Recursive bind becomes unresponsive with high load

/dev/rob0 rob0 at gmx.co.uk
Fri Apr 1 23:33:39 UTC 2016


On Fri, Apr 01, 2016 at 09:48:01PM +0000, Mike Mitchell wrote:
> Have you checked the Kernel's connection tracking statistics?
> Here's a link:
> https://kb.isc.org/article/AA-01183/0/Linux-connection-tracking-and-DNS.html
> 
> I've had to increase some network parameters on our busy 
> nameservers. I put the following in /etc/sysctl.conf

Did you try disabling connection tracking for UDP DNS, as the 
referenced article suggests?

> net.netfilter.nf_conntrack_udp_timeout_stream = 45
> net.nf_conntrack_max = 500000
> net.ipv4.neigh.default.gc_thresh1 = 512
> net.ipv4.neigh.default.gc_thresh2 = 1024
> net.ipv4.neigh.default.gc_thresh3 = 2048
> net.ipv4.tcp_max_syn_backlog = 4096
> net.ipv4.tcp_fin_timeout = 30
> net.ipv4.tcp_tw_recycle = 1

-- 
  http://rob0.nodns4.us/
  Offlist GMX mail is seen only if "/dev/rob0" is in the Subject:


More information about the bind-users mailing list