); @@ -1333,17 +2562,19 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) 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--; - if (graph_commit->generation != max_generation + 1) - graph_report(_("commit-graph generation for commit %s is %u != %u"), + generation = commit_graph_generation(graph_commit); + if (generation < max_generation + 1) + graph_report(_("commit-graph generation for commit %s is %"PRItime" < %"PRItime), oid_to_hex(&cur_oid), - graph_commit->generation, + generation, max_generation + 1); if (graph_commit->date != odb_commit->date) @@ -1354,17 +2585,28 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g) } stop_progress(&progress); - return verify_commit_graph_error; + local_error = verify_commit_graph_error; + + if (!(flags & COMMIT_GRAPH_VERIFY_SHALLOW) && g->base_graph) + local_error |= verify_commit_graph(r, g->base_graph, flags); + + return local_error; } void free_commit_graph(struct commit_graph *g) { if (!g) return; - if (g->graph_fd >= 0) { + if (g->data) { munmap((void *)g->data, g->data_len); g->data = NULL; - close(g->graph_fd); } + free(g->filename); + free(g->bloom_filter_settings); free(g); } + +void disable_commit_graph(struct repository *r) +{ + r->commit_graph_disabled = 1; +} |