It depends on how you're going to use it. See the
System Limits presentation, chart 23.
Bit
Thanks for all your contributions over the years Jeff, and wishing
you the best in the next chapter.
Bit
Thanks...I missed that... But even for the customer we're dealing
with, 1000GB (very round numbers)will eat that up.
And I dread even looking at MDISK statements with big numbers like:
MDISK 600 9336 21 4194200 LX2000 M
Lee
Eric R Farman wrote:
Hi Lee,
The biggest EDEV you c
Thanks Marcy,
I will look into this further.
Thank You,
Terry Martin
Lockheed Martin - Information Technology
z/OS & z/VM Systems - Performance and Tuning
Cell - 443 632-4191
Work - 410 786-0386
terry.mar...@cms.hhs.gov
-Original Message-
From: The IBM z/VM Operating System [mailto:ib.
It's a kernel setting. Googling provided this definition:
Swappiness is a kernel "knob" (located in /proc/sys/vm/swappiness) used
to tweak how much the kernel favors swap over RAM; high swappiness means
the kernel will swap out a lot, and low swappiness means the kernel will
try not to use swap s
Hi Marcy,
Forgive my ignorance but what is the "vm.swappiness setting"?
Thank You,
Terry Martin
Lockheed Martin - Information Technology
z/OS & z/VM Systems - Performance and Tuning
Cell - 443 632-4191
Work - 410 786-0386
terry.mar...@cms.hhs.gov
-Original Message-
From: The IBM z/VM O
>>> On 1/28/2009 at 1:11 PM, Jack Woehr wrote:
-snip-
> Linux on workstations and servers is not easy to push over the brink into
> thrashing.
Not hard at all. Just put 20 pounds of workload into a 10pound bag, which is
exactly what happens on System z as well.
Mark Post
On Wednesday, 01/28/2009 at 02:09 EST, "Horlick, Michael"
wrote:
> I agree that when the system slows down my app will slow down but since
> maybe there are fewer instructions to perform (as opposed to doing a CP
> Q TIME and REXX processing my exec statements) maybe it would be closer
> to nati
That's been my experience as well.
You may want to look at the vm.swappiness setting. We changed it from
60 to 20 because some of the applications swap space seemed to just grow
and grow and grow and CPU would start to creep up too. Dropping to 20
removed all the issues.
I'm not sure why and we
On Wednesday, 01/28/2009 at 01:12 EST, "Martin, Terry R. (CMS/CTR) (CTR)"
wrote:
> Currently we are using LDAP on our z/Linux Red Hat 4.6 which is running
on a
> z/VM 5.3 system to do our authentication. One of our z/OS folks said
they saw
> somewhere that under z/VM 5.4 that you could no l
Alan,
Suppose I write an assembler program that did the following:
Start_Loop:
STCK (record value 1)
Using logical 3270 device support "Press" Enter key and wait for
response
STCK (record value 2)
Compute the difference between value 2 and value 1
Do some action if too high
Wait so many seconds
What everyone else said.
Look at "z/VM Version 5 Release 4 Extending virtualization technology
leadership for System z" for a little more of an explanation.
"Martin, Terry R. (CMS/CTR) (CTR)"
Sent by: The IBM z/VM Operating System
01/28/2009 01:12 PM
Please respond to
The IBM z/VM Op
Thanks Dave and all for the quick response. I thought this was false but
I wanted to be sure!
Thank You,
Terry Martin
Lockheed Martin - Information Technology
z/OS & z/VM Systems - Performance and Tuning
Cell - 443 632-4191
Work - 410 786-0386
terry.mar...@cms.hhs.gov
-Original Message-
Hi Ron,
We have:
q share vtam
USER VTAM: ABSOLUTE SHARE = 4%
MAXIMUM SHARE = NOLIMIT
Ready;
It's not only VTAM users that suffer. I connect through TCP/IP for VM
and when the system is slow it's slow
Geeze - I got an email from Don just 2 weeks ago saying that he might
apply for a job opening here at SRU. You just never know what's in
your future.
