public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH] opensm/osm_vl15intf.c: In vl15_poller, drain unicast even if max_wire_smps are outstanding
@ 2009-10-20 13:41 Hal Rosenstock
  0 siblings, 0 replies; only message in thread
From: Hal Rosenstock @ 2009-10-20 13:41 UTC (permalink / raw)
  To: sashak-smomgflXvOZWk0Htik3J/w; +Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA


Unicast sends should not be blocked by waiting transactions.
In this case (one example is timeouts due to rebooting nodes),
this can cause trap represses to be delayed (which is not a good thing).

Signed-off-by: Hal Rosenstock <hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
diff --git a/opensm/opensm/osm_vl15intf.c b/opensm/opensm/osm_vl15intf.c
index 9e43a9c..07a2336 100644
--- a/opensm/opensm/osm_vl15intf.c
+++ b/opensm/opensm/osm_vl15intf.c
@@ -2,6 +2,7 @@
  * Copyright (c) 2004-2008 Voltaire, Inc. All rights reserved.
  * Copyright (c) 2002-2005 Mellanox Technologies LTD. All rights reserved.
  * Copyright (c) 1996-2003 Intel Corporation. All rights reserved.
+ * Copyright (c) 2009 HNR Consulting. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -115,6 +116,7 @@ static void vl15_poller(IN void *p_ptr)
 	osm_madw_t *p_madw;
 	osm_vl15_t *p_vl = p_ptr;
 	cl_qlist_t *p_fifo;
+	uint32_t ufifo_count = 0;
 
 	OSM_LOG_ENTER(p_vl->p_log);
 
@@ -132,10 +134,15 @@ static void vl15_poller(IN void *p_ptr)
 		 */
 		cl_spinlock_acquire(&p_vl->lock);
 
-		if (cl_qlist_count(&p_vl->ufifo) != 0)
+		if (ufifo_count)
 			p_fifo = &p_vl->ufifo;
-		else
-			p_fifo = &p_vl->rfifo;
+		else {
+			ufifo_count = cl_qlist_count(&p_vl->ufifo);
+			if (ufifo_count != 0)
+				p_fifo = &p_vl->ufifo;
+			else
+				p_fifo = &p_vl->rfifo;
+		}
 
 		p_madw = (osm_madw_t *) cl_qlist_remove_head(p_fifo);
 
@@ -157,7 +164,14 @@ static void vl15_poller(IN void *p_ptr)
 			status = cl_event_wait_on(&p_vl->signal,
 						  EVENT_NO_TIMEOUT, TRUE);
 
-		while (p_vl->p_stats->qp0_mads_outstanding_on_wire >=
+		if (ufifo_count) {
+			cl_spinlock_acquire(&p_vl->lock);
+                	ufifo_count = cl_qlist_count(&p_vl->ufifo);
+			cl_spinlock_release(&p_vl->lock);
+		}
+
+		while (!ufifo_count &&
+		       p_vl->p_stats->qp0_mads_outstanding_on_wire >=
 		       (int32_t) p_vl->max_wire_smps &&
 		       p_vl->thread_state == OSM_THREAD_STATE_RUN) {
 			status = cl_event_wait_on(&p_vl->signal,
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply related	[flat|nested] only message in thread

only message in thread, other threads:[~2009-10-20 13:41 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-10-20 13:41 [PATCH] opensm/osm_vl15intf.c: In vl15_poller, drain unicast even if max_wire_smps are outstanding Hal Rosenstock

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox