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 v2 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 will store corrected committer date offsets 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.

To minimize the space required to store corrrected commit date, Git
stores corrected commit date offsets into the commit-graph file, instea
of corrected commit dates. This saves us 4 bytes per commit, decreasing
the GDAT chunk size by half, but it's possible for the offset to
overflow the 4-bytes allocated for storage. As such overflows are and
should be exceedingly rare, we use the following overflow management
scheme:

We introduce a new commit-graph chunk, Generation Data OVerflow ('GDOV')
to store corrected commit dates for commits with offsets greater than
GENERATION_NUMBER_V2_OFFSET_MAX.

If the offset is greater than GENERATION_NUMBER_V2_OFFSET_MAX, we set
the MSB of the offset and the other bits store the position of corrected
commit date in GDOV chunk, similar to how Extra Edge List is maintained.

We test the overflow-related code with the following repo history:

           F - N - U
          /         \
U - N - U            N
         \          /
	  N - F - N

Where the commits denoted by U have committer date of zero seconds
since Unix epoch, the commits denoted by N have committer date of
1112354055 (default committer date for the test suite) seconds since
Unix epoch and the commits denoted by F have committer date of
(2 ^ 31 - 2) seconds since Unix epoch.

The largest offset observed is 2 ^ 31, just large enough to overflow.

[1]: https://lore.kernel.org/git/87a7gdspo4.fsf@evledraar.gmail.com/

Signed-off-by: Abhishek Kumar <abhishekkumar8222@gmail.com>
Reviewed-by: Taylor Blau <me@ttaylorr.com>
Reviewed-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

7 files changed, 93 insertions, 21 deletions

diff --git a/t/README b/t/README
index c730a70770..8a12148727 100644
--- a/t/README
+++ b/t/README
@@ -393,6 +393,9 @@ 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
diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index 5f585a1725..75927b2c81 100644
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -33,6 +33,10 @@ 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_generation_data_overflow)
+		printf(" generation_data_overflow");
 	if (graph->chunk_extra_edges)
 		printf(" extra_edges");
 	if (graph->chunk_bloom_indexes)
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index d11040ce41..dbde016188 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -40,11 +40,11 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 '
 
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 $(test_oid oid_version) $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
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index 2ed0c1544d..fa27df579a 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -76,7 +76,7 @@ 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)))
@@ -103,14 +103,14 @@ 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' '
@@ -219,7 +219,7 @@ 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
@@ -254,7 +254,7 @@ 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
@@ -264,7 +264,7 @@ 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
@@ -274,7 +274,7 @@ 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
@@ -287,7 +287,7 @@ 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
@@ -297,7 +297,7 @@ 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
@@ -307,7 +307,7 @@ 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
@@ -328,7 +328,7 @@ 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
@@ -454,8 +454,9 @@ test_expect_success 'warn on improper hash version' '
 
 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
@@ -741,4 +742,56 @@ test_expect_success 'corrupt commit-graph write (missing tree)' '
 	)
 '
 
+# We test the overflow-related code with the following repo history:
+#
+#               4:F - 5:N - 6:U
+#              /                \
+# 1:U - 2:N - 3:U                M:N
+#              \                /
+#               7:N - 8:F - 9:N
+#
+# Here the commits denoted by U have committer date of zero seconds
+# since Unix epoch, the commits denoted by N have committer date
+# starting from 1112354055 seconds since Unix epoch (default committer
+# date for the test suite), and the commits denoted by F have committer
+# date of (2 ^ 31 - 2) seconds since Unix epoch.
+#
+# The largest offset observed is 2 ^ 31, just large enough to overflow.
+#
+
+test_expect_success 'set up and verify repo with generation data overflow chunk' '
+	objdir=".git/objects" &&
+	UNIX_EPOCH_ZERO="@0 +0000" &&
+	FUTURE_DATE="@2147483646 +0000" &&
+	test_oid_cache <<-EOF &&
+	oid_version sha1:1
+	oid_version sha256:2
+	EOF
+	cd "$TRASH_DIRECTORY" &&
+	mkdir repo &&
+	cd repo &&
+	git init &&
+	test_commit --date "$UNIX_EPOCH_ZERO" 1 &&
+	test_commit 2 &&
+	test_commit --date "$UNIX_EPOCH_ZERO" 3 &&
+	git commit-graph write --reachable &&
+	graph_read_expect 3 generation_data &&
+	test_commit --date "$FUTURE_DATE" 4 &&
+	test_commit 5 &&
+	test_commit --date "$UNIX_EPOCH_ZERO" 6 &&
+	git branch left &&
+	git reset --hard 3 &&
+	test_commit 7 &&
+	test_commit --date "$FUTURE_DATE" 8 &&
+	test_commit 9 &&
+	git branch right &&
+	git reset --hard 3 &&
+	test_merge M left right &&
+	git commit-graph write --reachable &&
+	graph_read_expect 10 "generation_data generation_data_overflow" &&
+	git commit-graph verify
+'
+
+graph_git_behavior 'generation data overflow chunk repo' repo left right
+
 test_done
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 4d3842b83b..587757b62d 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -13,11 +13,11 @@ test_expect_success 'setup repo' '
 	infodir=".git/objects/info" &&
 	graphdir="$infodir/commit-graphs" &&
 	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
 
 	oid_version sha1:1
 	oid_version sha256:2
@@ -31,9 +31,9 @@ graph_read_expect() {
 		NUM_BASE=$2
 	fi
 	cat >expect <<- EOF
-	header: 43475048 1 $(test_oid oid_version) 3 $NUM_BASE
+	header: 43475048 1 $(test_oid oid_version) 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
diff --git a/t/t6600-test-reach.sh b/t/t6600-test-reach.sh
index af10f0dc09..e2d33a8a4c 100755
--- a/t/t6600-test-reach.sh
+++ b/t/t6600-test-reach.sh
@@ -55,6 +55,9 @@ test_expect_success 'setup' '
 	git show-ref -s commit-5-5 | git commit-graph write --stdin-commits &&
 	mv .git/objects/info/commit-graph commit-graph-half &&
 	chmod u+w commit-graph-half &&
+	GIT_TEST_COMMIT_GRAPH_NO_GDAT=1 git commit-graph write --reachable &&
+	mv .git/objects/info/commit-graph commit-graph-no-gdat &&
+	chmod u+w commit-graph-no-gdat &&
 	git config core.commitGraph true
 '
 
@@ -67,6 +70,9 @@ run_all_modes () {
 	test_cmp expect actual &&
 	cp commit-graph-half .git/objects/info/commit-graph &&
 	"$@" <input >actual &&
+	test_cmp expect actual &&
+	cp commit-graph-no-gdat .git/objects/info/commit-graph &&
+	"$@" <input >actual &&
 	test_cmp expect actual
 }
 
diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh
index 999982fe4a..3ad712c3ac 100644
--- a/t/test-lib-functions.sh
+++ b/t/test-lib-functions.sh
@@ -202,6 +202,12 @@ test_commit () {
 		--signoff)
 			signoff="$1"
 			;;
+		--date)
+			notick=yes
+			GIT_COMMITTER_DATE="$2"
+			GIT_AUTHOR_DATE="$2"
+			shift
+			;;
 		-C)
 			indir="$2"
 			shift