Re: RE： LINUX on IFL
On Tue, Apr 13, 2010 at 6:36 AM, Anson yeal_c...@yahoo.com.cn wrote: Below is the part of direct file for this linux: MACH ESA 1 CPU 06 COMMAND DEFINE CPU 06 IFL Forget about that 06 stuff. The CPU numbers here are virtual, and you want to start with 00 After I log on to this guest machine, I got below message: HCPCAM002E Invalid operand - IFL Am I wrong? And how to dedicate the whole IFL to that virtual server as you mentioned? Why would you want to use that IFL purely for this one virtual server. If that's the only one allowed to use it, there's no competition and it basically has exclusive right. When you add more Linux guests, they will share the IFL which is probably what you want. Rob
Re: RE： LINUX on IFL
On Tue, Apr 13, 2010 at 9:03 AM, Anson yeal_c...@yahoo.com.cn wrote: There are many general CPs and one IFL in this zVM LPAR. Many zLinux guests machines running on this zVM. We hope to use this IFL dedicate to one zLinux for performance testing reason while other zLinux guests still share the remaining general CP resource. When those other Linux guests are not defined to use the IFL, they will continue to use the CPs. I don't think we've ever dedicated CPUs for performance measurements. The entire motivation for running Linux on z/VM is to share the resources, so to me measuring the use of dedicated resources is not interesting. The performance monitor can distinguish overhead and virtual machine usage. Rob
Re: RE： LINUX on IFL
On Tue, Apr 13, 2010 at 10:29 AM, Anson yeal_c...@yahoo.com.cn wrote: Do you mean the zLinux running under zVM couldn't be used for performance testing purpose, even we dedicate one CPU to this guest machine? It depends on what you mean with performance testing Some people try to measure maximum throughput of a single server. Though this may seem easy to do, it has little business value for Linux on z/VM. In an environment where resources are shared and servers are utilized only part of the time, measuring maximum throughput does not tell you a lot. 10 virtual machines at 10% utilization behave completely different from one server at 100% utilization. I believe with Linux on z/VM your objective should be the most efficient (cheapest) way to deliver the service within the SLA. Running a single virtual machine at 100% does not provide much insight in this area. From my point of view, I think it's reasonable... We just don't want to create a new LPAR with dedicate CPU. If your ultimate goal is to run Linux in an LPAR with dedicated IFL, then your measurements on z/VM with a dedicated IFL (or shared only with yourself) will be pretty close. But very few run it like that. It's an interesting topic! If you were going to test the application performance on zLinux, what will you do? Install Linux on LPAR directly? We measure resource usage of the virtual machine and divide that by the number of transactions. You do that at different levels of utilization to understand how scalable the application is. You will often find that efficiency gets worse at very high utilization (lock contention, for example) and also often at low utilization (idle load, polling, etc). Rob -- Rob van der Heij Velocity Software http://www.velocitysoftware.com/
Re: RE： LINUX on IFL
On Tue, Apr 13, 2010 at 3:14 PM, Anson yeal_c...@yahoo.com.cn wrote: I agree with you on this measuring maximum throughput. But I think the dedicated CPU makes sense if we want to perform the benchmark compared to distributed platform. And it's also meaningful if we try to perform the stress verification test. Generally, we won't want each test result would be different due to other guest machines' influence. I think dedicate CPU to that Linux can help to eliminate the impact from other guest machines. That's just too simplistic. The single server throughput may be interesting for dedicated hardware where any resources not spent on your application are wasted. Those measurements do not provide any information on how the system would behave with two dozen Linux guests running a real life workload. We measure resource usage of the virtual machine and divide that by the number of transactions. You do that at different levels of utilization to understand how scalable the application is. You will often find that efficiency gets worse at very high utilization (lock contention, for example) and also often at low utilization (idle load, polling, etc). I don't understand how you can know the scalable of the application via this approach. Can you get the accurate application scalability? It's estimated pro rata? Scalability is determined by interpolation (not extrapolation, as some brave souls want us to believe) and understanding the application. When an application is single threaded, adding virtual CPUs does not help. By proper performance measurements, you separate these two questions: - how much resources does the workload need for acceptable response - given resource constraint, how do we ensure the right application goes first There's no such thing as a free lunch. When you share a resource, you may sometimes have to wait for it. Less important work may have to wait more. That's the price you pay for sharing resources, and you can because in real life not everyone needs the resources at the same time. The advantage is that you often can get more resources than what you could afford for your application when it would be dedicated. So you measure resource usage and do capacity planning to ensure that you will be able to deliver the service within the SLA (or otherwise determined acceptable response times). The desire to run a workload as fast as possible does not translate well into business requirements. Rob -- Rob van der Heij Velocity Software http://www.velocitysoftware.com/
