[bind10-dev] recent performance improvements

[Jeremy C. Reed]

On Mon, 19 Mar 2012, JINMEI Tatuya / ???? wrote:

> I bet there's something wrong in the test setup.  I did my test again
> on the bind10-testing1 box.  All cases were for single thread/worker
> thread.  The root zone case, using your root.zone-canonical zone file,
> sending "www.google.com/A" repeatedly by queryperf for 30 seconds as
> follows:
> % ./queryperf -p 5300 -l 30 < google-input.txt
> 
> And the results are:
> bind10 master (as of da4d1f0): 18456.889077 qps
> bind10-devel-20120301: 5974.164548 qps
> BIND 9.9.0 with acache: 15623.738072 qps
> BIND 9.9.0 without acache: 10005.986613 qps

Mine were:

master-2012-03-01 root-memory-cpus4.success 21713.859279 qps
master-2012-03-01 root-memory-.success 5987.714169 qps  (so near same as 
yours)

master-2012-03-15 root-memory-cpus4.success 23195.608941 qps
master-2012-03-15 root-memory-.success 6252.820647 qps

master root-memory-cpus4.success 54319.332055 qps
master root-memory-.success 19102.104800 qps  (also near yours)

bind-9.9.0 root-memory-cpus4.success 44901.344562 qps
bind-9.9.0 root-memory-.success 50519.012123 qps

Since this is Linux I manually enabled threads at BIND 9 configure time 
and I used optimum -n at named run time. Also this is with   
acache-enable yes;  notify no;  recursion no;

(Interesting to note that BIND 9.9.0 had some places where optimum -n 
caused regressions for some scenarios.)

> Does your tested "master" really contain the following tasks?
> #1568, #1599, #1600, #1603, #1608, #1747

commit 373eda27fc0e591356a7311e2ad560bb9441e64f
commit 555c57669226bca31e961412fde174f04db876ab
commit 1e62bf975ba54ebee2e5ddc2a2cc26ca5c254f44
commit 9a2a86f3f47b60ff017ce1a040941d0c145cfe16
commit 1af6565d9d5f789c82ececbf83ca725cf3208b3f
commit 12f57073eb9f5ff5d11035852e253d25071debab

Yes it looks like it.

I think the reason for difference is my bind9 tests are much faster.