Re: [PATCH -next] net: core: set qdisc pkt len before tc_classify

[Jamal Hadi Salim <jhs@mojatatu.com>]

On 05/13/15 07:02, Jamal Hadi Salim wrote:
>
>
> I dont think we need the stab on the ingress but we do need to account
> for gso. So option #1 with qdisc_pkt_len_init() alone is the only thing
> needed. i.e Florian's change becomes:
>
> -    qdisc_bstats_update_cpu(cl->q, skb);
> +    qdisc_pkt_len_init(skb)
>       skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
> +    qdisc_bstats_update_cpu(cl->q, skb);
>
> Alexei, why do you say this option will have overhead?
>

and the comment in qdisc_pkt_len_init() needs fixing too.
It says:
         /* To get more precise estimation of bytes sent on wire,
          * we add to pkt_len the headers size of all segments
          */


It implies transmit direction only - modern nics do set this
on receive.  Something like:

         /* To get more precise estimation of bytes rx or to be sent
           on the wire, we add to pkt_len the headers size of
           all segments
         */

cheers,
jamal