[Tmrg] Now, where were we...?
krasnoj at gmx.at (Stefan Hirschmann) Thu, 19 November 2009 20:05 UTC
From: "krasnoj at gmx.at"
Date: Thu, 19 Nov 2009 21:05:22 +0100
Subject: [Tmrg] Now, where were we...?
In-Reply-To: <BE0E1358-7C27-46A8-AF1E-D8D7CC834A52@ifi.uio.no>
References: <BE0E1358-7C27-46A8-AF1E-D8D7CC834A52@ifi.uio.no>
Message-ID: <4B05A502.4050402@gmx.at>
Michael Welzl wrote: > Hi, > > This prompts me to ask a question that I've been pondering > ever since a hallway conversation that I had with Stanislav > Shalunov at the Stockholm IETF: > > >> 2. How reliable are implicit congestion indicators? The prevailing >> wisdom in the IETF seems to be that "ECN=loss = congestion, delay = >> noise, nothing else is useful for congestion control". What criteria >> would "delay" have to satisfy in order to be a useful indicator of >> congestion? Should we listen to the average delay, the frequency with >> which delay exceeds a threshold, or the jitter? > > Can delay ever be worse as a congestion indicator than > loss is? Yes. It can be wrong in two ways: If there is physical corruption and data link repeating of the signals, any correlation between congestion and delay is just random. Error 1: There data link retransmissions (due to physical corruption / checksum errors) are increasing and the delay increases. Reality: Same state of congestion, but assumption that congestion increased. Error 2: There are less data link retransmissions (compared to beginning of connection). This leads to the wrong assumption that the congestion (the queue delay) is also less. In my opinion, delay should only be considered as limiting factor, but never as increasing factor: cwnd = min( f(delay), g(loss) ). Another bad effect is due to the burstiness of TCP: If a queue of a bottleneck is empty and a traffic burst arrives, the first packet of the burst have less RTT than the last packets of the burst (first packet is transported immediately, the other packets have an increasing queuing delay). A delay based approach can already lead to reduction of cwnd even if cwnd = 10% BDP. Cheers, Stefan
- [Tmrg] Now, where were we...? Lachlan Andrew
- [Tmrg] Now, where were we...? Larry Dunn
- [Tmrg] Now, where were we...? Michael Welzl
- [Tmrg] Now, where were we...? Stefan Hirschmann
- [Tmrg] Now, where were we...? Michael Welzl
- [Tmrg] Now, where were we...? Lachlan Andrew
- [Tmrg] Now, where were we...? Damon Wischik
- [Tmrg] Now, where were we...? Lachlan Andrew
- [Tmrg] Now, where were we...? John Heffner
- [Tmrg] Now, where were we...? Lachlan Andrew
- [Tmrg] Now, where were we...? Michael Welzl
- [Tmrg] Now, where were we...? Lachlan Andrew