vxge: prefetch RxD descriptors
This patch prefetches RxD descriptors which helps to lower the latency of a cache miss in vxge_hw_ring_rxd_next_completed. This lowers the % of CPU time used by vxge_hw_ring_rxd_next_completed() where the descriptor is accessed in profiling netperf on a P4 Xeon from 1.5% to 1.0%. Signed-off-by: Benjamin LaHaise <ben.lahaise@neterion.com> Signed-off-by: Sreenivasa Honnur <sreenivasa.honnur@neterion.com> Signed-off-by: Ramkrishna Vepa <ram.vepa@neterion.com> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
parent
ff1b974cf3
commit
3f23e436d2
2 changed files with 2 additions and 0 deletions
|
@ -445,6 +445,7 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
|
|||
vxge_hw_ring_replenish(ringh, 0);
|
||||
|
||||
do {
|
||||
prefetch((char *)dtr + L1_CACHE_BYTES);
|
||||
rx_priv = vxge_hw_ring_rxd_private_get(dtr);
|
||||
skb = rx_priv->skb;
|
||||
data_size = rx_priv->data_size;
|
||||
|
|
|
@ -731,6 +731,7 @@ vxge_hw_channel_dtr_try_complete(struct __vxge_hw_channel *channel, void **dtrh)
|
|||
vxge_assert(channel->compl_index < channel->length);
|
||||
|
||||
*dtrh = channel->work_arr[channel->compl_index];
|
||||
prefetch(*dtrh);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
Loading…
Reference in a new issue