Merge branch 'ps/fetch-mirror-optim'

Various optimization for "git fetch".

* ps/fetch-mirror-optim:
  refs/files-backend: optimize reading of symbolic refs
  remote: read symbolic refs via `refs_read_symbolic_ref()`
  refs: add ability for backends to special-case reading of symbolic refs
  fetch: avoid lookup of commits when not appending to FETCH_HEAD
  upload-pack: look up "want" lines via commit-graph

10 files changed, 122 insertions, 33 deletions

diff --git a/builtin/fetch.c b/builtin/fetch.c
index e8305b6662..4d12c2fd4d 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -1146,7 +1146,6 @@ static int store_updated_refs(const char *raw_url, const char *remote_name,
 	     want_status <= FETCH_HEAD_IGNORE;
 	     want_status++) {
 		for (rm = ref_map; rm; rm = rm->next) {
-			struct commit *commit = NULL;
 			struct ref *ref = NULL;
 
 			if (rm->status == REF_STATUS_REJECT_SHALLOW) {
@@ -1157,21 +1156,34 @@ static int store_updated_refs(const char *raw_url, const char *remote_name,
 			}
 
 			/*
-			 * References in "refs/tags/" are often going to point
-			 * to annotated tags, which are not part of the
-			 * commit-graph. We thus only try to look up refs in
-			 * the graph which are not in that namespace to not
-			 * regress performance in repositories with many
-			 * annotated tags.
+			 * When writing FETCH_HEAD we need to determine whether
+			 * we already have the commit or not. If not, then the
+			 * reference is not for merge and needs to be written
+			 * to the reflog after other commits which we already
+			 * have. We're not interested in this property though
+			 * in case FETCH_HEAD is not to be updated, so we can
+			 * skip the classification in that case.
 			 */
-			if (!starts_with(rm->name, "refs/tags/"))
-				commit = lookup_commit_in_graph(the_repository, &rm->old_oid);
-			if (!commit) {
-				commit = lookup_commit_reference_gently(the_repository,
-									&rm->old_oid,
-									1);
-				if (!commit)
-					rm->fetch_head_status = FETCH_HEAD_NOT_FOR_MERGE;
+			if (fetch_head->fp) {
+				struct commit *commit = NULL;
+
+				/*
+				 * References in "refs/tags/" are often going to point
+				 * to annotated tags, which are not part of the
+				 * commit-graph. We thus only try to look up refs in
+				 * the graph which are not in that namespace to not
+				 * regress performance in repositories with many
+				 * annotated tags.
+				 */
+				if (!starts_with(rm->name, "refs/tags/"))
+					commit = lookup_commit_in_graph(the_repository, &rm->old_oid);
+				if (!commit) {
+					commit = lookup_commit_reference_gently(the_repository,
+										&rm->old_oid,
+										1);
+					if (!commit)
+						rm->fetch_head_status = FETCH_HEAD_NOT_FOR_MERGE;
+				}
 			}
 
 			if (rm->fetch_head_status != want_status)
diff --git a/builtin/remote.c b/builtin/remote.c
index 6f27ddc47b..0142ed09b5 100644
--- a/builtin/remote.c
+++ b/builtin/remote.c
@@ -766,13 +766,15 @@ static int mv(int argc, const char **argv)
 	for_each_ref(read_remote_branches, &rename);
 	for (i = 0; i < remote_branches.nr; i++) {
 		struct string_list_item *item = remote_branches.items + i;
-		int flag = 0;
+		struct strbuf referent = STRBUF_INIT;
 
-		read_ref_full(item->string, RESOLVE_REF_READING, NULL, &flag);
-		if (!(flag & REF_ISSYMREF))
+		if (refs_read_symbolic_ref(get_main_ref_store(the_repository), item->string,
+					   &referent))
 			continue;
 		if (delete_ref(NULL, item->string, NULL, REF_NO_DEREF))
 			die(_("deleting '%s' failed"), item->string);
+
+		strbuf_release(&referent);
 	}
 	for (i = 0; i < remote_branches.nr; i++) {
 		struct string_list_item *item = remote_branches.items + i;
diff --git a/refs.c b/refs.c
index 1598fb13e2..0b79bdd7c3 100644
--- a/refs.c
+++ b/refs.c
@@ -1673,6 +1673,23 @@ int refs_read_raw_ref(struct ref_store *ref_store, const char *refname,
 					   type, failure_errno);
 }
 
