Form: Reply
Text: (9 lines follow)
Chuck,
Thanks for the response. I agree that optimizing segment size will optimise
throughput, particularly over satellite.
However, for short file transmission, it is arguably not worth spending time
doing the discovery, where this could be better spent sending the file. All
I'm suggesting is that this get moved from stand-mech I-D to res-issue I-D
unless someone has demonstrated its value for satellite links.
Thanks Matt
Original text: (41 lines follow)
>From NUNEZ@SMTPGATE (Chuck Nunez) {[email protected]}, on 25/3/98 5:44 PM:
To: HALSEM@INTELSAT (matthew halsey)
Cc: TCP-OVER@SMTPGATE {[email protected]}
Matt,
In my humble estimation, Path MTU Discovery makes sense regardless of file
size or satellite/non-satellite situations. Small files may be doomed to
sub-optimal performance in any case. If you know that you'll always be
transferring small files and can measure the difference, then I suppose it
might be worth a look. My gut instinct tells me that it might be difficult
to make such a case and that you'd be better served to take advantage of
the capability.
Regards,
Chuck
At 10:56 AM 3/25/98 -0500, matthew halsey wrote:
>Form: Memo
>Text: (13 lines follow)
>Has anyone done Path MTU Discovery over satellite and demonstrated the
>benefit?
>If so, maybe this information could be incorporated into the stand-mech
I-D.
>If not, then maybe Path MTU Discovery should be in the res-issues I-D
>instead? There is some 'handshaking' that takes place before transmission
>can start, so it maybe beneficial for files greater than a certain size and
>not beneficial to smaller files. Maybe this needs to be researched further
>and as such, should be in the res-issues I-D.
>
>I hope this is not too controversial.
>
>Thanks again
>Matt
>Use Proportional Font: true
>
>
Use Proportional Font: true
Previous From: NUNEZ@SMTPGATE (Chuck Nunez) {[email protected]}
Previous To: HALSEM@INTELSAT (matthew halsey)
Previous Cc: TCP-OVER@SMTPGATE {[email protected]}
Attachment Count: 0
This archive was generated by hypermail 2b29 : Mon Feb 14 2000 - 16:14:37 EST