From: Chuck Lever <chuck.lever@xxxxxxxxxx>
With large NFS WRITE requests on TCP, I measured 5-10 thread wake-
ups to receive each request. This is because the socket layer
calls ->sk_data_ready() frequently, and each call triggers a
thread wake-up. Each recvmsg() seems to pull in less than 100KB.
Have the socket layer hold ->sk_data_ready() calls until the full
incoming message has arrived to reduce the wake-up rate.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
---
net/sunrpc/svcsock.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 7b7358908a21..36e5070132ea 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1088,6 +1088,9 @@ static void svc_tcp_fragment_received(struct svc_sock *svsk)
/* If we have more data, signal svc_xprt_enqueue() to try again */
svsk->sk_tcplen = 0;
svsk->sk_marker = xdr_zero;
+
+ smp_wmb();
+ tcp_set_rcvlowat(svsk->sk_sk, 1);
}
/**
@@ -1177,10 +1180,17 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
goto err_delete;
if (len == want)
svc_tcp_fragment_received(svsk);
- else
+ else {
+ /* Avoid more ->sk_data_ready() calls until the rest
+ * of the message has arrived. This reduces service
+ * thread wake-ups on large incoming messages. */
+ tcp_set_rcvlowat(svsk->sk_sk,
+ svc_sock_reclen(svsk) - svsk->sk_tcplen);
+
trace_svcsock_tcp_recv_short(&svsk->sk_xprt,
svc_sock_reclen(svsk),
svsk->sk_tcplen - sizeof(rpc_fraghdr));
+ }
goto err_noclose;
error:
if (len != -EAGAIN)