/Fran Hensler at Slippery Rock University of Pennsylvania USA for 45 years
mailto:f...@zvm.sru.edu http://zvm.sru.edu/~fjh +1.724.738.2153
Hi Mike,
Do you give the VM VTAM userid any sort of preference? We've given
VTAM a SHARE ABS 3%.
Ron
On Wed, Jan 28, 2009 at 10:26 AM, Horlick, Michael
wrote:
> Greetings,
>
>
>
> Here is the situation.
>
>
>
> We are running z/VM 5.2 and 5 z/VSE 4.1.0 guest systems (3 production, 2
> developme
Hi, Terry.
No, your z/OS person is mistaken. You can still run LDAP on zLinux to do your
authentication. What the z/OS person might be referring to is that if you choose to run
the z/VM supplied LDAP server, it can use zVM's RACF to store Linux user ids and passwords.
Martin, Terry R. (CMS/CT
Mark Post wrote:
My experience isn't that it's the CPU cost of the paging I/O. It's more that
Linux, like any other virtual storage operating system, can get into a
thrashing mode, and all the kernel is doing is lots and lots of memory
management. The system runs at 100% busy, and nothing ge
There's absolutely nothing in z/VM 5.4 that would prevent you from using LDAP in Linux
for authentication. There's an LDAP Server in z/VM 5.4, but it was also included with
z/VM 5.3 (although a previous level).
Martin, Terry R. (CMS/CTR) (CTR) wrote:
Hi
Currently we are using LDAP on our
Hi
Currently we are using LDAP on our z/Linux Red Hat 4.6 which is running
on a z/VM 5.3 system to do our authentication. One of our z/OS folks
said they saw somewhere that under z/VM 5.4 that you could no longer use
LDAP on z/Linux to authenticate, that it would need to be done at the
z/VM le
>>> On 1/28/2009 at 9:57 AM, Robert J Brenneman wrote:
> Just a guess till the experts chime in:
>
> Linux disk I/O activity requires more CPU time than traditional Z
> Operating systems - so when one guest starts driving 5000 I/O ops per
> second to the swap device ( FBA mode vdisk in my case
it can be a memory hog but it drops from queue when true work is done, and
doesn't have this neverendingqueuefourpolling
problem. Note: queue 4 doesn't really exist in zvm i just coined the term to
connote my utter frustration with false work never endus.
I support clients with many small Orac
HA HA ha ha!!!
Seriously? I don't have any experience with WAS, but Oracle is a definite
memory lover.
MA
On Wed, Jan 28, 2009 at 11:08 AM, David Kreuter
wrote:
> with the effect of diminishing the value of virtualizing on this
> platform. Over commit ratios of 1.5 just aren't sufficient e
On Wednesday, 01/28/2009 at 11:27 EST, "Horlick, Michael"
wrote:
> I?m toying with creating a REXX EXEC which uses RXLDEV to create a
logical 3270
> session and have the EXEC basically ?press? the ENTER key say every 30
seconds.
>
> I?m hoping this will mimic what a real interactive CMS user
No, that's not too far off from the fact. I just thought that is was
some sort of batch report that people usually run after hours to see
what happened during the day.
Thanks for the info. I need to review VMRM and see if it will do the
trick. I don't think my client is interested in spending any
ESAMON will let you know that minute. It analyzes the data every
minute, alerts are set to check values every minute. So if that is after
the fact, then yes
Horlick, Michael wrote:
Hi,
Right now most users are still connected as SNA devices. We are slowly
moving to TCP/IP.
I assume t
I see info on VMRMSVM in z/VM Performance Guide. Will take a look at it.
Thanks,
Mike
From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On
Behalf Of Huegel, Thomas
Sent: January 28, 2009 11:35 AM
To: IBMVM@LISTSERV.UARK.EDU
Subject: R
Hi,
Right now most users are still connected as SNA devices. We are slowly
moving to TCP/IP.
