Git Mailing List Archive on lore.kernel.org
 help / color / Atom feed
From: Jonathan Tan <jonathantanmy@google.com>
To: git@vger.kernel.org
Cc: Jonathan Tan <jonathantanmy@google.com>,
	peff@peff.net, stolee@gmail.com, avarab@gmail.com,
	szeder.dev@gmail.com
Subject: [PATCH 1/2] One filter per commit
Date: Wed, 10 Oct 2018 18:21:20 -0700
Message-ID: <ebf0a811be047e9fd24b61fea3c4a164b3d18dc0.1539219248.git.jonathantanmy@google.com> (raw)
In-Reply-To: <cover.1539219248.git.jonathantanmy@google.com>

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 bloom-filter.c | 31 ++++++++++++++++++-------------
 bloom-filter.h | 12 ++++--------
 commit-graph.c | 26 ++++++++++++--------------
 revision.c     |  9 +++------
 4 files changed, 37 insertions(+), 41 deletions(-)

diff --git a/bloom-filter.c b/bloom-filter.c
index 7dce0e35fa..39b453908f 100644
--- a/bloom-filter.c
+++ b/bloom-filter.c
@@ -1,14 +1,17 @@
 #include "cache.h"
 #include "bloom-filter.h"
 
-void bloom_filter_init(struct bloom_filter *bf, uint32_t bit_size)
+void bloom_filter_init(struct bloom_filter *bf, uint32_t commit_nr, uint32_t bit_size)
 {
 	if (bit_size % CHAR_BIT)
 		BUG("invalid size for bloom filter");
+	if (bit_size > 1024)
+		BUG("aborting: the bit size is per commit, not for the whole filter");
 
 	bf->nr_entries = 0;
+	bf->commit_nr = commit_nr;
 	bf->bit_size = bit_size;
-	bf->bits = xmalloc(bit_size / CHAR_BIT);
+	bf->bits = xcalloc(1, commit_nr * bit_size / CHAR_BIT);
 }
 
 void bloom_filter_free(struct bloom_filter *bf)
@@ -19,24 +22,24 @@ void bloom_filter_free(struct bloom_filter *bf)
 }
 
 
-void bloom_filter_set_bits(struct bloom_filter *bf, const uint32_t *offsets,
+static void bloom_filter_set_bits(struct bloom_filter *bf, uint32_t graph_pos, const uint32_t *offsets,
 			   int nr_offsets, int nr_entries)
 {
 	int i;
 	for (i = 0; i < nr_offsets; i++) {
-		uint32_t byte_offset = (offsets[i] % bf->bit_size) / CHAR_BIT;
+		uint32_t byte_offset = (offsets[i] % bf->bit_size + graph_pos * bf->bit_size) / CHAR_BIT;
 		unsigned char mask = 1 << offsets[i] % CHAR_BIT;
 		bf->bits[byte_offset] |= mask;
 	}
 	bf->nr_entries += nr_entries;
 }
 
-int bloom_filter_check_bits(struct bloom_filter *bf, const uint32_t *offsets,
+static int bloom_filter_check_bits(struct bloom_filter *bf, uint32_t graph_pos, const uint32_t *offsets,
 			    int nr)
 {
 	int i;
 	for (i = 0; i < nr; i++) {
-		uint32_t byte_offset = (offsets[i] % bf->bit_size) / CHAR_BIT;
+		uint32_t byte_offset = (offsets[i] % bf->bit_size + graph_pos * bf->bit_size) / CHAR_BIT;
 		unsigned char mask = 1 << offsets[i] % CHAR_BIT;
 		if (!(bf->bits[byte_offset] & mask))
 			return 0;
@@ -45,19 +48,19 @@ int bloom_filter_check_bits(struct bloom_filter *bf, const uint32_t *offsets,
 }
 
