After getting PerfKit working...

2010-03-30 Thread RPN01
We can now see what is eating our system, and it turns out that it¹s z/VM...

CPU Load   Vector Facility   Status
or  
 PROC   TYPE   %CPU%CP   %EMU   %WT   %SYS   %SP   %SIC   %LOGLD
%VTOT   %VEMUREST   ded. User
 P00  IFL99   991   1   94   0   89100 ....   ... Master
 P01  IFL403   37  601   0   88 40 ....   ...
Alternate 
   
We¹re grinding CPU 0 at 99%, and it¹s all CP time.

Any insightful suggestions?

-- 
Robert P. Nix  Mayo Foundation.~.
RO-OE-5-55 200 First Street SW/V\
507-284-0844   Rochester, MN 55905   /( )\
-^^-^^
In theory, theory and practice are the same, but
 in practice, theory and practice are different.




After getting PerfKit working...

2010-03-30 Thread RPN01
And, it seems that our second LPAR (on another CEC) is playing the same
game...

P00  IFL   100  1000   0  100   0   61100 ....   ... Master
 P01  IFL712   69  291   0   88 71 ....   ...
Alternate

-- 
Robert P. Nix  Mayo Foundation.~.
RO-OE-5-55 200 First Street SW/V\
507-284-0844   Rochester, MN 55905   /( )\
-^^-^^
In theory, theory and practice are the same, but
 in practice, theory and practice are different.



Re: After getting PerfKit working...

2010-03-30 Thread Robert J McCarthy
Robert,
Have you looked in the bottom right corner of the display to see
what guest might be using the most CPU ? Or Option 21 from the main
PerfKit menu ?
 Bob 



From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On
Behalf Of RPN01
Sent: Tuesday, March 30, 2010 2:46 PM
To: IBMVM@LISTSERV.UARK.EDU
Subject: After getting PerfKit working...


We can now see what is eating our system, and it turns out that it's
z/VM...

CPU Load   Vector Facility
Status or  
PROC   TYPE   %CPU%CP   %EMU   %WT   %SYS   %SP   %SIC   %LOGLD
%VTOT   %VEMUREST   ded. User 
P00  IFL99   991   1   94   0   89100 ....   ...
Master
 P01  IFL403   37  601   0   88 40 ....   ...
Alternate 
   
We're grinding CPU 0 at 99%, and it's all CP time.

Any insightful suggestions?

-- 
Robert P. Nix  Mayo Foundation.~.
RO-OE-5-55 200 First Street SW/V\
507-284-0844   Rochester, MN 55905   /( )\
-^^-^^
In theory, theory and practice are the same, but
 in practice, theory and practice are different.




Re: After getting PerfKit working...

2010-03-30 Thread Rich Smrcina

On 03/30/2010 01:46 PM, RPN01 wrote:
We can now see what is eating our system, and it turns out that it’s 
z/VM...


CPU Load Vector Facility Status or
PROC TYPE %CPU %CP %EMU %WT %SYS %SP %SIC %LOGLD %VTOT %VEMU REST ded. 
User

P00 IFL 99 99 1 1 94 0 89 100 .. .. ... Master
P01 IFL 40 3 37 60 1 0 88 40 .. .. ... Alternate

We’re grinding CPU 0 at 99%, and it’s all CP time.

Any insightful suggestions?



Is this the old active wait key 3 issue, or doesn't VM use that anymore?

--
Rich Smrcina
Phone: 414-491-6001
http://www.linkedin.com/in/richsmrcina

Catch the WAVV! http://www.wavv.org
WAVV 2010 - Apr 9-13, 2010 Covington, KY


Re: After getting PerfKit working...

2010-03-30 Thread RPN01
The max CPU user extreme is 14%. This is all CP overhead time. Our paging
rate is 20 pgs/sec.

OPERATOR on both LPARs is unusually active, and I¹m about to take a walk
over to the data center to see what it thinks it¹s doing. There doesn¹t seem
to be anything else unusual going on.


On 3/30/10 1:55 PM, Robert J McCarthy bob.mccar...@custserv.com wrote:

 Robert,
 Have you looked in the bottom right corner of the display to see what
 guest might be using the most CPU ? Or Option 21 from the main PerfKit menu ?
  Bob
 
 
 From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf
 Of RPN01
 Sent: Tuesday, March 30, 2010 2:46 PM
 To: IBMVM@LISTSERV.UARK.EDU
 Subject: After getting PerfKit working...
 
 We can now see what is eating our system, and it turns out that it¹s z/VM...
 
 CPU Load   Vector Facility   Status or
 PROC   TYPE   %CPU%CP   %EMU   %WT   %SYS   %SP   %SIC   %LOGLD%VTOT
 %VEMUREST   ded. User
 P00  IFL99   991   1   94   0   89100 ....   ... Master
  P01  IFL403   37  601   0   88 40 ....   ...
 Alternate 

 We¹re grinding CPU 0 at 99%, and it¹s all CP time.
 
 Any insightful suggestions?



Re: After getting PerfKit working...

2010-03-30 Thread Bill Munson
They found the Christmas Tree program and it is running on both Operator 
user id's right now   ;-)
 
munson




RPN01 nix.rob...@mayo.edu 
Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU
03/30/2010 03:23 PM
Please respond to
The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU


To
IBMVM@LISTSERV.UARK.EDU
cc

Subject
Re: After getting PerfKit working...






The max CPU user extreme is 14%. This is all CP overhead time. Our paging 
rate is 20 pgs/sec.

OPERATOR on both LPARs is unusually active, and I?m about to take a walk 
over to the data center to see what it thinks it?s doing. There doesn?t 
seem to be anything else unusual going on.


On 3/30/10 1:55 PM, Robert J McCarthy bob.mccar...@custserv.com wrote:

Robert,
Have you looked in the bottom right corner of the display to see what 
guest might be using the most CPU ? Or Option 21 from the main PerfKit 
menu ?
 Bob 

From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On 
Behalf Of RPN01
Sent: Tuesday, March 30, 2010 2:46 PM
To: IBMVM@LISTSERV.UARK.EDU
Subject: After getting PerfKit working...

We can now see what is eating our system, and it turns out that it?s 
z/VM...

CPU Load   Vector Facility Status 
or  
PROC   TYPE   %CPU%CP   %EMU   %WT   %SYS   %SP   %SIC   %LOGLD %VTOT  
%VEMUREST   ded. User 
P00  IFL99   991   1   94   0   89100 ....   ... 
Master 
 P01  IFL403   37  601   0   88 40 ....   ... 
Alternate 
 
We?re grinding CPU 0 at 99%, and it?s all CP time.

Any insightful suggestions?

*** IMPORTANT
NOTE*-- The opinions expressed in this
message and/or any attachments are those of the author and not
necessarily those of Brown Brothers Harriman  Co., its
subsidiaries and affiliates (BBH). There is no guarantee that
this message is either private or confidential, and it may have
been altered by unauthorized sources without your or our knowledge.
Nothing in the message is capable or intended to create any legally
binding obligations on either party and it is not intended to
provide legal advice. BBH accepts no responsibility for loss or
damage from its use, including damage from virus.



Re: After getting PerfKit working...

2010-03-30 Thread Dave Wade
I always thought allowing OPERATOR to IPL CMS was a BAD thing.
Its been a while since I used VM but in the past issues like this were often
spool related.  Is something flooding the spool..

 -Original Message-
 From: The IBM z/VM Operating System 
 [mailto:ib...@listserv.uark.edu] On Behalf Of Bill Munson
 Sent: 30 March 2010 20:27
 To: IBMVM@LISTSERV.UARK.EDU
 Subject: Re: After getting PerfKit working...
 
