commit-graph: use generation v2 only if entire chain does

Since there are released versions of Git that understand generation
numbers in the commit-graph's CDAT chunk but do not understand the GDAT
chunk, the following scenario is possible:

1. "New" Git writes a commit-graph with the GDAT chunk.
2. "Old" Git writes a split commit-graph on top without a GDAT chunk.

If each layer of split commit-graph is treated independently, as it was
the case before this commit, with Git inspecting only the current layer
for chunk_generation_data pointer, commits in the lower layer (one with
GDAT) whould have corrected commit date as their generation number,
while commits in the upper layer would have topological levels as their
generation. Corrected commit dates usually have much larger values than
topological levels. This means that if we take two commits, one from the
upper layer, and one reachable from it in the lower layer, then the
expectation that the generation of a parent is smaller than the
generation of a child would be violated.

It is difficult to expose this issue in a test. Since we _start_ with
artificially low generation numbers, any commit walk that prioritizes
generation numbers will walk all of the commits with high generation
number before walking the commits with low generation number. In all the
cases I tried, the commit-graph layers themselves "protect" any
incorrect behavior since none of the commits in the lower layer can
reach the commits in the upper layer.

This issue would manifest itself as a performance problem in this case,
especially with something like "git log --graph" since the low
generation numbers would cause the in-degree queue to walk all of the
commits in the lower layer before allowing the topo-order queue to write
anything to output (depending on the size of the upper layer).

Therefore, When writing the new layer in split commit-graph, we write a
GDAT chunk only if the topmost layer has a GDAT chunk. This guarantees
that if a layer has GDAT chunk, all lower layers must have a GDAT chunk
as well.

Rewriting layers follows similar approach: if the topmost layer below
the set of layers being rewritten (in the split commit-graph chain)
exists, and it does not contain GDAT chunk, then the result of rewrite
does not have GDAT chunks either.

Signed-off-by: Derrick Stolee <dstolee@microsoft.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>
This commit is contained in:
Abhishek Kumar 2021-01-16 18:11:16 +00:00 committed by Junio C Hamano
parent e8b63005c4
commit 1fdc383c5c
3 changed files with 210 additions and 2 deletions

View File

@ -614,6 +614,21 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
return graph_chain;
}
static void validate_mixed_generation_chain(struct commit_graph *g)
{
int read_generation_data;
if (!g)
return;
read_generation_data = !!g->chunk_generation_data;
while (g) {
g->read_generation_data = read_generation_data;
g = g->base_graph;
}
}
struct commit_graph *read_commit_graph_one(struct repository *r,
struct object_directory *odb)
{
@ -622,6 +637,8 @@ struct commit_graph *read_commit_graph_one(struct repository *r,
if (!g)
g = load_commit_graph_chain(r, odb);
validate_mixed_generation_chain(g);
return g;
}
@ -791,7 +808,7 @@ 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);
if (g->chunk_generation_data) {
if (g->read_generation_data) {
offset = (timestamp_t)get_be32(g->chunk_generation_data + sizeof(uint32_t) * lex_index);
if (offset & CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW) {
@ -2019,6 +2036,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
if (i < ctx->num_commit_graphs_after)
ctx->commit_graph_hash_after[i] = xstrdup(oid_to_hex(&g->oid));
/*
* If the topmost remaining layer has generation data chunk, the
* resultant layer also has generation data chunk.
*/
if (i == ctx->num_commit_graphs_after - 2)
ctx->write_generation_data = !!g->chunk_generation_data;
i--;
g = g->base_graph;
}
@ -2343,6 +2367,8 @@ int write_commit_graph(struct object_directory *odb,
} else
ctx->num_commit_graphs_after = 1;
validate_mixed_generation_chain(ctx->r->objects->commit_graph);
compute_generation_numbers(ctx);
if (ctx->changed_paths)
@ -2541,7 +2567,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
* also GENERATION_NUMBER_V1_MAX. Decrement to avoid extra logic
* in the following condition.
*/
if (!g->chunk_generation_data && max_generation == GENERATION_NUMBER_V1_MAX)
if (!g->read_generation_data && max_generation == GENERATION_NUMBER_V1_MAX)
max_generation--;
generation = commit_graph_generation(graph_commit);

