Hi Enric, On 1/4/22 18:42, Eric Dumazet wrote: > > On 1/4/22 07:11, Aleksander Jan Bajkowski wrote: >> We can increase the efficiency of rx path by using buffers to receive >> packets then build SKBs around them just before passing into the network >> stack. In contrast, preallocating SKBs too early reduces CPU cache >> efficiency. >> >> NAT Performance results on BT Home Hub 5A (kernel 5.10.89, mtu 1500): >> >> Down Up >> Before 577 Mbps 648 Mbps >> After 624 Mbps 695 Mbps >> >> Signed-off-by: Aleksander Jan Bajkowski <olek2@xxxxx> >> --- > > > Not sure why GRO is not yet implemented in this driver... > > I changed netif_receive_skb() to napi_gro_receive() and did some tests. I don't see any performance difference. Are any further changes needed to support GRO? Maybe this is because this MAC is connected to a DSA switch and the napi_gro_receive() function cannot aggregate packets until the DSA tag is removed.
