For those of you interested in automating z/VM, our simple APIs have
been used by customers for years. Now we are providing the Ansible pod
/ playbooks for use for Ansible to interact safely and securely with
z/VM. No SMAPI, no Java, no extraneous Linux server required.
Exciting stuff!
Headed to the VM Workshop? "vmworkshop.org"...
On 5/15/2022 8:33 AM, Jake Anderson wrote:
Hello
For the last 2 years I have been building golden image for Linux on zVM and
am confident in it. Are there any new courses that I can start learning so
that it will be useful for future.
Any
and is this an internal ibm site?
On 4/27/2021 5:01 AM, blanc369 wrote:
Hi,
We are running a cluster of 3master nodes each 16gb 4cpu, 3 worker nodes 16gb
4cpu, 1 infra node 24gb 4cpu. In backend we have 9 IFL with smt2.
The biggest system load we usually see on Infra node, where elastic
If you would collect one minute CP MONITOR data, I would love to analyze
it for you. I've the best CP performance analysis tools at my disposal
On 2/6/2021 3:44 AM, Mariusz Walczak wrote:
Hello,
I hope someone can share the experience or put some light on the problem. I
will refer to
We here at Velocity Software have a really good story that has been
presented at SHARE, GSE, VM Workshop, and others. For those of you that
missed it, and especially those that think building a cloud on the
mainframe or on z/VM is complicated and messy, you might want to take a
look at
I don't see how steal time and the scsi would be related. There's an old
article about what steal time is at "http://velocitysoftware.com/STEAL.html;
On 11/4/2020 10:30 AM, Dave Jones wrote:
Hello, all.
I have a site that is using SCSI SAN (a V7000) to hold all z/VM
storagethe system
Diag 9C are low cost, Diag 44 not so much. 50 is a low number.
On 11/3/2020 12:27 PM, Grzegorz Powiedziuk wrote:
On Tue, Nov 3, 2020 at 1:58 PM Grzegorz Powiedziuk
wrote:
Thanks Christian.
There is no pagging (swapping) here besides just regular kernel's house
keeping (vm.swappiness =5 )
David, you might want to look at "http://velocitysoftware.com/smt.html;
at what are the available metrics and how to use them for chargeback.
Many of our Linux on z installations have a chargeback model, and SMT-2
required some updates to both the model and how to understand the metrics.
On
We've done some experiments with the onboard compression on our brand
new z15 and are implementing the compression in our products where it
makes sense. We have a CMS pipes stage written to make playing easy, so
have CMS functionality. As well as the assembler bits.
We also included the
Right. That’s what I’m hearing , that ‘unlimited ‘ is not available on Z
Barton
> On Oct 22, 2019, at 12:27 AM, Jim Elliott wrote:
>
> Sam:
>
> The Red Hat site above does not make sense to me as there is only ONE
> version of RHEL available for IBM Z. That is, Red Ha
I’m hearing at gse that red hat on z only supports 4 guests on kvm on z?
Here’s a link, am i missIng something?
https://access.redhat.com/articles/rhel-kvm-limits
Barton
--
For LINUX-390 subscribe / signoff / archive
Velocity Software offers to universities at no charge our complete zPRO,
allowing the universities to run their z/VM system without any knowledge
of z/VM. It is a complete web based interface that creates an on-prem
cloud, We will install it and support it. Takes 1/2 day to get it all
First, I happened to see an article on LinkedIn quoting Krebs on
Security. The Capital One hack of 106 million pieces of personal
information seems to have been on AWS? And an Engineer from AWS was the
hacker? The data was "improperly secured". Why would companies put
personal data
For those of you implementing MongoDB, or thinking about it, zVPS has
added support for it: http://velocitysoftware.com/mongodb.html
For those of you going to SHARE next week, you should be interested in
Kurt Acker's presentation presenting his MongoDB project and management
solutions
Isn't the ibm tool just for z/os and at the LPAR level? nothing to do
with what goes on inside z/vm. nothing to do with what goes on inside
linux for specific licensing.
I've been asked to provide such information by another vendor, and that
function will be released shortly. This allows the
ICF 3 3 00.500 0.5
ZIIP 1 0 18.5 7.9 0.1 0.5
On 2/1/2018 11:58 AM, Victor Echavarry wrote:
Barton:
This is the report of the CPU at the moment of the steal, VML2 is production
and VML4 is test.
ESALPAR - Logical Partition Analysis
It's very important to look at it first from the total IFL perspective.
What is the total IFL utilization? Then break that down by LPAR.
If 100% of your IFLs are in use, and one LPAR is using 60% of the IFL
resource and the other LPAR is using 40% of the IFL resource, then it's
a matter of
Yes. Gigahertz is gigahertz. If you can measure ghz consumed on x, you can
guestimate requirements on z. The only way to understand requirements is to
know current use.
Barton
> On Nov 7, 2017, at 8:28 PM, Victor Echavarry Diaz <vechava...@evertecinc.com>
> wrote:
>
On our website,
"http://velocitysoftware.com/present/flowchrt.html; , there is a
performance analysis flow chart. When there is wait, it is MOST often
not related to the linux server, it is MOST likely to be related to
resource constraints that the server just happens to be using (cpu,
He needs to know how to upload
Barton
> On Jan 22, 2017, at 2:10 AM, Tim Kessler <t...@velocitysoftware.com> wrote:
>
> Victor,
> Upload an hour of data from zwrite 191 from when the problem occurred
>
> -Original Message-
> From: Victor Echavarry Diaz
for the linux server.
On 12/20/2016 9:34 AM, Victor Echavarry Diaz wrote:
Barton:
The other LPAR has 3 active IFL's. The fourth is offline.
Regards,
Victor Echavarry
System Programmer
Operating Systems
-Original Message-
From: Linux on 390 Port [mailto:LINUX-390@VM.MARIST.EDU] On Behalf
How much of your IFLs are in use by the other LPAR(s)?
On 12/19/2016 2:19 PM, Victor Echavarry Diaz wrote:
Can someone explain why CPU steal is? We believe that when the VM LPAR is using
almost all is IFL's CPU stealing begins between guests. But today this specific
LPAR has 4 IFL and is
Yah, I've yet to see any data justifying wasting disk (except to get a
lunch from your disk vendor) for swap space instead of just moving the
extra disks to be part of the paging subsystem. If anybody has any data
that they think justifies this position, please send it.
VDISK gets paged out to
For those interested. We have a project to replace xcat/smapi with a
full backend for openstack on z/vm as part of our zpro offering. The
objective is for a user of openstack to have control over a z/vm service
the same as their vmware service.
Since our API already includes any or none of
No, monitor data does NOT contain storage information from other
LPARs. The CPU information comes from the HMC and is only available to
show CPU consumption by the LPAR - nothing within.
On 1/5/2016 6:28 AM, Grzegorz Powiedziuk wrote:
Hello,
I am trying to capture performance data with
I believe CMMA was withdrawn, and function completely removed in SLES 11.
On 12/18/2015 10:12 AM, Davis, Jim [PRI-1PP] wrote:
I am a systems programmer at Primerica Life Insurance.
We have been running SLES linux under VM for nine years.
We only have four production VMs on one lpar using a
experiment). End result was 40,000 less pages on
disk space and a LOT of page reads. Too bad no one from Endicott sees
my presentations.
On 12/11/2015 4:33 AM, Bill Holder wrote:
On Thu, 10 Dec 2015 14:05:26 -0800, Barton Robinson wrote:
If anybody in endicott is listening, ONE REQUEST
It couldn't be pgmbk, this was a result of a LINUX CMM command, and it
was the Linux storage assigned to the virtual machine that was targeted.
On 12/11/2015 11:01 AM, Bill Holder wrote:
Barton Robinson wrote:
Drop another 20,000 pages, and there
are 40,000 page reads (and 20,000 page writes
Altmark wrote:
On Wednesday, 12/09/2015 at 08:15 GMT, Barton Robinson
<bar...@velocitysoftware.com> wrote:
My request to get this fixed was rejected by ibm several years ago. The
problem is that even though linux doesn't have anything on the vdisk,
z/vm still has to back it. I asked for a di
My request to get this fixed was rejected by ibm several years ago. The
problem is that even though linux doesn't have anything on the vdisk,
z/vm still has to back it. I asked for a diagnose as we do with real
storage - a way for Linux to tell z/vm the page no longer needs
backing. So after
No, please don't do this. Having weights in the 1000's is what causes
this problem, creates excess share, the looping user takes over.
If you don't understand excess share, keep shares in the 100's, and use
absolute shares where you know exactly what is intended.
On 10/28/2015 7:13 AM,
The best way is to first understand your share settings and avoid excess
share.See Rob's paper on the topic
here "http://www.velocitysoftware.com/relshare.HTML;
Use zalert to detect problems, and have zoperator to give your
operations and applications people early indication.
i believe you
accomplished at the time. But we had a rather
standard Java workload across the board, and perhaps more a more complex
workloads and larger numbers of guests changes things.
That said, I acknowledge your expertise, and value to this forum Barton!
-Original Message-
From: Linux on 390
This is the reason I have re-invested in a full rewrite of ZPRO to
completely eliminate any need for SMAPI. Our community objectives
should be to make our systems easier to implement and maintain.
Companies are not investing in the training as in the past, skills are
harder to acquire, and
There is a GSE conference for Linux, z/VM and z/VSE in Stuttgart Germany
in 3 weeks. That same week, there is a performance class that will show
how to get exactly what you want using zVPS
"http://velocitysoftware.com/zvps.html;. If you care about performance
of Linux under z/VM, you need the
bc12 moved successfully and is back up.
--
For LINUX-390 subscribe / signoff / archive access instructions,
send email to lists...@vm.marist.edu with the message: INFO LINUX-390 or visit
Due to system upgrade, Velocity Software and other hosted sites will be
down today. Note these websites all run under z/VM on a BC12, secured
by RACF. Our growth, current projects, and many projected future
projects require a move to a larger space.
We are looking at a large number of
Hardware maintenance means the Velocity Software and LinuxVM.ORG
websites are temporarily down, as are a few of the local user groups
that we host. back up shortly
--
For LINUX-390 subscribe / signoff / archive access
0.0
On 7/9/2015 9:31 AM, Michael MacIsaac wrote:
Barton,
It reports on the /proc/buddyinfo values and anticipates vmcp failing?
On Thu, Jul 9, 2015 at 12:26 PM, Barton Robinson
bar...@velocitysoftware.com wrote:
And a good performance monitor would already have this reported - down
And a good performance monitor would already have this reported - down
to the process level.
On 7/9/2015 9:06 AM, Michael MacIsaac wrote:
Let me answer my own question. Perhaps kludgy, but by adding 'tee' to
sudo, this technique works:
root@lab141:~ # visudo
root@lab141:~ # tail -1
or you could do it from z/vm with ZVWS. It is very fast, and trivial to
use.
On 3/19/2015 8:40 AM, Vitale, Joseph wrote:
Hello,
I need to install a simple Web Server to server up 1 file. Internal load
balancing requirement.
Looked at Apache Web site, found binaries for Windows and Linux
Will miss you Annie, I've another 15 years to go
Barton
On Feb 26, 2015, at 3:55 PM, Smith, Ann (CTO Service Delivery)
ann.sm...@thehartford.com wrote:
Tomorrow is my last day at IBM
Hit the big 60 and I am retiring
8 years working in MVS, 22 in VM and 8 with Linux
I will miss the work
I've looked at the amazon and google chargeback models. One of their
options is a fixed price until some number of CPU hours is exceeded.
