How to Quicken TCP Re-transmission?

[Bruce A. Mah]

If memory serves me right, Mark Allman wrote:
>>      Thank you for your reminder. Actually, I understand you and
>> RFC 2018. What I really concern is how wide support (and being enabled
>> by default) SACK has obtained. For we do not always transfer data
>> between hosts running FreeBSD and maintained by network expert.
> 
> SACK is quite widely deployed.  See:
> 
>   Alberto Medina, Mark Allman, Sally Floyd.  Measuring the Evolution of
>   Transport Protocols in the Internet.  ACM Computer Communication
>   Review, 35(2), April 2005.
>   http://www.icir.org/mallman/papers/tcp-evo-ccr05.ps

What a trip, I just read this paper on the train to work this morning.
FWIW, I thought this was a well-done study on an interesting topic.  A
question and a nitpick:

Did you try doing any stack fingerprinting to get some idea of the mix
of TCP/IP stacks among the servers / clients you examined?

The percentages in the commentary on Table 5 in the text (second column
of p. 41 in the CCR printing) are sometimes one-off from the percentages
actually shown in Table 5.  It took me several tries to get through the
"huh?!?"-ness of this, though the lack of caffeine in my bloodstream at
the time might have been a contributing factor.  :-)

Cheers,

Bruce.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 250 bytes
Desc: OpenPGP digital signature
Url : http://lists.freebsd.org/pipermail/freebsd-net/attachments/20060523/9acc9fb9/signature.pgp