commit-graph: compute Bloom filters for changed paths
Add new COMMIT_GRAPH_WRITE_CHANGED_PATHS flag that makes Git compute Bloom filters for the paths that changed between a commit and it's first parent, for each commit in the commit-graph. This computation is done on a commit-by-commit basis. We will write these Bloom filters to the commit-graph file, to store this data on disk, in the next change in this series. Helped-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Garima Singh committed
Mar 30, 2020 at 00:31 UTC
f97b9325f6d7ad2a28bfaf6fab3197d207fcb278
2 files changed
+33
-2
commit-graph.c
+31
-1
@@ -16,6 +16,7 @@
16
#include "hashmap.h"
17
#include "replace-object.h"
18
#include "progress.h"
19
+#include "bloom.h"
20
21
#define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */
22
#define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
@@ -789,9 +790,11 @@ struct write_commit_graph_context {
790
unsigned append:1,
791
report_progress:1,
792
split:1,
792
- check_oids:1;
793
+ check_oids:1,
794
+ changed_paths:1;
795
796
const struct split_commit_graph_opts *split_opts;
797
+ size_t total_bloom_filter_data_size;
798
};
799
800
static void write_graph_chunk_fanout(struct hashfile *f,
@@ -1134,6 +1137,28 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
1137
stop_progress(&ctx->progress);
1138
}
1139
1140
+static void compute_bloom_filters(struct write_commit_graph_context *ctx)
1141
+{
1142
+ int i;
1143
+ struct progress *progress = NULL;
1144
+
1145
+ init_bloom_filters();
1146
+
1147
+ if (ctx->report_progress)
1148
+ progress = start_delayed_progress(
1149
+ _("Computing commit changed paths Bloom filters"),
1150
+ ctx->commits.nr);
1151
+
1152
+ for (i = 0; i < ctx->commits.nr; i++) {
1153
+ struct commit *c = ctx->commits.list[i];
1154
+ struct bloom_filter *filter = get_bloom_filter(ctx->r, c);
1155
+ ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
1156
+ display_progress(progress, i + 1);
1157
+ }
1158
+
1159
+ stop_progress(&progress);
1160
+}
1161
+
1162
static int add_ref_to_list(const char *refname,
1163
const struct object_id *oid,
1164
int flags, void *cb_data)
@@ -1776,6 +1801,8 @@ int write_commit_graph(struct object_directory *odb,
1801
ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
1802
ctx->check_oids = flags & COMMIT_GRAPH_WRITE_CHECK_OIDS ? 1 : 0;
1803
ctx->split_opts = split_opts;
1804
+ ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0;
1805
+ ctx->total_bloom_filter_data_size = 0;
1806
1807
if (ctx->split) {
1808
struct commit_graph *g;
@@ -1870,6 +1897,9 @@ int write_commit_graph(struct object_directory *odb,
1897
1898
compute_generation_numbers(ctx);
1899
1900
+ if (ctx->changed_paths)
1901
+ compute_bloom_filters(ctx);
1902
+
1903
res = write_commit_graph_file(ctx);
1904
1905
if (ctx->split)
commit-graph.h
+2
-1
@@ -79,7 +79,8 @@ enum commit_graph_write_flags {
79
COMMIT_GRAPH_WRITE_PROGRESS = (1 << 1),
80
COMMIT_GRAPH_WRITE_SPLIT = (1 << 2),
81
/* Make sure that each OID in the input is a valid commit OID. */
82
- COMMIT_GRAPH_WRITE_CHECK_OIDS = (1 << 3)
82
+ COMMIT_GRAPH_WRITE_CHECK_OIDS = (1 << 3),
83
+ COMMIT_GRAPH_WRITE_BLOOM_FILTERS = (1 << 4),
84
};
85
86
struct split_commit_graph_opts {