bloom: split 'get_bloom_filter()' in two

'get_bloom_filter' takes a flag to control whether it will compute a
Bloom filter if the requested one is missing. In the next patch, we'll
add yet another parameter to this method, which would force all but one
caller to specify an extra 'NULL' parameter at the end.

Instead of doing this, split 'get_bloom_filter' into two functions:
'get_bloom_filter' and 'get_or_compute_bloom_filter'. The former only
looks up a Bloom filter (and does not compute one if it's missing,
thus dropping the 'compute_if_not_present' flag). The latter does
compute missing Bloom filters, with an additional parameter to store
whether or not it needed to do so.

This simplifies many call-sites, since the majority of existing callers
to 'get_bloom_filter' do not want missing Bloom filters to be computed
(so they can drop the parameter entirely and use the simpler version of
the function).

While we're at it, instrument the new 'get_or_compute_bloom_filter()'
with counters in the 'write_commit_graph_context' struct which store
the number of filters that we did and didn't compute, as well as filters
that were truncated.

It would be nice to drop the 'compute_if_not_present' flag entirely,
since all remaining callers of 'get_or_compute_bloom_filter' pass it as
'1', but this will change in a future patch and hence cannot be removed.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 31 insertions, 3 deletions

diff --git a/commit-graph.c b/commit-graph.c
index 44dceb8..67a2812 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -965,6 +965,10 @@ struct write_commit_graph_context {
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
+
+	int count_bloom_filter_computed;
+	int count_bloom_filter_not_computed;
+	int count_bloom_filter_trunc_large;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1176,7 +1180,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 	uint32_t cur_pos = 0;
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1216,7 +1220,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1386,6 +1390,16 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+	trace2_data_intmax("commit-graph", ctx->r, "filter-computed",
+			   ctx->count_bloom_filter_computed);
+	trace2_data_intmax("commit-graph", ctx->r, "filter-not-computed",
+			   ctx->count_bloom_filter_not_computed);
+	trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large",
+			   ctx->count_bloom_filter_trunc_large);
+}
+
 static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
@@ -1408,12 +1422,26 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
+		enum bloom_filter_computed computed = 0;
 		struct commit *c = sorted_commits[i];
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		struct bloom_filter *filter = get_or_compute_bloom_filter(
+			ctx->r,
+			c,
+			1,
+			&computed);
+		if (computed & BLOOM_COMPUTED) {
+			ctx->count_bloom_filter_computed++;
+			if (computed & BLOOM_TRUNC_LARGE)
+				ctx->count_bloom_filter_trunc_large++;
+		} else if (computed & BLOOM_NOT_COMPUTED)
+			ctx->count_bloom_filter_not_computed++;
 		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}
 
+	if (trace2_is_enabled())
+		trace2_bloom_filter_write_statistics(ctx);
+
 	free(sorted_commits);
 	stop_progress(&progress);
 }