 
 They found the Christmas Tree program and it is running on 
 both Operator 
 user id's right now   ;-)
  
 munson
 
 
 
 
 RPN01 nix.rob...@mayo.edu 
 Sent by: The IBM z/VM Operating System 
 IBMVM@LISTSERV.UARK.EDU 03/30/2010 03:23 PM Please respond 
 to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU
 
 
 To
 IBMVM@LISTSERV.UARK.EDU
 cc
 
 Subject
 Re: After getting PerfKit working...
 
 
 
 
 
 
 The max CPU user extreme is 14%. This is all CP overhead 
 time. Our paging 
 rate is 20 pgs/sec.
 
 OPERATOR on both LPARs is unusually active, and I?m about to 
 take a walk 
 over to the data center to see what it thinks it?s doing. 
 There doesn?t 
 seem to be anything else unusual going on.
 
 
 On 3/30/10 1:55 PM, Robert J McCarthy 
 bob.mccar...@custserv.com wrote:
 
 Robert,
 Have you looked in the bottom right corner of the display 
 to see what 
 guest might be using the most CPU ? Or Option 21 from the 
 main PerfKit 
 menu ?
  Bob 
 
 From: The IBM z/VM Operating System 
 [mailto:ib...@listserv.uark.edu] On 
 Behalf Of RPN01
 Sent: Tuesday, March 30, 2010 2:46 PM
 To: IBMVM@LISTSERV.UARK.EDU
 Subject: After getting PerfKit working...
 
 We can now see what is eating our system, and it turns out that it?s 
 z/VM...
 
 CPU Load   Vector 
 Facility Status 
 or  
 PROC   TYPE   %CPU%CP   %EMU   %WT   %SYS   %SP   %SIC   
 %LOGLD %VTOT  
 %VEMUREST   ded. User 
 P00  IFL99   991   1   94   0   89100 ....   ... 
 Master 
  P01  IFL403   37  601   0   88 40 ....   ... 
 Alternate 
  
 We?re grinding CPU 0 at 99%, and it?s all CP time.
 
 Any insightful suggestions?
 
 *** IMPORTANT
 NOTE*-- The opinions expressed in 
 this message and/or any attachments are those of the author 
 and not necessarily those of Brown Brothers Harriman  Co., 
 its subsidiaries and affiliates (BBH). There is no 
 guarantee that this message is either private or 
 confidential, and it may have been altered by unauthorized 
 sources without your or our knowledge. Nothing in the message 
 is capable or intended to create any legally binding 
 obligations on either party and it is not intended to provide 
 legal advice. BBH accepts no responsibility for loss or 
 damage from its use, including damage from virus.
 **
 **


Re: After getting PerfKit working...

2010-03-30 Thread Alan Altmark
On Tuesday, 03/30/2010 at 03:30 EDT, Dave Wade 
g4...@dpwade.eclipse.co.uk wrote:
 I always thought allowing OPERATOR to IPL CMS was a BAD thing.
 Its been a while since I used VM but in the past issues like this were 
often
 spool related.  Is something flooding the spool..

As a general rule, the key system operation user IDs should IPL 190, not 
CMS in order to reduce the dependency on the spool.  If you're using 
something like IBM Operations Manager for z/VM to create console logs, 
then you eliminate still another spool touchpoint.

Alan Altmark
z/VM Development
IBM Endicott


Re: After getting PerfKit working...

2010-03-30 Thread Dave Wade
 -Original Message-
 From: The IBM z/VM Operating System 
 [mailto:ib...@listserv.uark.edu] On Behalf Of Alan Altmark
 Sent: 30 March 2010 20:40
 To: IBMVM@LISTSERV.UARK.EDU
 Subject: Re: After getting PerfKit working...
 
 
 On Tuesday, 03/30/2010 at 03:30 EDT, Dave Wade 
 g4...@dpwade.eclipse.co.uk wrote:
  I always thought allowing OPERATOR to IPL CMS was a BAD thing. Its 
  been a while since I used VM but in the past issues like this were
 often
  spool related.  Is something flooding the spool..
 