I assume that z/VM and ESAMON will let me know after the fact that there
was slow interactive response during some interval(s) of time during the
day.
I would like something that would be more immedia
Hi,
We are going to use a TS3500 tape library for our z/VM and z/OS systems.
With the RMM-support in IBM Tape Manager does anyone know if it is
possible
to share the same scratchpool between z/VM and z/OS in a TS3500?
Best regards
Tomas Norberg
Have you tried setting up VMRMSVM to monitor and adjust (via SET SHARE) on your
system? I think it works pretty good for me.
-Original Message-
From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu]on Behalf
Of Horlick, Michael
Sent: Wednesday, January 28, 2009 10:27 AM
To:
TCPIP in z/VM has metrics that can be used to show network response
time. z/VM provides transaction data. As a performance monitor that
analyzes both, ESAMON will cost you less than 1% of a cpu. Could
probably do what you want with just zMON at $1200/month.
Horlick, Michael wrote:
Greetings
Greetings,
Here is the situation.
We are running z/VM 5.2 and 5 z/VSE 4.1.0 guest systems (3 production, 2
development machines) on an IBM 2066 (z800). In 2 of these VSEs there is
a heavy duty CICS/TS system running.
We use SET SHARE ABS to give them a minimum target of CPU, no limits,
with the effect of diminishing the value of virtualizing on this platform.
Over commit ratios of 1.5 just aren't sufficient enough to have an attractive
TCO in the case of WAS and other IBM applications. The darn WAS machines never
queue drop.
Oracle a non-IBM product does not have this
I agree that in the past the Linux activity requirements
For I/O are different then zVM.
If your Linux Guest becoming unresponsive, review;
CMD: Q QUICKDSP userid
CMD: CP QUERY SRM STORBUF
CMD: CP SET SRM STORBUF xxx xxx xxx' (may really help)
CMD: QUERY ALLOC PAGE
CMD: Management may buy
The last time I looked at the cost of swap to vdisk, at 1,000 per
second, used 10% of an 890 processor. It's very hard to constrain a
system to swap this much, this was in the lab pushing limits not
normally pushed. With z10 IFL significantly faster, swapping to vdisk
would not be a significa
Just a guess till the experts chime in:
Linux disk I/O activity requires more CPU time than traditional Z
Operating systems - so when one guest starts driving 5000 I/O ops per
second to the swap device ( FBA mode vdisk in my case ) that in itself
consumes a big chunk of CPU. Then there's the addit
thanx
munson
Kris Buelens
Sent by: The IBM z/VM Operating System
01/28/2009 09:26 AM
Please respond to
The IBM z/VM Operating System
To
IBMVM@LISTSERV.UARK.EDU
cc
Subject
Re: Max EDEV size?
Read the z/VM performance reports. In general: with EDEVs you can sustain
a somewhat hig
Read the z/VM performance reports. In general: with EDEVs you can sustain a
somewhat higher page rate than with ECKD, but, the CPU cost to drive the
paging operations is much higher per page (even with z/VM 5.3 which is
better than 5.2).
2009/1/28 Bill Munson
>
> Eric,
>
> What about using SCSI
Last Thur afternoon my IFL's went to nearly 100% for extended periods. O
ne
linux guest running three WebSphere app servers was the culprit. After
determining the cause to be the JVM of one the servers causing linux to
swap the JVM, we increased the size and restarted server. Things are fin
Eric,
What about using SCSI (edev) for z/VM PAGE packs ??
thanx
Bill Munson
Brown Brothers Harriman
Sr. z/VM Systems Programmer
201-418-7588
President MVMUA
http://www2.marist.edu/~mvmua/
Eric R Farman
Sent by: The IBM z/VM Operating System
01/27/2009 08:39 PM
Please respond to
The IBM
40 matches
Mail list logo