Re: RE： LINUX on IFL
You just have one? Then put MACH ESA 1 COMMAND DEFINE CPU 0 TYPE IFL in the directory Marcy From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Anson Sent: Monday, April 12, 2010 9:37 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] RE： LINUX on IFL Marcy, I understand. Thank you! But I encountered a trouble after add COMMAND DEFINE CPU statement in the direct file. Below is the part of direct file for this linux: MACH ESA 1 CPU 06 COMMAND DEFINE CPU 06 IFL After I log on to this guest machine, I got below message: HCPCAM002E Invalid operand - IFL Am I wrong? And how to dedicate the whole IFL to that virtual server as you mentioned? Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 12:25:36 下午 主 题： Re: LINUX on IFL That is the official way to do it (to define a virtual server to run on the IFL(s)). It's just not clear from the doc that you use the COMMAND + the DEFINE instead of some format of the CPU statement as one would expect. The other option as mentioned here is to dedicate the whole IFL to that virtual server.That might also suit your purposes (but then you won't ever be able to run something else on that one too). Marcy From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Anson Sent: Monday, April 12, 2010 9:02 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: [IBMVM] LINUX on IFL Marcy, thanks! Do you mean it's not very clear from IBM doc on how to define the corresponding part in the directory entry and you submitted a reader's comments to IBM? The command you mentioned below is a workaround, right? COMMAND DEFINE CPU XX TYPE IFL. sorry, English is not my first language... Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 11:43:23 上午 主 题： Re: 回复： LINUX on IFL COMMAND DEFINE CPU XX TYPE IFL. In the directory entry Its not very clear from the IBM doc. I submitted a reader's comment and it was accepted. Marcy From: The IBM z/VM Operating System To: IBMVM@LISTSERV.UARK.EDU Sent: Mon Apr 12 22:20:57 2010 Subject: [IBMVM] 回复： LINUX on IFL Marcy, Thanks! How to do in user direct file if I want to permanent let this IFL dedicated to that zLinux? I used q cpu to know the CPU id of IFL. e.g. 03 is IFL. I defined CPU 03 in the linux user direct file. But it seems doesn't work. What else did I miss? Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 11:14:28 上午 主 题： Re: LINUX on IFL Everything will use the cps unless they have issued the DEFINE CPU command. So the answer is yes. Marcy From: The IBM z/VM Operating System To: IBMVM@LISTSERV.UARK.EDU Sent: Mon Apr 12 21:36:17 2010 Subject: [IBMVM] LINUX on IFL Hi All, I have question about Linux on IFL. If there is a zVM LPAR with both CPs and 1 IFL. Is it possible to let one Linux guest to excluded use this IFL and only use this IFL? (We assume this IFL is dedicated on this LPAR) Thanks! Best Regards Anson Y
Re: RE： LINUX on IFL
oh wait, add this too COMMAND SET VCONFIG MODE LINUX Marcy From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Anson Sent: Monday, April 12, 2010 9:37 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] RE： LINUX on IFL Marcy, I understand. Thank you! But I encountered a trouble after add COMMAND DEFINE CPU statement in the direct file. Below is the part of direct file for this linux: MACH ESA 1 CPU 06 COMMAND DEFINE CPU 06 IFL After I log on to this guest machine, I got below message: HCPCAM002E Invalid operand - IFL Am I wrong? And how to dedicate the whole IFL to that virtual server as you mentioned? Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 12:25:36 下午 主 题： Re: LINUX on IFL That is the official way to do it (to define a virtual server to run on the IFL(s)). It's just not clear from the doc that you use the COMMAND + the DEFINE instead of some format of the CPU statement as one would expect. The other option as mentioned here is to dedicate the whole IFL to that virtual server.That might also suit your purposes (but then you won't ever be able to run something else on that one too). Marcy From: The IBM z/VM Operating System [mailto:ib...@listserv.uark.edu] On Behalf Of Anson Sent: Monday, April 12, 2010 9:02 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: [IBMVM] LINUX on IFL Marcy, thanks! Do you mean it's not very clear from IBM doc on how to define the corresponding part in the directory entry and you submitted a reader's comments to IBM? The command you mentioned below is a workaround, right? COMMAND DEFINE CPU XX TYPE IFL. sorry, English is not my first language... Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 11:43:23 上午 主 题： Re: 回复： LINUX on IFL COMMAND DEFINE CPU XX TYPE IFL. In the directory entry Its not very clear from the IBM doc. I submitted a reader's comment and it was accepted. Marcy From: The IBM z/VM Operating System To: IBMVM@LISTSERV.UARK.EDU Sent: Mon Apr 12 22:20:57 2010 Subject: [IBMVM] 回复： LINUX on IFL Marcy, Thanks! How to do in user direct file if I want to permanent let this IFL dedicated to that zLinux? I used q cpu to know the CPU id of IFL. e.g. 03 is IFL. I defined CPU 03 in the linux user direct file. But it seems doesn't work. What else did I miss? Best Regards Anson Y 发件人： Marcy Cortes marcy.d.cor...@wellsfargo.com 收件人： IBMVM@LISTSERV.UARK.EDU 发送日期： 2010/4/13 (周二) 11:14:28 上午 主 题： Re: LINUX on IFL Everything will use the cps unless they have issued the DEFINE CPU command. So the answer is yes. Marcy From: The IBM z/VM Operating System To: IBMVM@LISTSERV.UARK.EDU Sent: Mon Apr 12 21:36:17 2010 Subject: [IBMVM] LINUX on IFL Hi All, I have question about Linux on IFL. If there is a zVM LPAR with both CPs and 1 IFL. Is it possible to let one Linux guest to excluded use this IFL and only use this IFL? (We assume this IFL is dedicated on this LPAR) Thanks! Best Regards Anson Y
