Merge branch 'ab/commit-graph-write-progress'

The codepath to show progress meter while writing out commit-graph file has been improved. * ab/commit-graph-write-progress: commit-graph write: emit a percentage for all progress commit-graph write: add itermediate progress commit-graph write: remove empty line for readability commit-graph write: add more descriptive progress output commit-graph write: show progress for object search commit-graph write: more descriptive "writing out" output commit-graph write: add "Writing out" progress output commit-graph: don't call write_graph_chunk_extra_edges() unnecessarily commit-graph: rename "large edges" to "extra edges"
luceliu · Feb 5, 2019 · e5eac57 · e5eac57
2 parents 04d67b6 + 49bbc57
commit e5eac57
Show file tree

Hide file tree

Showing 5 changed files with 106 additions and 48 deletions.
diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
@@ -76,15 +76,15 @@ CHUNK DATA:
       of the ith commit. Stores value 0x7000000 if no parent in that
       position. If there are more than two parents, the second value
       has its most-significant bit on and the other bits store an array
-      position into the Large Edge List chunk.
+      position into the Extra Edge List chunk.
     * The next 8 bytes store the generation number of the commit and
       the commit time in seconds since EPOCH. The generation number
       uses the higher 30 bits of the first 4 bytes, while the commit
       time uses the 32 bits of the second 4 bytes, along with the lowest
       2 bits of the lowest byte, storing the 33rd and 34th bit of the
       commit time.
 
-  Large Edge List (ID: {'E', 'D', 'G', 'E'}) [Optional]
+  Extra Edge List (ID: {'E', 'D', 'G', 'E'}) [Optional]
       This list of 4-byte values store the second through nth parents for
       all octopus merges. The second parent value in the commit data stores
       an array position within this list along with the most-significant bit

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
@@ -110,8 +110,8 @@ static int graph_read(int argc, const char **argv)
 		printf(" oid_lookup");
 	if (graph->chunk_commit_data)
 		printf(" commit_metadata");
-	if (graph->chunk_large_edges)
-		printf(" large_edges");
+	if (graph->chunk_extra_edges)
+		printf(" extra_edges");
 	printf("\n");
 
 	UNLEAK(graph);

diff --git a/commit-graph.c b/commit-graph.c
@@ -21,14 +21,14 @@
 #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
-#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
 #define GRAPH_VERSION_1 0x1
 #define GRAPH_VERSION GRAPH_VERSION_1
 
-#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000
+#define GRAPH_EXTRA_EDGES_NEEDED 0x80000000
 #define GRAPH_EDGE_LAST_MASK 0x7fffffff
 #define GRAPH_PARENT_NONE 0x70000000
 
@@ -209,11 +209,11 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 				graph->chunk_commit_data = data + chunk_offset;
 			break;
 
-		case GRAPH_CHUNKID_LARGEEDGES:
-			if (graph->chunk_large_edges)
+		case GRAPH_CHUNKID_EXTRAEDGES:
+			if (graph->chunk_extra_edges)
 				chunk_repeated = 1;
 			else
-				graph->chunk_large_edges = data + chunk_offset;
+				graph->chunk_extra_edges = data + chunk_offset;
 			break;
 		}
 
@@ -374,12 +374,12 @@ static int fill_commit_in_graph(struct repository *r,
 	edge_value = get_be32(commit_data + g->hash_len + 4);
 	if (edge_value == GRAPH_PARENT_NONE)
 		return 1;
-	if (!(edge_value & GRAPH_OCTOPUS_EDGES_NEEDED)) {
+	if (!(edge_value & GRAPH_EXTRA_EDGES_NEEDED)) {
 		pptr = insert_parent_or_die(r, g, edge_value, pptr);
 		return 1;
 	}
 
