Re: VMRMSVM - z/VM Resource Manager
Ok, thanks Bill. My goal is to use VMRM to control the resource usage with goals similar to what I do on z/OS with WLM. 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 WFH Tuesdays and Fridays -Original Message- From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Bill Munson Sent: Monday, November 02, 2009 2:26 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I am not using SFS or DIRMAINT here - I think that IBM VM Director is or was part of those products Tracy Dean mentioned. I started up VMRMSVM to use CMM and the config file is on the 191 mdisk and I log on to make changes. I also log on to maint and update the USER DIRECT on the 2cc mdisk and then use DIRECTXA I got help setting up VMRMSVM from that IBM web site at the link I sent you and a presentation from Chris Casey of IBM . good luck Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 11/02/2009 02:01 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager HI Bill, So the CONFIG file for VMRMSVM does not need to be on SFS even if you want the ability to change the configuration dynamically? BTW, I am not using DIRMAINT or anything like that to administer the Directory I am using DIRECTXA is that considered IBM VM DIRECTOR? 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 WFH Tuesdays and Fridays -Original Message- From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Bill Munson Sent: Monday, November 02, 2009 11:09 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, Nobody has said this but VMRMSVM does not need SFS to run like DFSMS does. But there is some documentation that says to use SFS if you are using IBM VM Director. and the files needed are on Maint's 193 mdisk http://www.vm.ibm.com/sysman/vmrm/vmrmcmm.html Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 10/30/2009 08:33 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM
Re: VMRMSVM - z/VM Resource Manager
Thanks yeah I saw that. Thanks Alan! 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 WFH Tuesdays and Fridays -Original Message- From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Alan Altmark Sent: Monday, November 02, 2009 4:39 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager On Monday, 11/02/2009 at 02:15 EST, Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov wrote: BTW, I am not using DIRMAINT or anything like that to administer the Directory I am using DIRECTXA is that considered IBM VM DIRECTOR? No, DIRECTXA and IBM Systems Director (IBM Director) are two different things. IBM Director is a GUI-based multiplatform management application that lives outside of z/VM, but can communicate with it to perform some basic systems programming tasks. Alan Altmark z/VM Development IBM Endicott
Re: VMRMSVM - z/VM Resource Manager
Terry, Nobody has said this but VMRMSVM does not need SFS to run like DFSMS does. But there is some documentation that says to use SFS if you are using IBM VM Director. and the files needed are on Maint's 193 mdisk http://www.vm.ibm.com/sysman/vmrm/vmrmcmm.html Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 10/30/2009 08:33 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job balancing when it sees all the work not just a small group of machines. 2) Place each of the heavy CPU machines in their own group. VMRM checks the CPU run/wait deltas proportion of all the machines in a group. One heavy CPU machine in a group will cause the group to exceed it's goals. VMRM then starts adjusting the relative shares downward for all the machines in the group, particularly the heavy CPU machine. With some of the Focus runs going for 8 hours or more I saw some relative shares of 1 which was a bit of shock. I found I needed to have 15-20 groups altogether with 10 of those being single machine groups 3) I used the option of being able to dynamically change configurations. I did this to reduce the goals for the Focus processing during the nightly VSE batch work. When the VSE work finishes, I raise the goals again. 4) It's been an iterative process of setting goals and mixing (or separating) machines. 5) I don't normally see much, if any change in the relative share values VMRM sets when the z9 is lightly loaded. Ed Neidhardt Mainline Information Systems, Inc. 770-321-0841 Office ed.neidha...@mainline.com - Original Message - From: Martin, Terry R. (CMS/CTR) (CTR) To: IBMVM@LISTSERV.UARK.EDU Sent: Thursday, October 29, 2009 8:06 PM Subject: VMRMSVM - z/VM Resource Manager Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side so I understand the principle behind it but I just wanted to know from those who use
Re: VMRMSVM - z/VM Resource Manager
HI Bill, So the CONFIG file for VMRMSVM does not need to be on SFS even if you want the ability to change the configuration dynamically? BTW, I am not using DIRMAINT or anything like that to administer the Directory I am using DIRECTXA is that considered IBM VM DIRECTOR? 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 WFH Tuesdays and Fridays -Original Message- From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Bill Munson Sent: Monday, November 02, 2009 11:09 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, Nobody has said this but VMRMSVM does not need SFS to run like DFSMS does. But there is some documentation that says to use SFS if you are using IBM VM Director. and the files needed are on Maint's 193 mdisk http://www.vm.ibm.com/sysman/vmrm/vmrmcmm.html Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 10/30/2009 08:33 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job balancing when it sees all the work not just a small group of machines. 