git-fetch: Avoid reading packed refs over and over again

When checking which tags to fetch, the old code used to call
git-show-ref --verify for each remote tag. Since reading even
packed refs is not a cheap operation when there are a lot of
local refs, the code became quite slow.

This fixes it by teaching git-show-ref to filter out existing
refs using a new mode of operation of git-show-ref.

Signed-off-by: Junio C Hamano <junkio@cox.net>

2 files changed, 62 insertions, 10 deletions

diff --git a/builtin-show-ref.c b/builtin-show-ref.c
index 073979855b..b36f15eeaa 100644
--- a/builtin-show-ref.c
+++ b/builtin-show-ref.c
@@ -2,8 +2,9 @@
 #include "refs.h"
 #include "object.h"
 #include "tag.h"
+#include "path-list.h"
 
-static const char show_ref_usage[] = "git show-ref [-q|--quiet] [--verify] [-h|--head] [-d|--dereference] [-s|--hash[=<length>]] [--abbrev[=<length>]] [--tags] [--heads] [--] [pattern*]";
+static const char show_ref_usage[] = "git show-ref [-q|--quiet] [--verify] [-h|--head] [-d|--dereference] [-s|--hash[=<length>]] [--abbrev[=<length>]] [--tags] [--heads] [--] [pattern*] | --filter-invalid < ref-list";
 
 static int deref_tags = 0, show_head = 0, tags_only = 0, heads_only = 0,
 	found_match = 0, verify = 0, quiet = 0, hash_only = 0, abbrev = 0;
@@ -86,6 +87,59 @@ match:
 	return 0;
 }
 
+static int add_existing(const char *refname, const unsigned char *sha1, int flag, void *cbdata)
+{
+	struct path_list *list = (struct path_list *)cbdata;
+	path_list_insert(refname, list);
+	return 0;
+}
+
+/*
+ * read "^(?:<anything>\s)?<refname>(?:\^\{\})?$" from the standard input,
+ * and
+ * (1) strip "^{}" at the end of line if any;
+ * (2) ignore if match is provided and does not head-match refname;
+ * (3) warn if refname is not a well-formed refname and skip;
+ * (4) ignore if refname is a ref that exists in the local repository;
+ * (5) otherwise output the line.
+ */
+static int exclude_existing(const char *match)
+{
+	static struct path_list existing_refs = { NULL, 0, 0, 0 };
+	char buf[1024];
+	int matchlen = match ? strlen(match) : 0;
+
+	for_each_ref(add_existing, &existing_refs);
+	while (fgets(buf, sizeof(buf), stdin)) {
+		int len = strlen(buf);
+		char *ref;
+		if (len > 0 && buf[len - 1] == '\n')
+			buf[--len] = '\0';
+		if (!strcmp(buf + len - 3, "^{}")) {
+			len -= 3;
+			buf[len] = '\0';
+		}
+		for (ref = buf + len; buf < ref; ref--)
+			if (isspace(ref[-1]))
+				break;
+		if (match) {
+			int reflen = buf + len - ref;
+			if (reflen < matchlen)
+				continue;
+			if (strncmp(ref, match, matchlen))
+				continue;
+		}
+		if (check_ref_format(ref)) {
+			fprintf(stderr, "warning: ref '%s' ignored\n", ref);
+			continue;
+		}
+		if (!path_list_has_path(&existing_refs, ref)) {
+			printf("%s\n", buf);
+		}
+	}
+	return 0;
+}
+
 int cmd_show_ref(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -153,6 +207,10 @@ int cmd_show_ref(int argc, const char **argv, const char *prefix)
 			heads_only = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--exclude-existing"))
+			return exclude_existing(NULL);
+		if (!strncmp(arg, "--exclude-existing=", 19))
+			return exclude_existing(arg + 19);
 		usage(show_ref_usage);
 	}
 	if (show_head)
diff --git a/git-fetch.sh b/git-fetch.sh
index fb35815a5f..38101a6ace 100755
--- a/git-fetch.sh
+++ b/git-fetch.sh
@@ -242,7 +242,7 @@ esac
 reflist=$(get_remote_refs_for_fetch "$@")
 if test "$tags"
 then
-	taglist=`IFS="	" &&
+	taglist=`IFS='	' &&
 		  echo "$ls_remote_result" |
 	          while read sha1 name
 		  do
@@ -438,17 +438,11 @@ case "$no_tags$tags" in
 	*:refs/*)
 		# effective only when we are following remote branch
 		# using local tracking branch.
-		taglist=$(IFS=" " &&
+		taglist=$(IFS='	' &&
 		echo "$ls_remote_result" |
-		sed -n	-e 's|^\('"$_x40"'\)	\(refs/tags/.*\)^{}$|\1 \2|p' \
-			-e 's|^\('"$_x40"'\)	\(refs/tags/.*\)$|\1 \2|p' |
+		git-show-ref --exclude-existing=refs/tags/ |
 		while read sha1 name
 		do
-			git-show-ref --verify --quiet -- "$name" && continue
-			git-check-ref-format "$name" || {
-				echo >&2 "warning: tag ${name} ignored"
-				continue
-			}
 			git-cat-file -t "$sha1" >/dev/null 2>&1 || continue
 			echo >&2 "Auto-following $name"
 			echo ".${name}:${name}"