[RFC PATCH 1/6] bloom: annotate filters with hash version
- From
Taylor Blau <me@ttaylorr.com>
- Date
- Aug 7, 2023, 16:37 UTC
- Message-ID
- <e23a956401c5619bd46e8ec9b0e1df958cbcbfec.1691426160.git.me@ttaylorr.com>
- In-Reply-To
- <cover.1691426160.git.me@ttaylorr.com>
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 "filter" field to each Bloom filter.
Signed-off-by: Taylor Blau <me@ttaylorr.com> --- bloom.c | 11 ++++++++--- bloom.h | 1 + 2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/bloom.c b/bloom.c index ebef5cfd2f..9b6a30f6f6 100644 --- a/bloom.c +++ b/bloom.c @@ -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; diff --git a/bloom.h b/bloom.h index 138d57a86b..330a140520 100644 --- a/bloom.h +++ b/bloom.h @@ -55,6 +55,7 @@ struct bloom_filter_settings { struct bloom_filter { unsigned char *data; size_t len; + int version; }; /*
-- 2.41.0.407.g6d1c33951b