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>
#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_GENERATION_DATA_OVERFLOW 0x47444f56 /* "GDOV" */
#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 9
#define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
+ GRAPH_FANOUT_SIZE + the_hash_algo->rawsz)
+#define CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW (1ULL << 31)
+
/* Remember to update object flag allocation in object.h */
#define REACHABLE (1u<<15)
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_GENERATION_DATA_OVERFLOW:
+ if (graph->chunk_generation_data_overflow)
+ chunk_repeated = 1;
+ else
+ graph->chunk_generation_data_overflow = data + chunk_offset;
+ break;
+
case GRAPH_CHUNKID_EXTRAEDGES:
if (graph->chunk_extra_edges)
chunk_repeated = 1;
{
const unsigned char *commit_data;
struct commit_graph_data *graph_data;
- uint32_t lex_index;
- uint64_t date_high, date_low;
+ uint32_t lex_index, offset_pos;
+ uint64_t date_high, date_low, offset;
while (pos < g->num_commits_in_base)
g = g->base_graph;
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) {
+ offset = (timestamp_t)get_be32(g->chunk_generation_data + sizeof(uint32_t) * lex_index);
+
+ if (offset & CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW) {
+ if (!g->chunk_generation_data_overflow)
+ die(_("commit-graph requires overflow generation data but has none"));
+
+ offset_pos = offset ^ CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW;
+ graph_data->generation = get_be64(g->chunk_generation_data_overflow + 8 * offset_pos);
+ } else
+ graph_data->generation = item->date + offset;
+ } else
+ graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
if (g->topo_levels)
*topo_level_slab_at(g->topo_levels, item) = get_be32(commit_data + g->hash_len + 8) >> 2;
struct oid_array oids;
struct packed_commit_list commits;
int num_extra_edges;
+ int num_generation_data_overflows;
unsigned long approx_nr_objects;
struct progress *progress;
int progress_done;
report_progress:1,
split:1,
changed_paths:1,
- order_by_pack:1;
+ order_by_pack:1,
+ write_generation_data:1;
struct topo_level_slab *topo_levels;
const struct commit_graph_opts *opts;
return 0;
}
+static int write_graph_chunk_generation_data(struct hashfile *f,
+ struct write_commit_graph_context *ctx)
+{
+ int i, num_generation_data_overflows = 0;
+
+ for (i = 0; i < ctx->commits.nr; i++) {
+ struct commit *c = ctx->commits.list[i];
+ timestamp_t offset = commit_graph_data_at(c)->generation - c->date;
+ display_progress(ctx->progress, ++ctx->progress_cnt);
+
+ if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) {
+ offset = CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW | num_generation_data_overflows;
+ num_generation_data_overflows++;
+ }
+
+ hashwrite_be32(f, offset);
+ }
+
+ return 0;
+}
+
+static int write_graph_chunk_generation_data_overflow(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];
+ timestamp_t offset = commit_graph_data_at(c)->generation - c->date;
+ display_progress(ctx->progress, ++ctx->progress_cnt);
+
+ if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) {
+ hashwrite_be32(f, offset >> 32);
+ hashwrite_be32(f, (uint32_t) offset);
+ }
+ }
+
+ return 0;
+}
+
static int write_graph_chunk_extra_edges(struct hashfile *f,
struct write_commit_graph_context *ctx)
{
if (current->date && current->date > max_corrected_commit_date)
max_corrected_commit_date = current->date - 1;
commit_graph_data_at(current)->generation = max_corrected_commit_date + 1;
+
+ if (commit_graph_data_at(current)->generation - current->date > GENERATION_NUMBER_V2_OFFSET_MAX)
+ ctx->num_generation_data_overflows++;
}
}
}
chunks[2].id = GRAPH_CHUNKID_DATA;
chunks[2].size = (hashsz + 16) * ctx->commits.nr;
chunks[2].write_fn = write_graph_chunk_data;
+
+ if (git_env_bool(GIT_TEST_COMMIT_GRAPH_NO_GDAT, 0))
+ ctx->write_generation_data = 0;
+ 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_generation_data_overflows) {
+ chunks[num_chunks].id = GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW;
+ chunks[num_chunks].size = sizeof(timestamp_t) * ctx->num_generation_data_overflows;
+ chunks[num_chunks].write_fn = write_graph_chunk_generation_data_overflow;
+ num_chunks++;
+ }
if (ctx->num_extra_edges) {
chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
chunks[num_chunks].size = 4 * ctx->num_extra_edges;
ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
ctx->opts = opts;
ctx->total_bloom_filter_data_size = 0;
+ ctx->write_generation_data = 1;
+ ctx->num_generation_data_overflows = 0;
bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
bloom_settings.bits_per_entry);
continue;
/*
- * If one of our parents has generation GENERATION_NUMBER_V1_MAX, then
- * our generation is also GENERATION_NUMBER_V1_MAX. Decrement to avoid
- * extra logic in the following condition.
+ * If we are using topological level and one of our parents has
+ * generation GENERATION_NUMBER_V1_MAX, then our generation is
+ * also GENERATION_NUMBER_V1_MAX. Decrement to avoid extra logic
+ * in the following condition.
*/
- if (max_generation == GENERATION_NUMBER_V1_MAX)
+ if (!g->chunk_generation_data && max_generation == GENERATION_NUMBER_V1_MAX)
max_generation--;
generation = commit_graph_generation(graph_commit);
- if (generation != max_generation + 1)
- graph_report(_("commit-graph generation for commit %s is %"PRItime" != %"PRItime),
+ if (generation < max_generation + 1)
+ graph_report(_("commit-graph generation for commit %s is %"PRItime" < %"PRItime),
oid_to_hex(&cur_oid),
generation,
max_generation + 1);
#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"
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_generation_data_overflow;
const unsigned char *chunk_extra_edges;
const unsigned char *chunk_base_graphs;
const unsigned char *chunk_bloom_indexes;
#define GENERATION_NUMBER_INFINITY ((1ULL << 63) - 1)
#define GENERATION_NUMBER_V1_MAX 0x3FFFFFFF
#define GENERATION_NUMBER_ZERO 0
+#define GENERATION_NUMBER_V2_OFFSET_MAX ((1ULL << 31) - 1)
struct commit_list {
struct commit *item;
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
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)
'
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
graph_read_expect() {
OPTIONAL=""
NUM_CHUNKS=3
- if test ! -z $2
+ if test ! -z "$2"
then
OPTIONAL=" $2"
NUM_CHUNKS=$((3 + $(echo "$2" | wc -w)))
# valid commit and tree OID
git rev-parse HEAD HEAD^{tree} >in &&
git commit-graph write --stdin-commits <in &&
- graph_read_expect 3
+ graph_read_expect 3 generation_data
'
test_expect_success 'write graph' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "3"
+ graph_read_expect "3" generation_data
'
test_expect_success POSIXPERM 'write graph has correct permissions' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "10" "extra_edges"
+ graph_read_expect "10" "generation_data extra_edges"
'
graph_git_behavior 'merge 1 vs 2' full merge/1 merge/2
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "11" "extra_edges"
+ graph_read_expect "11" "generation_data extra_edges"
'
graph_git_behavior 'full graph, commit 8 vs merge 1' full commits/8 merge/1
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "11" "extra_edges"
+ graph_read_expect "11" "generation_data extra_edges"
'
graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1
cd "$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
git rev-parse merge/1 >>commits-in &&
cat commits-in | git commit-graph write --stdin-commits &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "6"
+ graph_read_expect "6" "generation_data"
'
graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1
cd "$TRASH_DIRECTORY/full" &&
git rev-parse merge/3 | git commit-graph write --stdin-commits --append &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "10" "extra_edges"
+ graph_read_expect "10" "generation_data extra_edges"
'
graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write --reachable &&
test_path_is_file $objdir/info/commit-graph &&
- graph_read_expect "11" "extra_edges"
+ graph_read_expect "11" "generation_data extra_edges"
'
graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
cd "$TRASH_DIRECTORY/bare" &&
git commit-graph write &&
test_path_is_file $baredir/info/commit-graph &&
- graph_read_expect "11" "extra_edges"
+ graph_read_expect "11" "generation_data extra_edges"
'
graph_git_behavior 'bare repo with graph, commit 8 vs merge 1' bare commits/8 merge/1
test_expect_success 'git commit-graph verify' '
cd "$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
)
'
+# 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
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
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: $1
- chunks: oid_fanout oid_lookup commit_metadata
+ chunks: oid_fanout oid_lookup commit_metadata generation_data
EOF
test-tool read-graph >output &&
test_cmp expect output
git show-ref -s commit-5-5 | git commit-graph write --stdin-commits &&
mv .git/objects/info/commit-graph commit-graph-half &&
chmod u+w commit-graph-half &&
+ GIT_TEST_COMMIT_GRAPH_NO_GDAT=1 git commit-graph write --reachable &&
+ mv .git/objects/info/commit-graph commit-graph-no-gdat &&
+ chmod u+w commit-graph-no-gdat &&
git config core.commitGraph true
'
test_cmp expect actual &&
cp commit-graph-half .git/objects/info/commit-graph &&
"$@" <input >actual &&
+ test_cmp expect actual &&
+ cp commit-graph-no-gdat .git/objects/info/commit-graph &&
+ "$@" <input >actual &&
test_cmp expect actual
}
--signoff)
signoff="$1"
;;
+ --date)
+ notick=yes
+ GIT_COMMITTER_DATE="$2"
+ GIT_AUTHOR_DATE="$2"
+ shift
+ ;;
-C)
indir="$2"
shift
projects / thirdparty / git.git / commitdiff
