diff options
author | Junio C Hamano <gitster@pobox.com> | 2020-09-29 14:01:20 -0700 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2020-09-29 14:01:20 -0700 |
commit | 288ed98bf768f4df9b569d51a52c233a1402c0f5 (patch) | |
tree | 671cd2dddfb6b1adc8a9d1c7b516f4f5622bd092 | |
parent | Merge branch 'bc/faq-misc' (diff) | |
parent | commit-graph: introduce 'commitGraph.maxNewFilters' (diff) | |
download | tgif-288ed98bf768f4df9b569d51a52c233a1402c0f5.tar.xz |
Merge branch 'tb/bloom-improvements'
"git commit-graph write" learned to limit the number of bloom
filters that are computed from scratch with the --max-new-filters
option.
* tb/bloom-improvements:
commit-graph: introduce 'commitGraph.maxNewFilters'
builtin/commit-graph.c: introduce '--max-new-filters=<n>'
commit-graph: rename 'split_commit_graph_opts'
bloom: encode out-of-bounds filters as non-empty
bloom/diff: properly short-circuit on max_changes
bloom: use provided 'struct bloom_filter_settings'
bloom: split 'get_bloom_filter()' in two
commit-graph.c: store maximum changed paths
commit-graph: respect 'commitGraph.readChangedPaths'
t/helper/test-read-graph.c: prepare repo settings
commit-graph: pass a 'struct repository *' in more places
t4216: use an '&&'-chain
commit-graph: introduce 'get_bloom_filter_settings()'
-rw-r--r-- | Documentation/config.txt | 2 | ||||
-rw-r--r-- | Documentation/config/commitgraph.txt | 8 | ||||
-rw-r--r-- | Documentation/git-commit-graph.txt | 7 | ||||
-rw-r--r-- | Documentation/technical/commit-graph-format.txt | 2 | ||||
-rw-r--r-- | blame.c | 8 | ||||
-rw-r--r-- | bloom.c | 59 | ||||
-rw-r--r-- | bloom.h | 29 | ||||
-rw-r--r-- | builtin/commit-graph.c | 63 | ||||
-rw-r--r-- | commit-graph.c | 141 | ||||
-rw-r--r-- | commit-graph.h | 17 | ||||
-rw-r--r-- | diff.h | 2 | ||||
-rw-r--r-- | fuzz-commit-graph.c | 5 | ||||
-rw-r--r-- | line-log.c | 2 | ||||
-rw-r--r-- | repo-settings.c | 3 | ||||
-rw-r--r-- | repository.h | 1 | ||||
-rw-r--r-- | revision.c | 7 | ||||
-rw-r--r-- | t/helper/test-bloom.c | 4 | ||||
-rw-r--r-- | t/helper/test-read-graph.c | 3 | ||||
-rwxr-xr-x | t/t0095-bloom.sh | 8 | ||||
-rwxr-xr-x | t/t4216-log-bloom.sh | 242 | ||||
-rwxr-xr-x | t/t5324-split-commit-graph.sh | 13 | ||||
-rw-r--r-- | tree-diff.c | 5 |
22 files changed, 508 insertions, 123 deletions
diff --git a/Documentation/config.txt b/Documentation/config.txt index f93b6837e4..bf706b950e 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -340,6 +340,8 @@ include::config/column.txt[] include::config/commit.txt[] +include::config/commitgraph.txt[] + include::config/credential.txt[] include::config/completion.txt[] diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt new file mode 100644 index 0000000000..4582c39fc4 --- /dev/null +++ b/Documentation/config/commitgraph.txt @@ -0,0 +1,8 @@ +commitGraph.maxNewFilters:: + Specifies the default value for the `--max-new-filters` option of `git + commit-graph write` (c.f., linkgit:git-commit-graph[1]). + +commitGraph.readChangedPaths:: + If true, then git will use the changed-path Bloom filters in the + commit-graph file (if it exists, and they are present). Defaults to + true. See linkgit:git-commit-graph[1] for more information. diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index 17405c73a9..de6b6de230 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -67,6 +67,13 @@ this option is given, future commit-graph writes will automatically assume that this option was intended. Use `--no-changed-paths` to stop storing this data. + +With the `--max-new-filters=<n>` option, generate at most `n` new Bloom +filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is +enforced. Only commits present in the new layer count against this +limit. To retroactively compute Bloom filters over earlier layers, it is +advised to use `--split=replace`. Overrides the `commitGraph.maxNewFilters` +configuration. ++ With the `--split[=<strategy>]` option, write the commit-graph as a chain of multiple commit-graph files stored in `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt index 1f86031333..b3b58880b9 100644 --- a/Documentation/technical/commit-graph-format.txt +++ b/Documentation/technical/commit-graph-format.txt @@ -125,7 +125,7 @@ CHUNK DATA: * The rest of the chunk is the concatenation of all the computed Bloom filters for the commits in lexicographic order. * Note: Commits with no changes or more than 512 changes have Bloom filters - of length zero. + of length one, with either all bits set to zero or one respectively. * The BDAT chunk is present if and only if BIDX is present. Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional] @@ -1276,7 +1276,7 @@ static int maybe_changed_path(struct repository *r, if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY) return 1; - filter = get_bloom_filter(r, origin->commit, 0); + filter = get_bloom_filter(r, origin->commit); if (!filter) return 1; @@ -2892,16 +2892,18 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb, const char *path) { struct blame_bloom_data *bd; + struct bloom_filter_settings *bs; if (!sb->repo->objects->commit_graph) return; - if (!sb->repo->objects->commit_graph->bloom_filter_settings) + bs = get_bloom_filter_settings(sb->repo); + if (!bs) return; bd = xmalloc(sizeof(struct blame_bloom_data)); - bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings; + bd->settings = bs; bd->alloc = 4; bd->nr = 0; @@ -38,7 +38,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g, while (graph_pos < g->num_commits_in_base) g = g->base_graph; - /* The commit graph commit 'c' lives in doesn't carry bloom filters. */ + /* The commit graph commit 'c' lives in doesn't carry Bloom filters. */ if (!g->chunk_bloom_indexes) return 0; @@ -177,15 +177,25 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data, return strcmp(e1->path, e2->path); } -struct bloom_filter *get_bloom_filter(struct repository *r, - struct commit *c, - int compute_if_not_present) +static void init_truncated_large_filter(struct bloom_filter *filter) +{ + filter->data = xmalloc(1); + filter->data[0] = 0xFF; + filter->len = 1; +} + +struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, + struct commit *c, + int compute_if_not_present, + const struct bloom_filter_settings *settings, + enum bloom_filter_computed *computed) { struct bloom_filter *filter; - struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS; int i; struct diff_options diffopt; - int max_changes = 512; + + if (computed) + *computed = BLOOM_NOT_COMPUTED; if (!bloom_filters.slab_size) return NULL; @@ -194,12 +204,11 @@ struct bloom_filter *get_bloom_filter(struct repository *r, if (!filter->data) { load_commit_graph_info(r, c); - if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH && - r->objects->commit_graph->chunk_bloom_indexes) + if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH) load_bloom_filter_from_graph(r->objects->commit_graph, filter, c); } - if (filter->data) + if (filter->data && filter->len) return filter; if (!compute_if_not_present) return NULL; @@ -207,7 +216,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r, repo_diff_setup(r, &diffopt); diffopt.flags.recursive = 1; diffopt.detect_rename = 0; - diffopt.max_changes = max_changes; + diffopt.max_changes = settings->max_changed_paths; diff_setup_done(&diffopt); /* ensure commit is parsed so we have parent information */ @@ -219,7 +228,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r, diff_tree_oid(NULL, &c->object.oid, "", &diffopt); diffcore_std(&diffopt); - if (diffopt.num_changes <= max_changes) { + if (diff_queued_diff.nr <= settings->max_changed_paths) { struct hashmap pathmap; struct pathmap_hash_entry *e; struct hashmap_iter iter; @@ -256,23 +265,41 @@ struct bloom_filter *get_bloom_filter(struct repository *r, diff_free_filepair(diff_queued_diff.queue[i]); } - filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD; + if (hashmap_get_size(&pathmap) > settings->max_changed_paths) { + init_truncated_large_filter(filter); + if (computed) + *computed |= BLOOM_TRUNC_LARGE; + goto cleanup; + } + + filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD; + if (!filter->len) { + if (computed) + *computed |= BLOOM_TRUNC_EMPTY; + filter->len = 1; + } filter->data = xcalloc(filter->len, sizeof(unsigned char)); hashmap_for_each_entry(&pathmap, &iter, e, entry) { struct bloom_key key; - fill_bloom_key(e->path, strlen(e->path), &key, &settings); - add_key_to_filter(&key, filter, &settings); + fill_bloom_key(e->path, strlen(e->path), &key, settings); + add_key_to_filter(&key, filter, settings); } + cleanup: hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry); } else { for (i = 0; i < diff_queued_diff.nr; i++) diff_free_filepair(diff_queued_diff.queue[i]); - filter->data = NULL; - filter->len = 0; + init_truncated_large_filter(filter); + + if (computed) + *computed |= BLOOM_TRUNC_LARGE; } + if (computed) + *computed |= BLOOM_COMPUTED; + free(diff_queued_diff.queue); DIFF_QUEUE_CLEAR(&diff_queued_diff); @@ -28,9 +28,18 @@ struct bloom_filter_settings { * that contain n*b bits. */ uint32_t bits_per_entry; + + /* + * The maximum number of changed paths per commit + * before declaring a Bloom filter to be too-large. + * + * Not written to the commit-graph file. + */ + uint32_t max_changed_paths; }; -#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 } +#define DEFAULT_BLOOM_MAX_CHANGES 512 +#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES } #define BITS_PER_WORD 8 #define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t) @@ -80,9 +89,21 @@ void add_key_to_filter(const struct bloom_key *key, void init_bloom_filters(void); -struct bloom_filter *get_bloom_filter(struct repository *r, - struct commit *c, - int compute_if_not_present); +enum bloom_filter_computed { + BLOOM_NOT_COMPUTED = (1 << 0), + BLOOM_COMPUTED = (1 << 1), + BLOOM_TRUNC_LARGE = (1 << 2), + BLOOM_TRUNC_EMPTY = (1 << 3), +}; + +struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, + struct commit *c, + int compute_if_not_present, + const struct bloom_filter_settings *settings, + enum bloom_filter_computed *computed); + +#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \ + (r), (c), 0, NULL, NULL) int bloom_filter_contains(const struct bloom_filter *filter, const struct bloom_key *key, diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 523501f217..988445abdf 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"), N_("git commit-graph write [--object-dir <objdir>] [--append] " "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] " - "[--changed-paths] [--[no-]progress] <split options>"), + "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] " + "<split options>"), NULL }; @@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = { static const char * const builtin_commit_graph_write_usage[] = { N_("git commit-graph write [--object-dir <objdir>] [--append] " "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] " - "[--changed-paths] [--[no-]progress] <split options>"), + "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] " + "<split options>"), NULL }; @@ -106,7 +108,7 @@ static int graph_verify(int argc, const char **argv) FREE_AND_NULL(graph_name); if (open_ok) - graph = load_commit_graph_one_fd_st(fd, &st, odb); + graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb); else graph = read_commit_graph_one(the_repository, odb); @@ -119,7 +121,7 @@ static int graph_verify(int argc, const char **argv) } extern int read_replace_refs; -static struct split_commit_graph_opts split_opts; +static struct commit_graph_opts write_opts; static int write_option_parse_split(const struct option *opt, const char *arg, int unset) @@ -162,6 +164,35 @@ static int read_one_commit(struct oidset *commits, struct progress *progress, return 0; } +static int write_option_max_new_filters(const struct option *opt, + const char *arg, + int unset) +{ + int *to = opt->value; + if (unset) + *to = -1; + else { + const char *s; + *to = strtol(arg, (char **)&s, 10); + if (*s) + return error(_("%s expects a numerical value"), + optname(opt, opt->flags)); + } + return 0; +} + +static int git_commit_graph_write_config(const char *var, const char *value, + void *cb) +{ + if (!strcmp(var, "commitgraph.maxnewfilters")) + write_opts.max_new_filters = git_config_int(var, value); + /* + * No need to fall-back to 'git_default_config', since this was already + * called in 'cmd_commit_graph()'. + */ + return 0; +} + static int graph_write(int argc, const char **argv) { struct string_list pack_indexes = STRING_LIST_INIT_NODUP; @@ -187,27 +218,33 @@ static int graph_write(int argc, const char **argv) OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths, N_("enable computation for changed paths")), OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")), - OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL, + OPT_CALLBACK_F(0, "split", &write_opts.split_flags, NULL, N_("allow writing an incremental commit-graph file"), PARSE_OPT_OPTARG | PARSE_OPT_NONEG, write_option_parse_split), - OPT_INTEGER(0, "max-commits", &split_opts.max_commits, + OPT_INTEGER(0, "max-commits", &write_opts.max_commits, N_("maximum number of commits in a non-base split commit-graph")), - OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple, + OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple, N_("maximum ratio between two levels of a split commit-graph")), - OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time, + OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time, N_("only expire files older than a given date-time")), + OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters, + NULL, N_("maximum number of changed-path Bloom filters to compute"), + 0, write_option_max_new_filters), OPT_END(), }; opts.progress = isatty(2); opts.enable_changed_paths = -1; - split_opts.size_multiple = 2; - split_opts.max_commits = 0; - split_opts.expire_time = 0; + write_opts.size_multiple = 2; + write_opts.max_commits = 0; + write_opts.expire_time = 