[PATCH 23/34] commit-graph: load and use the Modified Path Bloom Filters chunk

From

SZEDER Gábor <szeder.dev@gmail.com>

Date

May 29, 2020, 08:50 UTC

Message-ID

<20200529085038.26008-24-szeder.dev@gmail.com>

In-Reply-To

<20200529085038.26008-1-szeder.dev@gmail.com>

The table below compares the average runtime and memory usage of

  git rev-list HEAD -- "$path"

                  Average runtime            |       Max RSS
                 without     with   Speedup  |  without   with
  -------------------------------------------+-------------------------
  android-base   0.8780s   0.1742s    5.04x  |   387MB   227MB   -41.4%
  cmssw          0.3143s   0.0452s    6.95x  |   181MB    79MB   -56.4%
  cpython        0.7453s   0.0956s    7.80x  |   159MB    71MB   -55.4%
  elasticsearch  0.1492s   0.0191s    7.82x  |   134MB    53MB   -60.2%
  gcc            7.1852s   0.3584s   20.05x  |   297MB   231MB   -22.3%
  gecko-dev      4.6113s   0.6318s    7.30x  |   832MB   600MB   -27.9%
  git            0.6180s   0.0405s   15.26x  |   131MB    43MB   -67.2%
  glibc          0.5618s   0.0471s   11.93x  |   136MB    50MB   -63.3%
  go             0.4913s   0.0515s    9.53x  |   130MB    50MB   -61.5%
  jdk            0.0482s   0.0089s    5.42x  |    52MB    39MB   -25.0%
  linux          0.7043s   0.1129s    6.24x  |   438MB   270MB   -38.4%
  llvm-project   2.6844s   0.4873s    5.51x  |   384MB   282MB   -26.6%
  rails          0.2784s   0.0484s    5.75x  |    88MB    51MB   -42.1%
  rust           0.7757s   0.0619s   12.53x  |   345MB    89MB   -74.3%
  tensorflow     0.6258s   0.0642s    9.74x  |   233MB    85MB   -63.5%
  webkit         1.9137s   0.3332s    5.74x  |   941MB   480MB   -49.0%
---
 commit-graph.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
 commit-graph.h |  2 ++
 2 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 3210ec2f93..f9a21ecdfb 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -327,6 +327,15 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 			}
 			break;
 
+		case GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTERS:
+			if (graph->chunk_mpbf_filters)
+				chunk_repeated = 1;
+			else {
+				graph->chunk_mpbf_filters = data + chunk_offset;
+				graph->chunk_mpbf_filters_size = next_chunk_offset - chunk_offset;
+			}
+			break;
+
 		case GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_EXCLUDES:
 			if (graph->chunk_mpbf_excludes)
 				chunk_repeated = 1;
@@ -830,6 +839,7 @@ static int load_modified_path_bloom_filter_from_graph(
 		struct commit *parent, struct bloom_filter *bf)
 {
 	const uint8_t *bloom_index;
+	uint64_t offset;
 	int first_parent = 0;
 
 	if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
@@ -857,9 +867,39 @@ static int load_modified_path_bloom_filter_from_graph(
 		bf->nr_bits = GRAPH_MODIFIED_PATH_BLOOM_FILTER_EMBEDDED_NR_BITS;
 		bf->bits = (uint8_t*) bloom_index;
 		return 1;
+	} else if (bloom_index[0] & (1 << 6)) {
+		/*
+		 * Modified path Bloom filters for second..nth parents of
+		 * merge commits are not implemented yet.
+		 */
+		return 0;
+	} else {
+		if (!first_parent)
+			return 0;
+		offset = get_be64(bloom_index);
 	}
-	/* support for non-embedded Bloom filters is not implemented yet. */
-	return 0;
+
+	if (!graph->chunk_mpbf_filters)
+		BUG("commit %s refers to offset %lu of the Modified Path Bloom Filters chunk, but that chunk is missing",
+		    oid_to_hex(&commit->object.oid), offset);
+
+	if (offset + sizeof(uint32_t) >= graph->chunk_mpbf_filters_size)
+		BUG("commit %s refers to offset %lu of the Modified Path Bloom Filters chunk, but that's too large for chunk of size %lu bytes",
+		    oid_to_hex(&commit->object.oid), offset,
+		    graph->chunk_mpbf_filters_size);
+
+	bf->nr_bits = get_be32(graph->chunk_mpbf_filters + offset);
+	if (!bf->nr_bits)
+		BUG("commit %s has a modified path Bloom filter at offset %lu, which has zero size",
+		    oid_to_hex(&commit->object.oid), offset);
+	if (offset + sizeof(uint32_t) + bloom_filter_bytes(bf) > graph->chunk_mpbf_filters_size)
+		BUG("commit %s has a modified path Bloom filter of %u bits at offset %lu, which doesn't fit into a Modified Path Bloom Filters chunk of %lu bytes",
+		    oid_to_hex(&commit->object.oid), bf->nr_bits, offset,
+		    graph->chunk_mpbf_filters_size);
+	/* Casting away const-ness :( */
+	bf->bits = (uint8_t*)(graph->chunk_mpbf_filters + offset + sizeof(uint32_t));
+
+	return 1;
 }
 
 enum bloom_result check_modified_path_bloom_filter(struct repository *r,
diff --git a/commit-graph.h b/commit-graph.h
index 09dfc16932..cde0d7fa30 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -69,6 +69,8 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_mpbf_index;
 	uint64_t chunk_mpbf_index_size;
+	const unsigned char *chunk_mpbf_filters;
+	uint64_t chunk_mpbf_filters_size;
 	const unsigned char *chunk_mpbf_excludes;
 
 	uint8_t num_modified_path_bloom_hashes;

-- 
2.27.0.rc1.431.g5c813f95dc