git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Garima Singh via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: stolee@gmail.com, szeder.dev@gmail.com, jonathantanmy@google.com,
	jeffhost@microsoft.com, me@ttaylorr.com, peff@peff.net,
	Junio C Hamano <gitster@pobox.com>,
	Garima Singh <garima.singh@microsoft.com>
Subject: [PATCH 5/9] commit-graph: write changed path bloom filters to commit-graph file.
Date: Fri, 20 Dec 2019 22:05:16 +0000	[thread overview]
Message-ID: <7648021072ca11153ac65c90f0ebed5973f20e1a.1576879520.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.497.git.1576879520.gitgitgadget@gmail.com>

From: Garima Singh <garima.singh@microsoft.com>

Write bloom filters to the commit-graph using the format described in
Documentation/technical/commit-graph-format.txt

Helped-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Garima Singh <garima.singh@microsoft.com>
---
 commit-graph.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++++-
 commit-graph.h |  5 ++++
 2 files changed, 85 insertions(+), 1 deletion(-)

diff --git a/commit-graph.c b/commit-graph.c
index 8c4941eeaa..def2ade166 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -24,7 +24,9 @@
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 5
+#define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
+#define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
+#define MAX_NUM_CHUNKS 7
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -282,6 +284,32 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 				chunk_repeated = 1;
 			else
 				graph->chunk_base_graphs = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMINDEXES:
+			if (graph->chunk_bloom_indexes)
+				chunk_repeated = 1;
+			else
+				graph->chunk_bloom_indexes = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMDATA:
+			if (graph->chunk_bloom_data)
+				chunk_repeated = 1;
+			else {
+				uint32_t hash_version;
+				graph->chunk_bloom_data = data + chunk_offset;
+				hash_version = get_be32(data + chunk_offset);
+
+				if (hash_version != 1)
+					break;
+
+				graph->settings = xmalloc(sizeof(struct bloom_filter_settings));
+				graph->settings->hash_version = hash_version;
+				graph->settings->num_hashes = get_be32(data + chunk_offset + 4);
+				graph->settings->bits_per_entry = get_be32(data + chunk_offset + 8);
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
@@ -996,6 +1024,39 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 	}
 }
 
+static void write_graph_chunk_bloom_indexes(struct hashfile *f,
+					    struct write_commit_graph_context *ctx)
+{
+	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);
+		cur_pos += filter->len;
+		hashwrite_be32(f, cur_pos);
+		list++;
+	}
+}
+
+static void write_graph_chunk_bloom_data(struct hashfile *f,
+					 struct write_commit_graph_context *ctx,
+					 struct bloom_filter_settings *settings)
+{
+	struct commit **first = ctx->commits.list;
+	struct commit **last = ctx->commits.list + ctx->commits.nr;
+
+	hashwrite_be32(f, settings->hash_version);
+	hashwrite_be32(f, settings->num_hashes);
+	hashwrite_be32(f, settings->bits_per_entry);
+
+	while (first < last) {
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *first);
+		hashwrite(f, filter->data, filter->len * sizeof(uint64_t));
+		first++;
+	}
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1388,6 +1449,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	struct strbuf progress_title = STRBUF_INIT;
 	int num_chunks = 3;
 	struct object_id file_hash;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -1432,6 +1494,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
 		num_chunks++;
 	}
+	if (ctx->bloom) {
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMINDEXES;
+		num_chunks++;
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMDATA;
+		num_chunks++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
 		num_chunks++;
@@ -1450,6 +1518,13 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 						4 * ctx->num_extra_edges;
 		num_chunks++;
 	}
+	if (ctx->bloom) {
+		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + sizeof(uint32_t) * ctx->commits.nr;
+		num_chunks++;
+
+		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] + sizeof(uint32_t) * 3 + ctx->total_bloom_filter_size;
+		num_chunks++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
 						hashsz * (ctx->num_commit_graphs_after - 1);
@@ -1487,6 +1562,10 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	write_graph_chunk_data(f, hashsz, ctx);
 	if (ctx->num_extra_edges)
 		write_graph_chunk_extra_edges(f, ctx);
+	if (ctx->bloom) {
+		write_graph_chunk_bloom_indexes(f, ctx);
+		write_graph_chunk_bloom_data(f, ctx, &bloom_settings);
+	}
 	if (ctx->num_commit_graphs_after > 1 &&
 	    write_graph_chunk_base(f, ctx)) {
 		return -1;
diff --git a/commit-graph.h b/commit-graph.h
index 952a4b83be..2202ad91ae 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -10,6 +10,7 @@
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD "GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD"
 
 struct commit;
+struct bloom_filter_settings;
 
 char *get_commit_graph_filename(const char *obj_dir);
 int open_commit_graph(const char *graph_file, int *fd, struct stat *st);
@@ -58,6 +59,10 @@ struct commit_graph {
 	const unsigned char *chunk_commit_data;
 	const unsigned char *chunk_extra_edges;
 	const unsigned char *chunk_base_graphs;
+	const unsigned char *chunk_bloom_indexes;
+	const unsigned char *chunk_bloom_data;
+
+	struct bloom_filter_settings *settings;
 };
 
 struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st);
-- 
gitgitgadget


  parent reply	other threads:[~2019-12-20 22:05 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 ` Garima Singh via GitGitGadget [this message]
2020-01-07 16:01   ` [PATCH 5/9] commit-graph: write changed path bloom filters to commit-graph file 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     ` [PATCH v3 04/16] bloom.c: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget
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=7648021072ca11153ac65c90f0ebed5973f20e1a.1576879520.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=garima.singh@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jeffhost@microsoft.com \
    --cc=jonathantanmy@google.com \
    --cc=me@ttaylorr.com \
    --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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public 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).