From: Junio C Hamano <gitster@pobox.com>
Date: Thu, 15 Mar 2018 22:10:58 +0000 (-0700)
Subject: Merge branch 'ti/fetch-everything-local-optim' into next
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/2be87aa7a7c1bd22f451acd08ec6b56d911046a0?hp=0c283dbe5e6bb6aa3da95dba4e7a2ba202893c6a

Merge branch 'ti/fetch-everything-local-optim' into next

A "git fetch" from a repository with insane number of refs into a
repository that is already up-to-date still wasted too many cycles
making many lstat(2) calls to see if these objects at the tips
exist as loose objects locally.  These lstat(2) calls are optimized
away by enumerating all loose objects beforehand.

It is unknown if the new strategy negatively affects existing use
cases, fetching into a repository with many loose objects from a
repository with small number of refs.

* ti/fetch-everything-local-optim:
fetch-pack.c: use oidset to check existence of loose object
---

diff --git a/cache.h b/cache.h
index 5593a657aa..4859e2be1a 100644
--- a/cache.h
+++ b/cache.h
@@ -1777,6 +1777,8 @@ struct object_info {
 #define OBJECT_INFO_SKIP_CACHED 4
 /* Do not retry packed storage after checking packed and loose storage */
 #define OBJECT_INFO_QUICK 8
+/* Do not check loose object */
+#define OBJECT_INFO_IGNORE_LOOSE 16
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 
 /*
diff --git a/fetch-pack.c b/fetch-pack.c
index d97461296d..2ea358861d 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -711,6 +711,28 @@ static void mark_alternate_complete(struct object *obj)
 	mark_complete(&obj->oid);
 }
 
+struct loose_object_iter {
+	struct oidset *loose_object_set;
+	struct ref *refs;
+};
+
+/*
+ *  If the number of refs is not larger than the number of loose objects,
+ *  this function stops inserting.
+ */
+static int add_loose_objects_to_set(const struct object_id *oid,
+				    const char *path,
+				    void *data)
+{
+	struct loose_object_iter *iter = data;
+	oidset_insert(iter->loose_object_set, oid);
+	if (iter->refs == NULL)
+		return 1;
+
+	iter->refs = iter->refs->next;
+	return 0;
+}
+
 static int everything_local(struct fetch_pack_args *args,
 			    struct ref **refs,
 			    struct ref **sought, int nr_sought)
@@ -719,16 +741,31 @@ static int everything_local(struct fetch_pack_args *args,
 	int retval;
 	int old_save_commit_buffer = save_commit_buffer;
 	timestamp_t cutoff = 0;
+	struct oidset loose_oid_set = OIDSET_INIT;
+	int use_oidset = 0;
+	struct loose_object_iter iter = {&loose_oid_set, *refs};
+
+	/* Enumerate all loose objects or know refs are not so many. */
+	use_oidset = !for_each_loose_object(add_loose_objects_to_set,
+					    &iter, 0);
 
 	save_commit_buffer = 0;
 
 	for (ref = *refs; ref; ref = ref->next) {
 		struct object *o;
+		unsigned int flags = OBJECT_INFO_QUICK;
 
-		if (!has_object_file_with_flags(&ref->old_oid,
-						OBJECT_INFO_QUICK))
-			continue;
+		if (use_oidset &&
+		    !oidset_contains(&loose_oid_set, &ref->old_oid)) {
+			/*
+			 * I know this does not exist in the loose form,
+			 * so check if it exists in a non-loose form.
+			 */
+			flags |= OBJECT_INFO_IGNORE_LOOSE;
+		}
 
+		if (!has_object_file_with_flags(&ref->old_oid, flags))
+			continue;
 		o = parse_object(&ref->old_oid);
 		if (!o)
 			continue;
@@ -744,6 +781,8 @@ static int everything_local(struct fetch_pack_args *args,
 		}
 	}
 
+	oidset_clear(&loose_oid_set);
+
 	if (!args->no_dependents) {
 		if (!args->deepen) {
 			for_each_ref(mark_complete_oid, NULL);
diff --git a/sha1_file.c b/sha1_file.c
index 669aadf2e0..6ec3f8d573 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1258,6 +1258,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		if (find_pack_entry(real, &e))
 			break;
 
+		if (flags & OBJECT_INFO_IGNORE_LOOSE)
+			return -1;
+
 		/* Most likely it's a loose object. */
 		if (!sha1_loose_object_info(real, oi, flags))
 			return 0;