This allows the 'easy' fixed fee, but also controls the resource
abuser. You would have to have tools in place to alert the abuser that
they have gone
zPRO has been out for about 4 years and was a project started almost 10
years ago. We had many customers create their own self service
applications using our web technology, it seemed reasonable to take
their ideas and make a common product.
ZPRO V2 is built on ALL native z/VM functionality,
AMEN
On 11/19/2014 9:38 AM, Mark Post wrote:
On 11/19/2014 at 03:18 AM, Guest, Darren darren.gu...@uk.experian.com
wrote:
Mark, are you suggesting that the Oracle team should have some actual data to
back up their claims? Not just a bloke with a stopwatch and an uneasy
feeling?! ;-) But yes,
I just had an installation demonstrate the perfect tool for you. In
looking at what alerts should be set for operations, one of their many
zlinux servers had a swap full condition. They were able to go back
thru reports from last 12 months, took less than a minute to identify
when the swap
, and what caused it? Or do you just
reboot?
On 11/9/2014 1:38 PM, Tito Garrido wrote:
If you are going to try SAR take a look on KSAR project...
http://sourceforge.net/projects/ksar/
Regards,
Tito
On Sun, Nov 9, 2014 at 1:30 PM, Barton Robinson bar...@velocitysoftware.com
wrote:
I just had
Our software (zVPS) is not free, but is no charge for POC. Our mission
is to help you succeed with the Linux on z POC.
On 8/25/2014 7:46 PM, Martin, Terry Contractor wrote:
I am in the same boat. I would like to use Velocity for my client but since is
a POC they want to sick with something
The RMFPMS was a brilliant but misguided piece of software that the
author stopped supporting about 10 years ago. If it costs several IFLs
to run free software, there's a lot of misguidance going around
The best thing about some of these tools is that your management can't
tell what their
Dear all,
we are offering our famous performance class for the VM-Workshop
attendees, on 24 25 June, in North Carolina.
For registration and more details please visit:
http://velocitysoftware.com/seminar/workshop.html
Please reach out with any questions.
Best wishes and see you in North
zOPERATOR, a no charge feature of zVPS (from Velocity Software) can
accept and record and respond to messages.
On 3/13/2014 9:13 PM, Morris, Kevin J. (RET-DAY) wrote:
I would like to send all operator messages to a zLinux guest for further
processing/storage, essentially replacing PROP. Is
-Original Message-
From: Linux on 390 Port [mailto:LINUX-390@VM.MARIST.EDU] On Behalf Of Barton
Robinson
Sent: Wednesday, January 15, 2014 2:23 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Swap behavior change between SLES 11SP2 and 11SP3?
With all of the installations (100s) i've worked
With all of the installations (100s) i've worked with using vdisk for
swap, this would be the first complaint i've heard with the exception of
some bad configuration defaults. If you had really good performance
management tools, I'd be happy to look at the data.
On 1/15/2014 5:44 AM, Veencamp,
This could be just new year workload. Or someone is running some new
scripts that are consuming LARGE amounts of CPU. The data shows nothing
strange in the CPU distribution between servers:
Report: ESAUSP2
---CPU time--
UserID (Percent) T:V
/Class Total Virt Rat
-
issues. IBM has a workaround you can GOOGLE.
-Original Message-
From: Linux on 390 Port [mailto:LINUX-390@VM.MARIST.EDU] On Behalf Of Barton
Robinson
Sent: Friday, January 10, 2014 12:19 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: High cpu utilization on vm/linux LPAR
This could be just
Due to hardware upgrade, several websites that we host on our z/VM
systems will be down on thursday. This includes:
LINUXVM.ORG
LINUXVM.COM
VelocitySoftware.com
DEMO.VelocitySoftware.com
If everything goes write, the new Velocity Cloud will be much bigger
than ever on Friday. Our VERY old P390
Guys, you DO know I read this stuff?
