System Performance

[Grayh]

This server has 64Gb memory (a lot of this is committed to oracle). See below the scan rate is 51000 (this seems to be very high? Or is it OK)

Output from top:

System: mdo01b Wed Mar 26
12:03:26 2008
Load averages: 0.37, 0.26, 0.24
257 processes: 217 sleeping, 39 running, 1 zombie Cpu states:
CPU LOAD USER NICE SYS IDLE BLOCK SWAIT INTR SSYS
0 0.34 7.0% 0.0% 4.8% 88.3% 0.0% 0.0% 0.0% 0.0%
1 0.30 12.9% 0.0% 8.5% 78.5% 0.0% 0.0% 0.0% 0.0%
2 0.64 82.9% 0.0% 0.6% 16.5% 0.0% 0.0% 0.0% 0.0%
3 0.19 13.7% 0.0% 5.2% 81.1% 0.0% 0.0% 0.0% 0.0%
--- ---- ----- ----- ----- ----- ----- ----- ----- -----
avg 0.37 29.2% 0.0% 4.8% 66.0% 0.0% 0.0% 0.0% 0.0%

Memory: 56582988K (26077844K) real, 69415172K (32729624K) virtual, 1404980K free Page# 1/6

CPU TTY PID USERNAME PRI NI SIZE RES STATE TIME %WCPU %CPU
COMMAND
2 ? 2025 oracle 239 20 65418M 28008K run 3:14 99.48 99.30
oracleitdst2
1 ? 54 root 152 20 50400K 44800K run 1100:41 2.81 2.80
vxfsd
0 ? 2157 oracle 154 20 65402M 12184K sleep 0:24 1.28 1.27
oracleitdst2
3 ? 2745 root 152 20 198M 13160K run 67:15 0.95 0.95
crsd.bin


Thanks
Mohan

[Steven E. Protter]

Shalom Mohan,

This seems likely an application or oracle configuration issue.

I see a system that is being pushed a bit by oracle. Perhaps the SGA setting require adjustment.

You might wish to learn more about the overall performance issues.

http://www.hpux.ws/?p=6
Full suite of tools to get good measurements.

SEP

[Yogeeraj_1]

hi Mohan,

could be a runaway process.

can you post the output of the following comamnds?:

First:
ps -ef|grep 14350

Second: (from SQLPLUS)
select b.sid SID,b.serial# "Serial#", c.spid "srvPID", b.osuser, b.username, b.status, b.client_info, machine
from v$session b, v$process c
where b.paddr = c.addr
and c.sPID =14350;

revert.

kind regards
Yogeeraj

[Grayh]

Hi SEP,

Thanks for the quick reply.When I was trying to access http://www.hpux.ws/merijn it is asking for a login and password....

Thanks,
Mohan

[Nick W]

Yogeeraj,

I realise you are a 'Pharoah' status (which is above 'Wizard') - but where on earth did you glean that Mohan needs to grep for PID=14350 from the info already supplied...?
- and where in that info does it show 'the scan rate is 51000'
Am I missing some info here...?

Nick

[Grayh]

Thanks for all

[Yogeeraj_1]

> Nick

Sorry for the confusion in my previous post.

The PID shold have been 2025 instead of 14350 as in my example above. The modified steps would have thus been:
=================================
First:
ps -ef|grep 2025

Second: (from SQLPLUS)
select b.sid SID,b.serial# "Serial#", c.spid "srvPID", b.osuser, b.username, b.status, b.client_info, machine
from v$session b, v$process c
where b.paddr = c.addr
and c.sPID =2025;
=================================

From these info, we would have know what the TOPmost process and which is consuming quite some resources, was doing.

Again sorry for any confusions. Hope this do help someone in the future.

Hope mohun clarifies more on the solution found for this problem.

kind regards
yogeeraj