Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Subject: [PATCH 15/21] SUNRPC: remove scheduling boost for "SWAPPER" tasks.
From:   NeilBrown <neilb@suse.de>
To:     Trond Myklebust <trond.myklebust@hammerspace.com>,
        Anna Schumaker <anna.schumaker@netapp.com>,
        Chuck Lever <chuck.lever@oracle.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Mark Hemment <markhemm@googlemail.com>,
        Christoph Hellwig <hch@infradead.org>,
        David Howells <dhowells@redhat.com>
Cc:     linux-nfs@vger.kernel.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Date:   Mon, 07 Feb 2022 15:46:01 +1100
Message-ID: <164420916121.29374.301108979284279934.stgit@noble.brown>
In-Reply-To: <164420889455.29374.17958998143835612560.stgit@noble.brown>
References: <164420889455.29374.17958998143835612560.stgit@noble.brown>
User-Agent: StGit/0.23
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Precedence: bulk

Currently, tasks marked as "swapper" tasks get put to the front of
non-priority rpc_queues, and are sorted earlier than non-swapper tasks on
the transport's ->xmit_queue.

This is pointless as currently *all* tasks for a mount that has swap
enabled on *any* file are marked as "swapper" tasks.  So the net result
is that the non-priority rpc_queues are reverse-ordered (LIFO).

This scheduling boost is not necessary to avoid deadlocks, and hurts
fairness, so remove it.  If there were a need to expedite some requests,
the tk_priority mechanism is a more appropriate tool.

Signed-off-by: NeilBrown <neilb@suse.de>
---
 net/sunrpc/sched.c |    7 -------
 net/sunrpc/xprt.c  |   11 -----------
 2 files changed, 18 deletions(-)

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index d5b6e897f5a5..256302bf6557 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -186,11 +186,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
 
 /*
  * Add new request to wait queue.
- *
- * Swapper tasks always get inserted at the head of the queue.
- * This should avoid many nasty memory deadlocks and hopefully
- * improve overall performance.
- * Everyone else gets appended to the queue to ensure proper FIFO behavior.
  */
 static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 		struct rpc_task *task,
@@ -199,8 +194,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 	INIT_LIST_HEAD(&task->u.tk_wait.timer_list);
 	if (RPC_IS_PRIORITY(queue))
 		__rpc_add_wait_queue_priority(queue, task, queue_priority);
-	else if (RPC_IS_SWAPPER(task))
-		list_add(&task->u.tk_wait.list, &queue->tasks[0]);
 	else
 		list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
 	task->tk_waitqueue = queue;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 47d207e416ab..a0a2583fe941 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1354,17 +1354,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				INIT_LIST_HEAD(&req->rq_xmit2);
 				goto out;
 			}
-		} else if (RPC_IS_SWAPPER(task)) {
-			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
-				if (pos->rq_cong || pos->rq_bytes_sent)
-					continue;
-				if (RPC_IS_SWAPPER(pos->rq_task))
-					continue;
-				/* Note: req is added _before_ pos */
-				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
-				INIT_LIST_HEAD(&req->rq_xmit2);
-				goto out;
-			}
 		} else if (!req->rq_seqno) {
 			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
 				if (pos->rq_task->tk_owner != task->tk_owner)