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

[PATCH v3 08/14] bloom: use provided 'struct bloom_filter_settings'

From
Taylor Blau <me@ttaylorr.com>
Date
Aug 11, 2020, 20:51 UTC
Message-ID
<4f08177dbe0f3cddfcc7cddbdb65446f410b6ecf.1597178915.git.me@ttaylorr.com>
In-Reply-To
<cover.1597178914.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 a8a21762f4..0cf1962dc5 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,
 						 int *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 = 0;
@@ -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 baa91926db..3f19e3fca4 100644
--- a/bloom.h
+++ b/bloom.h
@@ -92,10 +92,11 @@ void init_bloom_filters(void);
 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,
 						 int *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 ba2a2cfb22..48d4697f54 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1432,6 +1432,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			ctx->r,
 			c,
 			1,
+			ctx->bloom_settings,
 			&computed);
 		if (computed) {
 			ctx->count_bloom_filter_computed++;
@@ -1688,17 +1689,6 @@ 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;
@@ -2144,6 +2134,7 @@ 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;
@@ -2157,6 +2148,14 @@ 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 531af439c2..4af949164c 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.rc1.13.ge78abce653
Previous: Taylor BlauNext: Taylor Blau
Message 59 of 117 in “more miscellaneous Bloom filter improvements”
  1. 00/10 more miscellaneous Bloom filter improvementsTaylor Blau, Aug 3, 2020
  2. 01/10 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Aug 3, 2020
  3. Jeff KingAug 4, 2020
  4. Taylor BlauAug 4, 2020
  5. 02/10 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Aug 3, 2020
  6. 03/10 t4216: use an '&&'-chainTaylor Blau, Aug 3, 2020
  7. 04/10 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Aug 3, 2020
  8. 05/10 commit-graph: respect 'commitgraph.readChangedPaths'Taylor Blau, Aug 3, 2020
  9. 06/10 commit-graph.c: sort index into commits listTaylor Blau, Aug 3, 2020
  10. Derrick StoleeAug 4, 2020
  11. Taylor BlauAug 4, 2020
  12. 07/10 commit-graph: add large-filters bitmap chunkTaylor Blau, Aug 3, 2020
  13. Taylor BlauAug 3, 2020
  14. Derrick StoleeAug 4, 2020
  15. 08/10 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Aug 3, 2020
  16. Derrick StoleeAug 4, 2020
  17. Taylor BlauAug 4, 2020
  18. 09/10 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Aug 3, 2020
  19. 10/10 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Aug 3, 2020
  20. Derrick StoleeAug 4, 2020
  21. Taylor BlauAug 4, 2020
  22. 00/14 more miscellaneous Bloom filter improvementsTaylor Blau, Aug 5, 2020
  23. 01/14 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Aug 5, 2020
  24. 02/14 t4216: use an '&&'-chainTaylor Blau, Aug 5, 2020
  25. 09/14 bloom/diff: properly short-circuit on max_changesTaylor Blau, Aug 5, 2020
  26. 10/14 commit-graph.c: sort index into commits listTaylor Blau, Aug 5, 2020
  27. 08/14 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Aug 5, 2020
  28. 07/14 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Aug 5, 2020
  29. 12/14 commit-graph: add large-filters bitmap chunkTaylor Blau, Aug 5, 2020
  30. Junio C HamanoAug 5, 2020
  31. Taylor BlauAug 5, 2020
  32. Junio C HamanoAug 5, 2020
  33. Taylor BlauAug 5, 2020
  34. Taylor BlauAug 11, 2020
  35. Junio C HamanoAug 11, 2020
  36. 11/14 csum-file.h: introduce 'hashwrite_be64()'Taylor Blau, Aug 5, 2020
  37. 13/14 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Aug 5, 2020
  38. 03/14 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Aug 5, 2020
  39. 06/14 commit-graph.c: store maximum changed pathsTaylor Blau, Aug 5, 2020
  40. 04/14 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Aug 5, 2020
  41. 05/14 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Aug 5, 2020
