On Sun, 2004-12-19 at 14:54, jamal wrote:
> On Sun, 2004-12-19 at 14:31, jamal wrote:
>
> > How about releasing the qlock only when the LLTX transmit lock is
> > grabbed? That should bring it to par with what it was originally.
>
> Something like two attached patches... one showing how to do it for
> e1000. untested (not even compiled)
After attempting to compile, p2 take2.
cheers,
jamal
--- 2610-rc3-bk12/drivers/net/e1000/bak.e1000_main.c 2004-12-19
13:50:59.000000000 -0500
+++ 2610-rc3-bk12/drivers/net/e1000/e1000_main.c 2004-12-19
13:58:17.000000000 -0500
@@ -1809,6 +1809,10 @@
return NETDEV_TX_LOCKED;
}
+ /* new from sch_generic for LLTX */
+ spin_unlock(&netdev->queue_lock);
+ netdev->xmit_lock_owner = smp_processor_id();
+
/* need: count + 2 desc gap to keep tail from touching
* head, otherwise try next time */
if(E1000_DESC_UNUSED(&adapter->tx_ring) < count + 2) {
_______________________________________________
openib-general mailing list
[EMAIL PROTECTED]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