 
-void bloom_filter_add_hash(struct bloom_filter *bf, const unsigned char *hash)
+void bloom_filter_add_hash(struct bloom_filter *bf, uint32_t graph_pos, const unsigned char *hash)
 {
 	uint32_t offsets[GIT_MAX_RAWSZ / sizeof(uint32_t)];
 	hashcpy((unsigned char*)offsets, hash);
-	bloom_filter_set_bits(bf, offsets,
+	bloom_filter_set_bits(bf, graph_pos, offsets,
 			     the_hash_algo->rawsz / sizeof(*offsets), 1);
 }
 
-int bloom_filter_check_hash(struct bloom_filter *bf, const unsigned char *hash)
+int bloom_filter_check_hash(struct bloom_filter *bf, uint32_t graph_pos, const unsigned char *hash)
 {
 	uint32_t offsets[GIT_MAX_RAWSZ / sizeof(uint32_t)];
 	hashcpy((unsigned char*)offsets, hash);
-	return bloom_filter_check_bits(bf, offsets,
+	return bloom_filter_check_bits(bf, graph_pos, offsets,
 			the_hash_algo->rawsz / sizeof(*offsets));
 }
 
@@ -80,11 +83,12 @@ int bloom_filter_load(struct bloom_filter *bf)
 		return -1;
 
 	read_in_full(fd, &bf->nr_entries, sizeof(bf->nr_entries));
+	read_in_full(fd, &bf->commit_nr, sizeof(bf->commit_nr));
 	read_in_full(fd, &bf->bit_size, sizeof(bf->bit_size));
 	if (bf->bit_size % CHAR_BIT)
 		BUG("invalid size for bloom filter");
-	bf->bits = xmalloc(bf->bit_size / CHAR_BIT);
-	read_in_full(fd, bf->bits, bf->bit_size / CHAR_BIT);
+	bf->bits = xmalloc(bf->commit_nr * bf->bit_size / CHAR_BIT);
+	read_in_full(fd, bf->bits, bf->commit_nr * bf->bit_size / CHAR_BIT);
 
 	close(fd);
 
@@ -96,8 +100,9 @@ void bloom_filter_write(struct bloom_filter *bf)
 	int fd = xopen(git_path_bloom(), O_WRONLY | O_CREAT | O_TRUNC, 0666);
 
 	write_in_full(fd, &bf->nr_entries, sizeof(bf->nr_entries));
+	write_in_full(fd, &bf->commit_nr, sizeof(bf->commit_nr));
 	write_in_full(fd, &bf->bit_size, sizeof(bf->bit_size));
-	write_in_full(fd, bf->bits, bf->bit_size / CHAR_BIT);
+	write_in_full(fd, bf->bits, bf->commit_nr * bf->bit_size / CHAR_BIT);
 
 	close(fd);
 }
diff --git a/bloom-filter.h b/bloom-filter.h
index 94d0af1708..607649b8db 100644
--- a/bloom-filter.h
+++ b/bloom-filter.h
@@ -5,30 +5,26 @@
 
 struct bloom_filter {
 	uint32_t nr_entries;
+	uint32_t commit_nr;
 	uint32_t bit_size;
 	unsigned char *bits;
 };
 
 
-void bloom_filter_init(struct bloom_filter *bf, uint32_t bit_size);
+void bloom_filter_init(struct bloom_filter *bf, uint32_t commit_nr, uint32_t bit_size);
 void bloom_filter_free(struct bloom_filter *bf);
 
-void bloom_filter_set_bits(struct bloom_filter *bf, const uint32_t *offsets,
-			   int nr_offsets, int nr_enries);
-int bloom_filter_check_bits(struct bloom_filter *bf, const uint32_t *offsets,
-			    int nr);
-
 /*
  * Turns the given (SHA1) hash into 5 unsigned ints, and sets the bits at
  * those positions (modulo the bitmap's size) in the Bloom filter.
  */
-void bloom_filter_add_hash(struct bloom_filter *bf, const unsigned char *hash);
+void bloom_filter_add_hash(struct bloom_filter *bf, uint32_t graph_pos, const unsigned char *hash);
 /*
  * Turns the given (SHA1) hash into 5 unsigned ints, and checks the bits at
  * those positions (modulo the bitmap's size) in the Bloom filter.
  * Returns 1 if all those bits are set, 0 otherwise.
  */
-int bloom_filter_check_hash(struct bloom_filter *bf, const unsigned char *hash);
+int bloom_filter_check_hash(struct bloom_filter *bf, uint32_t graph_pos, const unsigned char *hash);
 
