Browse Source

IB/mthca: Work around kernel QP starvation

With mthca, RC QPs can starve each other and even UD QPs on the same
hardware schedule queue.  As a result, userspace MPI can starve
e.g. IPoIB traffic, with netdev watchdog warnings getting printed out,
and TCP connections getting stuck or failing.

Reduce the chance of this happening by using three separate hardware
schedule queues: one for userspace RC QPs, one for kernel RC QPs, and
one for all other QPs.

Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Michael S. Tsirkin 18 years ago
parent
commit
9ba6d5529d
1 changed files with 13 additions and 0 deletions
  1. 13 0
      drivers/infiniband/hw/mthca/mthca_qp.c

+ 13 - 0
drivers/infiniband/hw/mthca/mthca_qp.c

@@ -701,6 +701,19 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
 		qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_PRIMARY_ADDR_PATH);
 		qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_PRIMARY_ADDR_PATH);
 	}
 	}
 
 
+	if (ibqp->qp_type == IB_QPT_RC &&
+	    cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
+		u8 sched_queue = ibqp->uobject ? 0x2 : 0x1;
+
+		if (mthca_is_memfree(dev))
+			qp_context->rlkey_arbel_sched_queue |= sched_queue;
+		else
+			qp_context->tavor_sched_queue |= cpu_to_be32(sched_queue);
+
+		qp_param->opt_param_mask |=
+			cpu_to_be32(MTHCA_QP_OPTPAR_SCHED_QUEUE);
+	}
+
 	if (attr_mask & IB_QP_TIMEOUT) {
 	if (attr_mask & IB_QP_TIMEOUT) {
 		qp_context->pri_path.ackto = attr->timeout << 3;
 		qp_context->pri_path.ackto = attr->timeout << 3;
 		qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_ACK_TIMEOUT);
 		qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_ACK_TIMEOUT);