Operation cancelled Error

Wed May 23 18:14:02 UTC 2012

Hi,

I am doing load testing for bind as caching dns server.Fro that i 
configure one machine as client and one as server.I setup bind as 
caching dns server and set recursive-clients 30000.

While doing load test from client machine via resperf, i got many errors 
in named.run file which shows,I checked that time there is no cpu high 
usage / memory high usage on server and clients.Why server is not 
permitted operation.

23-May-2012 23:30:12.085 error (operation canceled) resolving 
'www.thethreadexchange.com/AAAA/IN': 192.33.14.30#53
23-May-2012 23:30:12.085 error (operation canceled) resolving 
'c2.nstld.net/A/IN': 192.42.93.31#53
23-May-2012 23:30:12.085 error (operation canceled) resolving 
'nothirst.com/A/IN': 192.54.112.30#53
23-May-2012 23:30:12.085 error (operation canceled) resolving 
'172.153.42.186.in-addr.arpa/PTR/IN': 199.212.0.53#53
23-May-2012 23:30:12.085 error (operation canceled) resolving 
'xxy.com/MX/IN': 192.12.94.30#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'192.140.138.187.in-addr.arpa/PTR/IN': 193.0.9.3#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'mail.n-u-c.ru/A/IN': 193.232.128.6#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'www.gayteacher.net/A/IN': 108.59.10.134#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'www.forever-christies.com/A/IN': 192.12.94.30#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'166.98.232.189.in-addr.arpa/PTR/IN': 200.3.13.10#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'89.140.112.200.in-addr.arpa/PTR/IN': 202.12.28.140#53
23-May-2012 23:30:12.086 error (operation canceled) resolving 
'9z772drlt.89ys/A/IN': 192.228.79.201#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'video327.myfreecams.com/A/IN': 192.26.92.30#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'ns1.thny.bbc.co.uk/A/IN': 194.83.244.131#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'6.246.26.190.in-addr.arpa/PTR/IN': 200.3.13.10#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'instagram.com/A/IN': 192.54.112.30#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'acriacao.com/A/IN': 192.12.94.30#53
23-May-2012 23:30:12.087 error (operation canceled) resolving 
'technologie.gazeta.pl/A/IN': 192.203.230.10#53

rndc status shows,

version: 9.7.3-P3-RedHat-9.7.3-8.P3.el6_2.2
CPUs found: 8
worker threads: 8
number of zones: 19
debug level: 0
xfers running: 0
xfers deferred: 0
soa queries in progress: 0
query logging is ON
recursive clients: 6400/29900/30000
tcp clients: 0/100
server is up and running

i constanly watch rndc status command , and at recuresive-clients tab , 
first values increases maximum up to 6000-6500, why it is not going to 
maximum which i define 30000..?
rndc status shows 8 worker process, when i checked  by pgrep named , it 
shows only single instance.so does it need to show 8 instance or ?
Currently we use bind as caching name server , so why rndc status shows 
number of zones 19..?

Kindly guide me to resolve above confusion.

Bind build info:
  named -V
BIND 9.7.3-P3-RedHat-9.7.3-8.P3.el6_2.2 built with 
'--build=x86_64-redhat-linux-gnu' '--host=x86_64-redhat-linux-gnu' 
'--target=x86_64-redhat-linux-gnu' '--program-prefix=' '--prefix=/usr' 
'--exec-prefix=/usr' '--bindir=/usr/bin' '--sbindir=/usr/sbin' 
'--sysconfdir=/etc' '--datadir=/usr/share' '--includedir=/usr/include' 
'--libdir=/usr/lib64' '--libexecdir=/usr/libexec' 
'--sharedstatedir=/var/lib' '--mandir=/usr/share/man' 
'--infodir=/usr/share/info' '--with-libtool' '--localstatedir=/var' 
'--enable-threads' '--enable-ipv6' '--with-pic' '--disable-static' 
'--disable-openssl-version-check' '--with-dlz-ldap=yes' 
'--with-dlz-postgres=yes' '--with-dlz-mysql=yes' 
'--with-dlz-filesystem=yes' '--with-gssapi=yes' '--disable-isc-spnego' 
'--with-docbook-xsl=/usr/share/sgml/docbook/xsl-stylesheets' 
'build_alias=x86_64-redhat-linux-gnu' 
'host_alias=x86_64-redhat-linux-gnu' 
'target_alias=x86_64-redhat-linux-gnu' 'CFLAGS= -O2 -g -pipe -Wall 
-Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector 
--param=ssp-buffer-size=4 -m64 -mtune=generic' 'CPPFLAGS= -DDIG_SIGCHASE'

 From client machine :

/usr/local/nom/bin/resperf -s 10.115.1.231 -d 
/root/dnsperf_test_queries.tsv
DNS Resolution Performance Testing Tool
Nominum Version 2.0.0.0

[Status] Command line: resperf -s 10.115.1.231 -d 
/root/dnsperf_test_queries.tsv
[Status] Sending
[Status] Reached 65536 outstanding queries
[Status] Waiting for more responses
[Status] Testing complete

Statistics:

   Queries sent:         74038
   Queries completed:    74038
   Queries lost:         0
   Run time (s):         100.000000
   Maximum throughput:   2838.000000 qps
   Lost at that point:   24.32%

what are the configuration parameter required to  increase QPS for 
server? I mean any fine tuning in bind / OS side, please suggest us.

Best Regards,
Ben

Regards,
Ben