xprtrdma: Reduce the doorbell rate (Receive)

Post RECV WRs in batches to reduce the hardware doorbell rate per
transport. This helps the RPC-over-RDMA client scale better in
number of transports.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

net/sunrpc/xprtrdma/verbs.c

@@ -1480,6 +1480,8 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 	if (ep->rep_receive_count > needed)
 		goto out;
 	needed -= ep->rep_receive_count;
+	if (!temp)
+		needed += RPCRDMA_MAX_RECV_BATCH;
 
 	count = 0;
 	wr = NULL;

net/sunrpc/xprtrdma/xprt_rdma.h

@@ -205,6 +205,16 @@ struct rpcrdma_rep {
 	struct ib_recv_wr	rr_recv_wr;
 };
 
+/* To reduce the rate at which a transport invokes ib_post_recv
+ * (and thus the hardware doorbell rate), xprtrdma posts Receive
+ * WRs in batches.
+ *
+ * Setting this to zero disables Receive post batching.
+ */
+enum {
+	RPCRDMA_MAX_RECV_BATCH = 7,
+};
+
 /* struct rpcrdma_sendctx - DMA mapped SGEs to unmap after Send completes
  */
 struct rpcrdma_req;