fetch-prune: optimize dangling-ref reporting

When pruning during `git fetch` we check each pruned ref against the
ref_store one at a time to decide whether to report it as dangling.
This causes every local ref to be scanned for each ref being pruned.

If there are N refs in the repo and M refs being pruned, this code is
O(M*N). However, `git remote prune` uses a very similar function that
is only O(N*log(M)).

Remove the wasteful ref scanning for each pruned ref and use the faster
version already available in refs_warn_dangling_symrefs. Change the
message to include the original refname since the message is no longer
printed immediately after the line that did just print the refname.

In a repo with 126,000 refs, where I was pruning 28,000 refs, this
code made about 3.6 billion calls to strcmp and consumed 410 seconds
of CPU. (Invariably in that time, my remote would timeout and the
fetch would fail anyway.)

After this change, the same operation completes in under a second.

Signed-off-by: Phil Hord <[email protected]>
Reviewed-by: Jacob Keller <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: phord

builtin/fetch.c

@@ -1384,9 +1384,13 @@ static int prune_refs(struct display_state *display_state,
 	int result = 0;
 	struct ref *ref, *stale_refs = get_stale_heads(rs, ref_map);
 	struct strbuf err = STRBUF_INIT;
+	struct string_list refnames = STRING_LIST_INIT_NODUP;
 	const char *dangling_msg = dry_run
-		? _("   (%s will become dangling)")
-		: _("   (%s has become dangling)");
+		? _("   %s will become dangling after %s is deleted")
+		: _("   %s has become dangling after %s was deleted");
+
+	for (ref = stale_refs; ref; ref = ref->next)
+		string_list_append(&refnames, ref->name);
 
 	if (!dry_run) {
 		if (transaction) {
@@ -1397,15 +1401,9 @@ static int prune_refs(struct display_state *display_state,
 					goto cleanup;
 			}
 		} else {
-			struct string_list refnames = STRING_LIST_INIT_NODUP;
-
-			for (ref = stale_refs; ref; ref = ref->next)
-				string_list_append(&refnames, ref->name);
-
 			result = refs_delete_refs(get_main_ref_store(the_repository),
 						  "fetch: prune", &refnames,
 						  0);
-			string_list_clear(&refnames, 0);
 		}
 	}
 
@@ -1417,12 +1415,14 @@ static int prune_refs(struct display_state *display_state,
 					   _("(none)"), ref->name,
 					   &ref->new_oid, &ref->old_oid,
 					   summary_width);
-			refs_warn_dangling_symref(get_main_ref_store(the_repository),
-						  stderr, dangling_msg, ref->name);
 		}
+		string_list_sort(&refnames);
+		refs_warn_dangling_symrefs(get_main_ref_store(the_repository),
+					   stderr, dangling_msg, &refnames);
 	}
 
 cleanup:
+	string_list_clear(&refnames, 0);
 	strbuf_release(&err);
 	free_refs(stale_refs);
 	return result;

builtin/remote.c

@@ -1516,8 +1516,8 @@ static int prune_remote(const char *remote, int dry_run)
 	struct string_list refs_to_prune = STRING_LIST_INIT_NODUP;
 	struct string_list_item *item;
 	const char *dangling_msg = dry_run
-		? _(" %s will become dangling!")
-		: _(" %s has become dangling!");
+		? _(" %s will become dangling after %s is deleted!")
+		: _(" %s has become dangling after %s was deleted!");
 
 	get_remote_ref_states(remote, &states, GET_REF_STATES);
 

refs.c

@@ -461,7 +461,7 @@ static int warn_if_dangling_symref(const char *refname, const char *referent UNU
 		return 0;
 	}
 
-	fprintf(d->fp, d->msg_fmt, refname);
+	fprintf(d->fp, d->msg_fmt, refname, resolves_to);
 	fputc('\n', d->fp);
 	return 0;
 }