  42. 14/14 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Aug 5, 2020
  43. 00/14 more miscellaneous Bloom filter improvementsTaylor Blau, Aug 11, 2020
  44. 01/14 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Aug 11, 2020
  45. SZEDER GáborAug 11, 2020
  46. Taylor BlauAug 11, 2020
  47. SZEDER GáborAug 11, 2020
  48. Taylor BlauAug 11, 2020
  49. SZEDER GáborAug 11, 2020
  50. Derrick StoleeAug 12, 2020
  51. Taylor BlauAug 14, 2020
  52. 02/14 t4216: use an '&&'-chainTaylor Blau, Aug 11, 2020
  53. 03/14 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Aug 11, 2020
  54. 04/14 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Aug 11, 2020
  55. 05/14 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Aug 11, 2020
  56. 06/14 commit-graph.c: store maximum changed pathsTaylor Blau, Aug 11, 2020
  57. 07/14 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Aug 11, 2020
  58. 11/14 csum-file.h: introduce 'hashwrite_be64()'Taylor Blau, Aug 11, 2020
  59. 08/14 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Aug 11, 2020
  60. 09/14 bloom/diff: properly short-circuit on max_changesTaylor Blau, Aug 11, 2020
  61. 10/14 commit-graph.c: sort index into commits listTaylor Blau, Aug 11, 2020
  62. 12/14 commit-graph: add large-filters bitmap chunkTaylor Blau, Aug 11, 2020
  63. Derrick StoleeAug 11, 2020
  64. Taylor BlauAug 11, 2020
  65. Taylor BlauAug 11, 2020
  66. SZEDER GáborAug 19, 2020
  67. Taylor BlauSep 2, 2020
  68. SZEDER GáborSep 1, 2020
  69. Taylor BlauSep 2, 2020
  70. 13/14 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Aug 11, 2020
  71. SZEDER GáborAug 19, 2020
  72. Taylor BlauSep 2, 2020
  73. 14/14 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Aug 11, 2020
  74. SZEDER GáborAug 12, 2020
  75. Taylor BlauAug 14, 2020
  76. SZEDER GáborAug 17, 2020
  77. Taylor BlauSep 2, 2020
  78. Derrick StoleeAug 12, 2020
  79. Taylor BlauAug 14, 2020
  80. SZEDER GáborAug 18, 2020
  81. Taylor BlauSep 3, 2020
  82. SZEDER GáborAug 19, 2020
  83. Taylor BlauSep 3, 2020
  84. SZEDER GáborSep 4, 2020
  85. SZEDER GáborSep 1, 2020
  86. Taylor BlauSep 3, 2020
  87. Junio C HamanoSep 3, 2020
  88. Taylor BlauSep 3, 2020
  89. 00/14 more miscellaneous Bloom filter improvementsTaylor Blau, Sep 3, 2020
  90. 01/14 commit-graph: introduce 'get_bloom_filter_settings()'Taylor Blau, Sep 3, 2020
  91. 02/14 t4216: use an '&&'-chainTaylor Blau, Sep 3, 2020
  92. 04/14 t/helper/test-read-graph.c: prepare repo settingsTaylor Blau, Sep 3, 2020
  93. 03/14 commit-graph: pass a 'struct repository *' in more placesTaylor Blau, Sep 3, 2020
  94. 05/14 commit-graph: respect 'commitGraph.readChangedPaths'Taylor Blau, Sep 3, 2020
  95. 06/14 commit-graph.c: store maximum changed pathsTaylor Blau, Sep 3, 2020
  96. 07/14 bloom: split 'get_bloom_filter()' in twoTaylor Blau, Sep 3, 2020
  97. Jakub NarębskiSep 5, 2020
  98. Taylor BlauSep 5, 2020
  99. Jakub NarębskiSep 5, 2020
  100. Taylor BlauSep 5, 2020
  101. Jakub NarębskiSep 5, 2020
  102. Taylor BlauSep 5, 2020
  103. Taylor BlauSep 5, 2020
  104. SZEDER GáborSep 5, 2020
  105. Taylor BlauSep 5, 2020
  106. Junio C HamanoSep 6, 2020
  107. 08/14 bloom: use provided 'struct bloom_filter_settings'Taylor Blau, Sep 3, 2020
  108. 09/14 bloom/diff: properly short-circuit on max_changesTaylor Blau, Sep 3, 2020
  109. 10/14 commit-graph.c: sort index into commits listTaylor Blau, Sep 3, 2020
  110. 11/14 csum-file.h: introduce 'hashwrite_be64()'Taylor Blau, Sep 3, 2020
  111. René ScharfeSep 4, 2020
  112. Taylor BlauSep 4, 2020
  113. 12/14 commit-graph: add large-filters bitmap chunkTaylor Blau, Sep 3, 2020
  114. 13/14 commit-graph: rename 'split_commit_graph_opts'Taylor Blau, Sep 3, 2020
  115. Taylor BlauSep 4, 2020
  116. 14/14 builtin/commit-graph.c: introduce '--max-new-filters=<n>'Taylor Blau, Sep 3, 2020
  117. Derrick StoleeSep 4, 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.