git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 08/13] bloom: use provided 'struct bloom_filter_settings'

From
Taylor Blau <me@ttaylorr.com>
Date
Sep 16, 2020, 18:07 UTC
Message-ID
<b8e1e48bef3bbee631dbb88b832fae98a20c940b.1600279373.git.me@ttaylorr.com>
In-Reply-To
<cover.1600279373.git.me@ttaylorr.com>

When 'get_or_compute_bloom_filter()' needs to compute a Bloom filter from scratch, it looks to the default 'struct bloom_filter_settings' in order to determine the maximum number of changed paths, number of bits per entry, and so on.

All of these values have so far been constant, and so there was no need to pass in a pointer from the caller (eg., the one that is stored in the 'struct write_commit_graph_context').

Start passing in a 'struct bloom_filter_settings *' instead of using the default values to respect graph-specific settings (eg., in the case of setting 'GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS').

In order to have an initialized value for these settings, move its initialization to earlier in the commit-graph write.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 bloom.c               | 13 ++++++-------
 bloom.h               |  3 ++-
 commit-graph.c        | 21 ++++++++++-----------
 t/helper/test-bloom.c |  1 +
 4 files changed, 19 insertions(+), 19 deletions(-)
diff --git a/bloom.c b/bloom.c
index 393c61b4bc..2d6aef9098 100644
--- a/bloom.c
+++ b/bloom.c
@@ -180,13 +180,12 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 enum bloom_filter_computed *computed)
 {
 	struct bloom_filter *filter;
-	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 	int i;
 	struct diff_options diffopt;
-	int max_changes = 512;
 
 	if (computed)
 		*computed = BLOOM_NOT_COMPUTED;
@@ -211,7 +210,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
 	diffopt.detect_rename = 0;
-	diffopt.max_changes = max_changes;
+	diffopt.max_changes = settings->max_changed_paths;
 	diff_setup_done(&diffopt);
 
 	/* ensure commit is parsed so we have parent information */
@@ -223,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= max_changes) {
+	if (diffopt.num_changes <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -260,13 +259,13 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
-		filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
 		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
 			struct bloom_key key;
-			fill_bloom_key(e->path, strlen(e->path), &key, &settings);
-			add_key_to_filter(&key, filter, &settings);
+			fill_bloom_key(e->path, strlen(e->path), &key, settings);
+			add_key_to_filter(&key, filter, settings);
 		}
 
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
diff --git a/bloom.h b/bloom.h
index e2e035ad14..c6d77e8393 100644
--- a/bloom.h
+++ b/bloom.h
@@ -98,10 +98,11 @@ enum bloom_filter_computed {
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 enum bloom_filter_computed *computed);
 
 #define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
-	(r), (c), 0, NULL)
+	(r), (c), 0, NULL, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index 45fcd62596..1ca754f19c 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1434,6 +1434,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			ctx->r,
 			c,
 			1,
+			ctx->bloom_settings,
 			&computed);
 		if (computed & BLOOM_COMPUTED) {
 			ctx->count_bloom_filter_computed++;
@@ -1691,17 +1692,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int num_chunks = 3;
 	uint64_t chunk_offset;
 	struct object_id file_hash;
-	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
-
-	if (!ctx->bloom_settings) {
-		bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
-							      bloom_settings.bits_per_entry);
-		bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
-							  bloom_settings.num_hashes);
-		bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
-							  bloom_settings.max_changed_paths);
-		ctx->bloom_settings = &bloom_settings;
-	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -2147,6 +2137,7 @@ int write_commit_graph(struct object_directory *odb,
 	uint32_t i, count_distinct = 0;
 	int res = 0;
 	int replace = 0;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -2160,6 +2151,14 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->split_opts = split_opts;
 	ctx->total_bloom_filter_data_size = 0;
 
