From: Naeem Khademi <[email protected]> Date: Wednesday, November 13, 2013 12:14 PM To: Preethi Natarajan <[email protected]> Cc: Michael Welzl <[email protected]>, "[email protected]" <[email protected]> Subject: Re: [aqm] AQM schemes: Queue length vs. delay based
> > Very true, though that's what ARED *is* with very low thresholds (e.g. > resonate between 1 or 2 packets on the average in the queue). Indeed there can > possibly be some future work on ARED's (or any other similar AQM) burst > allowance but I don't think e.g. letting a 100 ms burst of packets to pass > through can be a good way of fixing it as this can lead to massive variance in > overall RTT distribution. If you are referring to the burst_allowance parameter in PIE, this parameter allows burst to go through when a system goes from an idle state into some congestion state. The one we are talking about is accommodating bursts when the system is in equilibirum -- how does the AQM scheme accommodate bursts when already operating around target delay or congestion? Delay-based ARED behaves similar to tail drop at max threshold. This is unacceptable of an AQM even for max thresholds around 50ms. Clearly delay-based ARED needs significant and careful redesign. I suppose one can argue this task is as laborious as designing a new AQM scheme as opposed to previous notions that delay-based ARED would work right out of the box. Preethi
_______________________________________________ aqm mailing list [email protected] https://www.ietf.org/mailman/listinfo/aqm
