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: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Showing
想要评论请 注册 或 登录