diff options
| author | Bob Pearson <rpearsonhpe@gmail.com> | 2024-03-29 09:55:11 -0500 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@nvidia.com> | 2024-04-22 16:54:33 -0300 |
| commit | 23bc06af547f2ca3b7d345e09fd8d04575406274 (patch) | |
| tree | 83be7d44282435b82d30a51f6b109f0e288c6d69 | |
| parent | 3d807a3ebc48a2e1685ebfa9d26ea2c9ceb9c53e (diff) | |
| download | rdma-23bc06af547f2ca3b7d345e09fd8d04575406274.tar.gz | |
RDMA/rxe: Don't call direct between tasks
Replace calls to rxe_run_task() with rxe_sched_task(). This prevents the
tasks from all running on the same cpu.
This change slightly reduces performance for single qp send and write
benchmarks in loopback mode but greatly improves the performance with
multiple qps because if run task is used all the work tends to be
performed on one cpu. For actual on the wire benchmarks there is no
noticeable performance change.
Link: https://lore.kernel.org/r/20240329145513.35381-11-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_comp.c | 13 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_resp.c | 12 | ||||
| -rw-r--r-- | drivers/infiniband/sw/rxe/rxe_verbs.c | 2 |
3 files changed, 4 insertions, 23 deletions
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 357c1d516efbf..d48af21807458 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -129,18 +129,9 @@ void retransmit_timer(struct timer_list *t) void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) { - int must_sched; - - must_sched = skb_queue_len(&qp->resp_pkts) > 0; - if (must_sched != 0) - rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_SENDER_SCHED); - + rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_SENDER_SCHED); skb_queue_tail(&qp->resp_pkts, skb); - - if (must_sched) - rxe_sched_task(&qp->send_task); - else - rxe_run_task(&qp->send_task); + rxe_sched_task(&qp->send_task); } static inline enum comp_state get_wqe(struct rxe_qp *qp, diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 3ce7a32b5dcf8..c6a7fa3054fad 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -49,18 +49,8 @@ static char *resp_state_name[] = { /* rxe_recv calls here to add a request packet to the input queue */ void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) { - int must_sched; - struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); - skb_queue_tail(&qp->req_pkts, skb); - - must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) || - (skb_queue_len(&qp->req_pkts) > 1); - - if (must_sched) - rxe_sched_task(&qp->recv_task); - else - rxe_run_task(&qp->recv_task); + rxe_sched_task(&qp->recv_task); } static inline enum resp_states get_req(struct rxe_qp *qp, diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index d07f7bd3b2ae2..c7d4d8ab5a094 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -935,7 +935,7 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, if (qp->is_user) { /* Utilize process context to do protocol processing */ - rxe_run_task(&qp->send_task); + rxe_sched_task(&qp->send_task); } else { err = rxe_post_send_kernel(qp, wr, bad_wr); if (err) |