 void hashxor(const unsigned char *hash1, const unsigned char *hash2,
 	     unsigned char *out);
diff --git a/commit-graph.c b/commit-graph.c
index f415d3b41f..90b0b3df90 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -715,13 +715,11 @@ static int add_ref_to_list(const char *refname,
 static void add_changes_to_bloom_filter(struct bloom_filter *bf,
 					struct commit *parent,
 					struct commit *commit,
+					int index,
 					struct diff_options *diffopt)
 {
-	unsigned char p_c_hash[GIT_MAX_RAWSZ];
 	int i;
 
-	hashxor(parent->object.oid.hash, commit->object.oid.hash, p_c_hash);
-
 	diff_tree_oid(&parent->object.oid, &commit->object.oid, "", diffopt);
 	diffcore_std(diffopt);
 
@@ -756,8 +754,8 @@ static void add_changes_to_bloom_filter(struct bloom_filter *bf,
 			the_hash_algo->update_fn(&ctx, path, p - path);
 			the_hash_algo->final_fn(name_hash, &ctx);
 
-			hashxor(name_hash, p_c_hash, hash);
-			bloom_filter_add_hash(bf, hash);
+			hashxor(name_hash, parent->object.oid.hash, hash);
+			bloom_filter_add_hash(bf, index, hash);
 		} while (*p);
 
 		diff_free_filepair(diff_queued_diff.queue[i]);
@@ -768,11 +766,10 @@ static void add_changes_to_bloom_filter(struct bloom_filter *bf,
 }
 
 static void fill_bloom_filter(struct bloom_filter *bf,
-				    struct progress *progress)
+				    struct progress *progress, struct commit **commits, int commit_nr)
 {
 	struct rev_info revs;
 	const char *revs_argv[] = {NULL, "--all", NULL};
-	struct commit *commit;
 	int i = 0;
 
 	/* We (re-)create the bloom filter from scratch every time for now. */
@@ -783,18 +780,19 @@ static void fill_bloom_filter(struct bloom_filter *bf,
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed while preparing bloom filter");
 
-	while ((commit = get_revision(&revs))) {
+	for (i = 0; i < commit_nr; i++) {
+		struct commit *commit = commits[i];
 		struct commit_list *parent;
 
 		for (parent = commit->parents; parent; parent = parent->next)
-			add_changes_to_bloom_filter(bf, parent->item, commit,
+			add_changes_to_bloom_filter(bf, parent->item, commit, i,
 						    &revs.diffopt);
 
-		display_progress(progress, ++i);
+		display_progress(progress, i);
 	}
 }
 
-static void write_bloom_filter(int report_progress, int commit_nr)
+static void write_bloom_filter(int report_progress, struct commit **commits, int commit_nr)
 {
 	struct bloom_filter bf;
 	struct progress *progress = NULL;
@@ -809,13 +807,13 @@ static void write_bloom_filter(int report_progress, int commit_nr)
 	if (*end)
 		die("GIT_USE_POC_BLOOM_FILTER must specify the number of bits in the bloom filter (multiple of 8, n < 2^32)");
 
-	bloom_filter_init(&bf, bitsize);
+	bloom_filter_init(&bf, commit_nr, bitsize);
 
 	if (report_progress)
 		progress = start_progress(_("Computing bloom filter"),
 					  commit_nr);
 
-	fill_bloom_filter(&bf, progress);
+	fill_bloom_filter(&bf, progress, commits, commit_nr);
 
 	bloom_filter_write(&bf);
 	bloom_filter_free(&bf);
@@ -1030,7 +1028,7 @@ void write_commit_graph(const char *obj_dir,
 	finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
 	commit_lock_file(&lk);
 