0; + write_opts.max_new_filters = -1; trace2_cmd_mode("write"); + git_config(git_commit_graph_write_config, &opts); + argc = parse_options(argc, argv, NULL, builtin_commit_graph_write_options, builtin_commit_graph_write_usage, 0); @@ -232,7 +269,7 @@ static int graph_write(int argc, const char **argv) odb = find_odb(the_repository, opts.obj_dir); if (opts.reachable) { - if (write_commit_graph_reachable(odb, flags, &split_opts)) + if (write_commit_graph_reachable(odb, flags, &write_opts)) return 1; return 0; } @@ -261,7 +298,7 @@ static int graph_write(int argc, const char **argv) opts.stdin_packs ? &pack_indexes : NULL, opts.stdin_commits ? &commits : NULL, flags, - &split_opts)) + &write_opts)) result = 1; cleanup: diff --git a/commit-graph.c b/commit-graph.c index 695c1cf7a3..cb042bdba8 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -231,7 +231,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st) return 1; } -struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st, +struct commit_graph *load_commit_graph_one_fd_st(struct repository *r, + int fd, struct stat *st, struct object_directory *odb) { void *graph_map; @@ -247,7 +248,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st, } graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - ret = parse_commit_graph(graph_map, graph_size); + ret = parse_commit_graph(r, graph_map, graph_size); if (ret) ret->odb = odb; @@ -287,7 +288,8 @@ static int verify_commit_graph_lite(struct commit_graph *g) return 0; } -struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) +struct commit_graph *parse_commit_graph(struct repository *r, + void *graph_map, size_t graph_size) { const unsigned char *data, *chunk_lookup; uint32_t i; @@ -325,6 +327,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) return NULL; } + prepare_repo_settings(r); + graph = alloc_commit_graph(); graph->hash_len = the_hash_algo->rawsz; @@ -401,14 +405,14 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) case GRAPH_CHUNKID_BLOOMINDEXES: if (graph->chunk_bloom_indexes) chunk_repeated = 1; - else + else if (r->settings.commit_graph_read_changed_paths) graph->chunk_bloom_indexes = data + chunk_offset; break; case GRAPH_CHUNKID_BLOOMDATA: if (graph->chunk_bloom_data) chunk_repeated = 1; - else { + else if (r->settings.commit_graph_read_changed_paths) { uint32_t hash_version; graph->chunk_bloom_data = data + chunk_offset; hash_version = get_be32(data + chunk_offset); @@ -420,6 +424,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size) graph->bloom_filter_settings->hash_version = hash_version; graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4); graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8); + graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES; } break; } @@ -452,7 +457,8 @@ free_and_return: return NULL; } -static struct commit_graph *load_commit_graph_one(const char *graph_file, +static struct commit_graph *load_commit_graph_one(struct repository *r, + const char *graph_file, struct object_directory *odb) { @@ -464,7 +470,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file, if (!open_ok) return NULL; - g = load_commit_graph_one_fd_st(fd, &st, odb); + g = load_commit_graph_one_fd_st(r, fd, &st, odb); if (g) g->filename = xstrdup(graph_file); @@ -476,7 +482,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r, struct object_directory *odb) { char *graph_name = get_commit_graph_filename(odb); - struct commit_graph *g = load_commit_graph_one(graph_name, odb); + struct commit_graph *g = load_commit_graph_one(r, graph_name, odb); free(graph_name); return g; @@ -557,7 +563,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, valid = 0; for (odb = r->objects->odb; odb; odb = odb->next) { char *graph_name = get_split_graph_filename(odb, line.buf); - struct commit_graph *g = load_commit_graph_one(graph_name, odb); + struct commit_graph *g = load_commit_graph_one(r, graph_name, odb); free(graph_name); @@ -667,6 +673,17 @@ int generation_numbers_enabled(struct repository *r) return !!first_generation; } +struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r) +{ + struct commit_graph *g = r->objects->commit_graph; + while (g) { + if (g->bloom_filter_settings) + return g->bloom_filter_settings; + g = g->base_graph; + } + return NULL; +} + static void close_commit_graph_one(struct commit_graph *g) { if (!g) @@ -952,9 +969,14 @@ struct write_commit_graph_context { changed_paths:1, order_by_pack:1; - const struct split_commit_graph_opts *split_opts; + const struct commit_graph_opts *opts; size_t total_bloom_filter_data_size; const struct bloom_filter_settings *bloom_settings; + + int count_bloom_filter_computed; + int