 As a general rule, the key system operation user IDs should 
 IPL 190, not 
 CMS in order to reduce the dependency on the spool.  

I was thinking IPL any thing as historically they didn't have a 190 or 191
and so couldn't run anything, inlcuding games. 

 If you're using 
 something like IBM Operations Manager for z/VM to create 
 console logs, 
 then you eliminate still another spool touchpoint.
 



 Alan Altmark
 z/VM Development
 IBM Endicott


Re: After getting PerfKit working...

2010-03-30 Thread Alan Altmark
On Tuesday, 03/30/2010 at 03:50 EDT, Dave Wade 
g4...@dpwade.eclipse.co.uk wrote:
 I was thinking IPL any thing as historically they didn't have a 190 or 
191
 and so couldn't run anything, inlcuding games.

Captain, you're asking me to use equipment which isn't far ahead of stone 
knives and bearskins.

Operate CP without CMS?!?  I'll pretend I didn't hear that. 
Lalalalalala...

Alan Altmark
z/VM Development
IBM Endicott


Re: After getting PerfKit working...

2010-03-30 Thread Mike Walter
historically might be right.  Certainly since Programmable Operator came 
along (IIRC) in VM/SP R3, running CMS on OPERATOR has been a GOOD THING. 
 Later, more advanced console management products (IBM Operations Manager 
for z/VM, VM:Operator from CA, etc.) have vastly improved automation and 
productivity - to say nothing of all the pretty colored messages! 

These here days computer operators have much better and more advanced 
places to play Adventure, Zork, Pong, and all the rest.  There's this cool 
thing called an Atari, and another - a Magnavox Odyssey (just supply your 
own TV as a monitor)... well, we were speaking historically, right?  :-)

Mike Walter
Hewitt Associates
The opinions expressed herein are mine alone, not my employer's.






Dave Wade g4...@dpwade.eclipse.co.uk 

Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU
03/30/2010 02:49 PM
Please respond to
The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU



To
IBMVM@LISTSERV.UARK.EDU
cc

Subject
Re: After getting PerfKit working...






 -Original Message-
 From: The IBM z/VM Operating System 
 [mailto:ib...@listserv.uark.edu] On Behalf Of Alan Altmark
 Sent: 30 March 2010 20:40
 To: IBMVM@LISTSERV.UARK.EDU
 Subject: Re: After getting PerfKit working...
 
 
 On Tuesday, 03/30/2010 at 03:30 EDT, Dave Wade 
 g4...@dpwade.eclipse.co.uk wrote:
  I always thought allowing OPERATOR to IPL CMS was a BAD thing. Its 
  been a while since I used VM but in the past issues like this were
 often
  spool related.  Is something flooding the spool..
 
 As a general rule, the key system operation user IDs should 
 IPL 190, not 
 CMS in order to reduce the dependency on the spool. 

I was thinking IPL any thing as historically they didn't have a 190 or 191
and so couldn't run anything, inlcuding games. 

 If you're using 
 something like IBM Operations Manager for z/VM to create 
 console logs, 
 then you eliminate still another spool touchpoint.
 



 Alan Altmark
 z/VM Development
 IBM Endicott






The information contained in this e-mail and any accompanying documents may 
contain information that is confidential or otherwise protected from 
disclosure. If you are not the intended recipient of this message, or if this 
message has been addressed to you in error, please immediately alert the sender 
by reply e-mail and then delete this message, including any attachments. Any 
dissemination, distribution or other use of the contents of this message by 
anyone other than the intended recipient is strictly prohibited. All messages 
sent to and from this e-mail address may be monitored as permitted by 
applicable law and regulations to ensure compliance with our internal policies 
and to protect our business. E-mails are not secure and cannot be guaranteed to 
be error free as they can be intercepted, amended, lost or destroyed, or 
contain viruses. You are deemed to have accepted these risks if you communicate 
with us by e-mail.