SUNRPC: Replace jiffies-based metrics with ktime-based metrics

Currently RPC performance metrics that tabulate elapsed time use
jiffies time values.  This is problematic on systems that use slow
jiffies (for instance 100HZ systems built for paravirtualized
environments).  It is also a problem for computing precise latency
statistics for advanced network transports, such as InfiniBand,
that can have round-trip latencies significanly faster than a single
clock tick.

For the RPC client, adopt the high resolution time stamp mechanism
already used by the network layer and blktrace: ktime.

We use ktime format time stamps for all internal computations, and
convert to milliseconds for presentation.  As a result, we need only
addition operations in the performance critical paths; multiply/divide
is required only for presentation.

We could report RTT metrics in microseconds.  In fact the mountstats
format is versioned to accomodate exactly this kind of interface
improvement.

For now, however, we'll stay with millisecond precision for
presentation to maintain backwards compatibility with the handful of
currently deployed user space tools.  At a later point, we'll move to
an API such as BDI_STATS where a finer timestamp precision can be
reported.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

3 files changed, 9 insertions, 6 deletions

diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h
index 77f78e5..b6edbc0 100644
--- a/include/linux/sunrpc/metrics.h
+++ b/include/linux/sunrpc/metrics.h
@@ -26,6 +26,7 @@
 #define _LINUX_SUNRPC_METRICS_H
 
 #include <linux/seq_file.h>
+#include <linux/ktime.h>
 
 #define RPC_IOSTATS_VERS	"1.0"
 
@@ -58,9 +59,9 @@ struct rpc_iostats {
 	 * and the total time the request spent from init to release
 	 * are measured.
 	 */
-	unsigned long long	om_queue,	/* jiffies queued for xmit */
-				om_rtt,		/* jiffies for RPC RTT */
-				om_execute;	/* jiffies for RPC execution */
+	ktime_t			om_queue,	/* queued for xmit */
+				om_rtt,		/* RPC RTT */
+				om_execute;	/* RPC execution */
 } ____cacheline_aligned;
 
 struct rpc_task;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 7bc7fd5..76720d2 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -10,6 +10,7 @@
 #define _LINUX_SUNRPC_SCHED_H_
 
 #include <linux/timer.h>
+#include <linux/ktime.h>
 #include <linux/sunrpc/types.h>
 #include <linux/spinlock.h>
 #include <linux/wait.h>
@@ -80,8 +81,8 @@ struct rpc_task {
 
 	unsigned short		tk_timeouts;	/* maj timeouts */
 	size_t			tk_bytes_sent;	/* total bytes sent */
-	unsigned long		tk_start;	/* RPC task init timestamp */
-	long			tk_rtt;		/* round-trip time (jiffies) */
+	ktime_t			tk_start,	/* RPC task init timestamp */
+				tk_rtt;		/* round-trip time */
 
 	pid_t			tk_owner;	/* Process id for batching tasks */
 	unsigned char		tk_priority : 2;/* Task priority */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 04fc342..f885186 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -13,6 +13,7 @@
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/kref.h>
+#include <linux/ktime.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/msg_prot.h>
@@ -94,7 +95,7 @@ struct rpc_rqst {
 	 */
 	u32			rq_bytes_sent;	/* Bytes we have sent */
 
-	unsigned long		rq_xtime;	/* when transmitted */
+	ktime_t			rq_xtime;	/* transmit time stamp */
 	int			rq_ntrans;
 
 #if defined(CONFIG_NFS_V4_1)