diff mbox series

[v2,01/13] commit-graph: introduce 'get_bloom_filter_settings()'

Message ID db305fe3d698f297f1d3359516f5e5d18627adbe.1600279373.git.me@ttaylorr.com
State Superseded
Headers show
Series more miscellaneous Bloom filter improvements, redux | expand

Commit Message

Taylor Blau Sept. 16, 2020, 6:06 p.m. UTC
Many places in the code often need a pointer to the commit-graph's
'struct bloom_filter_settings', in which case they often take the value
from the top-most commit-graph.

In the non-split case, this works as expected. In the split case,
however, things get a little tricky. Not all layers in a chain of
incremental commit-graphs are required to themselves have Bloom data,
and so whether or not some part of the code uses Bloom filters depends
entirely on whether or not the top-most level of the commit-graph chain
has Bloom filters.

This has been the behavior since Bloom filters were introduced, and has
been codified into the tests since a759bfa9ee (t4216: add end to end
tests for git log with Bloom filters, 2020-04-06). In fact, t4216.130
requires that Bloom filters are not used in exactly the case described
earlier.

There is no reason that this needs to be the case, since it is perfectly
valid for commits in an earlier layer to have Bloom filters when commits
in a newer layer do not.

Since Bloom settings are guaranteed in practice to be the same for any
layer in a chain that has Bloom data, it is sufficient to traverse the
'->base_graph' pointer until either (1) a non-null 'struct
bloom_filter_settings *' is found, or (2) until we are at the root of
the commit-graph chain.

Introduce a 'get_bloom_filter_settings()' function that does just this,
and use it instead of purely dereferencing the top-most graph's
'->bloom_filter_settings' pointer.

While we're at it, add an additional test in t5324 to guard against code
in the commit-graph writing machinery that doesn't correctly handle a
NULL 'struct bloom_filter *'.

Co-authored-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 blame.c                       |  6 ++++--
 bloom.c                       |  6 +++---
 commit-graph.c                | 11 +++++++++++
 commit-graph.h                |  2 ++
 revision.c                    |  5 +----
 t/t4216-log-bloom.sh          |  9 ++++++---
 t/t5324-split-commit-graph.sh | 13 +++++++++++++
 7 files changed, 40 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/blame.c b/blame.c
index 1be1cd82a2..903e23af23 100644
--- a/blame.c
+++ b/blame.c
@@ -2892,16 +2892,18 @@  void setup_blame_bloom_data(struct blame_scoreboard *sb,
 			    const char *path)
 {
 	struct blame_bloom_data *bd;
+	struct bloom_filter_settings *bs;
 
 	if (!sb->repo->objects->commit_graph)
 		return;
 
-	if (!sb->repo->objects->commit_graph->bloom_filter_settings)
+	bs = get_bloom_filter_settings(sb->repo);
+	if (!bs)
 		return;
 
 	bd = xmalloc(sizeof(struct blame_bloom_data));
 
-	bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings;
+	bd->settings = bs;
 
 	bd->alloc = 4;
 	bd->nr = 0;
diff --git a/bloom.c b/bloom.c
index 1a573226e7..cd9380ac62 100644
--- a/bloom.c
+++ b/bloom.c
@@ -38,7 +38,7 @@  static int load_bloom_filter_from_graph(struct commit_graph *g,
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
+	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
@@ -195,8 +195,8 @@  struct bloom_filter *get_bloom_filter(struct repository *r,
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
 		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			r->objects->commit_graph->chunk_bloom_indexes)
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
+				return filter;
 	}
 
 	if (filter->data)
diff --git a/commit-graph.c b/commit-graph.c
index 0ed003e218..6a36ed0b06 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -667,6 +667,17 @@  int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
+{
+	struct commit_graph *g = r->objects->commit_graph;
+	while (g) {
+		if (g->bloom_filter_settings)
+			return g->bloom_filter_settings;
+		g = g->base_graph;
+	}
+	return NULL;
+}
+
 static void close_commit_graph_one(struct commit_graph *g)
 {
 	if (!g)
diff --git a/commit-graph.h b/commit-graph.h
index 09a97030dc..0677dd1031 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -87,6 +87,8 @@  struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
  */
 int generation_numbers_enabled(struct repository *r);
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r);
+
 enum commit_graph_write_flags {
 	COMMIT_GRAPH_WRITE_APPEND     = (1 << 0),
 	COMMIT_GRAPH_WRITE_PROGRESS   = (1 << 1),
diff --git a/revision.c b/revision.c
index 1239023f93..6aeb764821 100644
--- a/revision.c
+++ b/revision.c
@@ -681,10 +681,7 @@  static void prepare_to_use_bloom_filter(struct rev_info *revs)
 
 	repo_parse_commit(revs->repo, revs->commits->item);
 
-	if (!revs->repo->objects->commit_graph)
-		return;
-
-	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
+	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
 	if (!revs->bloom_filter_settings)
 		return;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 4bb9e9dbe2..715912ad0f 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -65,7 +65,7 @@  setup () {
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":${2:-0},\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -139,8 +139,11 @@  test_expect_success 'setup - add commit-graph to the chain without Bloom filters
 	test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
 '
 
-test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
-	test_bloom_filters_not_used "-- A/B"
+test_expect_success 'use Bloom filters even if the latest graph does not have Bloom filters' '
+	# Ensure that the number of empty filters is equal to the number of
+	# filters in the latest graph layer to prove that they are loaded (and
+	# ignored).
+	test_bloom_filters_used "-- A/B" 3
 '
 
 test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 18216463c7..c334ee9155 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -427,4 +427,17 @@  done <<\EOF
 0600 -r--------
 EOF
 
+test_expect_success '--split=replace with partial Bloom data' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git commit-graph write --split=no-merge --stdin-commits --changed-paths <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=replace --stdin-commits --changed-paths <c &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir
+'
+
 test_done