RE: Confirmation of trace data

From: Cary Millsap <cary.millsap_at_hotsos.com>
Date: Mon, 2 Aug 2004 23:04:16 -0500
Message-ID: <003f01c4790e$f5005800$6801a8c0@CVMLAP02>

I think it's probably time spent preempted, waiting either in the CPU = run
queue or swapped out. If it were practically any OS other than Windows, = it
would be relatively easy to get corroborating evidence from the OS about involuntary context switch counts, average CPU run queue lengths, = swap-out
counts, and such as that.

But on Windows, I'm not sure. I guess the search begins at www.sysinternals.com....

Cary Millsap
Hotsos Enterprises, Ltd.
http://www.hotsos.com
* Nullius in verba *

Upcoming events:
- Performance Diagnosis 101: 8/10 Boston, 9/14 San Francisco, 10/5 = Charlotte
- SQL Optimization 101: 7/26 Washington DC, 8/16 Minneapolis, 9/20 = Hartford
- Hotsos Symposium 2005: March 6-10 Dallas - Visit www.hotsos.com for schedule details...

-----Original Message-----
From: oracle-l-bounce_at_freelists.org =
[mailto:oracle-l-bounce_at_freelists.org]
On Behalf Of Paul Baumgartel
Sent: Monday, August 02, 2004 4:11 PM
To: oracle-l_at_freelists.org
Subject: Confirmation of trace data

List--

Is there anything I'm missing here? The following SQL is taking 6 to 8 seconds of elapsed time to run. There are *no* wait events in the trace file (all trace data connected with this SQL appears below).=20 Total CPU for the operations is about .12 seconds, yet as you can see, the elapsed time for each fetch is 6 to 8 seconds.

This SQL is running during a load test; there are approximately 100 other sessions on the server (Windows 2K, dual-hyper-threaded CPU, about 2 GB of memory allotted to Oracle) and at times the CPUs are pegged at 100%. Oracle9iR2.

Given that I see no wait events, can I conclude that the elapsed time is due to waiting for CPU service? Is the fact that I'm joining to DBA_ROLE_PRIVS problematic? =20

TIA. =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D PARSING IN CURSOR #6 len=3D142 dep=3D2 uid=3D828 oct=3D3 lid=3D828 = tim=3D3027624861
hv=3D2231874444 ad=3D'6fd24b08'
SELECT t1.schema_name

        from tsc_schemata t1, dba_role_privs t2
        where t2.grantee =3D :b1 and t1.application_role =3D

t2.granted_role
END OF STMT
PARSE =
#6:c=3D0,e=3D92,p=3D0,cr=3D0,cu=3D0,mis=3D0,r=3D0,dep=3D2,og=3D4,tim=3D30=
27624847
EXEC =
#6:c=3D0,e=3D201,p=3D0,cr=3D0,cu=3D0,mis=3D0,r=3D0,dep=3D2,og=3D4,tim=3D3=
027677087
FETCH
#6:c=3D31250,e=3D8150816,p=3D0,cr=3D53,cu=3D0,mis=3D0,r=3D1,dep=3D2,og=3D=
4,tim=3D3035838225
EXEC =
#6:c=3D0,e=3D101,p=3D0,cr=3D0,cu=3D0,mis=3D0,r=3D0,dep=3D2,og=3D4,tim=3D3=
036090408
FETCH
#6:c=3D93750,e=3D6570233,p=3D0,cr=3D53,cu=3D0,mis=3D0,r=3D1,dep=3D2,og=3D=
4,tim=3D3042667603

=09

Do you Yahoo!?
Take Yahoo! Mail with you! Get it on your mobile phone. http://mobile.yahoo.com/maildemo=20

Please see the official ORACLE-L FAQ: http://www.orafaq.com

To unsubscribe send email to: oracle-l-request_at_freelists.org put 'unsubscribe' in the subject line.

--
Archives are at http://www.freelists.org/archives/oracle-l/
FAQ is at http://www.freelists.org/help/fom-serve/cache/1.html
-----------------------------------------------------------------

----------------------------------------------------------------
Please see the official ORACLE-L FAQ: http://www.orafaq.com
----------------------------------------------------------------
To unsubscribe send email to:  oracle-l-request_at_freelists.org
put 'unsubscribe' in the subject line.
--
Archives are at http://www.freelists.org/archives/oracle-l/
FAQ is at http://www.freelists.org/help/fom-serve/cache/1.html
-----------------------------------------------------------------

Received on Mon Aug 02 2004 - 23:00:37 CDT