On Mar 19, 2013, at 10:41 PM, Ron Tsoref wrote:

> The PipeBackend seems easy to implement.  Does anyone actually use a 
> PipeBackend in production and can share some general performance information? 
> Is it much slower than other backends?
> 

We've been able to squeeze 50000 qps out of a pipe backend. On a philosophical 
note, pipes are likely to be faster than TCP/IP, and SQL 
marshalling/unmarshaling is not free either.

People associate 'text based' with slow, but most SQL protocols are just as 
parsed, or even more so.

The pipe backend does have a performance bottleneck in 3.2 if you specify a 
timeout, see http://wiki.powerdns.com/trac/ticket/661

        Bert

_______________________________________________
Pdns-users mailing list
[email protected]
http://mailman.powerdns.com/mailman/listinfo/pdns-users

Reply via email to