Re: [PATCH] tproxy: nf_tproxy_assign_sock() can handle tw sockets

[Eric Dumazet <eric.dumazet@gmail.com>]

Le mardi 13 juillet 2010 à 11:24 -0300, Felipe W Damasio a écrit :
> Hi Mr. Dumazet,
> 
> 2010/7/12 Felipe W Damasio <felipewd@gmail.com>:
> > Here's the result using ethtool-2.6.34:
> >
> > ./ethtool -k eth1
> >
> > Offload parameters for eth1:
> > rx-checksumming: on
> > tx-checksumming: on
> > scatter-gather: on
> > tcp-segmentation-offload: on
> > udp-fragmentation-offload: off
> > generic-segmentation-offload: on
> > generic-receive-offload: off
> > large-receive-offload: off
> > ntuple-filters: off
> > receive-hashing: off
> >
> >
> > ./ethtool -k eth2
> >
> > Offload parameters for eth2:
> > rx-checksumming: on
> > tx-checksumming: on
> > scatter-gather: on
> > tcp-segmentation-offload: on
> > udp-fragmentation-offload: off
> > generic-segmentation-offload: on
> > generic-receive-offload: off
> > large-receive-offload: off
> > ntuple-filters: off
> > receive-hashing: off
> 
> Did these help you track down the issue?
> 
> Sorry to insist, it's just that my bosses are kind of pressuring me to
> solve the problem and put the squid machine back online :-)
> 
> Is there a test I can run to try and trigger the issue?
> 
> I have the same scenario (hardware and network setup) on my lab...
> 

I currently have no fresh ideas. If you want this problem to be solved,
its important to setup in your lab a workload to trigger again and again
the bug, in order to provide us more crash information.

After code review doesnt spot obvious bugs, this is time for brute force
hunting, using git bisection for example...