SUNRPC: Don't allow low priority tasks to pre-empt higher priority ones

Currently, the priority queues attempt to be 'fair' to lower priority
tasks by scheduling them after a certain number of higher priority tasks
have run. The problem is that both the transport send queue and
the NFSv4.1 session slot queue have strong ordering requirements.

This patch therefore removes the fairness code in favour of strong
ordering of task priorities.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

include/linux/sunrpc/sched.h

@@ -192,7 +192,6 @@ struct rpc_wait_queue {
 	pid_t			owner;			/* process id of last task serviced */
 	unsigned char		maxpriority;		/* maximum priority (0 if queue is not a priority queue) */
 	unsigned char		priority;		/* current priority */
-	unsigned char		count;			/* # task groups remaining serviced so far */
 	unsigned char		nr;			/* # tasks remaining for cookie */
 	unsigned short		qlen;			/* total # tasks waiting in queue */
 	struct rpc_timer	timer_list;

net/sunrpc/sched.c

@@ -98,6 +98,23 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
+static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
+{
+	queue->priority = priority;
+}
+
+static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
+{
+	queue->owner = pid;
+	queue->nr = RPC_BATCH_COUNT;
+}
+
+static void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue)
+{
+	rpc_set_waitqueue_priority(queue, queue->maxpriority);
+	rpc_set_waitqueue_owner(queue, 0);
+}
+
 /*
  * Add new request to a priority queue.
  */
@@ -109,9 +126,11 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
 	struct rpc_task *t;
 
 	INIT_LIST_HEAD(&task->u.tk_wait.links);
-	q = &queue->tasks[queue_priority];
 	if (unlikely(queue_priority > queue->maxpriority))
-		q = &queue->tasks[queue->maxpriority];
+		queue_priority = queue->maxpriority;
+	if (queue_priority > queue->priority)
+		rpc_set_waitqueue_priority(queue, queue_priority);
+	q = &queue->tasks[queue_priority];
 	list_for_each_entry(t, q, u.tk_wait.list) {
 		if (t->tk_owner == task->tk_owner) {
 			list_add_tail(&task->u.tk_wait.list, &t->u.tk_wait.links);
@@ -180,24 +199,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas
 			task->tk_pid, queue, rpc_qname(queue));
 }
 
-static inline void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
-{
-	queue->priority = priority;
-	queue->count = 1 << (priority * 2);
-}
-
-static inline void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
-{
-	queue->owner = pid;
-	queue->nr = RPC_BATCH_COUNT;
-}
-
-static inline void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue)
-{
-	rpc_set_waitqueue_priority(queue, queue->maxpriority);
-	rpc_set_waitqueue_owner(queue, 0);
-}
-
 static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues)
 {
 	int i;
@@ -464,8 +465,7 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q
 		/*
 		 * Check if we need to switch queues.
 		 */
-		if (--queue->count)
-			goto new_owner;
+		goto new_owner;
 	}
 
 	/*