| commit | c033a6d1390bb6cc0c11c3b4137b856dfd8cb7c8 | |
| author | Santiago Leon <santil@linux.vnet.ibm.com> | |
| Fri, 3 Sep 2010 18:28:09 +0000 (3 18:28 +0000) | ||
| committer | David S. Miller <davem@davemloft.net> | |
| Tue, 7 Sep 2010 01:20:32 +0000 (6 18:20 -0700) | ||
| tree | ff296183b963b75d0da43e3c809b58083316e3af | treesnapshot (tar.gz zip) |
| parent | a613f581489aff23189c4945aec9567f6663b0c6 | commitdiff |
ibmveth: batch rx buffer replacement
At the moment we try and replenish the receive ring on every rx interrupt.
We even have a pool->threshold but aren't using it.
To limit the maximum latency incurred when refilling, change the threshold
from 1/2 to 7/8 and reduce the largest rx pool from 768 buffers to 512 which
should be more than enough.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Santiago Leon <santil@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At the moment we try and replenish the receive ring on every rx interrupt.
We even have a pool->threshold but aren't using it.
To limit the maximum latency incurred when refilling, change the threshold
from 1/2 to 7/8 and reduce the largest rx pool from 768 buffers to 512 which
should be more than enough.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Santiago Leon <santil@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
| drivers/net/ibmveth.c | diffblobblamehistory | |
| drivers/net/ibmveth.h | diffblobblamehistory |