odb: Be smarter when refreshing backends

In the current implementation of ODB backends, each backend is tasked
with refreshing itself after a failed lookup. This is standard Git
behavior: we want to e.g. reload the packfiles on disk in case they have
changed and that's the reason we can't find the object we're looking
for.

This behavior, however, becomes pathological in repositories where
multiple alternates have been loaded. Given that each alternate counts
as a separate backend, a miss in the main repository (which can
potentially be very frequent in cases where object storage comes from
the alternate) will result in refreshing all its packfiles before we
move on to the alternate backend where the object will most likely be
found.

To fix this, the code in `odb.c` has been refactored as to perform the
refresh of all the backends externally, once we've verified that the
object is nowhere to be found.

If the refresh is successful, we then perform the lookup sequentially
through all the backends, skipping the ones that we know for sure
weren't refreshed (because they have no refresh API).

The on-disk pack backend has been adjusted accordingly: it no longer
performs refreshes internally.

1 files changed, 156 insertions, 75 deletions

diff --git a/src/odb.c b/src/odb.c
index 2b2c35fe8..af1ff7fa2 100644
--- a/src/odb.c
+++ b/src/odb.c
@@ -620,23 +620,18 @@ void git_odb_free(git_odb *db)
 	GIT_REFCOUNT_DEC(db, odb_free);
 }
 
-int git_odb_exists(git_odb *db, const git_oid *id)
+static int odb_exists_1(git_odb *db, const git_oid *id, bool only_refreshed)
 {
-	git_odb_object *object;
 	size_t i;
 	bool found = false;
 
-	assert(db && id);
-
-	if ((object = git_cache_get_raw(odb_cache(db), id)) != NULL) {
-		git_odb_object_free(object);
-		return (int)true;
-	}
-
 	for (i = 0; i < db->backends.length && !found; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
 		git_odb_backend *b = internal->backend;
 
+		if (only_refreshed && !b->refresh)
+			continue;
+
 		if (b->exists != NULL)
 			found = (bool)b->exists(b, id);
 	}
@@ -644,43 +639,45 @@ int git_odb_exists(git_odb *db, const git_oid *id)
 	return (int)found;
 }
 
-int git_odb_exists_prefix(
-	git_oid *out, git_odb *db, const git_oid *short_id, size_t len)
+int git_odb_exists(git_odb *db, const git_oid *id)
 {
-	int error = GIT_ENOTFOUND, num_found = 0;
-	size_t i;
-	git_oid key = {{0}}, last_found = {{0}}, found;
-
-	assert(db && short_id);
+	git_odb_object *object;
 
-	if (len < GIT_OID_MINPREFIXLEN)
-		return git_odb__error_ambiguous("prefix length too short");
-	if (len > GIT_OID_HEXSZ)
-		len = GIT_OID_HEXSZ;
+	assert(db && id);
 
-	if (len == GIT_OID_HEXSZ) {
-		if (git_odb_exists(db, short_id)) {
-			if (out)
-				git_oid_cpy(out, short_id);
-			return 0;
-		} else {
-			return git_odb__error_notfound("no match for id prefix", short_id);
-		}
+	if ((object = git_cache_get_raw(odb_cache(db), id)) != NULL) {
+		git_odb_object_free(object);
+		return (int)true;
 	}
 
-	/* just copy valid part of short_id */
-	memcpy(&key.id, short_id->id, (len + 1) / 2);
-	if (len & 1)
-		key.id[len / 2] &= 0xF0;
+	if (odb_exists_1(db, id, false))
+		return 1;
+
+	if (!git_odb_refresh(db))
+		return odb_exists_1(db, id, true);
+
+	/* Failed to refresh, hence not found */
+	return 0;
+}
+
+static int odb_exists_prefix_1(git_oid *out, git_odb *db,
+	const git_oid *key, size_t len, bool only_refreshed)
+{
+	size_t i;
+	int error = GIT_ENOTFOUND, num_found = 0;
+	git_oid last_found = {{0}}, found;
 
 	for (i = 0; i < db->backends.length; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
 		git_odb_backend *b = internal->backend;
 
