In <[EMAIL PROTECTED]> John Ackermann N8UR <[EMAIL PROTECTED]> writes:
> Karel Sandler wrote: > >> What is the averaging time for your rps values? Sometimes you can >> get say 6000 requests per minute although 1500 of them arrived at >> one single second. For such a case even xx/1 Mbps line is slow, any >> packets get an asymmetric delay. Of course, this is not a problem >> for any ntpd client with a good configuration. > > I don't know for sure; my crontab runs the script that updates the > logfile every 15 minutes, but I'm not sure how the value that ges logged > is created (Wayne's scripts use tcpdump to analyze the traffic flow; I > haven't dug into just how he parses the data). In order to keep the CPU and memory consumption down, I don't keep track of all requests for a given time period, and then average them. Instead, I use a "decaying average" similar to the way the unix "load average" is calculated. The most recent data gives the most weight, while older values exponentially decay in significance. The "short term" rates returned by the NTP monitoring script is going to be pretty close to the exact average over the last 15-30 minutes, while the the "long term" rates are going to be close to the last 15-30 days. If there really are peaks of 1500 requests in a single second, or 6000 requests in a minute when the normal average is closer to 10, then even the short term rate will not have a chance to jump to those levels. It would probably jump to several hundred, but not 1000. Looking at John's logs, I do see spikes to 100req/sec for what I'm guessing is the 15-30 minute "short term" average. The bursts when your server got put into the pool didn't use to be that bad, but maybe it is time to take a closer look. Hmm... -wayne _______________________________________________ timekeepers mailing list [email protected] https://fortytwo.ch/mailman/cgi-bin/listinfo/timekeepers
