[I work on NTP software so I'm interested in network delays.] > I've been holding off on iperf 2 public servers until I found an additional > value add and a way to pay for them.
AT&T ran fiber down my street. I can get a gigabit link, symmetric, no data caps, for $80/month. I'll be happy to setup a server if that will help. I'm in Silicon Valley. > Much of > the iperf 2 work has been > around one way delay (OWD) or latency. Doing this well requires GPS clock > sync on both the data center servers and the end host devices How accurate do you need the time? > I checked into this a few years ago and found that this level of clock sync > wasn't available via rented servers (e.g. linode or Hurricane Electric) so I > put on hold any further investigation of public servers for iperf 2 as being > redundant with iperf 3. Those that need true e2e latency (vs RTTs) have to > build their own so-to-speak. I can see 2 approaches. One is to find good local NTP servers. HE has NTP servers. https://www.he.net/adm/ntp.html NIST has servers in Gaithersburg MD and Boulder and Fort Colins in Colorado. https://tf.nist.gov/tf-cgi/servers.cgi Google and Cloudflare have good servers and they probably have good connectivity. https://developers.google.com/time https://www.cloudflare.com/time/ In Germany, PTB has good servers: https://www.ptb.de/cms/en/ptb/fachabteilungen/abtq/gruppe-q4/ref-q42/time-syn chronization-of-computers-using-the-network-time-protocol-ntp.html ..... The other approach would be to do your own NTP like time sync with the server before and after a test run. This assumes you can find a quiet time to get a good measurement. NTP assumes that the routing delays are symmetric. Unless something wild is going on, that's a reasonable assumption. Less so on longer paths. I'll be glad to help set something up and/or run some tests. -- These are my opinions. I hate spam. _______________________________________________ Bloat mailing list [email protected] https://lists.bufferbloat.net/listinfo/bloat
