Commit 7de62bc0 authored by Olga Kornievskaia's avatar Olga Kornievskaia Committed by Trond Myklebust
Browse files

SUNRPC dont update timeout value on connection reset 



Current behaviour: every time a v3 operation is re-sent to the server
we update (double) the timeout. There is no distinction between whether
or not the previous timer had expired before the re-sent happened.

Here's the scenario:
1. Client sends a v3 operation
2. Server RST-s the connection (prior to the timeout) (eg., connection
is immediately reset)
3. Client re-sends a v3 operation but the timeout is now 120sec.

As a result, an application sees 2mins pause before a retry in case
server again does not reply.

Instead, this patch proposes to keep track off when the minor timeout
should happen and if it didn't, then don't update the new timeout.
Value is updated based on the previous value to make timeouts
predictable.

Signed-off-by: default avatarOlga Kornievskaia <kolga@netapp.com>
Signed-off-by: default avatarTrond Myklebust <trond.myklebust@hammerspace.com>
parent ce368536

include/linux/sunrpc/xprt.h

+1 −0
Original line number Diff line number Diff line
@@ -101,6 +101,7 @@ struct rpc_rqst { 
							 * used in the softirq.

							 */

	unsigned long		rq_majortimeo;	/* major timeout alarm */

	unsigned long		rq_minortimeo;	/* minor timeout alarm */

	unsigned long		rq_timeout;	/* Current timeout value */

	ktime_t			rq_rtt;		/* round-trip time */

	unsigned int		rq_retries;	/* # of retries */

net/sunrpc/xprt.c

+9 −0
Original line number Diff line number Diff line
@@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req) 
	req->rq_majortimeo += xprt_calc_majortimeo(req);

}



static void xprt_reset_minortimeo(struct rpc_rqst *req)

{

	req->rq_minortimeo += req->rq_timeout;

}



static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)

{

	unsigned long time_init;
@@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req) 
		time_init = xprt_abs_ktime_to_jiffies(task->tk_start);

	req->rq_timeout = task->tk_client->cl_timeout->to_initval;

	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);

	req->rq_minortimeo = time_init + req->rq_timeout;

}



/**
@@ -631,6 +637,8 @@ int xprt_adjust_timeout(struct rpc_rqst *req) 
	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;

	int status = 0;



	if (time_before(jiffies, req->rq_minortimeo))

		return status;

	if (time_before(jiffies, req->rq_majortimeo)) {

		if (to->to_exponential)

			req->rq_timeout <<= 1;
@@ -649,6 +657,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req) 
		spin_unlock(&xprt->transport_lock);

		status = -ETIMEDOUT;

	}

	xprt_reset_minortimeo(req);



	if (req->rq_timeout == 0) {

		printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");

CRA Git | Maintained and supported by SUSTech CRA and CCSE