-	parent_data_ptr = (uint32_t*)(g->chunk_large_edges +
+	parent_data_ptr = (uint32_t*)(g->chunk_extra_edges +
 			  4 * (uint64_t)(edge_value & GRAPH_EDGE_LAST_MASK));
 	do {
 		edge_value = get_be32(parent_data_ptr);
@@ -466,7 +466,9 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 
 static void write_graph_chunk_fanout(struct hashfile *f,
 				     struct commit **commits,
-				     int nr_commits)
+				     int nr_commits,
+				     struct progress *progress,
+				     uint64_t *progress_cnt)
 {
 	int i, count = 0;
 	struct commit **list = commits;
@@ -480,6 +482,7 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 		while (count < nr_commits) {
 			if ((*list)->object.oid.hash[0] != i)
 				break;
+			display_progress(progress, ++*progress_cnt);
 			count++;
 			list++;
 		}
@@ -489,12 +492,16 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 }
 
 static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
-				   struct commit **commits, int nr_commits)
+				   struct commit **commits, int nr_commits,
+				   struct progress *progress,
+				   uint64_t *progress_cnt)
 {
 	struct commit **list = commits;
 	int count;
-	for (count = 0; count < nr_commits; count++, list++)
+	for (count = 0; count < nr_commits; count++, list++) {
+		display_progress(progress, ++*progress_cnt);
 		hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
+	}
 }
 
 static const unsigned char *commit_to_sha1(size_t index, void *table)
@@ -504,7 +511,9 @@ static const unsigned char *commit_to_sha1(size_t index, void *table)
 }
 
 static void write_graph_chunk_data(struct hashfile *f, int hash_len,
-				   struct commit **commits, int nr_commits)
+				   struct commit **commits, int nr_commits,
+				   struct progress *progress,
+				   uint64_t *progress_cnt)
 {
 	struct commit **list = commits;
 	struct commit **last = commits + nr_commits;
@@ -514,6 +523,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 		struct commit_list *parent;
 		int edge_value;
 		uint32_t packedDate[2];
+		display_progress(progress, ++*progress_cnt);
 
 		parse_commit(*list);
 		hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len);
@@ -542,7 +552,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 		if (!parent)
 			edge_value = GRAPH_PARENT_NONE;
 		else if (parent->next)
-			edge_value = GRAPH_OCTOPUS_EDGES_NEEDED | num_extra_edges;
+			edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges;
 		else {
 			edge_value = sha1_pos(parent->item->object.oid.hash,
 					      commits,
@@ -556,7 +566,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 		hashwrite_be32(f, edge_value);
 
-		if (edge_value & GRAPH_OCTOPUS_EDGES_NEEDED) {
+		if (edge_value & GRAPH_EXTRA_EDGES_NEEDED) {
 			do {
 				num_extra_edges++;
 				parent = parent->next;
@@ -577,16 +587,21 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 	}
 }
 
-static void write_graph_chunk_large_edges(struct hashfile *f,
+static void write_graph_chunk_extra_edges(struct hashfile *f,
 					  struct commit **commits,
-					  int nr_commits)
+					  int nr_commits,
+					  struct progress *progress,
+					  uint64_t *progress_cnt)
 {
 	struct commit **list = commits;
 	struct commit **last = commits + nr_commits;
 	struct commit_list *parent;
 
 	while (list < last) {
 		int num_parents = 0;
+
+		display_progress(progress, ++*progress_cnt);
+
 		for (parent = (*list)->parents; num_parents < 3 && parent;
 		     parent = parent->next)
 			num_parents++;
@@ -680,15 +695,15 @@ static void add_missing_parents(struct packed_oid_list *oids, struct commit *com
 
 static void close_reachable(struct packed_oid_list *oids, int report_progress)
 {
-	int i, j;
+	int i;
 	struct commit *commit;
 	struct progress *progress = NULL;
 
