bloom: annotate filters with hash version

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 <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Taylor Blau
2023-10-18 14:33:03 -04:00
committed by Junio C Hamano
parent 7617234a59
commit b090ebf2ea
2 changed files with 9 additions and 3 deletions

11
bloom.c
View File

@ -55,6 +55,7 @@ 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;
}
@ -240,11 +241,13 @@ 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,
@ -329,13 +332,15 @@ 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;
@ -355,7 +360,7 @@ 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;

View File

@ -55,6 +55,7 @@ struct bloom_filter_settings {
struct bloom_filter {
unsigned char *data;
size_t len;
int version;
};
/*