[Discussion] About over-MTU-sized skb in virtualized env

[Discussion] About over-MTU-sized skb in virtualized env

[Du Fan]

Sorry for resend this mail, because my company email is rejected by netdev.


Hi Florian

  214 static int ip_finish_output_gso(struct sk_buff *skb)
  215 {
  216     netdev_features_t features;
  217     struct sk_buff *segs;
  218     int ret = 0;
  219
  220     /* common case: locally created skb or seglen is <= mtu */
  221     if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
  222           skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
  223         return ip_finish_output2(skb);

Could you please state _concrete_ reason why locally created skb
length is ＿always＿ fitting into MTU size? or why we needs this
checking.
Especially in below scenario:
http://docs.openstack.org/admin-guide-cloud/content/figures/14/a/a/common/figures/under-the-hood-scenario-1-ovs-compute.png

As many people have discuss it in this thread:
http://marc.info/?t=141715669700004&r=1&w=2

Re: [Discussion] About over-MTU-sized skb in virtualized env

[Florian Westphal]

Du Fan <fengyuleidian0615@gmail.com> wrote:
> Sorry for resend this mail, because my company email is rejected by netdev.
> 
> 
> Hi Florian
> 
>  214 static int ip_finish_output_gso(struct sk_buff *skb)
>  215 {
>  216     netdev_features_t features;
>  217     struct sk_buff *segs;
>  218     int ret = 0;
>  219
>  220     /* common case: locally created skb or seglen is <= mtu */
>  221     if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
>  222           skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
>  223         return ip_finish_output2(skb);
> 
> Could you please state _concrete_ reason why locally created skb
> length is ＿always＿ fitting into MTU size? or why we needs this
> checking.

We don't "need" this checking.  Its just to avoid skb_gso_network_seglen()
computation for the common (local-out) case.

Locally generated GSO packet is not supposed to exceed dst_mtu, as that
is the PMTU discovery start point in absence of lower/learned value.

[Discussion] About over-MTU-sized skb in virtualized env

[Du, Fan]

Hi Florian

214 static int ip_finish_output_gso(struct sk_buff *skb)
 215 {
 216     netdev_features_t features;
 217     struct sk_buff *segs;
 218     int ret = 0;
 219
 220     /* common case: locally created skb or seglen is <= mtu */
 221     if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
 222           skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
 223         return ip_finish_output2(skb);

Could you please state _concrete_ _reason_ why locally created skb length is ＿always＿ fitting into MTU size?
Especially in below scenario:
http://docs.openstack.org/admin-guide-cloud/content/figures/14/a/a/common/figures/under-the-hood-scenario-1-ovs-compute.png

As many people have discuss it in this thread:
http://marc.info/?t=141715669700004&r=1&w=2







_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev