commit-graph: implement generation data chunk

As discovered by Ævar, we cannot increment graph version to
distinguish between generation numbers v1 and v2 [1]. Thus, one of
pre-requistes before implementing generation number was to distinguish
between graph versions in a backwards compatible manner.

We are going to introduce a new chunk called Generation Data chunk (or
GDAT). GDAT stores generation number v2 (and any subsequent versions),
whereas CDAT will still store topological level.

Old Git does not understand GDAT chunk and would ignore it, reading
topological levels from CDAT. New Git can parse GDAT and take advantage
of newer generation numbers, falling back to topological levels when
GDAT chunk is missing (as it would happen with a commit graph written
by old Git).

We introduce a test environment variable 'GIT_TEST_COMMIT_GRAPH_NO_GDAT'
which forces commit-graph file to be written without generation data
chunk to emulate a commit-graph file written by old Git.

[1]: https://lore.kernel.org/git/[email protected]/

Signed-off-by: Abhishek Kumar <[email protected]>

Author: abhishekkumar2718

commit-graph.c

@@ -38,11 +38,12 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
+#define GRAPH_CHUNKID_GENERATION_DATA 0x47444154 /* "GDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 8
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -392,6 +393,13 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 				graph->chunk_commit_data = data + chunk_offset;
 			break;
 
+		case GRAPH_CHUNKID_GENERATION_DATA:
+			if (graph->chunk_generation_data)
+				chunk_repeated = 1;
+			else
+				graph->chunk_generation_data = data + chunk_offset;
+			break;
+
 		case GRAPH_CHUNKID_EXTRAEDGES:
 			if (graph->chunk_extra_edges)
 				chunk_repeated = 1;
@@ -758,7 +766,10 @@ static void fill_commit_graph_info(struct commit *item, struct commit_graph *g,
 	date_low = get_be32(commit_data + g->hash_len + 12);
 	item->date = (timestamp_t)((date_high << 32) | date_low);
 
-	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+	if (g->chunk_generation_data)
+		graph_data->generation = get_be32(g->chunk_generation_data + sizeof(uint32_t) * lex_index);
+	else
+		graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
 }
 
 static inline void set_commit_tree(struct commit *c, struct tree *t)
@@ -951,7 +962,8 @@ struct write_commit_graph_context {
 		 report_progress:1,
 		 split:1,
 		 changed_paths:1,
-		 order_by_pack:1;
+		 order_by_pack:1,
+		 write_generation_data:1;
 
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
@@ -1105,8 +1117,21 @@ static int write_graph_chunk_data(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_generation_data(struct hashfile *f,
+					      struct write_commit_graph_context *ctx)
+{
+	int i;
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = ctx->commits.list[i];
+		display_progress(ctx->progress, ++ctx->progress_cnt);
+		hashwrite_be32(f, commit_graph_data_at(c)->generation);
+	}
+
+	return 0;
+}
+
 static int write_graph_chunk_extra_edges(struct hashfile *f,
-					 struct write_commit_graph_context *ctx)
+					  struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -1710,6 +1735,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	chunks[2].id = GRAPH_CHUNKID_DATA;
 	chunks[2].size = (hashsz + 16) * ctx->commits.nr;
 	chunks[2].write_fn = write_graph_chunk_data;
+	if (ctx->write_generation_data) {
+		chunks[num_chunks].id = GRAPH_CHUNKID_GENERATION_DATA;
+		chunks[num_chunks].size = sizeof(uint32_t) * ctx->commits.nr;
+		chunks[num_chunks].write_fn = write_graph_chunk_generation_data;
+		num_chunks++;
+	}
 	if (ctx->num_extra_edges) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
 		chunks[num_chunks].size = 4 * ctx->num_extra_edges;
@@ -2113,6 +2144,7 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
 	ctx->split_opts = split_opts;
 	ctx->total_bloom_filter_data_size = 0;
+	ctx->write_generation_data = !git_env_bool(GIT_TEST_COMMIT_GRAPH_NO_GDAT, 0);
 
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;

commit-graph.h

@@ -6,6 +6,7 @@
 #include "oidset.h"
 
 #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
+#define GIT_TEST_COMMIT_GRAPH_NO_GDAT "GIT_TEST_COMMIT_GRAPH_NO_GDAT"
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE"
 #define GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS "GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS"
 
@@ -67,6 +68,7 @@ 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_generation_data;
 	const unsigned char *chunk_extra_edges;
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_bloom_indexes;

t/README

@@ -379,6 +379,9 @@ GIT_TEST_COMMIT_GRAPH=<boolean>, when true, forces the commit-graph to
 be written after every 'git commit' command, and overrides the
 'core.commitGraph' setting to true.
 
+GIT_TEST_COMMIT_GRAPH_NO_GDAT=<boolean>, when true, forces the
+commit-graph to be written without generation data chunk.
+
 GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=<boolean>, when true, forces
 commit-graph write to compute and write changed path Bloom filters for
 every 'git commit-graph write', as if the `--changed-paths` option was

t/helper/test-read-graph.c

@@ -32,6 +32,8 @@ int cmd__read_graph(int argc, const char **argv)
 		printf(" oid_lookup");
 	if (graph->chunk_commit_data)
 		printf(" commit_metadata");
+	if (graph->chunk_generation_data)
+		printf(" generation_data");
 	if (graph->chunk_extra_edges)
 		printf(" extra_edges");
 	if (graph->chunk_bloom_indexes)

t/t4216-log-bloom.sh

@@ -33,11 +33,11 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	git commit-graph write --reachable --changed-paths
 '
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 1 $NUM_CHUNKS 0
 	num_commits: $1
-	chunks: oid_fanout oid_lookup commit_metadata bloom_indexes bloom_data
+	chunks: oid_fanout oid_lookup commit_metadata generation_data bloom_indexes bloom_data
 	EOF
 	test-tool read-graph >actual &&
 	test_cmp expect actual

t/t5318-commit-graph.sh

@@ -72,7 +72,7 @@ graph_git_behavior 'no graph' full commits/3 commits/1
 graph_read_expect() {
 	OPTIONAL=""
 	NUM_CHUNKS=3
-	if test ! -z $2
+	if test ! -z "$2"
 	then
 		OPTIONAL=" $2"
 		NUM_CHUNKS=$((3 + $(echo "$2" | wc -w)))
@@ -99,14 +99,14 @@ test_expect_success 'exit with correct error on bad input to --stdin-commits' '
 	# valid commit and tree OID
 	git rev-parse HEAD HEAD^{tree} >in &&
 	git commit-graph write --stdin-commits <in &&
-	graph_read_expect 3
+	graph_read_expect 3 generation_data
 '
 
 test_expect_success 'write graph' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "3"
+	graph_read_expect "3" generation_data
 '
 
 test_expect_success POSIXPERM 'write graph has correct permissions' '
@@ -215,7 +215,7 @@ test_expect_success 'write graph with merges' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "10" "extra_edges"
+	graph_read_expect "10" "generation_data extra_edges"
 '
 
 graph_git_behavior 'merge 1 vs 2' full merge/1 merge/2
@@ -250,7 +250,7 @@ test_expect_success 'write graph with new commit' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "11" "extra_edges"
+	graph_read_expect "11" "generation_data extra_edges"
 '
 
 graph_git_behavior 'full graph, commit 8 vs merge 1' full commits/8 merge/1
@@ -260,7 +260,7 @@ test_expect_success 'write graph with nothing new' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "11" "extra_edges"
+	graph_read_expect "11" "generation_data extra_edges"
 '
 
 graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1
@@ -270,7 +270,7 @@ test_expect_success 'build graph from latest pack with closure' '
 	cd "$TRASH_DIRECTORY/full" &&
 	cat new-idx | git commit-graph write --stdin-packs &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "9" "extra_edges"
+	graph_read_expect "9" "generation_data extra_edges"
 '
 
 graph_git_behavior 'graph from pack, commit 8 vs merge 1' full commits/8 merge/1
@@ -283,7 +283,7 @@ test_expect_success 'build graph from commits with closure' '
 	git rev-parse merge/1 >>commits-in &&
 	cat commits-in | git commit-graph write --stdin-commits &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "6"
+	graph_read_expect "6" "generation_data"
 '
 
 graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1
@@ -293,7 +293,7 @@ test_expect_success 'build graph from commits with append' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git rev-parse merge/3 | git commit-graph write --stdin-commits --append &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "10" "extra_edges"
+	graph_read_expect "10" "generation_data extra_edges"
 '
 
 graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
@@ -303,7 +303,7 @@ test_expect_success 'build graph using --reachable' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git commit-graph write --reachable &&
 	test_path_is_file $objdir/info/commit-graph &&
-	graph_read_expect "11" "extra_edges"
+	graph_read_expect "11" "generation_data extra_edges"
 '
 
 graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
@@ -324,7 +324,7 @@ test_expect_success 'write graph in bare repo' '
 	cd "$TRASH_DIRECTORY/bare" &&
 	git commit-graph write &&
 	test_path_is_file $baredir/info/commit-graph &&
-	graph_read_expect "11" "extra_edges"
+	graph_read_expect "11" "generation_data extra_edges"
 '
 
 graph_git_behavior 'bare repo with graph, commit 8 vs merge 1' bare commits/8 merge/1
@@ -421,8 +421,9 @@ test_expect_success 'replace-objects invalidates commit-graph' '
 
 test_expect_success 'git commit-graph verify' '
 	cd "$TRASH_DIRECTORY/full" &&
-	git rev-parse commits/8 | git commit-graph write --stdin-commits &&
-	git commit-graph verify >output
+	git rev-parse commits/8 | GIT_TEST_COMMIT_GRAPH_NO_GDAT=1 git commit-graph write --stdin-commits &&
+	git commit-graph verify >output &&
+	graph_read_expect 9 extra_edges
 '
 
 NUM_COMMITS=9

t/t5324-split-commit-graph.sh

@@ -14,11 +14,11 @@ test_expect_success 'setup repo' '
 	graphdir="$infodir/commit-graphs" &&
 	test_oid_init &&
 	test_oid_cache <<-EOM
-	shallow sha1:1760
-	shallow sha256:2064
+	shallow sha1:2132
+	shallow sha256:2436
 
-	base sha1:1376
-	base sha256:1496
+	base sha1:1408
+	base sha256:1528
 	EOM
 '
 
@@ -29,9 +29,9 @@ graph_read_expect() {
 		NUM_BASE=$2
 	fi
 	cat >expect <<- EOF
-	header: 43475048 1 1 3 $NUM_BASE
+	header: 43475048 1 1 4 $NUM_BASE
 	num_commits: $1
-	chunks: oid_fanout oid_lookup commit_metadata
+	chunks: oid_fanout oid_lookup commit_metadata generation_data
 	EOF
 	test-tool read-graph >output &&
 	test_cmp expect output