Anybody that knows me, had a beer with me, or much about my business
would never imagine me working for someone else. I work hard at being a
technology leader - that means investing in things the bean counters
can't even imagine having value, investing in a
Mauro, please Read That Fine Manual/article again, licensing does NOT
equal acquisition.
product news
CA Technologies Signs Global Licensing and Distribution Agreement with
Velocity Software, a Leading Linux Performance Management Company
all good.
On 10/3/2013 2:42 PM, Gregg Levine wrote:
Hello!
Thank you Barton. Now did I properly describe the situation? The
important phrase was indeed licensing in your statement. I chose
simply acting as a vendor. I didn't want to go into too much detail.
-
Gregg C Levine gregg.drw
Really good performance monitors would give you lots of good information.
On 10/2/2013 4:28 AM, van Sleeuwen, Berry wrote:
If anything I even would like to decrease the memory configuration rather than
increase it. Unfortunately I got overruled by the Oracle guys who still think
more memory
dedicated IFL's or GPs always look 100% busy from the LPAR perspective,
and that is the data fed into RMF or CP Monitor
On 8/20/2013 9:01 AM, Richards, Robert B. wrote:
My VM/Linux guy came to me with a several disparate displays (a HMC Activity
Display, a TMONMVS LPAR Summary screen and s
CMMA is gone, didn't work right and support was pulled.
VMRM does not have proper feedback and is more likely to crash your
linux server than help
CPUPLUGD - never seen any measured value.
Focus on understanding the storage requirements. One of the
presentations at the VMWorkshop last week was
I've seen several installations over the last few years build their own
web based applications for cloning. That was my incentive for producing
a low cost web based application that included cloning
(http://VelocitySoftware.com/zpro.html;) and to provide some level of
standardization.
How many
If you investigate the ESALNXP report provided by ZVPS, you will see a
cron job with your latest patches, and not before that. One just
needs good tools
Srivastava, Sagar wrote:
We implemented latest patches on our SLES11 SP1 systems recently
Now all the zLINUX guest are using
please make 20% of your storage ExStore. This only matters if you are
storage constrained, so benchmarking differences when there are no
constraints will not show a difference. When you become storage
constrained, the 20% ExStore will easily show better performance.
Richards, Robert B. wrote:
It's called zTUNE. http://velocitysoftware.com/zztune.html;
Michel Beaulieu wrote:
Hello Linux-390,
I know this is the LINUX-390 list,
However, let me ask:
Do we have any equivalent System Health Checker for z/VM?
Michel Beaulieu
IBM SO-Delivery (Canada)
And ZVPS from Velocity Software supports microsoft as well as linux on
x86 for operations as well as full performance management.
David Boyes wrote:
Looking at the Microsoft websites (not very
helpful of course, more marketing, little
technical) for SCOM (System Center Operations Manager 2007
one lpar works well, shares storage, shares other resources, reduces
overhead, reduces system programming efforts, reduces costs. And I can
show other mixed mode LPARs with both VSE and linux in the same LPAR.
Was it a hardware vendor recommending increasing your hardware costs
Michael
Re performance, there has been no need to change time slice since qdio,
about 5 years ago.
Offer Baruch wrote:
Hi all,
Well we conducted another test (much better than the last one - it had too many
unpredictable variables):
1. 1 destination machine let's call it dest1
2. dest1 has 2 nics
Before I get REALLY excited, has anyone tried this and validated they
can get Linux servers running WAS to drop from QUEUE (as in drop from
QUEUE 3)?
Jim Elliott wrote:
I don't believe this has been posted here before, but IBM has
published a TechDoc on this subject.
Are you looking at monitoring network traffic? uptime? availability?
resource consumption? ZVPS ( http://velocitysoftware.com/zvps.html; )
does all that and more.
Kowalski, Steve S wrote:
Hello,
Is anyone using any monitoring tool (except the MOSS Console) for Communication
Controller for
I really despise the system defaults of REL 1500, or REL 5000. They
seem (were) provided by someone ignorant of how the scheduler actually
works.
