commit-graph.c: store maximum changed paths
For now, we assume that there is a fixed constant describing the maximum number of changed paths we are willing to store in a Bloom filter. Prepare for that to (at least partially) not be the case by making it a member of the 'struct bloom_filter_settings'. This will be helpful in the subsequent patches by reducing the size of test cases that exercise storing too many changed paths, as well as preparing for an eventual future in which this value might change. This patch alone does not cause newly generated Bloom filters to use a custom upper-bound on the maximum number of changed paths a single Bloom filter can hold, that will occur in a later patch. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Taylor Blau committed
Sep 17, 2020 at 09:34 UTC
97ffa4fab504a9c5e3b63ff886686c7f6ccd4e70
3 files changed
+16
-3
bloom.h
+10
-1
@@ -28,9 +28,18 @@ struct bloom_filter_settings {
28
* that contain n*b bits.
29
*/
30
uint32_t bits_per_entry;
31
+
32
+ /*
33
+ * The maximum number of changed paths per commit
34
+ * before declaring a Bloom filter to be too-large.
35
+ *
36
+ * Not written to the commit-graph file.
37
+ */
38
+ uint32_t max_changed_paths;
39
};
40
33
-#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 }
41
+#define DEFAULT_BLOOM_MAX_CHANGES 512
42
+#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
43
#define BITS_PER_WORD 8
44
#define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
45
commit-graph.c
+4
@@ -417,6 +417,7 @@ struct commit_graph *parse_commit_graph(struct repository *r,
417
graph->bloom_filter_settings->hash_version = hash_version;
418
graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4);
419
graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
420
+ graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES;
421
}
422
break;
423
}
@@ -1194,6 +1195,7 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
1195
jw_object_intmax(&jw, "hash_version", ctx->bloom_settings->hash_version);
1196
jw_object_intmax(&jw, "num_hashes", ctx->bloom_settings->num_hashes);
1197
jw_object_intmax(&jw, "bits_per_entry", ctx->bloom_settings->bits_per_entry);
1198
+ jw_object_intmax(&jw, "max_changed_paths", ctx->bloom_settings->max_changed_paths);
1199
jw_end(&jw);
1200
1201
trace2_data_json("bloom", ctx->r, "settings", &jw);
@@ -1662,6 +1664,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
1664
bloom_settings.bits_per_entry);
1665
bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
1666
bloom_settings.num_hashes);
1667
+ bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
1668
+ bloom_settings.max_changed_paths);
1669
ctx->bloom_settings = &bloom_settings;
1670
}
1671
t/t4216-log-bloom.sh
+2
-2
@@ -169,11 +169,11 @@ test_expect_success 'persist filter settings' '
169
GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=9 \
170
GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY=15 \
171
git commit-graph write --reachable --changed-paths &&
172
- grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2.txt &&
172
+ grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15,\"max_changed_paths\":512" trace2.txt &&
173
GIT_TRACE2_EVENT="$(pwd)/trace2-auto.txt" \
174
GIT_TRACE2_EVENT_NESTING=5 \
175
git commit-graph write --reachable --changed-paths &&
176
- grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt
176
+ grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15,\"max_changed_paths\":512" trace2-auto.txt
177
'
178
179
test_expect_success 'correctly report changes over limit' '