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>
This commit is contained in:
Michael S. Tsirkin 2007-04-12 18:10:25 +03:00 committed by Roland Dreier
parent c3af664adb
commit 9ba6d5529d
1 changed files with 13 additions and 0 deletions

View File

@ -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);
}
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) {
qp_context->pri_path.ackto = attr->timeout << 3;
qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_ACK_TIMEOUT);