Hi Christoph, On 24/10/2022 01:46, Christoph via Pdns-users wrote:
Is this unexpected or not unusual? If unusual: what would be the usual ways to further track this issue down?
Clearly unexpected. You might be able to get more information about what is going by setting setVerboseHealthChecks [1] in dnsdist. Otherwise you might have to look at the metrics reported by the recursor, or capture the traffic (look for UDP queries for a.root-servers.net type A).
One unrelated thing I noticed in your configuration is that you are setting maxInFlight to 1000 on newServer, telling dnsdist to send up to 1000 concurrent queries on an outgoing TCP connection to the backend, but on the recursor's side it looks like max-concurrent-requests-per-tcp-connection [2] is set to the default of 10. This might lead to terrible latency numbers over TCP, so I would suggest increasing that setting, or decreasing the maxInFlight value in the dnsdist configuration.
[1]: https://dnsdist.org/reference/config.html#setVerboseHealthChecks[2]: https://docs.powerdns.com/recursor/settings.html#max-concurrent-requests-per-tcp-connection
Best regards, -- Remi Gacogne PowerDNS.COM BV - https://www.powerdns.com/
OpenPGP_signature
Description: OpenPGP digital signature
_______________________________________________ Pdns-users mailing list Pdns-users@mailman.powerdns.com https://mailman.powerdns.com/mailman/listinfo/pdns-users