View File

@ -64,6 +64,7 @@ struct commit_graph {
struct object_directory *odb;
uint32_t num_commits_in_base;
unsigned int read_generation_data;
struct commit_graph *base_graph;
const uint32_t *chunk_oid_fanout;

View File

@ -453,4 +453,185 @@ test_expect_success 'prevent regression for duplicate commits across layers' '
git -C dup commit-graph verify
'
NUM_FIRST_LAYER_COMMITS=64
NUM_SECOND_LAYER_COMMITS=16
NUM_THIRD_LAYER_COMMITS=7
NUM_FOURTH_LAYER_COMMITS=8
NUM_FIFTH_LAYER_COMMITS=16
SECOND_LAYER_SEQUENCE_START=$(($NUM_FIRST_LAYER_COMMITS + 1))
SECOND_LAYER_SEQUENCE_END=$(($SECOND_LAYER_SEQUENCE_START + $NUM_SECOND_LAYER_COMMITS - 1))
THIRD_LAYER_SEQUENCE_START=$(($SECOND_LAYER_SEQUENCE_END + 1))
THIRD_LAYER_SEQUENCE_END=$(($THIRD_LAYER_SEQUENCE_START + $NUM_THIRD_LAYER_COMMITS - 1))
FOURTH_LAYER_SEQUENCE_START=$(($THIRD_LAYER_SEQUENCE_END + 1))
FOURTH_LAYER_SEQUENCE_END=$(($FOURTH_LAYER_SEQUENCE_START + $NUM_FOURTH_LAYER_COMMITS - 1))
FIFTH_LAYER_SEQUENCE_START=$(($FOURTH_LAYER_SEQUENCE_END + 1))
FIFTH_LAYER_SEQUENCE_END=$(($FIFTH_LAYER_SEQUENCE_START + $NUM_FIFTH_LAYER_COMMITS - 1))
# Current split graph chain:
#
# 16 commits (No GDAT)
# ------------------------
# 64 commits (GDAT)
#
test_expect_success 'setup repo for mixed generation commit-graph-chain' '
graphdir=".git/objects/info/commit-graphs" &&
test_oid_cache <<-EOF &&
oid_version sha1:1
oid_version sha256:2
EOF
git init mixed &&
(
cd mixed &&
git config core.commitGraph true &&
git config gc.writeCommitGraph false &&
for i in $(test_seq $NUM_FIRST_LAYER_COMMITS)
do
test_commit $i &&
git branch commits/$i || return 1
done &&
git commit-graph write --reachable --split &&
graph_read_expect $NUM_FIRST_LAYER_COMMITS &&
test_line_count = 1 $graphdir/commit-graph-chain &&
for i in $(test_seq $SECOND_LAYER_SEQUENCE_START $SECOND_LAYER_SEQUENCE_END)
do
test_commit $i &&
git branch commits/$i || return 1
done &&
GIT_TEST_COMMIT_GRAPH_NO_GDAT=1 git commit-graph write --reachable --split=no-merge &&
test_line_count = 2 $graphdir/commit-graph-chain &&
test-tool read-graph >output &&
cat >expect <<-EOF &&
header: 43475048 1 $(test_oid oid_version) 4 1
num_commits: $NUM_SECOND_LAYER_COMMITS
chunks: oid_fanout oid_lookup commit_metadata
EOF
test_cmp expect output &&
git commit-graph verify &&
cat $graphdir/commit-graph-chain
)
'
# The new layer will be added without generation data chunk as it was not
# present on the layer underneath it.
#
# 7 commits (No GDAT)
# ------------------------
# 16 commits (No GDAT)
# ------------------------
# 64 commits (GDAT)
#
test_expect_success 'do not write generation data chunk if not present on existing tip' '
git clone mixed mixed-no-gdat &&
(
cd mixed-no-gdat &&
for i in $(test_seq $THIRD_LAYER_SEQUENCE_START $THIRD_LAYER_SEQUENCE_END)
do
test_commit $i &&
git branch commits/$i || return 1
done &&
git commit-graph write --reachable --split=no-merge &&
test_line_count = 3 $graphdir/commit-graph-chain &&
test-tool read-graph >output &&
cat >expect <<-EOF &&
header: 43475048 1 $(test_oid oid_version) 4 2