-	write_bloom_filter(report_progress, commits.nr);
+	write_bloom_filter(report_progress, commits.list, commits.nr);
 
 	free(graph_name);
 	free(commits.list);
diff --git a/revision.c b/revision.c
index d5ba2b1598..c84a997928 100644
--- a/revision.c
+++ b/revision.c
@@ -490,7 +490,6 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 						 struct commit *parent,
 						 struct commit *commit)
 {
-	unsigned char p_c_hash[GIT_MAX_RAWSZ];
 	int i;
 
 	if (!bf.bits)
@@ -509,17 +508,15 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 	 */
 	if (!the_repository->objects->commit_graph)
 		return -1;
-	if (commit->generation == GENERATION_NUMBER_INFINITY)
+	if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
 		return -1;
 
-	hashxor(parent->object.oid.hash, commit->object.oid.hash, p_c_hash);
-
 	for (i = 0; i < revs->pruning.pathspec.nr; i++) {
 		struct pathspec_item *pi = &revs->pruning.pathspec.items[i];
 		unsigned char hash[GIT_MAX_RAWSZ];
 
-		hashxor(pi->name_hash, p_c_hash, hash);
-		if (bloom_filter_check_hash(&bf, hash)) {
+		hashxor(pi->name_hash, parent->object.oid.hash, hash);
+		if (bloom_filter_check_hash(&bf, commit->graph_pos, hash)) {
 			/*
 			 * At least one of the interesting pathspecs differs,
 			 * so we can return early and let the diff machinery
-- 
2.19.0.271.gfe8321ec05.dirty


