Maksim Yevmenkin cd1fb2e095 Before it gets lost in the noise.
Put a bandaid to prevent ixgbe(4) from completely locking up the system
under high load. Our platform has a few CPU cores and a single active
ixgbe(4) port with 4 queues. Under high enough traffic load, at about
7.5GBs and 700,000 packets/sec (outbound), the entire system would
deadlock. What we found was that each CPU was in an endless loop on a
different ix taskqueue thread. The OACTIVE flag had gotten set on each
queue, and the ixgbe_handle_queue() function was continuously rescheduling
itself via the taskqueue_enqueue. Since all CPUs were busy with their
taskqueue threads, the ixgbe_local_timer() function couldn't run to clear
the OACTIVE flag.

Submitted by:	scottl
MFC after:	1 week
2012-06-05 18:48:02 +00:00
..
2012-03-12 20:31:58 +00:00
2012-04-04 21:09:02 +00:00
2012-06-02 19:41:28 +00:00
2011-12-17 10:23:17 +00:00
2012-03-27 15:13:12 +00:00
2012-05-25 03:00:34 +00:00
2012-05-24 23:03:23 +00:00
2012-05-23 06:49:50 +00:00
2012-01-10 20:52:02 +00:00
2012-01-15 13:23:18 +00:00
2012-04-16 23:29:12 +00:00
2012-05-23 13:23:40 +00:00
2012-01-31 13:00:40 +00:00
2012-01-15 13:23:43 +00:00
2012-04-13 18:21:56 +00:00
2012-06-05 18:48:02 +00:00
2011-10-18 08:09:44 +00:00
2011-12-17 10:23:17 +00:00
2012-05-25 15:05:17 +00:00
2012-01-11 15:00:16 +00:00
2012-02-27 08:57:02 +00:00
2012-01-15 13:23:18 +00:00
2012-05-11 03:17:32 +00:00
2012-06-02 19:41:28 +00:00
2011-12-15 05:07:16 +00:00
2012-02-11 08:12:52 +00:00
2011-12-22 15:13:32 +00:00
2011-10-18 08:09:44 +00:00
2011-11-23 05:34:01 +00:00
2012-06-01 04:23:20 +00:00