+		if (only_refreshed && !b->refresh)
+			continue;
+
 		if (!b->exists_prefix)
 			continue;
 
-		error = b->exists_prefix(&found, b, &key, len);
+		error = b->exists_prefix(&found, b, key, len);
 		if (error == GIT_ENOTFOUND || error == GIT_PASSTHROUGH)
 			continue;
 		if (error)
@@ -697,13 +694,53 @@ int git_odb_exists_prefix(
 	}
 
 	if (!num_found)
-		return git_odb__error_notfound("no match for id prefix", &key);
+		return GIT_ENOTFOUND;
+
 	if (out)
 		git_oid_cpy(out, &last_found);
 
 	return 0;
 }
 
+int git_odb_exists_prefix(
+	git_oid *out, git_odb *db, const git_oid *short_id, size_t len)
+{
+	int error;
+	git_oid key = {{0}}; 
+
+	assert(db && short_id);
+
+	if (len < GIT_OID_MINPREFIXLEN)
+		return git_odb__error_ambiguous("prefix length too short");
+	if (len > GIT_OID_HEXSZ)
+		len = GIT_OID_HEXSZ;
+
+	if (len == GIT_OID_HEXSZ) {
+		if (git_odb_exists(db, short_id)) {
+			if (out)
+				git_oid_cpy(out, short_id);
+			return 0;
+		} else {
+			return git_odb__error_notfound("no match for id prefix", short_id);
+		}
+	}
+
+	/* just copy valid part of short_id */
+	memcpy(&key.id, short_id->id, (len + 1) / 2);
+	if (len & 1)
+		key.id[len / 2] &= 0xF0;
+
+	error = odb_exists_prefix_1(out, db, &key, len, false);
+
+	if (error == GIT_ENOTFOUND && !git_odb_refresh(db))
+		error = odb_exists_prefix_1(out, db, &key, len, true);
+
+	if (error == GIT_ENOTFOUND)
+		return git_odb__error_notfound("no match for id prefix", &key);
+
+	return error;
+}
+
 int git_odb_read_header(size_t *len_p, git_otype *type_p, git_odb *db, const git_oid *id)
 {
 	int error;
@@ -783,36 +820,38 @@ static int hardcoded_objects(git_rawobj *raw, const git_oid *id)
 	}
 }
 
-int git_odb_read(git_odb_object **out, git_odb *db, const git_oid *id)
+static int odb_read_1(git_odb_object **out, git_odb *db, const git_oid *id,
+		bool only_refreshed)
 {
-	size_t i, reads = 0;
-	int error;
+	size_t i;
 	git_rawobj raw;
 	git_odb_object *object;
+	bool found = false;
 
-	assert(out && db && id);
-
-	*out = git_cache_get_raw(odb_cache(db), id);
-	if (*out != NULL)
-		return 0;
-
-	error = hardcoded_objects(&raw, id);
+	if (!hardcoded_objects(&raw, id))
+		found = true;
 
-	for (i = 0; i < db->backends.length && error < 0; ++i) {
+	for (i = 0; i < db->backends.length && !found; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
 		git_odb_backend *b = internal->backend;
 
+		if (only_refreshed && !b->refresh)
+			continue;
+
 		if (b->read != NULL) {
-			++reads;
-			error = b->read(&raw.data, &raw.len, &raw.type, b, id);
+			int error = b->read(&raw.data, &raw.len, &raw.type, b, id);
+			if (error == GIT_PASSTHROUGH || error == GIT_ENOTFOUND)
+				continue;
+
+			if (error < 0)
+				return error;
+
+			found = true;
 		}
 	}
 
-	if (error && error != GIT_PASSTHROUGH) {
-		if (!reads)
-			return git_odb__error_notfound("no match for id", id);
-		return error;
-	}
+	if (!found)
+		return GIT_ENOTFOUND;
 
 	giterr_clear();
 	if ((object = odb_object__alloc(id, &raw)) == NULL)
@@ -822,42 +861,48 @@ int git_odb_read(git_odb_object **out, git_odb *db, const git_oid *id)
 	return 0;
 }
 