+int refs_read_symbolic_ref(struct ref_store *ref_store, const char *refname,
+			   struct strbuf *referent)
+{
+	struct object_id oid;
+	int ret, failure_errno = 0;
+	unsigned int type = 0;
+
+	if (ref_store->be->read_symbolic_ref)
+		return ref_store->be->read_symbolic_ref(ref_store, refname, referent);
+
+	ret = refs_read_raw_ref(ref_store, refname, &oid, referent, &type, &failure_errno);
+	if (ret || !(type & REF_ISSYMREF))
+		return -1;
+
+	return 0;
+}
+
 const char *refs_resolve_ref_unsafe(struct ref_store *refs,
 				    const char *refname,
 				    int resolve_flags,
diff --git a/refs.h b/refs.h
index 1ae12c410a..23479c7ee0 100644
--- a/refs.h
+++ b/refs.h
@@ -82,6 +82,9 @@ int read_ref_full(const char *refname, int resolve_flags,
 		  struct object_id *oid, int *flags);
 int read_ref(const char *refname, struct object_id *oid);
 
+int refs_read_symbolic_ref(struct ref_store *ref_store, const char *refname,
+			   struct strbuf *referent);
+
 /*
  * Return 0 if a reference named refname could be created without
  * conflicting with the name of an existing reference. Otherwise,
diff --git a/refs/debug.c b/refs/debug.c
index 2b0771ca53..c590d37720 100644
--- a/refs/debug.c
+++ b/refs/debug.c
@@ -435,6 +435,7 @@ struct ref_storage_be refs_be_debug = {
 
 	debug_ref_iterator_begin,
 	debug_read_raw_ref,
+	NULL,
 
 	debug_reflog_iterator_begin,
 	debug_for_each_reflog_ent,
diff --git a/refs/files-backend.c b/refs/files-backend.c
index f59589d6cc..0457ecdb42 100644
--- 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 @@ stat_ref:
 	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 @@ stat_ref:
 		 * 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 @@ out:
 	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)
@@ -3286,6 +3308,7 @@ struct ref_storage_be refs_be_files = {
 
 	files_ref_iterator_begin,
 	files_read_raw_ref,
+	files_read_symbolic_ref,
 
 	files_reflog_iterator_begin,
 	files_for_each_reflog_ent,
diff --git a/refs/packed-backend.c b/refs/packed-backend.c
index 27dd8c3922..f56e2cc635 100644
--- a/refs/packed-backend.c
+++ b/refs/packed-backend.c
@@ -1684,6 +1684,7 @@ struct ref_storage_be refs_be_packed = {
 
 	packed_ref_iterator_begin,
 	packed_read_raw_ref,
+	NULL,
 
 	packed_reflog_iterator_begin,
 	packed_for_each_reflog_ent,
diff --git a/refs/refs-internal.h b/refs/refs-internal.h
index 6e15db3ca4..001ef15835 100644
--- a/refs/refs-internal.h
+++ b/refs/refs-internal.h
@@ -649,6 +649,21 @@ typedef int read_raw_ref_fn(struct ref_store *ref_store, const char *refname,
 			    struct object_id *oid, struct strbuf *referent,
 			    unsigned int *type, int *failure_errno);
 
+/*
+ * Read a symbolic reference from the specified reference store. This function
+ * is optional: if not implemented by a backend, then `read_raw_ref_fn` is used
+ * to read the symbolcic reference instead. It is intended to be implemented
+ * only in case the backend can optimize the reading of symbolic references.
+ *
+ * Return 0 on success, or -1 on failure. `referent` will be set to the target
+ * of the symbolic reference on success. This function explicitly does not
+ * distinguish between error cases and the reference not being a symbolic
+ * reference to allow backends to optimize this operation in case symbolic and
+ * non-symbolic references are treated differently.
+ */
+typedef int read_symbolic_ref_fn(struct ref_store *ref_store, const char *refname,
+				 struct strbuf *referent);
+
 struct ref_storage_be {
 	struct ref_storage_be *next;
 	const char *name;
@@ -668,6 +683,7 @@ struct ref_storage_be {
 
 	ref_iterator_begin_fn *iterator_begin;
 	read_raw_ref_fn *read_raw_ref;
+	read_symbolic_ref_fn *read_symbolic_ref;
 
 	reflog_iterator_begin_fn *reflog_iterator_begin;
 	for_each_reflog_ent_fn *for_each_reflog_ent;
diff --git a/remote.c b/remote.c
index c97c626eaa..42a4e7106e 100644
--- a/remote.c
+++ b/remote.c
@@ -1945,13 +1945,9 @@ const char *branch_get_push(struct branch *branch, struct strbuf *err)
 	return branch->push_tracking_ref;
 }
 