count_bloom_filter_not_computed; + int count_bloom_filter_trunc_empty; + int count_bloom_filter_trunc_large; }; static int write_graph_chunk_fanout(struct hashfile *f, @@ -1166,7 +1188,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f, 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); @@ -1185,6 +1207,7 @@ 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); @@ -1205,7 +1228,7 @@ 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); @@ -1270,8 +1293,8 @@ 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( @@ -1375,11 +1398,24 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx) stop_progress(&ctx->progress); } +static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx) +{ + trace2_data_intmax("commit-graph", ctx->r, "filter-computed", + ctx->count_bloom_filter_computed); + trace2_data_intmax("commit-graph", ctx->r, "filter-not-computed", + ctx->count_bloom_filter_not_computed); + trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-empty", + ctx->count_bloom_filter_trunc_empty); + trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large", + ctx->count_bloom_filter_trunc_large); +} + static void compute_bloom_filters(struct write_commit_graph_context *ctx) { int i; struct progress *progress = NULL; struct commit **sorted_commits; + int max_new_filters; init_bloom_filters(); @@ -1396,13 +1432,34 @@ 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); } @@ -1431,7 +1488,7 @@ 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; @@ -1448,7 +1505,7 @@ 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; @@ -1563,8 +1620,8 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx) 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) @@ -1646,15 +1703,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) int num_chunks = 3; uint64_t chunk_offset; struct object_id file_hash; - 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; - } if (ctx->split) { struct strbuf tmp_file = STRBUF_INIT; @@ -1858,13 +1906,13 @@ 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; @@ -2042,8 +2090,8 @@ 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_commit_graph_chain_filename(ctx->odb); unlink(chain_file_name); @@ -2094,12 +2142,13 @@ 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; int res = 0; int replace = 0; + struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS; if (!commit_graph_compatible(the_repository)) return 0; @@ -2110,9 +2159,17 @@ int write_commit_graph(struct object_directory *odb, ctx->append = flags & COMMIT_GRAPH_WRITE_APPEND ? 1 : 0; ctx->report_progress = flags & COMMIT_GRAPH_WRITE_PROGRESS ? 1 : 0; ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0; - ctx->split_opts = split_opts; + ctx->opts = opts; ctx->total_bloom_filter_data_size = 0; + bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY", + bloom_settings.bits_per_entry); + bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES", + bloom_settings.num_hashes); + bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS", + bloom_settings.max_changed_paths); + ctx->bloom_settings = &bloom_settings; + if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS) ctx->changed_paths = 1; if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) { @@ -2150,15 +2207,15 @@ 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->split && opts && ctx->oids.alloc > opts->max_commits) + ctx->oids.alloc = opts->max_commits; if (ctx->append) { prepare_commit_graph_one(ctx->r, ctx->odb); diff --git a/commit-graph.h b/commit-graph.h index 765221cdcc..f8e92500c6 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -76,11 +76,13 @@ struct commit_graph { struct bloom_filter_settings *bloom_filter_settings; }; -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); struct commit_graph *read_commit_graph_one(struct repository *r, struct object_directory *odb); -struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size); +struct commit_graph *parse_commit_graph(struct repository *r, + void *graph_map, size_t graph_size); /* * Return 1 if and only if the repository has a commit-graph @@ -88,6 +90,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size); */ int generation_numbers_enabled(struct repository *r); +struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r); + enum commit_graph_write_flags { COMMIT_GRAPH_WRITE_APPEND = (1 << 0), COMMIT_GRAPH_WRITE_PROGRESS = (1 << 1), @@ -102,11 +106,12 @@ enum commit_graph_split_flags { COMMIT_GRAPH_SPLIT_REPLACE = 2 }; -struct split_commit_graph_opts { +struct commit_graph_opts { int size_multiple; int max_commits; timestamp_t expire_time; - enum commit_graph_split_flags flags; + enum commit_graph_split_flags split_flags; + int |