2) Place each of the heavy CPU machines in their own group. VMRM checks the CPU run/wait deltas proportion of all the machines in a group. One heavy CPU machine in a group will cause the group to exceed it's goals. VMRM then starts adjusting the relative shares downward for all the machines in the group, particularly the heavy CPU machine. With some of the Focus runs going for 8 hours or more I saw some relative shares of 1 which was a bit of shock. I found I needed to have 15-20 groups altogether with 10 of those being single machine groups 3) I used the option of being able to dynamically change configurations. I did this to reduce the goals for the Focus processing during the nightly VSE batch work. When the VSE work finishes, I raise the goals again. 4) It's been an iterative process of setting goals and mixing (or separating) machines. 5) I don't normally see much
Re: VMRMSVM - z/VM Resource Manager
Terry, I am not using SFS or DIRMAINT here - I think that IBM VM Director is or was part of those products Tracy Dean mentioned. I started up VMRMSVM to use CMM and the config file is on the 191 mdisk and I log on to make changes. I also log on to maint and update the USER DIRECT on the 2cc mdisk and then use DIRECTXA I got help setting up VMRMSVM from that IBM web site at the link I sent you and a presentation from Chris Casey of IBM . good luck Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 11/02/2009 02:01 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager HI Bill, So the CONFIG file for VMRMSVM does not need to be on SFS even if you want the ability to change the configuration dynamically? BTW, I am not using DIRMAINT or anything like that to administer the Directory I am using DIRECTXA is that considered IBM VM DIRECTOR? 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 WFH Tuesdays and Fridays -Original Message- From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Bill Munson Sent: Monday, November 02, 2009 11:09 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, Nobody has said this but VMRMSVM does not need SFS to run like DFSMS does. But there is some documentation that says to use SFS if you are using IBM VM Director. and the files needed are on Maint's 193 mdisk http://www.vm.ibm.com/sysman/vmrm/vmrmcmm.html Bill Munson Sr. z/VM Systems Programmer Brown Brothers Harriman CO. 525 Washington Blvd. Jersey City, NJ 07310 201-418-7588 President MVMUA http://www2.marist.edu/~mvmua/ http://www.linkedin.com/in/BillMunson Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 10/30/2009 08:33 PM Please respond to The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU To IBMVM@LISTSERV.UARK.EDU cc Subject Re: VMRMSVM - z/VM Resource Manager Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job
Re: VMRMSVM - z/VM Resource Manager
On Monday, 11/02/2009 at 02:15 EST, Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov wrote: BTW, I am not using DIRMAINT or anything like that to administer the Directory I am using DIRECTXA is that considered IBM VM DIRECTOR? No, DIRECTXA and IBM Systems Director (IBM Director) are two different things. IBM Director is a GUI-based multiplatform management application that lives outside of z/VM, but can communicate with it to perform some basic systems programming tasks. Alan Altmark z/VM Development IBM Endicott
Re: VMRMSVM - z/VM Resource Manager
On Sat, Oct 31, 2009 at 1:33 AM, Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov wrote: Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? The MONDCSS size really does not matter. It must be configured large enough to hold full sample configuration data so that you can make sense of the sample data. When the MONDCSS is large enough, the default partitioning will leave enough data for sample configuration. Otherwise you must specify the startup parameters. Once that is done, it should be good enough for all. When the amount of monitor event records is high (seeks enabled, or many virtual machines dropping from queue often) it may be a challenge for a virtual machine to consume the event buffers before they expire. With multiple virtual machines processing the same monitor data, you have more work to be done in a timely manner. If you can't keep up with event buffers, the bottleneck is normally the number of outstanding IUCV msgs rather than the available pages in MONDCSS. This is addressed with the parameters for the monitor rather than the size of the DCSS. If I were looking at VMRM, I would also investigate what happens when the system is so constrained that VMRM does not get the resources to process the sample in time (that happens sometimes when CP has paged out the MONDCSS). It would be interesting to see if VMRM at that time can undo the settings it did before that got z/VM in the thrashing situation... Rob -- Rob van der Heij Velocity Software http://www.velocitysoftware.com/
Re: VMRMSVM - z/VM Resource Manager
