Statistics Question

Jorg B. jorg_b at cwo.com
Tue Feb 22 16:38:52 UTC 2000


Hello,

We are running bind 8.2.2P5 on a Linux System (kernel 2.2.14).
At any given time we have about 600 concurrent connections hitting the DNS 
server. It seems that at peak times the server takes longer to respond to 
DNS lookup requests. Therefore, I was wondering if I've reached at point 
where I have to upgrade and/or distribute the load.

Here are some numbers:

This server is authoritative for 650 Internet Domain names and provides DNS 
services to 600 concurrent customers.
The machine is a 350 MHZ Pentium II with 128 MB of RAM an SCSI drives. It 
connects to the network at 100MB Full duplex.

Here is a snip from the message log:

Feb 21 20:34:34 ns1 named[51]: USAGE 951194074 946445368 
CPU=18739.3u/7414.35s CHILDCPU=0.16u/0.38s

Feb 21 20:34:34 ns1 named[51]: NSTATS 951194074 946445368 0=29985 
A=39515177 NS=41 CNAME=17273 SOA=176024 MB=122 MG=1462 MR=120 WKS=1 
PTR=25312797 HINFO=47 MINFO=2 MX=1866868 TXT=160 RP=1 X25=8 AAAA=1615 
LOC=20 SRV=60020 42=1 47=1 85=1 87=1 115=1 154=2 234=1 AXFR=442 MAILB=13 
ANY=8847196

Feb 21 20:34:34 ns1 named[51]: XSTATS 951194074 946445368 RR=10232852 
RNXD=845429 RFwdR=7371000 RDupR=23317 RFail=71471 RFErr=0 RErr=6728 
RAXFR=442 RLame=308062 ROpts=0 SSysQ=2226512 SAns=68991377 SFwdQ=6991547 
SDupQ=3200035 SErr=50747 RQ=75840413 RIQ=8 RFwdQ=0 RDupQ=118004 RTCP=83485 
SFwdR=7371000 SFail=13195 SFErr=0 SNaAns=16943464 SNXD=1719767Feb


Any info would be appreciated

Thanks
Jorg B.




More information about the bind-users mailing list