builtin/commit-graph.c: introduce '--max-new-filters=<n>'

Introduce a command-line flag to specify the maximum number of new Bloom
filters that a 'git commit-graph write' is willing to compute from
scratch.

Prior to this patch, a commit-graph write with '--changed-paths' would
compute Bloom filters for all selected commits which haven't already
been computed (i.e., by a previous commit-graph write with '--split'
such that a roll-up or replacement is performed).

This behavior can cause prohibitively-long commit-graph writes for a
variety of reasons:

  * There may be lots of filters whose diffs take a long time to
    generate (for example, they have close to the maximum number of
    changes, diffing itself takes a long time, etc).

  * Old-style commit-graphs (which encode filters with too many entries
    as not having been computed at all) cause us to waste time
    recomputing filters that appear to have not been computed only to
    discover that they are too-large.

This can make the upper-bound of the time it takes for 'git commit-graph
write --changed-paths' to be rather unpredictable.

To make this command behave more predictably, introduce
'--max-new-filters=<n>' to allow computing at most '<n>' Bloom filters
from scratch. This lets "computing" already-known filters proceed
quickly, while bounding the number of slow tasks that Git is willing to
do.

Helped-by: Junio C Hamano <[email protected]>
Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

Documentation/git-commit-graph.txt

@@ -67,6 +67,12 @@ this option is given, future commit-graph writes will automatically assume
 that this option was intended. Use `--no-changed-paths` to stop storing this
 data.
 +
+With the `--max-new-filters=<n>` option, generate at most `n` new Bloom
+filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is
+enforced. Only commits present in the new layer count against this
+limit. To retroactively compute Bloom filters over earlier layers, it is
+advised to use `--split=replace`.
++
 With the `--split[=<strategy>]` option, write the commit-graph as a
 chain of multiple commit-graph files stored in
 `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the

bloom.c

@@ -204,12 +204,11 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
-		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
-				return filter;
+		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
 	}
 
-	if (filter->data)
+	if (filter->data && filter->len)
 		return filter;
 	if (!compute_if_not_present)
 		return NULL;

builtin/commit-graph.c

@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -162,6 +164,23 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
 static int graph_write(int argc, const char **argv)
 {
 	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
@@ -197,6 +216,9 @@ static int graph_write(int argc, const char **argv)
 			N_("maximum ratio between two levels of a split commit-graph")),
 		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of changed-path Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
@@ -205,6 +227,7 @@ static int graph_write(int argc, const char **argv)
 	write_opts.size_multiple = 2;
 	write_opts.max_commits = 0;
 	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
 
 	trace2_cmd_mode("write");
 

commit-graph.c

@@ -1408,6 +1408,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int i;
 	struct progress *progress = NULL;
 	struct commit **sorted_commits;
+	int max_new_filters;
 
 	init_bloom_filters();
 
@@ -1424,13 +1425,16 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	else
 		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
+	max_new_filters = ctx->opts && ctx->opts->max_new_filters >= 0 ?
+		ctx->opts->max_new_filters : ctx->commits.nr;
+
 	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_or_compute_bloom_filter(
 			ctx->r,
 			c,
-			1,
+			ctx->count_bloom_filter_computed < max_new_filters,
 			ctx->bloom_settings,
 			&computed);
 		if (computed & BLOOM_COMPUTED) {
@@ -1441,7 +1445,8 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 				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;
+		ctx->total_bloom_filter_data_size += filter
+			? sizeof(unsigned char) * filter->len : 0;
 		display_progress(progress, i + 1);
 	}
 

commit-graph.h

@@ -110,6 +110,7 @@ struct commit_graph_opts {
 	int max_commits;
 	timestamp_t expire_time;
 	enum commit_graph_split_flags split_flags;
+	int max_new_filters;
 };
 
 /*

t/t4216-log-bloom.sh

@@ -305,4 +305,74 @@ test_expect_success 'correctly report commits with no changed paths' '
 	)
 '
 
+test_expect_success 'Bloom generation is limited by --max-new-filters' '
+	(
+		cd limits &&
+		test_commit c2 filter &&
+		test_commit c3 filter &&
+		test_commit c4 no-filter &&
+
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --split=replace \
+				--changed-paths --max-new-filters=2 &&
+
+		test_filter_computed 2 trace.event &&
+		test_filter_not_computed 3 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success 'Bloom generation backfills previously-skipped filters' '
+	(
+		cd limits &&
+
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --changed-paths \
+				--split=replace --max-new-filters=1 &&
+		test_filter_computed 1 trace.event &&
+		test_filter_not_computed 4 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success 'Bloom generation backfills empty commits' '
+	git init empty &&
+	test_when_finished "rm -fr empty" &&
+	(
+		cd empty &&
+		for i in $(test_seq 1 6)
+		do
+			git commit --allow-empty -m "$i"
+		done &&
+
+		# Generate Bloom filters for empty commits 1-6, two at a time.
+		for i in $(test_seq 1 3)
+		do
+			rm -f trace.event &&
+			GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+				git commit-graph write --reachable \
+					--changed-paths --max-new-filters=2 &&
+			test_filter_computed 2 trace.event &&
+			test_filter_not_computed 4 trace.event &&
+			test_filter_trunc_empty 2 trace.event &&
+			test_filter_trunc_large 0 trace.event
+		done &&
+
+		# Finally, make sure that once all commits have filters, that
+		# none are subsequently recomputed.
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable \
+				--changed-paths --max-new-filters=2 &&
+		test_filter_computed 0 trace.event &&
+		test_filter_not_computed 6 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
 test_done