-int git_odb_read_prefix(
-	git_odb_object **out, git_odb *db, const git_oid *short_id, size_t len)
+int git_odb_read(git_odb_object **out, git_odb *db, const git_oid *id)
+{
+	int error;
+
+	assert(out && db && id);
+
+	*out = git_cache_get_raw(odb_cache(db), id);
+	if (*out != NULL)
+		return 0;
+
+	error = odb_read_1(out, db, id, false);
+
+	if (error == GIT_ENOTFOUND && !git_odb_refresh(db))
+		error = odb_read_1(out, db, id, true);
+
+	if (error == GIT_ENOTFOUND)
+		return git_odb__error_notfound("no match for id", id);
+
+	return error;
+}
+
+static int read_prefix_1(git_odb_object **out, git_odb *db,
+		const git_oid *key, size_t len, bool only_refreshed)
 {
 	size_t i;
 	int error = GIT_ENOTFOUND;
-	git_oid key = {{0}}, found_full_oid = {{0}};
+	git_oid found_full_oid = {{0}};
 	git_rawobj raw;
 	void *data = NULL;
 	bool found = false;
 	git_odb_object *object;
 
-	assert(out && db);
-
-	if (len < GIT_OID_MINPREFIXLEN)
-		return git_odb__error_ambiguous("prefix length too short");
-	if (len > GIT_OID_HEXSZ)
-		len = GIT_OID_HEXSZ;
-
-	if (len == GIT_OID_HEXSZ) {
-		*out = git_cache_get_raw(odb_cache(db), short_id);
-		if (*out != NULL)
-			return 0;
-	}
-
-	/* just copy valid part of short_id */
-	memcpy(&key.id, short_id->id, (len + 1) / 2);
-	if (len & 1)
-		key.id[len / 2] &= 0xF0;
-
 	for (i = 0; i < db->backends.length; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
 		git_odb_backend *b = internal->backend;
 
+		if (only_refreshed && !b->refresh)
+			continue;
+
 		if (b->read_prefix != NULL) {
 			git_oid full_oid;
-			error = b->read_prefix(&full_oid, &raw.data, &raw.len, &raw.type, b, &key, len);
+			error = b->read_prefix(&full_oid, &raw.data, &raw.len, &raw.type, b, key, len);
 			if (error == GIT_ENOTFOUND || error == GIT_PASSTHROUGH)
 				continue;
 
@@ -878,7 +923,7 @@ int git_odb_read_prefix(
 	}
 
 	if (!found)
-		return git_odb__error_notfound("no match for prefix", &key);
+		return GIT_ENOTFOUND;
 
 	if ((object = odb_object__alloc(&found_full_oid, &raw)) == NULL)
 		return -1;
@@ -887,6 +932,42 @@ int git_odb_read_prefix(
 	return 0;
 }
 
+int git_odb_read_prefix(
+	git_odb_object **out, git_odb *db, const git_oid *short_id, size_t len)
+{
+	git_oid key = {{0}};
+	int error;
+
+	assert(out && db);
+
+	if (len < GIT_OID_MINPREFIXLEN)
+		return git_odb__error_ambiguous("prefix length too short");
+
+	if (len > GIT_OID_HEXSZ)
+		len = GIT_OID_HEXSZ;
+
+	if (len == GIT_OID_HEXSZ) {
+		*out = git_cache_get_raw(odb_cache(db), short_id);
+		if (*out != NULL)
+			return 0;
+	}
+
+	/* just copy valid part of short_id */
+	memcpy(&key.id, short_id->id, (len + 1) / 2);
+	if (len & 1)
+		key.id[len / 2] &= 0xF0;
+
+	error = read_prefix_1(out, db, &key, len, false);
+
+	if (error == GIT_ENOTFOUND && !git_odb_refresh(db))
+		error = read_prefix_1(out, db, &key, len, true);
+
+	if (error == GIT_ENOTFOUND)
+		return git_odb__error_notfound("no match for prefix", &key);
+
+	return error;
+}
+
 int git_odb_foreach(git_odb *db, git_odb_foreach_cb cb, void *payload)
 {
 	unsigned int i;