From 2c2ee6d20b10594892c1d31c7b959f4780adde63 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 23 Nov 2016 14:44:58 +1100 Subject: [PATCH] sunrpc: Don't engage exponential backoff when connection attempt is rejected. xs_connect() contains an exponential backoff mechanism so the repeated connection attempts are delayed by longer and longer amounts. This is appropriate when the connection failed due to a timeout, but it not appropriate when a definitive "no" answer is received. In such cases, call_connect_status() imposes a minimum 3-second back-off, so not having the exponetial back-off will never result in immediate retries. The current situation is a problem when the NFS server tries to register with rpcbind but rpcbind isn't running. All connection attempts are made on the same "xprt" and as the connection is never "closed", the exponential back delays successive attempts to register, or de-register, different protocols. This results in a multi-minute delay with no benefit. So, when call_connect_status() receives a definitive "no", use xprt_conditional_disconnect() to cancel the previous connection attempt. This will set XPRT_CLOSE_WAIT so that xprt->ops->close() calls xs_close() which resets the reestablish_timeout. To ensure xprt_conditional_disconnect() does the right thing, we ensure that rq_connect_cookie is set before a connection attempt, and allow xprt_conditional_disconnect() to complete even when the transport is not fully connected. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- net/sunrpc/clnt.c | 2 ++ net/sunrpc/xprt.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 62a482790937..1efbe48e794f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1926,6 +1926,8 @@ call_connect_status(struct rpc_task *task) case -EADDRINUSE: case -ENOBUFS: case -EPIPE: + xprt_conditional_disconnect(task->tk_rqstp->rq_xprt, + task->tk_rqstp->rq_connect_cookie); if (RPC_IS_SOFTCONN(task)) break; /* retry with existing socket, after a delay */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 685e6d225414..9a6be030ca7d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -669,7 +669,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie) spin_lock_bh(&xprt->transport_lock); if (cookie != xprt->connect_cookie) goto out; - if (test_bit(XPRT_CLOSING, &xprt->state) || !xprt_connected(xprt)) + if (test_bit(XPRT_CLOSING, &xprt->state)) goto out; set_bit(XPRT_CLOSE_WAIT, &xprt->state); /* Try to schedule an autoclose RPC call */ @@ -772,6 +772,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_connected(xprt)) { task->tk_rqstp->rq_bytes_sent = 0; task->tk_timeout = task->tk_rqstp->rq_timeout; + task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on(&xprt->pending, task, xprt_connect_status); if (test_bit(XPRT_CLOSING, &xprt->state)) -- 2.20.1