BIND 9.x caching Performance under heavy loads

sthaug at sthaug at
Thu Mar 24 22:00:21 UTC 2005

> Steinar, I'm working tracking down a simliar problem where for some
> unexplained reason bind 9.3.0 spins the CPU at 100% after weeks of normal
> (and perfectly acceptable) operation - the is long after my cache has
> stabalized, obviously.
> There are graphs of which is the one that most recently
> exhibited the CPU surge - last Friday.
> The only cache relevant  options that are set are the following:
> 	cleaning-interval 60; //Default?
> 	max-ncache-ttl 120;

max-ncache-ttl counts in seconds, according to the documentation. Why
do you want to limit this to 2 minutes?

Aside from that, I can only recommend the same as has been mentioned
by several others on the list:

- Make sure your name server has enough memory. Let the cache reach its
"natural" size (let it stabilize), don't try to limit it.
- Make sure IPv6 name resolution is only turned on if you actually have
real IPv6 connectivity.
- Look at how much logging is turned on. Logging can be a real CPU hog.
- Consider trying ISC_MEM_USE_INTERNAL_MALLOC instead of the default
(system) malloc.

Also, if you have a uniprocessor system, you might want to test the
patch I recently posted to enable better BIND9 statistics.

Steinar Haug, Nethelp consulting, sthaug at

More information about the bind-users mailing list