Merge branch 'ds/commit-graph-bloom-updates' into master

Updates to the changed-paths bloom filter.

* ds/commit-graph-bloom-updates:
  commit-graph: check all leading directories in changed path Bloom filters
  revision: empty pathspecs should not use Bloom filters
  revision.c: fix whitespace
  commit-graph: check chunk sizes after writing
  commit-graph: simplify chunk writes into loop
  commit-graph: unify the signatures of all write_graph_chunk_*() functions
  commit-graph: persist existence of changed-paths
  bloom: fix logic in get_bloom_filter()
  commit-graph: change test to die on parse, not load
  commit-graph: place bloom_settings in context

1 files changed, 110 insertions, 38 deletions

diff --git a/commit-graph.c b/commit-graph.c
index 1f37097dff..e51c91dd5b 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -17,6 +17,8 @@
 #include "bloom.h"
 #include "commit-slab.h"
 #include "shallow.h"
+#include "json-writer.h"
+#include "trace2.h"
 
 void git_test_write_commit_graph_or_die(void)
 {
@@ -617,10 +619,6 @@ static int prepare_commit_graph(struct repository *r)
 		return !!r->objects->commit_graph;
 	r->objects->commit_graph_attempted = 1;
 
-	if (git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD, 0))
-		die("dying as requested by the '%s' variable on commit-graph load!",
-		    GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD);
-
 	prepare_repo_settings(r);
 
 	if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
@@ -849,6 +847,14 @@ static int parse_commit_in_graph_one(struct repository *r,
 
 int parse_commit_in_graph(struct repository *r, struct commit *item)
 {
+	static int checked_env = 0;
+
+	if (!checked_env &&
+	    git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE, 0))
+		die("dying as requested by the '%s' variable on commit-graph parse!",
+		    GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE);
+	checked_env = 1;
+
 	if (!prepare_commit_graph(r))
 		return 0;
 	return parse_commit_in_graph_one(r, r->objects->commit_graph, item);
@@ -941,10 +947,11 @@ 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;
 };
 
-static void write_graph_chunk_fanout(struct hashfile *f,
-				     struct write_commit_graph_context *ctx)
+static int write_graph_chunk_fanout(struct hashfile *f,
+				    struct write_commit_graph_context *ctx)
 {
 	int i, count = 0;
 	struct commit **list = ctx->commits.list;
@@ -965,17 +972,21 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 
 		hashwrite_be32(f, count);
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
-				   struct write_commit_graph_context *ctx)
+static int write_graph_chunk_oids(struct hashfile *f,
+				  struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	int count;
 	for (count = 0; count < ctx->commits.nr; count++, list++) {
 		display_progress(ctx->progress, ++ctx->progress_cnt);
-		hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
+		hashwrite(f, (*list)->object.oid.hash, the_hash_algo->rawsz);
 	}
+
+	return 0;
 }
 
 static const unsigned char *commit_to_sha1(size_t index, void *table)
@@ -984,8 +995,8 @@ static const unsigned char *commit_to_sha1(size_t index, void *table)
 	return commits[index]->object.oid.hash;
 }
 
-static void write_graph_chunk_data(struct hashfile *f, int hash_len,
-				   struct write_commit_graph_context *ctx)
+static int write_graph_chunk_data(struct hashfile *f,
+				  struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -1002,7 +1013,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 			die(_("unable to parse commit %s"),
 				oid_to_hex(&(*list)->object.oid));
 		tree = get_commit_tree_oid(*list);
-		hashwrite(f, tree->hash, hash_len);
+		hashwrite(f, tree->hash, the_hash_algo->rawsz);
 
 		parent = (*list)->parents;
 
@@ -1082,10 +1093,12 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 		list++;
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_extra_edges(struct hashfile *f,
-					  struct write_commit_graph_context *ctx)
+static int write_graph_chunk_extra_edges(struct hashfile *f,
+					 struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -1134,10 +1147,12 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 
 		list++;
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_bloom_indexes(struct hashfile *f,
-					    struct write_commit_graph_context *ctx)
+static int write_graph_chunk_bloom_indexes(struct hashfile *f,
+					   struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -1145,30 +1160,54 @@ static void write_graph_chunk_bloom_indexes(struct hashfile *f,
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
-		cur_pos += filter->len;
+		size_t len = filter ? filter->len : 0;
+		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
 		hashwrite_be32(f, cur_pos);
 		list++;
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_bloom_data(struct hashfile *f,
-					 struct write_commit_graph_context *ctx,
-					 const struct bloom_filter_settings *settings)
+static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "hash_version", ctx->bloom_settings->hash_version);
+	jw_object_intmax(&jw, "num_hashes", ctx->bloom_settings->num_hashes);
+	jw_object_intmax(&jw, "bits_per_entry", ctx->bloom_settings->bits_per_entry);
+	jw_end(&jw);
+
+	trace2_data_json("bloom", ctx->r, "settings", &jw);
+
+	jw_release(&jw);
+}
+
+static int write_graph_chunk_bloom_data(struct hashfile *f,
+					struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
 
