afs: Probe multiple fileservers simultaneously

Send probes to all the unprobed fileservers in a fileserver list on all
addresses simultaneously in an attempt to find out the fastest route whilst
not getting stuck for 20s on any server or address that we don't get a
reply from.

This alleviates the problem whereby attempting to access a new server can
take a long time because the rotation algorithm ends up rotating through
all servers and addresses until it finds one that responds.

Signed-off-by: David Howells <dhowells@redhat.com>

1 files changed, 105 insertions, 54 deletions

diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index ead6dedbb561..b64a284b99d2 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -58,8 +58,8 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 	if (!vc->server_list || !vc->server_list->nr_servers)
 		return false;
 
-	vc->start = READ_ONCE(vc->server_list->index);
-	vc->index = vc->start;
+	vc->untried = (1UL << vc->server_list->nr_servers) - 1;
+	vc->index = -1;
 	return true;
 }
 
@@ -71,11 +71,12 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 {
 	struct afs_addr_list *alist;
 	struct afs_vlserver *vlserver;
-	int error = vc->ac.error;
+	u32 rtt;
+	int error = vc->ac.error, abort_code, i;
 
-	_enter("%u/%u,%u/%u,%d,%d",
-	       vc->index, vc->start,
-	       vc->ac.index, vc->ac.start,
+	_enter("%lx[%d],%lx[%d],%d,%d",
+	       vc->untried, vc->index,
+	       vc->ac.tried, vc->ac.index,
 	       error, vc->ac.abort_code);
 
 	if (vc->flags & AFS_VL_CURSOR_STOP) {
@@ -145,23 +146,52 @@ restart_from_beginning:
 start:
 	_debug("start");
 
-	/* TODO: Consider checking the VL server list */
-
 	if (!afs_start_vl_iteration(vc))
 		goto failed;
 
-use_server:
-	_debug("use");
+	error = afs_send_vl_probes(vc->cell->net, vc->key, vc->server_list);
+	if (error < 0)
+		goto failed_set_error;
+
+pick_server:
+	_debug("pick [%lx]", vc->untried);
+
+	error = afs_wait_for_vl_probes(vc->server_list, vc->untried);
+	if (error < 0)
+		goto failed_set_error;
+
+	/* Pick the untried server with the lowest RTT. */
+	vc->index = vc->server_list->preferred;
+	if (test_bit(vc->index, &vc->untried))
+		goto selected_server;
+
+	vc->index = -1;
+	rtt = U32_MAX;
+	for (i = 0; i < vc->server_list->nr_servers; i++) {
+		struct afs_vlserver *s = vc->server_list->servers[i].server;
+
+		if (!test_bit(i, &vc->untried) || !s->probe.responded)
+			continue;
+		if (s->probe.rtt < rtt) {
+			vc->index = i;
+			rtt = s->probe.rtt;
+		}
+	}
+
+	if (vc->index == -1)
+		goto no_more_servers;
+
+selected_server:
+	_debug("use %d", vc->index);
+	__clear_bit(vc->index, &vc->untried);
+
 	/* We're starting on a different vlserver from the list.  We need to
 	 * check it, find its address list and probe its capabilities before we
 	 * use it.
 	 */
 	ASSERTCMP(vc->ac.alist, ==, NULL);
 	vlserver = vc->server_list->servers[vc->index].server;
-
-	// TODO: Check the vlserver occasionally
-	//if (!afs_check_vlserver_record(vc, vlserver))
-	//	goto failed;
+	vc->server = vlserver;
 
 	_debug("USING VLSERVER: %s", vlserver->name);
 
@@ -173,62 +203,84 @@ use_server:
 
 	memset(&vc->ac, 0, sizeof(vc->ac));
 
-	/* Probe the current vlserver if we haven't done so yet. */
-#if 0 // TODO
-	if (!test_bit(AFS_VLSERVER_FL_PROBED, &vlserver->flags)) {
-		vc->ac.alist = afs_get_addrlist(alist);
-
-		if (!afs_probe_vlserver(vc)) {
-			error = vc->ac.error;
-			switch (error) {
-			case -ENOMEM:
-			case -ERESTARTSYS:
-			case -EINTR:
-				goto failed_set_error;
-			default:
-				goto next_server;
-			}
-		}
-	}
-#endif
-
 	if (!vc->ac.alist)
 		vc->ac.alist = alist;
 	else
 		afs_put_addrlist(alist);
 