 	if (report_progress)
 		progress = start_delayed_progress(
-			_("Loading known commits in commit graph"), j = 0);
+			_("Loading known commits in commit graph"), oids->nr);
 	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, ++j);
+		display_progress(progress, i + 1);
 		commit = lookup_commit(the_repository, &oids->list[i]);
 		if (commit)
 			commit->object.flags |= UNINTERESTING;
@@ -702,9 +717,9 @@ static void close_reachable(struct packed_oid_list *oids, int report_progress)
 	 */
 	if (report_progress)
 		progress = start_delayed_progress(
-			_("Expanding reachable commits in commit graph"), j = 0);
+			_("Expanding reachable commits in commit graph"), oids->nr);
 	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, ++j);
+		display_progress(progress, i + 1);
 		commit = lookup_commit(the_repository, &oids->list[i]);
 
 		if (commit && !parse_commit(commit))
@@ -714,9 +729,9 @@ static void close_reachable(struct packed_oid_list *oids, int report_progress)
 
 	if (report_progress)
 		progress = start_delayed_progress(
-			_("Clearing commit marks in commit graph"), j = 0);
+			_("Clearing commit marks in commit graph"), oids->nr);
 	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, ++j);
+		display_progress(progress, i + 1);
 		commit = lookup_commit(the_repository, &oids->list[i]);
 
 		if (commit)
@@ -811,12 +826,16 @@ void write_commit_graph(const char *obj_dir,
 	struct commit_list *parent;
 	struct progress *progress = NULL;
 	const unsigned hashsz = the_hash_algo->rawsz;
+	uint64_t progress_cnt = 0;
+	struct strbuf progress_title = STRBUF_INIT;
+	unsigned long approx_nr_objects;
 
 	if (!commit_graph_compatible(the_repository))
 		return;
 
 	oids.nr = 0;
-	oids.alloc = approximate_object_count() / 32;
+	approx_nr_objects = approximate_object_count();
+	oids.alloc = approx_nr_objects / 32;
 	oids.progress = NULL;
 	oids.progress_done = 0;
 
@@ -846,8 +865,12 @@ void write_commit_graph(const char *obj_dir,
 		strbuf_addf(&packname, "%s/pack/", obj_dir);
 		dirlen = packname.len;
 		if (report_progress) {
-			oids.progress = start_delayed_progress(
-				_("Finding commits for commit graph"), 0);
+			strbuf_addf(&progress_title,
+				    Q_("Finding commits for commit graph in %d pack",
+				       "Finding commits for commit graph in %d packs",
+				       pack_indexes->nr),
+				    pack_indexes->nr);
+			oids.progress = start_delayed_progress(progress_title.buf, 0);
 			oids.progress_done = 0;
 		}
 		for (i = 0; i < pack_indexes->nr; i++) {
@@ -865,14 +888,20 @@ void write_commit_graph(const char *obj_dir,
 			free(p);
 		}
 		stop_progress(&oids.progress);
+		strbuf_reset(&progress_title);
 		strbuf_release(&packname);
 	}
 
 	if (commit_hex) {
-		if (report_progress)
-			progress = start_delayed_progress(
-				_("Finding commits for commit graph"),
-				commit_hex->nr);
+		if (report_progress) {
+			strbuf_addf(&progress_title,
+				    Q_("Finding commits for commit graph from %d ref",
+				       "Finding commits for commit graph from %d refs",
+				       commit_hex->nr),
+				    commit_hex->nr);
+			progress = start_delayed_progress(progress_title.buf,
+							  commit_hex->nr);
+		}
 		for (i = 0; i < commit_hex->nr; i++) {
 			const char *end;
 			struct object_id oid;
@@ -892,26 +921,36 @@ void write_commit_graph(const char *obj_dir,
 			}
 		}
 		stop_progress(&progress);
+		strbuf_reset(&progress_title);
 	}
 
 	if (!pack_indexes && !commit_hex) {
 		if (report_progress)
 			oids.progress = start_delayed_progress(
-				_("Finding commits for commit graph"), 0);
+				_("Finding commits for commit graph among packed objects"),
+				approx_nr_objects);
 		for_each_packed_object(add_packed_commits, &oids,
 				       FOR_EACH_OBJECT_PACK_ORDER);
+		if (oids.progress_done < approx_nr_objects)
+			display_progress(oids.progress, approx_nr_objects);
 		stop_progress(&oids.progress);
 	}
 
 	close_reachable(&oids, report_progress);
 
