diff --git a/commit-graph.c b/commit-graph.c index df4b4a125e..9abe62bd5a 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1319,6 +1319,37 @@ static int write_graph_chunk_data(struct hashfile *f, return 0; } +/* + * Compute the generation offset between the commit date and its generation. + * This is what's ultimately stored as generation number in the commit graph. + * + * Note that the computation of the commit date is more involved than you might + * think. Instead of using the full commit date, we're in fact masking bits so + * that only the 34 lowest bits are considered. This results from the fact that + * commit graphs themselves only ever store 34 bits of the commit date + * themselves. + * + * This means that if we have a commit date that exceeds 34 bits we'll end up + * in situations where depending on whether the commit has been parsed from the + * object database or the commit graph we'll have different dates, where the + * ones parsed from the object database would have full 64 bit precision. + * + * But ultimately, we only ever want the offset to be relative to what we + * actually end up storing on disk, and hence we have to mask all the other + * bits. + */ +static timestamp_t compute_generation_offset(struct commit *c) +{ + timestamp_t masked_date; + + if (sizeof(timestamp_t) > 4) + masked_date = c->date & (((timestamp_t) 1 << 34) - 1); + else + masked_date = c->date; + + return commit_graph_data_at(c)->generation - masked_date; +} + static int write_graph_chunk_generation_data(struct hashfile *f, void *data) { @@ -1329,7 +1360,7 @@ static int write_graph_chunk_generation_data(struct hashfile *f, struct commit *c = ctx->commits.items[i]; timestamp_t offset; repo_parse_commit(ctx->r, c); - offset = commit_graph_data_at(c)->generation - c->date; + offset = compute_generation_offset(c); display_progress(ctx->progress, ++ctx->progress_cnt); if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) { @@ -1350,7 +1381,7 @@ static int write_graph_chunk_generation_data_overflow(struct hashfile *f, int i; for (i = 0; i < ctx->commits.nr; i++) { struct commit *c = ctx->commits.items[i]; - timestamp_t offset = commit_graph_data_at(c)->generation - c->date; + timestamp_t offset = compute_generation_offset(c); display_progress(ctx->progress, ++ctx->progress_cnt); if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) { @@ -1741,7 +1772,7 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx) for (i = 0; i < ctx->commits.nr; i++) { struct commit *c = ctx->commits.items[i]; - timestamp_t offset = commit_graph_data_at(c)->generation - c->date; + timestamp_t offset = compute_generation_offset(c); if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) ctx->num_generation_data_overflows++; } diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 98c6910963..1c40f904f8 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -417,6 +417,26 @@ test_expect_success TIME_IS_64BIT,TIME_T_IS_64BIT 'lower layers have overflow ch test_cmp full/.git/objects/info/commit-graph commit-graph-upgraded ' +test_expect_success TIME_IS_64BIT,TIME_T_IS_64BIT 'overflow chunk when replacing commit-graph' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + cat >commit <<-EOF && + tree $(test_oid empty_tree) + author Example 9223372036854775 +0000 + committer Example 9223372036854775 +0000 + + Weird commit date + EOF + commit_id=$(git hash-object -t commit -w commit) && + git reset --hard "$commit_id" && + git commit-graph write --reachable && + git commit-graph write --reachable --split=replace && + git log + ) +' + # the verify tests below expect the commit-graph to contain # exactly the commits reachable from the commits/8 branch. # If the file changes the set of commits in the list, then the