+	bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
+						      bloom_settings.bits_per_entry);
+	bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
+						  bloom_settings.num_hashes);
+	bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							 bloom_settings.max_changed_paths);
+	ctx->bloom_settings = &bloom_settings;
+
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;
 	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 9f7bb729fc..46e97b04eb 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -40,6 +40,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
 	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     &settings,
 					     NULL);
 	print_bloom_filter(filter);
 }
-- 
2.28.0.510.g86fdc5f89a
Previous: Taylor BlauNext: Taylor Blau
Message 37 of 75 in “more miscellaneous Bloom filter improvements, redux”
  1. 00/12 more miscellaneous Bloom filter improvements, reduxTaylor Blau, Sep 9, 2020
  2. 03/12 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Sep 9, 2020
  3. 11/12 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Sep 9, 2020
  4. 12/12 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Sep 9, 2020
  5. Jeff KingSep 11, 2020
  6. Taylor BlauSep 11, 2020
  7. Taylor BlauSep 11, 2020
  8. Taylor BlauSep 14, 2020
  9. Derrick StoleeSep 14, 2020
  10. Taylor BlauSep 14, 2020
  11. Derrick StoleeSep 15, 2020
  12. Taylor BlauSep 15, 2020
  13. Junio C HamanoSep 15, 2020
  14. Taylor BlauSep 15, 2020
  15. Jeff KingSep 11, 2020
  16. Junio C HamanoSep 11, 2020
  17. 04/12 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Sep 9, 2020
  18. 05/12 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Sep 9, 2020
  19. 08/12 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Sep 9, 2020
  20. 06/12 commit-graph.c: store maximum changed pathsTaylor Blau, Sep 9, 2020
  21. 09/12 bloom/diff: properly short-circuit on max_changesTaylor Blau, Sep 9, 2020
  22. 10/12 bloom: encode out-of-bounds filters as non-emptyTaylor Blau, Sep 9, 2020
  23. Taylor BlauSep 10, 2020
  24. Taylor BlauSep 10, 2020
  25. Derrick StoleeSep 11, 2020
  26. 07/12 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Sep 9, 2020
  27. 02/12 t4216: use an '&&'-chainTaylor Blau, Sep 9, 2020
  28. 01/12 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Sep 9, 2020
  29. 00/13 more miscellaneous Bloom filter improvements, reduxTaylor Blau, Sep 16, 2020
  30. 04/13 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Sep 16, 2020
  31. 03/13 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Sep 16, 2020
  32. 05/13 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Sep 16, 2020
  33. 06/13 commit-graph.c: store maximum changed pathsTaylor Blau, Sep 16, 2020
  34. 02/13 t4216: use an '&&'-chainTaylor Blau, Sep 16, 2020
  35. 01/13 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Sep 16, 2020
  36. 07/13 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Sep 16, 2020
  37. 08/13 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Sep 16, 2020
  38. 10/13 bloom: encode out-of-bounds filters as non-emptyTaylor Blau, Sep 16, 2020
  39. SZEDER GáborSep 17, 2020
  40. Taylor BlauSep 17, 2020
  41. Junio C HamanoSep 18, 2020
  42. Taylor BlauSep 18, 2020
  43. 11/13 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Sep 16, 2020
  44. 12/13 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Sep 16, 2020
  45. SZEDER GáborSep 18, 2020
  46. Taylor BlauSep 18, 2020
  47. 09/13 bloom/diff: properly short-circuit on max_changesTaylor Blau, Sep 16, 2020
  48. 13/13 commit-graph: introduce 'commitGraph.maxNewFilters'Taylor Blau, Sep 16, 2020
  49. Derrick StoleeSep 16, 2020
  50. Junio C HamanoSep 16, 2020
  51. Taylor BlauSep 17, 2020
  52. Junio C HamanoSep 17, 2020
  53. Taylor BlauSep 17, 2020
  54. Taylor BlauSep 17, 2020
  55. Derrick StoleeSep 17, 2020
  56. 00/13 more miscellaneous Bloom filter improvements, reduxTaylor Blau, Sep 18, 2020
  57. 01/13 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Sep 18, 2020
  58. 03/13 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Sep 18, 2020
  59. 02/13 t4216: use an '&&'-chainTaylor Blau, Sep 18, 2020
  60. 05/13 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Sep 18, 2020
  61. 04/13 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Sep 18, 2020
  62. 08/13 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Sep 18, 2020
  63. SZEDER GáborSep 18, 2020
  64. Taylor BlauSep 18, 2020
  65. 07/13 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Sep 18, 2020
  66. 06/13 commit-graph.c: store maximum changed pathsTaylor Blau, Sep 18, 2020
  67. 10/13 bloom: encode out-of-bounds filters as non-emptyTaylor Blau, Sep 18, 2020
  68. 11/13 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Sep 18, 2020
  69. 13/13 commit-graph: introduce 'commitGraph.maxNewFilters'Taylor Blau, Sep 18, 2020
  70. Taylor BlauSep 18, 2020
  71. Junio C HamanoSep 18, 2020
  72. 12/13 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Sep 18, 2020
  73. 09/13 bloom/diff: properly short-circuit on max_changesTaylor Blau, Sep 18, 2020
  74. Taylor BlauSep 18, 2020
  75. Taylor BlauSep 18, 2020

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.