sunrpc: add info about xprt queue times to svc_xprt_dequeue tracepoint

I've been looking at a problem where we see increased RPC timeouts in
clients when the nfs_layout_flexfiles dataserver_timeo value is tuned
very low (6s). This is necessary to ensure quick failover to a different
mirror if a server goes down, but it causes a lot more major RPC timeouts.

Ultimately, the problem is server-side however. It's sometimes doesn't
respond to connection attempts. My theory is that the interrupt handler
runs when a connection comes in, the xprt ends up being enqueued, but it
takes a significant amount of time for the nfsd thread to pick it up.

Currently, the svc_xprt_dequeue tracepoint displays "wakeup-us". This is
the time between the wake_up() call, and the thread dequeueing the xprt.
If no thread was woken, or the thread ended up picking up a different
xprt than intended, then this value won't tell us how long the xprt was
waiting.

Add a new xpt_qtime field to struct svc_xprt and set it in
svc_xprt_enqueue(). When the dequeue tracepoint fires, also store the
time that the xprt sat on the queue in total. Display it as "qtime-us".

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 72be609525796792274d5b8cb5ff37f73723fc23..369a89aea18618748607ee943247c327bf62c8d5 100644 (file)
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -53,6 +53,7 @@ struct svc_xprt {
        struct svc_xprt_class   *xpt_class;
        const struct svc_xprt_ops *xpt_ops;
        struct kref             xpt_ref;
+       ktime_t                 xpt_qtime;
        struct list_head        xpt_list;
        struct lwq_node         xpt_ready;
        unsigned long           xpt_flags;

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5d331383047b79b9f6dcd699c87287453c1a5f49..67db3f2953d5d64f2e8e455b218f7f6ecb7753ec 100644 (file)
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2040,19 +2040,20 @@ TRACE_EVENT(svc_xprt_dequeue,
 
        TP_STRUCT__entry(
                SVC_XPRT_ENDPOINT_FIELDS(rqst->rq_xprt)
-
                __field(unsigned long, wakeup)
+               __field(unsigned long, qtime)
        ),
 
        TP_fast_assign(
-               SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+               ktime_t ktime = ktime_get();
 
-               __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(),
-                                                       rqst->rq_qtime));
+               SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+               __entry->wakeup = ktime_to_us(ktime_sub(ktime, rqst->rq_qtime));
+               __entry->qtime = ktime_to_us(ktime_sub(ktime, rqst->rq_xprt->xpt_qtime));
        ),
 
-       TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu",
-               SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup)
+       TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu qtime-us=%lu",
+               SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup, __entry->qtime)
 );
 
 DECLARE_EVENT_CLASS(svc_xprt_event,

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index ae25405d8bd22672a361d1fd3adfdcebb403f90f..32018557797b1f683d8b7259f5fccd029aebcd71 100644 (file)
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -488,6 +488,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
        pool = svc_pool_for_cpu(xprt->xpt_server);
 
        percpu_counter_inc(&pool->sp_sockets_queued);
+       xprt->xpt_qtime = ktime_get();
        lwq_enqueue(&xprt->xpt_ready, &pool->sp_xprts);
 
        svc_pool_wake_idle_thread(pool);