Thanks Rob, In Velocity do you interact at all with VMRM in terms of seeing the settings in the CONFIG file and such? Terry Martin Lockheed Martin CITIC Contract z/OS Operating System Support/Performance and Tuning (443) 348-4196 From: The IBM z/VM Operating System on behalf of Rob van der Heij Sent: Sat 10/31/2009 6:01 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager On Sat, Oct 31, 2009 at 1:33 AM, Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov wrote: Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? The MONDCSS size really does not matter. It must be configured large enough to hold full sample configuration data so that you can make sense of the sample data. When the MONDCSS is large enough, the default partitioning will leave enough data for sample configuration. Otherwise you must specify the startup parameters. Once that is done, it should be good enough for all. When the amount of monitor event records is high (seeks enabled, or many virtual machines dropping from queue often) it may be a challenge for a virtual machine to consume the event buffers before they expire. With multiple virtual machines processing the same monitor data, you have more work to be done in a timely manner. If you can't keep up with event buffers, the bottleneck is normally the number of outstanding IUCV msgs rather than the available pages in MONDCSS. This is addressed with the parameters for the monitor rather than the size of the DCSS. If I were looking at VMRM, I would also investigate what happens when the system is so constrained that VMRM does not get the resources to process the sample in time (that happens sometimes when CP has paged out the MONDCSS). It would be interesting to see if VMRM at that time can undo the settings it did before that got z/VM in the thrashing situation... Rob -- Rob van der Heij Velocity Software http://www.velocitysoftware.com/
Re: VMRMSVM - z/VM Resource Manager
On Sat, Oct 31, 2009 at 10:41 PM, Martin, Terry R. (CMS/CTR) (CTR) terry.mar...@cms.hhs.gov wrote: Thanks Rob, In Velocity do you interact at all with VMRM in terms of seeing the settings in the CONFIG file and such? There's no interaction other than that both receive the same monitor data from CP. When ESALPS starts the monitor and does not complain about it, then it should be good for others like VMRM as well. Just make sure you start them a minute after ESASERVE Rob -- Rob van der Heij Velocity Software http://www.velocitysoftware.com/
Re: VMRMSVM - z/VM Resource Manager
Terry, I would ask if you use it AND HAVE VALIDATED RESULTS? I've seen several sites install it during early days when there was no contention. So no problems means it is working? But when there is contention, the question is does it help when there is contention, or does it force servers to abend Martin, Terry R. (CMS/CTR) (CTR) wrote: Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side so I understand the principle behind it but I just wanted to know from those who use it how it is working. Also any specifics on setting it up in terms of what to watch out for etc…. //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 mailto:terry.mar...@cms.hhs.gov// //WFH on Tuesdays and Fridays//
Re: VMRMSVM - z/VM Resource Manager
Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job balancing when it sees all the work not just a small group of machines. 2) Place each of the heavy CPU machines in their own group. VMRM checks the CPU run/wait deltas proportion of all the machines in a group. One heavy CPU machine in a group will cause the group to exceed it's goals. VMRM then starts adjusting the relative shares downward for all the machines in the group, particularly the heavy CPU machine. With some of the Focus runs going for 8 hours or more I saw some relative shares of 1 which was a bit of shock. I found I needed to have 15-20 groups altogether with 10 of those being single machine groups 3) I used the option of being able to dynamically change configurations. I did this to reduce the goals for the Focus processing during the nightly VSE batch work. When the VSE work finishes, I raise the goals again. 4) It's been an iterative process of setting goals and mixing (or separating) machines. 5) I don't normally see much, if any change in the relative share values VMRM sets when the z9 is lightly loaded. Ed Neidhardt Mainline Information Systems, Inc. 770-321-0841 Office ed.neidha...@mainline.com - Original Message - From: Martin, Terry R. (CMS/CTR) (CTR) To: IBMVM@LISTSERV.UARK.EDU Sent: Thursday, October 29, 2009 8:06 PM Subject: VMRMSVM - z/VM Resource Manager Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side so I understand the principle behind it but I just wanted to know from those who use it how it is working. Also any specifics on setting it up in terms of what to watch out for etc.. 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 WFH on Tuesdays and Fridays
Re: VMRMSVM - z/VM Resource Manager
Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 mailto:terry.mar...@cms.hhs.gov WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job balancing when it sees all the work not just a small group of machines. 2) Place each of the heavy CPU machines in their own group. VMRM checks the CPU run/wait deltas proportion of all the machines in a group. One heavy CPU machine in a group will cause the group to exceed it's goals. VMRM then starts adjusting the relative shares downward for all the machines in the group, particularly the heavy CPU machine. With some of the Focus runs going for 8 hours or more I saw some relative shares of 1 which was a bit of shock. I found I needed to have 15-20 groups altogether with 10 of those being single machine groups 3) I used the option of being able to dynamically change configurations. I did this to reduce the goals for the Focus processing during the nightly VSE batch work. When the VSE work finishes, I raise the goals again. 4) It's been an iterative process of setting goals and mixing (or separating) machines. 5) I don't normally see much, if any change in the relative share values VMRM sets when the z9 is lightly loaded. Ed Neidhardt Mainline Information Systems, Inc. 770-321-0841 Office ed.neidha...@mainline.com - Original Message - From: Martin, Terry R. (CMS/CTR) (CTR) mailto:terry.mar...@cms.hhs.gov To: IBMVM@LISTSERV.UARK.EDU Sent: Thursday, October 29, 2009 8:06 PM Subject: VMRMSVM - z/VM Resource Manager Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side so I understand the principle behind it but I just wanted to know from those who use it how it is working. Also any specifics on setting it up in terms of what to watch out for etc 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 WFH on Tuesdays and Fridays