Rob has a nice paper showing the damage. Though ibm might try and code
around how this damage impacts your system, changing these defaults to
it's really hard to make the mondcss go away unless there was a purge
done, and when the application went away, so did the dcss
Dean, David (I/S) wrote:
How do you make MONDCSS permanent? We IPL'd, the segment did not come back,
and monitoring is not working. I know how to set it up
Just in from IBM systems magazine. CICS on z/os workloads moving to
Linux on z. wow.
Organizations are consolidating workloads onto Linux on IBM System z to
lower costs, standardize operations and enhance IT flexibility. Now you
can move online and batch mainframe applications to scalable
: Barton Robinson bar...@vm1.velocity-software.com
To: LINUX-390@vm.marist.edu
Date: 03/18/2011 04:04 PM
Subject:Re: Moving Oracle off zLinux boxes -- comments from the field?
Sent by:Linux on 390 Port LINUX-390@vm.marist.edu
wow, your DBAs have the authority to spend
wow, your DBAs have the authority to spend that kind of money and make
that kind of change without management signature? So no financial
analysis, no technical reason, sounds religious.
CHAPLIN, JAMES (CTR) wrote:
We just had a surprise announcement by one of the Oracle DBAs during a
zLinux
Well, since you are ready.
First, Oracle is VERY virtual friendly. And has been the most virtual
friendly application there is.
BUT, if you use RAC, it seems that someone decided to compete in the
virtual hostile arena by making it poll at a high enough rate to
ensure you need to buy a LOT
For those of you interested in performance, or performance management of
your Linux and z/VM environment, our Performance Education schedule is
now posted for 1st half, at
http://velocitysoftware.com/seminar/index.html;.
Offerings are the 4 day workshop and 1 day seminars.
Rules of thumb change, or get old. The linux spin locking has greatly
improved. new evidence is showing that letting z/vm do the scheduling
is more efficient for later releases of Linux - as long as there are no
spin locks occurring. For example, in a one-ifl configuration, having
WAS servers
The consideration is the LPAR overhead. The more dispatching there is,
the more is the physical overhead. I've seen that running as high as
5% of each processor on overcommitted systems, and .1% normally.
Joe Martin wrote:
Have a development system that has 2 IFLs and both are configured to the
Isn't the real problem that the VMWare vendor(s) does a LOT of
advertising and marketing, and the z/VM vendor does not (other than
preaching to the choir)?
Graves, Aaron wrote:
The implication is that these represent the leading edge of
virtualization, completely ignoring z/VM's capabilities.
Yes, this is a problem. We call it virtual hostile. Rob van der Heij
has been doing a tremendous amount of research in this area for the last
4 years, we've been trying to educate our customers (and IBM) on what
this means.
Back in 2001, there was the Linux timer, had the same problem. Got
Yep, this is exactly the problem. These processes do not use much
cpu, but they blip every 10ms or so. You need to check the queue from
the z/VM side to see if they are in Q3. If in Q3, then they are blipping
(think i need to trademark that word).
The reason these blips are so virtual
But, Oracle is VERY virtual friendly, and DB2 is VERY virtual HOSTILE.
From a system performance perspective, I REALLY LIKE Oracle.
Mark Post wrote:
On 7/30/2010 at 12:03 PM, Marcy Cortes marcy.d.cor...@wellsfargo.com wrote:
Does this make Oracle a better fit on Linux on z than DB2?
That
So the biggest announcement of the year, i'm on my second pot of coffee,
and there's still only one post about this? Is this a non-event?
Dave Jones wrote:
And what's old is new againthere's a water cooled version of the
z196. :-)
DJ
On 07/22/2010 06:38 AM, Jim Elliott wrote:
The IBM
-...@vm.marist.edu] On Behalf Of Barton
Robinson
Sent: Thursday, July 22, 2010 8:33 AM
To: LINUX-390@vm.marist.edu
Subject: Re: [LINUX-390] IBM zEnterprise System announced???
