On Fri, Jul 13, 2001 at 01:14:07PM -0700, Julian Elischer wrote:
> I would suggest that 2 * the current window may be too small
> because the window might be increasing and
> reception of one ack might move the window up by
> the entire transmitted window size, resulting in starvation
> if the waiting data can be sent quickly. therefore I suggest a few
> modifying factors:
Actually, I doubt 2 * cwin would be too small, and here's my
rational:
* The majority of the "large increases" should be during slow start.
These values should all be below the minimum buffer size, so there
is no thrashing. Note, this requires a good minimum buffer size.
* When dealing with large bandwidth*delay number (say, a 1 meg
cross country 100Mbps path) we don't really want to buffer 3 meg,
rather than 2 meg. In fact, I could question if we really want
2 meg, but it's an ok compromise for now.
--
Leo Bicknell - [EMAIL PROTECTED]
Systems Engineer - Internetworking Engineer - CCIE 3440
Read TMBG List - [EMAIL PROTECTED], www.tmbg.org
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
