Date: Mon, 5 Aug 1996 22:31:09 -0500 (CDT) From: Tony Kimball <alk@think.com> To: gpalmer@freebsd.org Cc: questions@freebsd.org Subject: Re: tcp tuning Message-ID: <199608060331.WAA26963@compound.Think.COM> References: <199608052205.RAA25880@compound.Think.COM> <17750.839300640@orion.webspan.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Quoth Gary Palmer on Mon, 5 August: : > way to tune the TCP timing parameters to provide optimal latency under : > lossy conditions, perhaps at the expense of bandwidth. Retrying more : > rapidly, for example, would be a help. What else would be helpful? : : Asking MCI what they plan to do to address the packet loss you are : suffering? :-) I can't fix MCI. I can't fix Capitalism. I can fix the timing characteristics of the ip stack. You can help if you like:-) I feel confident that there are papers on the subject of tcp tuning in lossy environments available online somewhere, but I'm not looking in the right places, *yet*, anyhow... As for MCI, I've told them repeatedly, and this probably affects 20% of the US Internet traffic (wild guess) and has done for about two weeks, so I doubt that my complaints are helping the cause much. They must have their own reasons not to fix it. Money, politics, something like that. MCI kills Internet in Willow Springs, claims self-defense, news at 11. Follow-up on global politics we should move to another place, as ever:-)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199608060331.WAA26963>