On Mon, Mar 23, 2015 at 5:39 PM, Wesley Eddy <[email protected]> wrote:
> On 3/23/2015 6:22 PM, Joe Touch wrote:
>>> > Well, SACK? But, I guess common cases will be a combination of
>>> > extensions, not a specific one.
>> SACK can use as much space as it is given, AFAICT ;-)
>
>
> That's right, and there have been multiple studies that even
> showed it was useful to be able to carry a larger number of
> SACK blocks.
Please share the studies.
After today's meeting, my concerns are
1. EDO's incompatibility with HW/SW offload. I am positive we can
probably fix the SW-offload but pessimistic about changes in
HW-offload.
Here is another data point, in addition to the iperf data
presented today: (L|G)RO and (G|T)SO are critical for Google Linux
servers.
2. Salvage operation when middleboxes strip EDO randomly in the middle
of connection
>
> In my opinion, this alone could be worthy motivation, without
> even trying to enumerate all the experimental or combinations
> of options that might (or might not) find EDO useful.
>
> --
> Wes Eddy
> MTI Systems
_______________________________________________
Tcpinc mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/tcpinc