So the biggest announcement of the year, i'm on my second pot of coffee,
and there's still only one post about this? Is this a non
announced)
Alan Altmark wrote:
On Thursday, 07/22/2010 at 11:34 EDT, Barton Robinson
bar...@vm1.velocity-software.com wrote:
So the biggest announcement of the year, i'm on my second pot of coffee,
and there's still only one post about this? Is this a non-event?
Kind of hard to talk about
You really need a decent performance monitor. I can already see that
your settings would not be my view of best practices
Rogério Soares wrote:
Listeners,
I have a strange problem again...
on my lpar for development, i have now queue E3, each time a run #cp q exp i
have a different
ibm-m...@tpg.com.au wrote:
Now there's a lad that gets around.
He was speaking here in Aus just a couple of weeks back.
Yes, I think Barton logs more air miles than most migratory birds.
Mark Post
--
For LINUX-390 subscribe
So, monitoring mainframe software is really about MANAGING, this is
not the pc world. Does your objectives have anything to do with the
following disciplines:
1) Performance analysis including all subsystems (DASD, Storage, PAging,
CPU, Network)
2) Capacity Planning (same subsystems), with
Any chance VMRM was active and too storage away?
Mark Perry wrote:
Hi Ron,
thats a support question if ever I heard one. Contact SAP/IBM. (Which of
course will lead to a question on maintenace levels of linux and sap.)
If kill -9 doesn't work then the process is in a system routine that can be
There are many samples on the customer area of our website in:
http://velocitysoftware.com/customer/tips/index.html; beyond what is
shipped with the product.
Rodery, Floyd A Mr CIV US DISA CDB12 wrote:
I was curious if anyone is sending alerts to their enterprise monitor
using Velocity's
IF you have a good performance monitor, you would know exactly what
process on what server is using CPU.
With zVPS (ESALPS), on one screen, you can see ALL the top processes
across your entire Linux farm, with one PFK, you can sort them by cpu.
Knowing where your cpu is going means you can do
of any performance studies done for weblogic.
Carson, Brad wrote:
Barton,
Well, we are using the z/VM performance Toolkit and BMC Mainview for our
monitoring on this lpar.
This is how we were able to get down to the which guest is behaving bad
and the threads within that
guest that are giving us
First rule of thumb, don't guess. Since Oracle SGA can be anywhere from
a few hundred megabytes to 10's of gigabytes, you need to size the
server larger than the SGA. If you undersize the server, you WILL have
undesirable performance. On intel they size based on low cost of
storage and I/O
I think you are missing several things. (And jiffies are in 10ms
increments, not 1ms increments)
First, have you verified the accuracy of your CPU numbers? Does RHEL4
include the steal timer patch and is it working correctly on both VMWare
and z/VM? Even with current levels of Linux and z/VM,
Or even keep one minute data, 15 minute data, and/or any other
combination you would like, all at the same time.
Thomas Kern wrote:
If a customer were having a problem with a particular linux guest, could
they modify that ESALPS condensation process, say to condense after a
week? Or condense
Martin, please correct me if i am wrong.
Large page support supports 1mb pages - meaning consecutive 256 4k pages
in hardware. These pages are fixed, are not pageable with current
technology. The advantage is that there is one TLB entry per megabyte
instead of one per 4k page, so that the TLB is
Having seen a very good performance presentation from IBM on the value
of huge pages, I'm interested in knowing what value y'all expect from this?
Mark Post wrote:
On 11/27/2009 at 12:36 PM, Szefler Jakub - Hurt TP
jakub.szef...@telekomunikacja.pl wrote:
Yes :) It may be poorly understood.
I
I thought IBM stopped pushing RMFPM about 5 years ago because of
overhead and lack of development interest? This was developed in the RMF
lab for installations that were z/OS, no z/VM and running Linux in an
LPAR. Ask your boss to talk to references (for something that has been
out almost 10
1 - 100 of 329 matches
Mail list logo
