SUNRPC: Revert e0a912e

Flamegraph analysis showed that the cork/uncork calls consume
nearly a third of the CPU time spent in svc_tcp_sendto(). The
other two consumers are mutex lock/unlock and svc_tcp_sendmsg().

Now that svc_tcp_sendto() coalesces RPC messages properly, there
is no need to introduce artificial delays to prevent sending
partial messages.

After applying this change, I measured a 1.2K read IOPS increase
for 8KB random I/O (several percent) on 56Gb IP over IB.

Reviewed-by: David Howells <[email protected]>
Signed-off-by: Chuck Lever <[email protected]>

Author: chucklever

include/linux/sunrpc/svcsock.h

@@ -35,8 +35,6 @@ struct svc_sock {
 	/* Total length of the data (not including fragment headers)
 	 * received so far in the fragments making up this rpc: */
 	u32			sk_datalen;
-	/* Number of queued send requests */
-	atomic_t		sk_sendqlen;
 
 	struct page_frag_cache  sk_frag_cache;
 

net/sunrpc/svcsock.c

@@ -1268,22 +1268,17 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
 	rqstp->rq_xprt_ctxt = NULL;
 
-	atomic_inc(&svsk->sk_sendqlen);
 	mutex_lock(&xprt->xpt_mutex);
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
-	tcp_sock_set_cork(svsk->sk_sk, true);
 	err = svc_tcp_sendmsg(svsk, rqstp, marker, &sent);
 	trace_svcsock_tcp_send(xprt, err < 0 ? (long)err : sent);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))
 		goto out_close;
-	if (atomic_dec_and_test(&svsk->sk_sendqlen))
-		tcp_sock_set_cork(svsk->sk_sk, false);
 	mutex_unlock(&xprt->xpt_mutex);
 	return sent;
 
 out_notconn:
-	atomic_dec(&svsk->sk_sendqlen);
 	mutex_unlock(&xprt->xpt_mutex);
 	return -ENOTCONN;
 out_close:
@@ -1292,7 +1287,6 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 		  (err < 0) ? "got error" : "sent",
 		  (err < 0) ? err : sent, xdr->len);
 	svc_xprt_deferred_close(xprt);
-	atomic_dec(&svsk->sk_sendqlen);
 	mutex_unlock(&xprt->xpt_mutex);
 	return -EAGAIN;
 }