From: "Garima Singh via GitGitGadget" <gitgitgadget@gmail.com> To: git@vger.kernel.org Cc: stolee@gmail.com, szeder.dev@gmail.com, jonathantanmy@google.com, Garima Singh <garima.singh@microsoft.com>, Garima Singh <garima.singh@microsoft.com> Subject: [PATCH v3 04/16] bloom.c: core Bloom filter implementation for changed paths. Date: Mon, 30 Mar 2020 00:31:26 +0000 [thread overview] Message-ID: <8304c2975207ee847c6709abd71efee918fc4142.1585528298.git.gitgitgadget@gmail.com> (raw) In-Reply-To: <pull.497.v3.git.1585528298.gitgitgadget@gmail.com> From: Garima Singh <garima.singh@microsoft.com> Add the core implementation for computing Bloom filters for the paths changed between a commit and it's first parent. We fill the Bloom filters as (const char *data, int len) pairs as `struct bloom_filters" within a commit slab. Filters for commits with no changes and more than 512 changes, is represented with a filter of length zero. There is no gain in distinguishing between a computed filter of length zero for a commit with no changes, and an uncomputed filter for new commits or for commits with more than 512 changes. The effect on `git log -- path` is the same in both cases. We will fall back to the normal diffing algorithm when we can't benefit from the existence of Bloom filters. Helped-by: Jeff King <peff@peff.net> Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> --- bloom.c | 97 +++++++++++++++++++++++++++++++++++++++++++ bloom.h | 8 ++++ t/helper/test-bloom.c | 20 +++++++++ t/t0095-bloom.sh | 47 +++++++++++++++++++++ 4 files changed, 172 insertions(+) diff --git a/bloom.c b/bloom.c index 888b67f1ea6..881a9841ede 100644 --- a/bloom.c +++ b/bloom.c @@ -1,5 +1,18 @@ #include "git-compat-util.h" #include "bloom.h" +#include "diff.h" +#include "diffcore.h" +#include "revision.h" +#include "hashmap.h" + +define_commit_slab(bloom_filter_slab, struct bloom_filter); + +struct bloom_filter_slab bloom_filters; + +struct pathmap_hash_entry { + struct hashmap_entry entry; + const char path[FLEX_ARRAY]; +}; static uint32_t rotate_left(uint32_t value, int32_t count) { @@ -107,3 +120,87 @@ void add_key_to_filter(const struct bloom_key *key, filter->data[block_pos] |= get_bitmask(hash_mod); } } + +void init_bloom_filters(void) +{ + init_bloom_filter_slab(&bloom_filters); +} + +struct bloom_filter *get_bloom_filter(struct repository *r, + struct commit *c) +{ + struct bloom_filter *filter; + struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS; + int i; + struct diff_options diffopt; + + if (bloom_filters.slab_size == 0) + return NULL; + + filter = bloom_filter_slab_at(&bloom_filters, c); + + repo_diff_setup(r, &diffopt); + diffopt.flags.recursive = 1; + diff_setup_done(&diffopt); + + if (c->parents) + diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &diffopt); + else + diff_tree_oid(NULL, &c->object.oid, "", &diffopt); + diffcore_std(&diffopt); + + if (diff_queued_diff.nr <= 512) { + struct hashmap pathmap; + struct pathmap_hash_entry *e; + struct hashmap_iter iter; + hashmap_init(&pathmap, NULL, NULL, 0); + + for (i = 0; i < diff_queued_diff.nr; i++) { + const char *path = diff_queued_diff.queue[i]->two->path; + + /* + * Add each leading directory of the changed file, i.e. for + * 'dir/subdir/file' add 'dir' and 'dir/subdir' as well, so + * the Bloom filter could be used to speed up commands like + * 'git log dir/subdir', too. + * + * Note that directories are added without the trailing '/'. + */ + do { + char *last_slash = strrchr(path, '/'); + + FLEX_ALLOC_STR(e, path, path); + hashmap_entry_init(&e->entry, strhash(path)); + hashmap_add(&pathmap, &e->entry); + + if (!last_slash) + last_slash = (char*)path; + *last_slash = '\0'; + + } while (*path); + + 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; + 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); + } + + 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; + } + + free(diff_queued_diff.queue); + DIFF_QUEUE_CLEAR(&diff_queued_diff); + + return filter; +} diff --git a/bloom.h b/bloom.h index b9ce422ca2d..85ab8e9423d 100644 --- a/bloom.h +++ b/bloom.h @@ -1,6 +1,9 @@ #ifndef BLOOM_H #define BLOOM_H +struct commit; +struct repository; + struct bloom_filter_settings { /* * The version of the hashing technique being used. @@ -73,4 +76,9 @@ void