Subject: Re: README: new callout code committed
To: None <thorpej@zembu.com>
From: Jonathan Stone <jonathan@DSG.Stanford.EDU>
List: current-users
Date: 03/23/2000 13:48:58
In message <20000323124318.B25508@dr-evil.z.zembu.com>Jason R Thorpe writes
>On Thu, Mar 23, 2000 at 04:00:27PM +0000, Martin J. Laubach wrote:
>Now that we *have* a better timer facility, we can use it in a lot more
>places. One of these places is going to be TCP timers. The current scheme
>for TCP timers does not scale well at all. Route timers are another good
>candidate.
Just FYI:
Using a timing-wheel based callout for TCP timers is better than what
we have, but it has its own problems. One of them is that most TCP
timeouts never fire; they get canceleld. Another is timer management
for TIME_WAIT. The state of the art here is already better than simply
using the Costello & Vargese techniques. (ISTR a Usenix paper, but I
couldnt find the title by grepping my bibilography).
The second, which dates to Tahoe TCP, is that for "typical" wide-area
TCP connections, you dont want too fine a timer granularity; that can
interact with RTT estimation in ways that are counter-intuitive, at
first. Whehter still that applies to New-Reno, I forget. I'll try
and remember to check with some of Dave Clark's former group members.
( might be worth asking tcp-impl, too).
Jason may well have already taken all this into consideration, tho'.