-static int ignore_symref_update(const char *refname)
+static int ignore_symref_update(const char *refname, struct strbuf *scratch)
 {
-	int flag;
-
-	if (!resolve_ref_unsafe(refname, 0, NULL, &flag))
-		return 0; /* non-existing refs are OK */
-	return (flag & REF_ISSYMREF);
+	return !refs_read_symbolic_ref(get_main_ref_store(the_repository), refname, scratch);
 }
 
 /*
@@ -1964,6 +1960,7 @@ static int ignore_symref_update(const char *refname)
 static struct ref *get_expanded_map(const struct ref *remote_refs,
 				    const struct refspec_item *refspec)
 {
+	struct strbuf scratch = STRBUF_INIT;
 	const struct ref *ref;
 	struct ref *ret = NULL;
 	struct ref **tail = &ret;
@@ -1971,11 +1968,13 @@ static struct ref *get_expanded_map(const struct ref *remote_refs,
 	for (ref = remote_refs; ref; ref = ref->next) {
 		char *expn_name = NULL;
 
+		strbuf_reset(&scratch);
+
 		if (strchr(ref->name, '^'))
 			continue; /* a dereference item */
 		if (match_name_with_pattern(refspec->src, ref->name,
 					    refspec->dst, &expn_name) &&
-		    !ignore_symref_update(expn_name)) {
+		    !ignore_symref_update(expn_name, &scratch)) {
 			struct ref *cpy = copy_ref(ref);
 
 			cpy->peer_ref = alloc_ref(expn_name);
@@ -1987,6 +1986,7 @@ static struct ref *get_expanded_map(const struct ref *remote_refs,
 		free(expn_name);
 	}
 
+	strbuf_release(&scratch);
 	return ret;
 }
 
diff --git a/upload-pack.c b/upload-pack.c
index 8acc98741b..3a851b3606 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -1400,13 +1400,19 @@ static int parse_want(struct packet_writer *writer, const char *line,
 	const char *arg;
 	if (skip_prefix(line, "want ", &arg)) {
 		struct object_id oid;
+		struct commit *commit;
 		struct object *o;
 
 		if (get_oid_hex(arg, &oid))
 			die("git upload-pack: protocol error, "
 			    "expected to get oid, not '%s'", line);
 
-		o = parse_object(the_repository, &oid);
+		commit = lookup_commit_in_graph(the_repository, &oid);
+		if (commit)
+			o = &commit->object;
+		else
+			o = parse_object(the_repository, &oid);
+
 		if (!o) {
 			packet_writer_error(writer,
 					    "upload-pack: not our ref %s",
@@ -1434,7 +1440,7 @@ static int parse_want_ref(struct packet_writer *writer, const char *line,
 	if (skip_prefix(line, "want-ref ", &refname_nons)) {
 		struct object_id oid;
 		struct string_list_item *item;
-		struct object *o;
+		struct object *o = NULL;
 		struct strbuf refname = STRBUF_INIT;
 
 		strbuf_addf(&refname, "%s%s", get_git_namespace(), refname_nons);
@@ -1448,7 +1454,15 @@ static int parse_want_ref(struct packet_writer *writer, const char *line,
 		item = string_list_append(wanted_refs, refname_nons);
 		item->util = oiddup(&oid);
 
-		o = parse_object_or_die(&oid, refname_nons);
+		if (!starts_with(refname_nons, "refs/tags/")) {
+			struct commit *commit = lookup_commit_in_graph(the_repository, &oid);
+			if (commit)
+				o = &commit->object;
+		}
+
+		if (!o)
+			o = parse_object_or_die(&oid, refname_nons);
+
 		if (!(o->flags & WANTED)) {
 			o->flags |= WANTED;
 			add_object_array(o, NULL, want_obj);