diff mbox series

[for-rc,1/2] IB/hfi1: Fix a latency issue for small messages

Message ID 20181128144428.10591.47294.stgit@scvm10.sc.intel.com (mailing list archive)
State Accepted
Commit 90b2620e6a8aa08c40cc78d61603e0acd853c33a
Headers show
Series Patches for 4.20 rc cycle | expand

Commit Message

Dennis Dalessandro Nov. 28, 2018, 2:44 p.m. UTC 
From: Michael J. Ruhl <michael.j.ruhl@intel.com>

A recent performance enhancement introduced a latency issue in the
HFI message path.  The new algorithm removed a forced call send for
PIO messages and added a forced schedule event for messages larger
than the MTU.

For PIO, the schedule path can introduce thrashing that can
significantly impact the throughput for small messages.

If a message size is within the PIO threshold, always take the send
path.

Fixes: 0b79b27748cb ("IB/{hfi1, qib, rdmavt}: Schedule multi RC/UC packets instead of posting")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
---
 drivers/infiniband/hw/hfi1/qp.c |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)
diff mbox series

Patch

diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 6f3bc4d..1a01624 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -340,6 +340,13 @@  int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe, bool *call_send)
 	default:
 		break;
 	}
+
+	/*
+	 * System latency between send and schedule is large enough that
+	 * forcing call_send to true for piothreshold packets is necessary.
+	 */
+	if (wqe->length <= piothreshold)
+		*call_send = true;
 	return 0;
 }