nanog mailing list archives
Re: 1500 does not work: Thoughts on increasing MTUs on the internet
From: Petri Helenius <pete () he iki fi>
Date: Sun, 15 Apr 2007 18:48:47 +0300
Marshall Eubanks wrote:
Dear Pete;The streaming servers that I have dealt with (such as Darwin Streaming Server) do the fragmentation at the application layer. They thus send out lots of packets at or near (in this case) 1450 bytes, but they are not UDP fragments. That's the whole point - many networks will not deliver fragments at all, much less the increased risk of loss when they do. (I use Cox Cable at home, and this network apparently does not forward fragments and also has an apparent MTU of 1480 bytes.)Just looked at a YouTube dump, btw, and almost all of the packets are 1448 bytes.
I'm referring to Windows Media and Real. They are the worst offenders, though not too many use them without HTTP.
Pete
Current thread:
- Re: Thoughts on increasing MTUs on the internet, (continued)
- Re: Thoughts on increasing MTUs on the internet David W. Hankins (Apr 12)
- Re: Thoughts on increasing MTUs on the internet Daniel Senie (Apr 12)
- Re: Thoughts on increasing MTUs on the internet David W. Hankins (Apr 12)
- Re: Thoughts on increasing MTUs on the internet Fred Baker (Apr 13)
- 1500 does not work: Thoughts on increasing MTUs on the internet Peter Dambier (Apr 14)
- Re: 1500 does not work: Thoughts on increasing MTUs on the internet Marshall Eubanks (Apr 14)
- Re: 1500 does not work: Thoughts on increasing MTUs on the internet Petri Helenius (Apr 14)
- Re: 1500 does not work: Thoughts on increasing MTUs on the internet Marshall Eubanks (Apr 15)
- Re: 1500 does not work: Thoughts on increasing MTUs on the internet Petri Helenius (Apr 15)