  reply index

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-03 13:23 We should add a "git gc --auto" after "git clone" due to commit graph Ævar Arnfjörð Bjarmason
2018-10-03 13:36 ` SZEDER Gábor
2018-10-03 13:42   ` Derrick Stolee
2018-10-03 14:18     ` Ævar Arnfjörð Bjarmason
2018-10-03 14:01   ` Ævar Arnfjörð Bjarmason
2018-10-03 14:17     ` SZEDER Gábor
2018-10-03 14:22       ` Ævar Arnfjörð Bjarmason
2018-10-03 14:53         ` SZEDER Gábor
2018-10-03 15:19           ` Ævar Arnfjörð Bjarmason
2018-10-03 16:59             ` SZEDER Gábor
2018-10-05  6:09               ` Junio C Hamano
2018-10-10 22:07                 ` SZEDER Gábor
2018-10-10 23:01                   ` Ævar Arnfjörð Bjarmason
2018-10-03 19:08           ` Stefan Beller
2018-10-03 19:21             ` Jeff King
2018-10-03 20:35               ` Ævar Arnfjörð Bjarmason
2018-10-03 17:47         ` Stefan Beller
2018-10-03 18:47           ` Ævar Arnfjörð Bjarmason
2018-10-03 18:51             ` Jeff King
2018-10-03 18:59               ` Derrick Stolee
2018-10-03 19:18                 ` Jeff King
2018-10-08 16:41                   ` SZEDER Gábor
2018-10-08 16:57                     ` Derrick Stolee
2018-10-08 18:10                       ` SZEDER Gábor
2018-10-08 18:29                         ` Derrick Stolee
2018-10-09  3:08                           ` Jeff King
2018-10-09 13:48                             ` Bloom Filters (was Re: We should add a "git gc --auto" after "git clone" due to commit graph) Derrick Stolee
2018-10-09 18:45                               ` Ævar Arnfjörð Bjarmason
2018-10-09 18:46                               ` Jeff King
2018-10-09 19:03                                 ` Derrick Stolee
2018-10-09 21:14                                   ` Jeff King
2018-10-09 23:12                                     ` Bloom Filters Jeff King
2018-10-09 23:13                                       ` [PoC -- do not apply 1/3] initial tree-bitmap proof of concept Jeff King
2018-10-09 23:14                                       ` [PoC -- do not apply 2/3] test-tree-bitmap: add "dump" mode Jeff King
2018-10-10  0:48                                         ` Junio C Hamano
2018-10-11  3:13                                           ` Jeff King
2018-10-09 23:14                                       ` [PoC -- do not apply 3/3] test-tree-bitmap: replace ewah with custom rle encoding Jeff King
2018-10-10  0:58                                         ` Junio C Hamano
2018-10-11  3:20                                           ` Jeff King
2018-10-11 12:33                                       ` Bloom Filters Derrick Stolee
2018-10-11 13:43                                         ` Jeff King
2018-10-09 21:30                             ` We should add a "git gc --auto" after "git clone" due to commit graph SZEDER Gábor
2018-10-09 19:34                       ` [PATCH 0/4] Bloom filter experiment SZEDER Gábor
2018-10-09 19:34                         ` [PATCH 1/4] Add a (very) barebones Bloom filter implementation SZEDER Gábor
2018-10-09 19:34                         ` [PATCH 2/4] commit-graph: write a Bloom filter containing changed paths for each commit SZEDER Gábor
2018-10-09 21:06                           ` Jeff King
2018-10-09 21:37                             ` SZEDER Gábor
2018-10-09 19:34                         ` [PATCH 3/4] revision.c: use the Bloom filter to speed up path-limited revision walks SZEDER Gábor
2018-10-09 19:34                         ` [PATCH 4/4] revision.c: add GIT_TRACE_BLOOM_FILTER for a bit of statistics SZEDER Gábor
2018-10-09 19:47                         ` [PATCH 0/4] Bloom filter experiment Derrick Stolee
2018-10-11  1:21                         ` [PATCH 0/2] Per-commit filter proof of concept Jonathan Tan
2018-10-11  1:21                           ` Jonathan Tan [this message]
2018-10-11 12:49                             ` [PATCH 1/2] One filter per commit Derrick Stolee
2018-10-11 19:11                               ` [PATCH] Per-commit and per-parent filters for 2 parents Jonathan Tan
2018-10-11  1:21                           ` [PATCH 2/2] Only make bloom filter for first parent Jonathan Tan
2018-10-11  7:37                           ` [PATCH 0/2] Per-commit filter proof of concept Ævar Arnfjörð Bjarmason
2018-10-15 14:39                         ` [PATCH 0/4] Bloom filter experiment Derrick Stolee
2018-10-16  4:45                           ` Junio C Hamano
2018-10-16 11:13                             ` Derrick Stolee
2018-10-16 12:57                               ` Ævar Arnfjörð Bjarmason
2018-10-16 13:03                                 ` Derrick Stolee
2018-10-18  2:00                                 ` Junio C Hamano
2018-10-16 23:41                           ` Jonathan Tan
2018-10-08 23:02                     ` We should add a "git gc --auto" after "git clone" due to commit graph Junio C Hamano
2018-10-03 14:32     ` Duy Nguyen
2018-10-03 16:45 ` Duy Nguyen
2018-10-04 21:42 ` [RFC PATCH] " Ævar Arnfjörð Bjarmason
2018-10-05 12:05   ` Derrick Stolee
2018-10-05 13:05     ` Ævar Arnfjörð Bjarmason
2018-10-05 13:45       ` Derrick Stolee
2018-10-05 14:04         ` Ævar Arnfjörð Bjarmason
2018-10-05 19:21         ` Jeff King
2018-10-05 19:41           ` Derrick Stolee
2018-10-05 19:47             ` Jeff King
2018-10-05 20:00               ` Derrick Stolee
2018-10-05 20:02                 ` Jeff King
2018-10-05 20:01               ` Ævar Arnfjörð Bjarmason
2018-10-05 20:09                 ` Jeff King

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

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ebf0a811be047e9fd24b61fea3c4a164b3d18dc0.1539219248.git.jonathantanmy@google.com \
    --to=jonathantanmy@google.com \
    --cc=avarab@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=peff@peff.net \
    --cc=stolee@gmail.com \
    --cc=szeder.dev@gmail.com \
    /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

Git Mailing List Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/git/0 git/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 git git/ https://lore.kernel.org/git \
		git@vger.kernel.org
	public-inbox-index git

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.git


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git