Re: AW: ACK behaviour difference LRO/GRO

[Erez Shitrit <erezsh-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>]

בתאריך 10/29/2013 1:43 PM, ציטוט Or Gerlitz:
> On 29/10/2013 13:10, Markus Stockhausen wrote:
>> Just to be on the right way: What are the basics to get GRO working
>> with a ConnectX (not 2 or 3) card in 2044 MTU datagram mode?
>>
>> - enable GRO with ethtool.
>> - Activate Coalescing with ethtool? If yes how?
> GRO is SW element of the network stack, so the HCA doesn't matter, you 
> need IPoIB to support that correct and enable it with ethtool
> -- 
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
In addition to what Or just wrote,
GRO currently doesn't work on ipoib interfaces, that according to bad 
handling mac address that are not 6 bytes (we have plans to fix that in 
the near future), that is the reason you don't see 64k packets on 
tcpdump (like you see in LRO).

you have few options:
1. use old kernels and enable LRO (which works fine with ipoib)
2. use CM mode instead of UD, that probably will improve the performance.

Thanks, Erez
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html