num_commits: $NUM_THIRD_LAYER_COMMITS
chunks: oid_fanout oid_lookup commit_metadata
EOF
test_cmp expect output &&
git commit-graph verify
)
'
# Number of commits in each layer of the split-commit graph before merge:
#
# 8 commits (No GDAT)
# ------------------------
# 7 commits (No GDAT)
# ------------------------
# 16 commits (No GDAT)
# ------------------------
# 64 commits (GDAT)
#
# The top two layers are merged and do not have generation data chunk as layer below them does
# not have generation data chunk.
#
# 15 commits (No GDAT)
# ------------------------
# 16 commits (No GDAT)
# ------------------------
# 64 commits (GDAT)
#
test_expect_success 'do not write generation data chunk if the topmost remaining layer does not have generation data chunk' '
git clone mixed-no-gdat mixed-merge-no-gdat &&
(
cd mixed-merge-no-gdat &&
for i in $(test_seq $FOURTH_LAYER_SEQUENCE_START $FOURTH_LAYER_SEQUENCE_END)
do
test_commit $i &&
git branch commits/$i || return 1
done &&
git commit-graph write --reachable --split --size-multiple 1 &&
test_line_count = 3 $graphdir/commit-graph-chain &&
test-tool read-graph >output &&
cat >expect <<-EOF &&
header: 43475048 1 $(test_oid oid_version) 4 2
num_commits: $(($NUM_THIRD_LAYER_COMMITS + $NUM_FOURTH_LAYER_COMMITS))
chunks: oid_fanout oid_lookup commit_metadata
EOF
test_cmp expect output &&
git commit-graph verify
)
'
# Number of commits in each layer of the split-commit graph before merge:
#
# 16 commits (No GDAT)
# ------------------------
# 15 commits (No GDAT)
# ------------------------
# 16 commits (No GDAT)
# ------------------------
# 64 commits (GDAT)
#
# The top three layers are merged and has generation data chunk as the topmost remaining layer
# has generation data chunk.
#
# 47 commits (GDAT)
# ------------------------
# 64 commits (GDAT)
#
test_expect_success 'write generation data chunk if topmost remaining layer has generation data chunk' '
git clone mixed-merge-no-gdat mixed-merge-gdat &&
(
cd mixed-merge-gdat &&
for i in $(test_seq $FIFTH_LAYER_SEQUENCE_START $FIFTH_LAYER_SEQUENCE_END)
do
test_commit $i &&
git branch commits/$i || return 1
done &&
git commit-graph write --reachable --split --size-multiple 1 &&
test_line_count = 2 $graphdir/commit-graph-chain &&
test-tool read-graph >output &&
cat >expect <<-EOF &&
header: 43475048 1 $(test_oid oid_version) 5 1
num_commits: $(($NUM_SECOND_LAYER_COMMITS + $NUM_THIRD_LAYER_COMMITS + $NUM_FOURTH_LAYER_COMMITS + $NUM_FIFTH_LAYER_COMMITS))
chunks: oid_fanout oid_lookup commit_metadata generation_data
EOF
test_cmp expect output
)
'
test_expect_success 'write generation data chunk when commit-graph chain is replaced' '
git clone mixed mixed-replace &&
(
cd mixed-replace &&
git commit-graph write --reachable --split=replace &&
test_path_is_file $graphdir/commit-graph-chain &&
test_line_count = 1 $graphdir/commit-graph-chain &&
verify_chain_files_exist $graphdir &&
graph_read_expect $(($NUM_FIRST_LAYER_COMMITS + $NUM_SECOND_LAYER_COMMITS)) &&
git commit-graph verify
)
'
test_done