[v7,10/16] bloom: annotate filters with hash version

Commit Message

Taylor Blau June 25, 2024, 5:39 p.m. UTC

In subsequent commits, we will want to load existing Bloom filters out
of a commit-graph, even when the hash version they were computed with
does not match the value of `commitGraph.changedPathVersion`.

In order to differentiate between the two, add a "version" field to each
Bloom filter.

Signed-off-by: Taylor Blau <[e-mail]>
---
 bloom.c | 11 ++++++++---
 bloom.h |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

Patch

diff --git a/bloom.c b/bloom.c
index 401999ed3c..e64e53bc4c 100644
--- a/bloom.c
+++ b/bloom.c
@@ -88,6 +88,7 @@  int load_bloom_filter_from_graph(struct commit_graph *g,
 	filter->data = (unsigned char *)(g->chunk_bloom_data +
 					sizeof(unsigned char) * start_index +
 					BLOOMDATA_CHUNK_HEADER_SIZE);
+	filter->version = g->bloom_filter_settings->hash_version;
 
 	return 1;
 }
@@ -210,11 +211,13 @@  static int pathmap_cmp(const void *hashmap_cmp_fn_data UNUSED,
 	return strcmp(e1->path, e2->path);
 }
 
-static void init_truncated_large_filter(struct bloom_filter *filter)
+static void init_truncated_large_filter(struct bloom_filter *filter,
+					int version)
 {
 	filter->data = xmalloc(1);
 	filter->data[0] = 0xFF;
 	filter->len = 1;
+	filter->version = version;
 }
 
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
@@ -299,13 +302,15 @@  struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		}
 
 		if (hashmap_get_size(&pathmap) > settings->max_changed_paths) {
-			init_truncated_large_filter(filter);
+			init_truncated_large_filter(filter,
+						    settings->hash_version);
 			if (computed)
 				*computed |= BLOOM_TRUNC_LARGE;
 			goto cleanup;
 		}
 
 		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		filter->version = settings->hash_version;
 		if (!filter->len) {
 			if (computed)
 				*computed |= BLOOM_TRUNC_EMPTY;
@@ -325,7 +330,7 @@  struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	} else {
 		for (i = 0; i < diff_queued_diff.nr; i++)
 			diff_free_filepair(diff_queued_diff.queue[i]);
-		init_truncated_large_filter(filter);
+		init_truncated_large_filter(filter, settings->hash_version);
 
 		if (computed)
 			*computed |= BLOOM_TRUNC_LARGE;
diff --git a/bloom.h b/bloom.h
index 1e4f612d2c..c9dd7d4022 100644
--- a/bloom.h
+++ b/bloom.h
@@ -53,6 +53,7 @@  struct bloom_filter_settings {
 struct bloom_filter {
 	unsigned char *data;
 	size_t len;
+	int version;
 };
 
 /*