| > The effectiveness of using suboptimal samples (with a delta between 1 and 4) was | > confirmed by instrumenting the algorithm with counters. The results of two 20 | > second test runs were: | > * With the old algorithm and a total of 38442 function calls, only 394 of these | > calls resulted in usable RTT samples (about 1%), 378 out of these were | > "perfect" samples, and 28013 (unused) samples had a delta of 1..3. | > * With the new algorithm and a total of 37057 function calls, 1702 usable RTT | > samples were retrieved (about 4.6%), 5 out of these were "perfect" samples. | > This means an almost five-fold increase in the number of samples. | > | | Great work. This should make a real improvement. | Unfortunately it does not change some of the conceptual problems. When the sender is sending at a rate of less than one packet per RTT then it can happen that there are no usable RTT samples for a long while. MP3 streaming is an example, and there are other audio/voice streaming formats which also do not need to send more than one packet per RTT. In one case of MP3 streaming there was not a single usable RTT estimate over the course of almost 1-2 hours (found via printk to syslot). What happens if meanwhile the link properties change? I am not at all happy with this algorithm, it is probably as good as it can get, but it won't help if the sending rate is low. -- To unsubscribe from this list: send the line "unsubscribe dccp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
