diff mbox series

[09/34] commit-graph: simplify write_commit_graph_file() #1

Message ID 20200529085038.26008-10-szeder.dev@gmail.com (mailing list archive)
State New, archived
Headers show
Series An alternative modified path Bloom filters implementation | expand

Commit Message

SZEDER Gábor May 29, 2020, 8:50 a.m. UTC
In write_commit_graph_file() one block of code fills the array of
chunk IDs, another block of code fills the array of chunk offsets,
then the chunk IDs and offsets are written to the Chunk Lookup table,
and finally a third block of code writes the actual chunks.  In case
of optional chunks like Extra Edge List and Base Graphs List there is
also a condition checking whether that chunk is necessary/desired, and
that same condition is repeated in all those three blocks of code.
This patch series is about to add more optional chunks, so there would
be even more repeated conditions.

Those chunk offsets are relative to the beginning of the file, so they
inherently depend on the size of the Chunk Lookup table, which in turn
depends on the number of chunks that are to be written to the
commit-graph file.  IOW at the time we set the first chunk's ID we
can't yet know its offset, because we don't yet know how many chunks
there are.

Simplify this by initially filling an array of chunk sizes, not
offsets, and calculate the offsets based on the chunk sizes only
later, while we are writing the Chunk Lookup table.  This way we can
fill the arrays of chunk IDs and sizes in one go, eliminating one set
of repeated conditions.

Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com>
---
 commit-graph.c | 33 +++++++++++++--------------------
 1 file changed, 13 insertions(+), 20 deletions(-)
diff mbox series

Patch

diff --git a/commit-graph.c b/commit-graph.c
index f64b1c01a8..416f4b2468 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1351,10 +1351,11 @@  static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	struct hashfile *f;
 	struct lock_file lk = LOCK_INIT;
 	uint32_t chunk_ids[6];
-	uint64_t chunk_offsets[6];
+	uint64_t chunk_sizes[6];
 	const unsigned hashsz = the_hash_algo->rawsz;
 	struct strbuf progress_title = STRBUF_INIT;
 	int num_chunks = 3;
+	uint64_t chunk_offset;
 	struct object_id file_hash;
 
 	if (ctx->split) {
@@ -1394,35 +1395,24 @@  static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	}
 
 	chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT;
+	chunk_sizes[0] = GRAPH_FANOUT_SIZE;
 	chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
+	chunk_sizes[1] = hashsz * ctx->commits.nr;
 	chunk_ids[2] = GRAPH_CHUNKID_DATA;
+	chunk_sizes[2] = (hashsz + 16) * ctx->commits.nr;
 	if (ctx->num_extra_edges) {
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
+		chunk_sizes[3] = 4 * ctx->num_extra_edges;
 		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
+		chunk_sizes[4] = hashsz * (ctx->num_commit_graphs_after - 1);
 		num_chunks++;
 	}
 
 	chunk_ids[num_chunks] = 0;
-
-	chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
-	chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
-	chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr;
-	chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr;
-
-	num_chunks = 3;
-	if (ctx->num_extra_edges) {
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						4 * ctx->num_extra_edges;
-		num_chunks++;
-	}
-	if (ctx->num_commit_graphs_after > 1) {
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						hashsz * (ctx->num_commit_graphs_after - 1);
-		num_chunks++;
-	}
+	chunk_sizes[num_chunks] = 0;
 
 	hashwrite_be32(f, GRAPH_SIGNATURE);
 
@@ -1431,13 +1421,16 @@  static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	hashwrite_u8(f, num_chunks);
 	hashwrite_u8(f, ctx->num_commit_graphs_after - 1);
 
+	chunk_offset = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
 	for (i = 0; i <= num_chunks; i++) {
 		uint32_t chunk_write[3];
 
 		chunk_write[0] = htonl(chunk_ids[i]);
-		chunk_write[1] = htonl(chunk_offsets[i] >> 32);
-		chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff);
+		chunk_write[1] = htonl(chunk_offset >> 32);
+		chunk_write[2] = htonl(chunk_offset & 0xffffffff);
 		hashwrite(f, chunk_write, 12);
+
+		chunk_offset += chunk_sizes[i];
 	}
 
 	if (ctx->report_progress) {