-	vc->ac.start = READ_ONCE(alist->index);
-	vc->ac.index = vc->ac.start;
+	vc->ac.index = -1;
 
 iterate_address:
 	ASSERT(vc->ac.alist);
-	_debug("iterate %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
 	if (!afs_iterate_addresses(&vc->ac))
 		goto next_server;
 
+	_debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
+
 	_leave(" = t %pISpc", &vc->ac.alist->addrs[vc->ac.index].transport);
 	return true;
 
 next_server:
 	_debug("next");
 	afs_end_cursor(&vc->ac);
-	vc->index++;
-	if (vc->index >= vc->server_list->nr_servers)
-		vc->index = 0;
-	if (vc->index != vc->start)
-		goto use_server;
+	goto pick_server;
 
+no_more_servers:
 	/* That's all the servers poked to no good effect.  Try again if some
 	 * of them were busy.
 	 */
 	if (vc->flags & AFS_VL_CURSOR_RETRY)
 		goto restart_from_beginning;
 
-	goto failed;
+	abort_code = 0;
+	error = -EDESTADDRREQ;
+	for (i = 0; i < vc->server_list->nr_servers; i++) {
+		struct afs_vlserver *s = vc->server_list->servers[i].server;
+		int probe_error = READ_ONCE(s->probe.error);
+
+		switch (probe_error) {
+		case 0:
+			continue;
+		default:
+			if (error == -ETIMEDOUT ||
+			    error == -ETIME)
+				continue;
+		case -ETIMEDOUT:
+		case -ETIME:
+			if (error == -ENOMEM ||
+			    error == -ENONET)
+				continue;
+		case -ENOMEM:
+		case -ENONET:
+			if (error == -ENETUNREACH)
+				continue;
+		case -ENETUNREACH:
+			if (error == -EHOSTUNREACH)
+				continue;
+		case -EHOSTUNREACH:
+			if (error == -ECONNREFUSED)
+				continue;
+		case -ECONNREFUSED:
+			if (error == -ECONNRESET)
+				continue;
+		case -ECONNRESET: /* Responded, but call expired. */
+			if (error == -ECONNABORTED)
+				continue;
+		case -ECONNABORTED:
+			abort_code = s->probe.abort_code;
+			error = probe_error;
+			continue;
+		}
+	}
+
+	if (error == -ECONNABORTED)
+		error = afs_abort_to_error(abort_code);
 
+failed_set_error:
+	vc->error = error;
 failed:
 	vc->flags |= AFS_VL_CURSOR_STOP;
 	afs_end_cursor(&vc->ac);
@@ -250,8 +302,8 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 
 	rcu_read_lock();
 	pr_notice("EDESTADDR occurred\n");
-	pr_notice("VC: st=%u ix=%u ni=%hu fl=%hx err=%hd\n",
-		  vc->start, vc->index, vc->nr_iterations, vc->flags, vc->error);
+	pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n",
+		  vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error);
 
 	if (vc->server_list) {
 		const struct afs_vlserver_list *sl = vc->server_list;
@@ -259,26 +311,25 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 			  sl->nr_servers, sl->index);
 		for (i = 0; i < sl->nr_servers; i++) {
 			const struct afs_vlserver *s = sl->servers[i].server;
-			pr_notice("VC: server fl=%lx %s+%hu\n",
-				  s->flags, s->name, s->port);
+			pr_notice("VC: server %s+%hu fl=%lx E=%hd\n",
+				  s->name, s->port, s->flags, s->probe.error);
 			if (s->addresses) {
 				const struct afs_addr_list *a =
 					rcu_dereference(s->addresses);
-				pr_notice("VC:  - av=%u nr=%u/%u/%u ax=%u\n",
-					  a->version,
+				pr_notice("VC:  - nr=%u/%u/%u pf=%u\n",
 					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
-					  a->index);
-				pr_notice("VC:  - pr=%lx yf=%lx\n",
-					  a->probed, a->yfs);
+					  a->preferred);
+				pr_notice("VC:  - pr=%lx R=%lx F=%lx\n",
+					  a->probed, a->responded, a->failed);
 				if (a == vc->ac.alist)
 					pr_notice("VC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: as=%u ax=%u ac=%d er=%d b=%u r=%u ni=%hu\n",
-		  vc->ac.start, vc->ac.index, vc->ac.abort_code, vc->ac.error,
-		  vc->ac.begun, vc->ac.responded, vc->ac.nr_iterations);
+	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
+		  vc->ac.tried, vc->ac.index, vc->ac.abort_code, vc->ac.error,
+		  vc->ac.responded, vc->ac.nr_iterations);
 	rcu_read_unlock();
 }