-	hashwrite_be32(f, settings->hash_version);
-	hashwrite_be32(f, settings->num_hashes);
-	hashwrite_be32(f, settings->bits_per_entry);
+	trace2_bloom_filter_settings(ctx);
+
+	hashwrite_be32(f, ctx->bloom_settings->hash_version);
+	hashwrite_be32(f, ctx->bloom_settings->num_hashes);
+	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		size_t len = filter ? filter->len : 0;
+
 		display_progress(ctx->progress, ++ctx->progress_cnt);
-		hashwrite(f, filter->data, filter->len * sizeof(unsigned char));
+		if (len)
+			hashwrite(f, filter->data, len * sizeof(unsigned char));
 		list++;
 	}
+
+	return 0;
 }
 
 static int oid_compare(const void *_a, const void *_b)
@@ -1579,9 +1618,13 @@ static int write_graph_chunk_base(struct hashfile *f,
 	return 0;
 }
 
+typedef int (*chunk_write_fn)(struct hashfile *f,
+			      struct write_commit_graph_context *ctx);
+
 struct chunk_info {
 	uint32_t id;
 	uint64_t size;
+	chunk_write_fn write_fn;
 };
 
 static int write_commit_graph_file(struct write_commit_graph_context *ctx)
@@ -1596,7 +1639,15 @@ 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;
-	const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
+	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);
+		ctx->bloom_settings = &bloom_settings;
+	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -1644,27 +1695,34 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 
 	chunks[0].id = GRAPH_CHUNKID_OIDFANOUT;
 	chunks[0].size = GRAPH_FANOUT_SIZE;
+	chunks[0].write_fn = write_graph_chunk_fanout;
 	chunks[1].id = GRAPH_CHUNKID_OIDLOOKUP;
 	chunks[1].size = hashsz * ctx->commits.nr;
+	chunks[1].write_fn = write_graph_chunk_oids;
 	chunks[2].id = GRAPH_CHUNKID_DATA;
 	chunks[2].size = (hashsz + 16) * ctx->commits.nr;
+	chunks[2].write_fn = write_graph_chunk_data;
 	if (ctx->num_extra_edges) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
 		chunks[num_chunks].size = 4 * ctx->num_extra_edges;
+		chunks[num_chunks].write_fn = write_graph_chunk_extra_edges;
 		num_chunks++;
 	}
 	if (ctx->changed_paths) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMINDEXES;
 		chunks[num_chunks].size = sizeof(uint32_t) * ctx->commits.nr;
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_indexes;
 		num_chunks++;
 		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMDATA;
 		chunks[num_chunks].size = sizeof(uint32_t) * 3
 					  + ctx->total_bloom_filter_data_size;
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
 		chunks[num_chunks].size = hashsz * (ctx->num_commit_graphs_after - 1);
+		chunks[num_chunks].write_fn = write_graph_chunk_base;
 		num_chunks++;
 	}
 
@@ -1700,19 +1758,19 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 			progress_title.buf,
 			num_chunks * ctx->commits.nr);
 	}
-	write_graph_chunk_fanout(f, ctx);
-	write_graph_chunk_oids(f, hashsz, ctx);
-	write_graph_chunk_data(f, hashsz, ctx);
-	if (ctx->num_extra_edges)
-		write_graph_chunk_extra_edges(f, ctx);
-	if (ctx->changed_paths) {
-		write_graph_chunk_bloom_indexes(f, ctx);
-		write_graph_chunk_bloom_data(f, ctx, &bloom_settings);
-	}
-	if (ctx->num_commit_graphs_after > 1 &&
-	    write_graph_chunk_base(f, ctx)) {
-		return -1;
+
+	for (i = 0; i < num_chunks; i++) {
+		uint64_t start_offset = f->total + f->offset;
+
+		if (chunks[i].write_fn(f, ctx))
+			return -1;
+
+		if (f->total + f->offset != start_offset + chunks[i].size)
+			BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead",
+			    chunks[i].size, chunks[i].id,
+			    f->total + f->offset - start_offset);
 	}
+
 	stop_progress(&ctx->progress);
 	strbuf_release(&progress_title);
 
@@ -2046,9 +2104,23 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->report_progress = flags & COMMIT_GRAPH_WRITE_PROGRESS ? 1 : 0;
 	ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
 	ctx->split_opts = split_opts;
-	ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0;
 	ctx->total_bloom_filter_data_size = 0;
 
+	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
+		ctx->changed_paths = 1;
+	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
+		struct commit_graph *g;
+		prepare_commit_graph_one(ctx->r, ctx->odb);
+
+		g = ctx->r->objects->commit_graph;
+
+		/* We have changed-paths already. Keep them in the next graph */
+		if (g && g->chunk_bloom_data) {
+			ctx->changed_paths = 1;
+			ctx->bloom_settings = g->bloom_filter_settings;
+		}
+	}
+
 	if (ctx->split) {
 		struct commit_graph *g;
 		prepare_commit_graph(ctx->r);