+	if (report_progress)
+		progress = start_delayed_progress(
+			_("Counting distinct commits in commit graph"),
+			oids.nr);
+	display_progress(progress, 0); /* TODO: Measure QSORT() progress */
 	QSORT(oids.list, oids.nr, commit_compare);
-
 	count_distinct = 1;
 	for (i = 1; i < oids.nr; i++) {
+		display_progress(progress, i + 1);
 		if (!oideq(&oids.list[i - 1], &oids.list[i]))
 			count_distinct++;
 	}
+	stop_progress(&progress);
 
 	if (count_distinct >= GRAPH_EDGE_LAST_MASK)
 		die(_("the commit graph format cannot write %d commits"), count_distinct);
@@ -921,8 +960,13 @@ void write_commit_graph(const char *obj_dir,
 	ALLOC_ARRAY(commits.list, commits.alloc);
 
 	num_extra_edges = 0;
+	if (report_progress)
+		progress = start_delayed_progress(
+			_("Finding extra edges in commit graph"),
+			oids.nr);
 	for (i = 0; i < oids.nr; i++) {
 		int num_parents = 0;
+		display_progress(progress, i + 1);
 		if (i > 0 && oideq(&oids.list[i - 1], &oids.list[i]))
 			continue;
 
@@ -939,6 +983,7 @@ void write_commit_graph(const char *obj_dir,
 		commits.nr++;
 	}
 	num_chunks = num_extra_edges ? 4 : 3;
+	stop_progress(&progress);
 
 	if (commits.nr >= GRAPH_EDGE_LAST_MASK)
 		die(_("too many commits to write graph"));
@@ -966,7 +1011,7 @@ void write_commit_graph(const char *obj_dir,
 	chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
 	chunk_ids[2] = GRAPH_CHUNKID_DATA;
 	if (num_extra_edges)
-		chunk_ids[3] = GRAPH_CHUNKID_LARGEEDGES;
+		chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES;
 	else
 		chunk_ids[3] = 0;
 	chunk_ids[4] = 0;
@@ -986,10 +1031,23 @@ void write_commit_graph(const char *obj_dir,
 		hashwrite(f, chunk_write, 12);
 	}
 
-	write_graph_chunk_fanout(f, commits.list, commits.nr);
-	write_graph_chunk_oids(f, hashsz, commits.list, commits.nr);
-	write_graph_chunk_data(f, hashsz, commits.list, commits.nr);
-	write_graph_chunk_large_edges(f, commits.list, commits.nr);
+	if (report_progress) {
+		strbuf_addf(&progress_title,
+			    Q_("Writing out commit graph in %d pass",
+			       "Writing out commit graph in %d passes",
+			       num_chunks),
+			    num_chunks);
+		progress = start_delayed_progress(
+			progress_title.buf,
+			num_chunks * commits.nr);
+	}
+	write_graph_chunk_fanout(f, commits.list, commits.nr, progress, &progress_cnt);
+	write_graph_chunk_oids(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
+	write_graph_chunk_data(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
+	if (num_extra_edges)
+		write_graph_chunk_extra_edges(f, commits.list, commits.nr, progress, &progress_cnt);
+	stop_progress(&progress);
+	strbuf_release(&progress_title);
 
 	close_commit_graph(the_repository);
 	finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);

diff --git a/commit-graph.h b/commit-graph.h
@@ -49,7 +49,7 @@ struct commit_graph {
 	const uint32_t *chunk_oid_fanout;
 	const unsigned char *chunk_oid_lookup;
 	const unsigned char *chunk_commit_data;
-	const unsigned char *chunk_large_edges;
+	const unsigned char *chunk_extra_edges;
 };
 
 struct commit_graph *load_commit_graph_one(const char *graph_file);