[18/34] commit-graph: write "empty" Modified Path Bloom Filter Index chunk

Commit Message

SZEDER Gábor May 29, 2020, 8:50 a.m. UTC

Write the Modifed Path Bloom Filter Index chunk if the
'core.modifiedPathBloomFilters' configuration variable is set.  For
now store only "no Bloom filter for this commit" entries.

The format of the various modified path Bloom filter-related chunks
are not (yet) compatible with split commit-graph files, so ignore the
config setting and don't write modifed path Bloom filters with
'--split'.
---
 Documentation/config/core.txt |  6 ++++++
 commit-graph.c                | 40 +++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

Patch

diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt
index 9e440b160d..820f7d3bcf 100644
--- a/Documentation/config/core.txt
+++ b/Documentation/config/core.txt
@@ -588,6 +588,12 @@  core.commitGraph::
 	to parse the graph structure of commits. Defaults to true. See
 	linkgit:git-commit-graph[1] for more information.
 
+core.modifiedPathBloomFilters::
+	EXPERIMENTAL!!
+	If true, then Git will store and use Bloom filters in the
+	commit-graph file to speed up pathspec-limited revision walks.
+	Defaults to false.
+
 core.useReplaceRefs::
 	If set to `false`, behave as if the `--no-replace-objects`
 	option was given on the command line. See linkgit:git[1] and
diff --git a/commit-graph.c b/commit-graph.c
index e3adffd58b..28f147a418 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -21,6 +21,7 @@ 
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
+#define GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_INDEX 0x4d504249 /* "MPBI" */
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -33,6 +34,10 @@ 
 
 #define GRAPH_LAST_EDGE 0x80000000
 
+#define GRAPH_MODIFIED_PATH_BLOOM_FILTER_NONE 0xffffffffffffffff
+
+#define GRAPH_MODIFIED_PATH_BLOOM_FILTER_DEFAULT_NR_HASHES 7
+
 #define GRAPH_HEADER_SIZE 8
 #define GRAPH_FANOUT_SIZE (4 * 256)
 #define GRAPH_CHUNKLOOKUP_WIDTH 12
@@ -791,6 +796,11 @@  struct write_commit_graph_context {
 		 check_oids:1;
 
 	const struct split_commit_graph_opts *split_opts;
+
+	struct modified_path_bloom_filter_context {
+		unsigned use_modified_path_bloom_filters:1;
+		unsigned int num_hashes;
+	} mpbfctx;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -990,6 +1000,20 @@  static int write_graph_chunk_extra_edges(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_modified_path_bloom_index(struct hashfile *f,
+		struct write_commit_graph_context *ctx)
+{
+	const uint64_t no_bloom_filter = GRAPH_MODIFIED_PATH_BLOOM_FILTER_NONE;
+	int i;
+
+	hashwrite(f, &ctx->mpbfctx.num_hashes, sizeof(uint8_t));
+	for (i = 0; i < ctx->commits.nr; i++) {
+		display_progress(ctx->progress, ++ctx->progress_cnt);
+		hashwrite(f, &no_bloom_filter, sizeof(no_bloom_filter));
+	}
+	return 0;
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1428,6 +1452,14 @@  static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		chunks[chunks_nr].write_fn = write_graph_chunk_extra_edges;
 		chunks_nr++;
 	}
+	if (ctx->mpbfctx.use_modified_path_bloom_filters) {
+		ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+		chunks[chunks_nr].id = GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_INDEX;
+		chunks[chunks_nr].size = sizeof(uint8_t) +
+					 ctx->commits.nr * sizeof(uint64_t);
+		chunks[chunks_nr].write_fn = write_graph_chunk_modified_path_bloom_index;
+		chunks_nr++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
 		chunks[chunks_nr].id = GRAPH_CHUNKID_BASE;
@@ -1824,6 +1856,14 @@  int write_commit_graph(const char *obj_dir,
 	ctx->check_oids = flags & COMMIT_GRAPH_WRITE_CHECK_OIDS ? 1 : 0;
 	ctx->split_opts = split_opts;
 
+	git_config_get_bool("core.modifiedPathBloomFilters", &res);
+	if (res && ctx->split) {
+		warning("not writing modified path Bloom filters with --split");
+	} else if (res) {
+		ctx->mpbfctx.use_modified_path_bloom_filters = 1;
+		ctx->mpbfctx.num_hashes = GRAPH_MODIFIED_PATH_BLOOM_FILTER_DEFAULT_NR_HASHES;
+	}
+
 	if (ctx->split) {
 		struct commit_graph *g;
 		prepare_commit_graph(ctx->r);