add_key_to_filter(const struct bloom_key *key, struct bloom_filter *filter, const struct bloom_filter_settings *settings); +void init_bloom_filters(void); + +struct bloom_filter *get_bloom_filter(struct repository *r, + struct commit *c); + #endif \ No newline at end of file diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c index 20460cde775..f18d1b722e1 100644 --- a/t/helper/test-bloom.c +++ b/t/helper/test-bloom.c @@ -1,6 +1,7 @@ #include "git-compat-util.h" #include "bloom.h" #include "test-tool.h" +#include "commit.h" struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS; @@ -32,6 +33,16 @@ static void print_bloom_filter(struct bloom_filter *filter) { printf("\n"); } +static void get_bloom_filter_for_commit(const struct object_id *commit_oid) +{ + struct commit *c; + struct bloom_filter *filter; + setup_git_directory(); + c = lookup_commit(the_repository, commit_oid); + filter = get_bloom_filter(the_repository, c); + print_bloom_filter(filter); +} + int cmd__bloom(int argc, const char **argv) { if (!strcmp(argv[1], "get_murmur3")) { @@ -57,5 +68,14 @@ int cmd__bloom(int argc, const char **argv) print_bloom_filter(&filter); } + if (!strcmp(argv[1], "get_filter_for_commit")) { + struct object_id oid; + const char *end; + if (parse_oid_hex(argv[2], &oid, &end)) + die("cannot parse oid '%s'", argv[2]); + init_bloom_filters(); + get_bloom_filter_for_commit(&oid); + } + return 0; } \ No newline at end of file diff --git a/t/t0095-bloom.sh b/t/t0095-bloom.sh index 36a086c7c60..8f9eef116dc 100755 --- a/t/t0095-bloom.sh +++ b/t/t0095-bloom.sh @@ -67,4 +67,51 @@ test_expect_success 'compute bloom key for test string 2' ' test_cmp expect actual ' +test_expect_success 'get bloom filters for commit with no changes' ' + git init && + git commit --allow-empty -m "c0" && + cat >expect <<-\EOF && + Filter_Length:0 + Filter_Data: + EOF + test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual && + test_cmp expect actual +' + +test_expect_success 'get bloom filter for commit with 10 changes' ' + rm actual && + rm expect && + mkdir smallDir && + for i in $(test_seq 0 9) + do + echo $i >smallDir/$i + done && + git add smallDir && + git commit -m "commit with 10 changes" && + cat >expect <<-\EOF && + Filter_Length:25 + Filter_Data:82|a0|65|47|0c|92|90|c0|a1|40|02|a0|e2|40|e0|04|0a|9a|66|cf|80|19|85|42|23| + EOF + test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual && + test_cmp expect actual +' + +test_expect_success EXPENSIVE 'get bloom filter for commit with 513 changes' ' + rm actual && + rm expect && + mkdir bigDir && + for i in $(test_seq 0 512) + do + echo $i >bigDir/$i + done && + git add bigDir && + git commit -m "commit with 513 changes" && + cat >expect <<-\EOF && + Filter_Length:0 + Filter_Data: + EOF + test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual && + test_cmp expect actual +' + test_done \ No newline at end of file -- gitgitgadget
next prev parent reply other threads:[~2020-03-30 0:31 UTC|newest] Thread overview: 159+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-12-20 22:05 [PATCH 0/9] [RFC] Changed Paths Bloom Filters Garima Singh via GitGitGadget 2019-12-20 22:05 ` [PATCH 1/9] commit-graph: add --changed-paths option to write Garima Singh via GitGitGadget 2020-01-01 20:20 ` Jakub Narebski 2019-12-20 22:05 ` [PATCH 2/9] commit-graph: write changed paths bloom filters Garima Singh via GitGitGadget 2019-12-21 16:48 ` Philip Oakley 2020-01-06 18:44 ` Jakub Narebski 2020-01-13 19:48 ` Garima Singh 2019-12-20 22:05 ` [PATCH 3/9] commit-graph: use MAX_NUM_CHUNKS Garima Singh via GitGitGadget 2020-01-07 12:19 ` Jakub Narebski 2019-12-20 22:05 ` [PATCH 4/9] commit-graph: document bloom filter format Garima Singh via GitGitGadget 2020-01-07 14:46 ` Jakub Narebski 2019-12-20 22:05 ` [PATCH 5/9] commit-graph: write changed path bloom filters to commit-graph file Garima Singh via GitGitGadget 2020-01-07 16:01 ` Jakub Narebski 2020-01-14 15:14 ` Garima Singh 2019-12-20 22:05 ` [PATCH 6/9] commit-graph: test commit-graph write --changed-paths Garima Singh via GitGitGadget 2020-01-08 0:32 ` Jakub Narebski 2019-12-20 22:05 ` [PATCH 7/9] commit-graph: reuse existing bloom filters during write Garima Singh via GitGitGadget 2020-01-09 19:12 ` Jakub Narebski 2019-12-20 22:05 ` [PATCH 8/9] revision.c: use bloom filters to speed up path based revision walks Garima Singh via GitGitGadget 2020-01-11 0:27 ` Jakub Narebski 2020-01-15 0:08 ` Garima Singh 2019-12-20 22:05 ` [PATCH 9/9] commit-graph: add GIT_TEST_COMMIT_GRAPH_BLOOM_FILTERS test flag Garima Singh via GitGitGadget 2020-01-11 19:56 ` Jakub Narebski 2020-01-15 0:55 ` Garima Singh 2019-12-20 22:14 ` [PATCH 0/9] [RFC] Changed Paths Bloom Filters Junio C Hamano 2019-12-22 9:26 ` Christian Couder 2019-12-22 9:38 ` Jeff King 2020-01-01 12:04 ` Jakub Narebski 2019-12-22 9:30 ` Jeff King 2019-12-22 9:32 ` [PATCH 1/3] commit-graph: examine changed-path objects in pack order Jeff King 2019-12-27 14:51 ` Derrick Stolee 2019-12-29 6:12 ` Jeff King 2019-12-29 6:28 ` Jeff King 2019-12-30 14:37 ` Derrick Stolee 2019-12-30 14:51 ` Derrick Stolee 2019-12-22 9:32 ` [PATCH 2/3] commit-graph: free large diffs, too Jeff King 2019-12-27 14:52 ` Derrick Stolee 2019-12-22 9:32 ` [PATCH 3/3] commit-graph: stop using full rev_info for diffs Jeff King 2019-12-27 14:53 ` Derrick Stolee 2019-12-26 14:21 ` [PATCH 0/9] [RFC] Changed Paths Bloom Filters Derrick Stolee 2019-12-29 6:03 ` Jeff King 2019-12-27 16:11 ` Derrick Stolee 2019-12-29 6:24 ` Jeff King 2019-12-30 16:04 ` Derrick Stolee 2019-12-30 17:02 ` Junio C Hamano 2019-12-31 16:45 ` Jakub Narebski 2020-01-13 16:54 ` Garima Singh 2020-01-20 13:48 ` Jakub Narebski 2020-01-21 16:14 ` Garima Singh 2020-02-02 18:43 ` Jakub Narebski 2020-01-21 23:40 ` Emily Shaffer 2020-01-27 18:24 ` Garima Singh 2020-02-01 23:32 ` Jakub Narebski 2020-02-05 22:56 ` [PATCH v2 00/11] " Garima Singh via GitGitGadget 2020-02-05 22:56 ` [PATCH v2 01/11] commit-graph: use MAX_NUM_CHUNKS Garima Singh via GitGitGadget 2020-02-09 12:39 ` Jakub Narebski 2020-02-05 22:56 ` [PATCH v2 02/11] bloom: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget 2020-02-15 17:17 ` Jakub Narebski 2020-02-16 16:49 ` Jakub Narebski 2020-02-22 0:32 ` Garima Singh 2020-02-23 13:38 ` Jakub Narebski 2020-02-24 17:34 ` Garima Singh 2020-02-24 18:20 ` Jakub Narebski 2020-02-05 22:56 ` [PATCH v2 03/11] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget 2020-02-17 0:00 ` Jakub Narebski 2020-02-22 0:37 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 04/11] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget 2020-02-17 21:56 ` Jakub Narebski 2020-02-22 0:55 ` Garima Singh 2020-02-23 17:34 ` Jakub Narebski 2020-02-05 22:56 ` [PATCH v2 05/11] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget 2020-02-18 17:59 ` Jakub Narebski 2020-02-24 18:29 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 06/11] commit-graph: examine commits by generation number Derrick Stolee via GitGitGadget 2020-02-19 0:32 ` Jakub Narebski 2020-02-24 20:45 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 07/11] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget 2020-02-19 15:13 ` Jakub Narebski 2020-02-24 21:14 ` Garima Singh 2020-02-25 11:40 ` Jakub Narebski 2020-02-25 15:58 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 08/11] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget 2020-02-20 18:48 ` Jakub Narebski 2020-02-24 21:45 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 09/11] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget 2020-02-20 20:28 ` Jakub Narebski 2020-02-24 21:51 ` Garima Singh 2020-02-25 12:10 ` Jakub Narebski 2020-02-20 22:10 ` Bryan Turner 2020-02-22 1:44 ` Garima Singh 2020-02-05 22:56 ` [PATCH v2 10/11] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget 2020-02-21 17:31 ` Jakub Narebski 2020-02-21 22:45 ` Jakub Narebski 2020-02-05 22:56 ` [PATCH v2 11/11] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget 2020-02-22 0:11 ` Jakub Narebski 2020-02-07 13:52 ` [PATCH v2 00/11] Changed Paths Bloom Filters SZEDER Gábor 2020-02-07 15:09 ` Garima Singh 2020-02-07 15:36 ` Derrick Stolee 2020-02-07 16:15 ` SZEDER Gábor 2020-02-07 16:33 ` Derrick Stolee 2020-02-11 19:08 ` Garima Singh 2020-02-08 23:04 ` Jakub Narebski 2020-02-21 17:41 ` Garima Singh 2020-03-29 18:36 ` Junio C Hamano 2020-03-30 0:31 ` [PATCH v3 00/16] " Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 01/16] commit-graph: define and use MAX_NUM_CHUNKS Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 02/16] bloom.c: add the murmur3 hash implementation Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 03/16] bloom.c: introduce core Bloom filter constructs Garima Singh via GitGitGadget 2020-03-30 0:31 ` Garima Singh via GitGitGadget [this message] 2020-03-30 0:31 ` [PATCH v3 05/16] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 06/16] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 07/16] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 08/16] commit-graph: examine commits by generation number Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 09/16] diff: skip batch object download when possible Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 10/16] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 11/16] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 12/16] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 13/16] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 14/16] revision.c: add trace2 stats around Bloom filter usage Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 15/16] t4216: add end to end tests for git log with Bloom filters Garima Singh via GitGitGadget 2020-03-30 0:31 ` [PATCH v3 16/16] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 00/15] Changed Paths Bloom Filters Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 01/15] commit-graph: define and use MAX_NUM_CHUNKS Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 02/15] bloom.c: add the murmur3 hash implementation Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 03/15] bloom.c: introduce core Bloom filter constructs Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 04/15] bloom.c: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget 2020-06-27 15:53 ` SZEDER Gábor 2020-04-06 16:59 ` [PATCH v4 05/15] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget 2020-08-04 14:47 ` SZEDER Gábor 2020-08-04 16:25 ` Derrick Stolee 2020-08-04 17:00 ` SZEDER Gábor 2020-08-04 17:31 ` Derrick Stolee 2020-08-05 17:08 ` Derrick Stolee 2020-04-06 16:59 ` [PATCH v4 06/15] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 07/15] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 08/15] commit-graph: examine commits by generation number Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 09/15] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget 2020-05-29 8:57 ` SZEDER Gábor 2020-05-29 13:35 ` Derrick Stolee 2020-05-31 17:23 ` SZEDER Gábor 2020-07-09 17:00 ` [PATCH] commit-graph: fix "Writing out commit graph" progress counter SZEDER Gábor 2020-07-09 18:01 ` Derrick Stolee 2020-07-09 18:20 ` Derrick Stolee 2020-04-06 16:59 ` [PATCH v4 10/15] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget 2020-06-19 14:02 ` SZEDER Gábor 2020-06-19 19:28 ` Junio C Hamano 2020-07-27 21:33 ` SZEDER Gábor 2020-04-06 16:59 ` [PATCH v4 11/15] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget 2020-06-07 22:21 ` SZEDER Gábor 2020-04-06 16:59 ` [PATCH v4 12/15] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget 2020-06-26 6:34 ` SZEDER Gábor 2020-04-06 16:59 ` [PATCH v4 13/15] revision.c: add trace2 stats around Bloom filter usage Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 14/15] t4216: add end to end tests for git log with Bloom filters Garima Singh via GitGitGadget 2020-04-06 16:59 ` [PATCH v4 15/15] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget 2020-04-08 15:51 ` [PATCH v4 00/15] Changed Paths Bloom Filters Derrick Stolee 2020-04-08 19:21 ` Junio C Hamano 2020-04-08 20:05 ` Jakub Narębski 2020-04-12 20:34 ` Taylor Blau 2020-03-05 19:49 ` [PATCH 0/9] [RFC] " Garima Singh
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style List information: http://vger.kernel.org/majordomo-info.html * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=8304c2975207ee847c6709abd71efee918fc4142.1585528298.git.gitgitgadget@gmail.com \ --to=gitgitgadget@gmail.com \ --cc=garima.singh@microsoft.com \ --cc=git@vger.kernel.org \ --cc=jonathantanmy@google.com \ --cc=stolee@gmail.com \ --cc=szeder.dev@gmail.com \ --subject='Re: [PATCH v3 04/16] bloom.c: core Bloom filter implementation for changed paths.' \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Code repositories for project(s) associated with this inbox: https://80x24.org/mirrors/git.git This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).