Re: VMRMSVM - z/VM Resource Manager
Ed, I forgot to ask if you are running a performance monitor and if so did VMRM and the monitor play nicely together in terms of the MONDCSS? In other words did you have to adjust either the VMRM or the monitor in terms of the MONDCSS? 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 mailto:terry.mar...@cms.hhs.gov WFH Tuesdays and Fridays From: Martin, Terry R. (CMS/CTR) (CTR) Sent: Friday, October 30, 2009 8:33 PM To: 'Ed Neidhardt'; IBMVM@LISTSERV.UARK.EDU Subject: RE: VMRMSVM - z/VM Resource Manager Thanks Ed. I am not running SFS and I understand that VMRM requires the config file to be under SFS control is this correct? Also the only thing that came on the A disk for the VMRMSVM user was the PROFILE EXEC. I read that there should be a sample config file as well as some other files on the A disk also, is there another place theses file can be found? 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 mailto:terry.mar...@cms.hhs.gov WFH Tuesdays and Fridays From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Ed Neidhardt Sent: Friday, October 30, 2009 12:19 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VMRMSVM - z/VM Resource Manager Terry, I've been using it for around 10 months now at one of my customers and it appears to be doing the job. Their environment experiences huge CPU spikes during it's month end processing (4-6 days of 95-100%, where normally CPU is around 40%). They are using Focus to produce a large number of reports from databases with several million records in each. Before trying VMRMSVM the operators where busy adjusting relative shares during month end to keep the VSE nightly batch cycle from running over, while also trying to keep the Focus machines processing to meet their deadline. We tried various combinations of relative and absolute shares, but were never able to get the right mix to meet everyone's deadlines. The problems were: month end started on different days of the week (each day has it's unique processing), the amount of data being processed varied by hundred's of thousands records, and the mix of Focus runs would change (quarter end, year end, etc) Getting a larger z9 or using capacity on demand (on a monthly basis) were too costly to do, especially with the much lower utilization during the rest of the month. Using VMRMSVM to adjust the relative appears to help because both the VSE and the Focus workloads are getting finished before their deadline. The operators are no longer allowed to adjust the relative shares and I'm not getting calls in the night about VSE or Focus jobs being too slow. I don't profess to fully understand VMRMSVM, but here are some observations I've found while using this: 1) Put all your zVM machines under it's control (there are some exceptions like VMRMSVM, PERFSVM, and there could be others in your case). VMRMSVM appears to do a better job balancing when it sees all the work not just a small group of machines. 2) Place each of the heavy CPU machines in their own group. VMRM checks the CPU run/wait deltas proportion of all the machines in a group. One heavy CPU machine in a group will cause the group to exceed it's goals. VMRM then starts adjusting the relative shares downward for all the machines in the group, particularly the heavy CPU machine. With some of the Focus runs going for 8 hours or more I saw some relative shares of 1 which was a bit of shock. I found I needed to have 15-20 groups altogether with 10 of those being single machine groups 3) I used the option of being able to dynamically change configurations. I did this to reduce the goals for the Focus processing during the nightly VSE batch work. When the VSE work finishes, I raise the goals again. 4) It's been an iterative process of setting goals and mixing (or separating) machines. 5) I don't normally see much, if any change in the relative share values VMRM sets when the z9 is lightly loaded. Ed Neidhardt Mainline Information Systems, Inc. 770-321-0841 Office ed.neidha...@mainline.com - Original Message - From: Martin, Terry R. (CMS/CTR) (CTR) mailto:terry.mar...@cms.hhs.gov To: IBMVM@LISTSERV.UARK.EDU Sent: Thursday, October 29, 2009 8:06 PM Subject: VMRMSVM - z/VM Resource Manager Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side
VMRMSVM - z/VM Resource Manager
Hi, I am looking at implementing VMRM. I was wondering if you use it and if it is working as advertised? I want to mainly use it for managing the priority of my different workloads running in z/Linux. I am familiar with the goal concept from WLM on the z/OS side so I understand the principle behind it but I just wanted to know from those who use it how it is working. Also any specifics on setting it up in terms of what to watch out for etc 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 WFH on Tuesdays and Fridays