refs/files-backend: optimize reading of symbolic refs

pks-t · gitster · commit 0a7b38707d5d · 2022-03-01T10:13:46.000-08:00
When reading references via `files_read_raw_ref()` we always consult
both the loose reference, and if that wasn't found, we also consult the
packed-refs file. While this makes sense to read a generic reference, it
is wasteful in the case where we only care about symbolic references:
the packed-refs backend does not support them, and thus it cannot ever
return one for us.

Special-case reading of symbolic references for the files backend such
that we always skip asking the packed-refs backend.

We use `refs_read_symbolic_ref()` extensively to determine whether we
need to skip updating local symbolic references during a fetch, which is
why the change results in a significant speedup when doing fetches in
repositories with huge numbers of references. The following benchmark
executes a mirror-fetch in a repository with about 2 million references
via `git fetch --prune --no-write-fetch-head +refs/*:refs/*`:

    Benchmark 1: HEAD~
      Time (mean ± σ):     68.372 s ±  2.344 s    [User: 65.629 s, System: 8.786 s]
      Range (min … max):   65.745 s … 70.246 s    3 runs

    Benchmark 2: HEAD
      Time (mean ± σ):     60.259 s ±  0.343 s    [User: 61.019 s, System: 7.245 s]
      Range (min … max):   60.003 s … 60.649 s    3 runs

    Summary
      'HEAD' ran
        1.13 ± 0.04 times faster than 'HEAD~'

Signed-off-by: Patrick Steinhardt &lt;ps@pks.im&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/refs/files-backend.c b/refs/files-backend.c
@@ -338,9 +338,9 @@ static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs)
 	return refs->loose;
 }
 
-static int files_read_raw_ref(struct ref_store *ref_store, const char *refname,
-			      struct object_id *oid, struct strbuf *referent,
-			      unsigned int *type, int *failure_errno)
+static int read_ref_internal(struct ref_store *ref_store, const char *refname,
+			     struct object_id *oid, struct strbuf *referent,
+			     unsigned int *type, int *failure_errno, int skip_packed_refs)
 {
 	struct files_ref_store *refs =
 		files_downcast(ref_store, REF_STORE_READ, "read_raw_ref");
@@ -381,7 +381,7 @@ static int files_read_raw_ref(struct ref_store *ref_store, const char *refname,
 	if (lstat(path, &st) < 0) {
 		int ignore_errno;
 		myerr = errno;
-		if (myerr != ENOENT)
+		if (myerr != ENOENT || skip_packed_refs)
 			goto out;
 		if (refs_read_raw_ref(refs->packed_ref_store, refname, oid,
 				      referent, type, &ignore_errno)) {
@@ -425,7 +425,8 @@ static int files_read_raw_ref(struct ref_store *ref_store, const char *refname,
 		 * ref is supposed to be, there could still be a
 		 * packed ref:
 		 */
-		if (refs_read_raw_ref(refs->packed_ref_store, refname, oid,
+		if (skip_packed_refs ||
+		    refs_read_raw_ref(refs->packed_ref_store, refname, oid,
 				      referent, type, &ignore_errno)) {
 			myerr = EISDIR;
 			goto out;
@@ -470,6 +471,27 @@ static int files_read_raw_ref(struct ref_store *ref_store, const char *refname,
 	return ret;
 }
 
+static int files_read_raw_ref(struct ref_store *ref_store, const char *refname,
+			      struct object_id *oid, struct strbuf *referent,
+			      unsigned int *type, int *failure_errno)
+{
+	return read_ref_internal(ref_store, refname, oid, referent, type, failure_errno, 0);
+}
+
+static int files_read_symbolic_ref(struct ref_store *ref_store, const char *refname,
+				   struct strbuf *referent)
+{
+	struct object_id oid;
+	int failure_errno, ret;
+	unsigned int type;
+
+	ret = read_ref_internal(ref_store, refname, &oid, referent, &type, &failure_errno, 1);
+	if (ret)
+		return ret;
+
+	return !(type & REF_ISSYMREF);
+}
+
 int parse_loose_ref_contents(const char *buf, struct object_id *oid,
 			     struct strbuf *referent, unsigned int *type,
 			     int *failure_errno)
@@ -3286,7 +3308,7 @@ struct ref_storage_be refs_be_files = {
 
 	files_ref_iterator_begin,
 	files_read_raw_ref,
-	NULL,
+	files_read_symbolic_ref,
 
 	files_reflog_iterator_begin,
 	files_for_each_reflog_ent,
