[dns-operations] new public DNS service:

abang abang at t-ipnet.net
Mon Dec 4 07:29:22 UTC 2017

Am 22.11.2017 um 09:14 schrieb P Vix:
> On November 21, 2017 11:56:25 PM PST, abang at t-ipnet.net wrote:
>>> no.
>>> you're welcome to show your math.
>> Well. Yes. There is math. But it's easier to measure it. From client
>> perspective. It can also be seen in the metrics of the resolver.
> Ok! Please show your measurements and metrics. Your assertion is most intriguing.
This [1] is a measurement of query/answer (qa) latency within a DNS 
resolver. The traffic I sent to this resolver is a sample of a copy of 
real customer traffic with a increasing sample rate.

I started with a query rate of 1 query per second (qps) which is the 
average equivalent of 10 clients. After two days I increased the query 
rate to 10qps (100 clients). After another day 100qps and so on. The 
average qa latency at 1qps is ~60ms, while it is ~3ms at 30kqps:

10 clients (1qps): ~60ms
100 clients (10qps): ~35ms
1.000 clients (100qps): ~25ms
10.000 clients (1kqps): ~10ms
100.000 clients (10kqps): ~6ms
300.000 clients (30kqps): ~3ms

I suppose, the reasons for these unexpected results are the increasing 
use of CDNs and their use of very short TTLs for their RRs.

[1] https://goo.gl/j8PkG7


More information about the dns-operations mailing list