Roch - PAE wrote:
> If the hearth of the matter is doing something Nagle-like
> for loopback connection, how about introducing a minimum
> time delay between wakeups of the reader (if TCP_NODELAY is
> not set of course).
>
> With Nagle, there is a natural delay which is proportional
> to the RTT. But fused connection, we could just have
> N times (say 20->50 times) bigger than the scheduling
> overhead.
It is worth trying. But I suspect that the delay may
need to be dynamic and adaptive. For example, if the app is
doing a simple request/response type of transaction, the
above will introduce the minimum delay for every request and
response.
> The would allow the read buffer to build up. It would not
> help the application's write side to reduce it's number of
> writes but the behavior would be similar to a network
> deployment.
We will need to compare the results and see the difference.
Anyone interested in trying it out?
--
K. Poon.
[EMAIL PROTECTED]
_______________________________________________
networking-discuss mailing list
[email protected]
