Home / server / Questions / 1040516
Accepted
Dunner1991
Asked: 2020-10-30 05:21:05 +0800 CST

Is there a way to increase the QPS limit for a bind 9 centos server?

  • 772

I have been benchmark testing 2 DNS servers over the last few days and I am running into the following issue

1 DNS server has a qps per seconf limit of ~6500 qps while the other DNS server gets only ~1500 qps when i use dnsperf

Statistics:
Queries sent:         77511
  Queries completed:    77511 (100.00%)
  Queries lost:         0 (0.00%)

  Response codes:       NOERROR 69982 (90.29%), NXDOMAIN 7529 (9.71%)
  Average packet size:  request 48, response 281
  Run time (s):         11.473787
  Queries per second:   6755.485351

  Average Latency (s):  1.190392 (min 0.000293, max 1.753760)
  Latency StdDev (s):   0.443875



Statistics:

  Queries sent:         34372
  Queries completed:    14676 (42.70%)
  Queries lost:         19696 (57.30%)

  Response codes:       NOERROR 13246 (90.26%), NXDOMAIN 1430 (9.74%)
  Average packet size:  request 47, response 247
  Run time (s):         10.132536
  Queries per second:   1448.403440

  Average Latency (s):  0.111563 (min 0.000680, max 1.615017)
  Latency StdDev (s):   0.050619

Both DNS servers are the same centos and bind versions they both have 16 vCPUs and 16 GB RAM They are located in different datacentres and each I have dnsperf (benchmark server) built locally for each.

Is there a way to increase this qps limit or a way to troubleshoot it?

domain-name-system bind centos7

1 Answers

  1. Best Answer

    After looking further into this issue, i found that the QPS limit for this server was being caused by the amount of logging i had enabled in the named.conf file.

    I had roughly serveral channels created for different types of query logging.

    Once these were commented out in the named.conf file and the service restarted I ran a number of other tests and I now see roughly 6500 QP which is inline with my other VMs

    • 0