Re: Value added by z/VM versus VMWARE
On Tue, 4 Nov 2008 15:57:12 -0600, Alan Ackerman <[EMAIL PROTECTED] .NET> wrote: >Don Cox of IBM sent me this one: > >IBM System z: The Ultimate Virtualization Platform >The future runs on System z > >Reed A. Mullen >[EMAIL PROTECTED] >IBM Systems and Technology Group > >Is that the Reed Mullen presentation you are talking about? > >Alan Ackerman >Alan (dot) Ackerman (at) Bank of America (dot) com > = == = I read this. Great job, Reed! It really does a good job of outlining the value added of z/VM + System z. As several others pointed out, you cannot separate the combinat ion of z/VM and System z. Nor do you need to. VMWARE runs on Intel, and z/VM runs on System z, s o you do not need to separate them. z/VM and System z grew up together, after all. Thanks for all the good ideas. (Keep those cards and letters coming!) It only has a small amount of information about VMWARE and (many) other v irtualization technologies, though. Certainly more than I knew, but not as much as I th ink I am going to need to know. Are there other references people can recommend on VMWARE? Thanks! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
I don't think so Gary. Look at the pure cost of processing resources. A typical IFL today has what, 500 or so MIPs at a miniumum? That isn't going to emulate a typical bloated X86 system all that fast, even given the processing map within virtual machines. At least in general, it is difficult and expensive to match the pure processing power of modern x86 systems, even on modern mainframes. Also, I have doubts that z/VM would do a much better job virtualizing x86 machines than VMWare does. The x86 architechture is just - wierd. :) -Paul On Nov 4, 2008, at 11:58 AM, Gary M. Dennis wrote: If z/VM supported virtual x86 systems, that support would make the platforms extremely competitive and, potentially, cause a sea change in the source of computing resource for x86. Considering the average CPU utilization for x86 desktop systems (less than 15% by some estimates), such support could make for a good match; guest systems that do practically nothing and a virtualization system with a remarkable ability to allocate resources among a large number of guests. On 11/2/08 2:12 PM, "Paul Raulerson" <[EMAIL PROTECTED]> wrote: That's what confuses me- the two platforms, mainframe and x86 are hardly competitive to each other. --. .- .-. -.-- Gary Dennis
Re: Value added by z/VM versus VMWARE
On Sat, 1 Nov 2008 13:25:01 +0100, Rob van der Heij <[EMAIL PROTECTED]> wrote: >On Sat, Nov 1, 2008 at 7:26 AM, Alan Ackerman ><[EMAIL PROTECTED]> wrote: > >> Ideas on what value z/VM adds would be appreciated! > >Starting point should be the presentations that Reed Mullen does at >various events on the value of z/VM for running Linux workloads, and >the comparison between z/VM and other virtualization options. Those >presentations work both ways to explain technology of the other >platform. Don Cox of IBM sent me this one: IBM System z: The Ultimate Virtualization Platform The future runs on System z Reed A. Mullen [EMAIL PROTECTED] IBM Systems and Technology Group Is that the Reed Mullen presentation you are talking about? Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
On Sat, 1 Nov 2008 01:26:06 -0500, Alan Ackerman <[EMAIL PROTECTED]> wrote: >Another question from the same architecture person. What is the value ad ded by z/VM over >VMWARE for a Linux workload? (That's my wording, not his.) > >As usual, I don't know anything about what VMWARE can or cannot do. I'm sure it can run fewer >guests than VM, but not how many. VM has shared DASD and DCSSes and NSSe s, but most Linux >people don't see the value of those things -- disks are cheap and come w ith the PC, memory is >cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli >products to tie them together, report performance, provide high availability, etc. > >I think the advantage on the mainframe is economy of scale. But how do y ou measure that? > >At present, you can save money on software and peripherals enough to cost-justify the >mainframe. Reduced people costs are hard to quantify and scare the heck out of the midrange >folks. > >But I wonder how long those software prices will last? Red Hat charges $18,000 per IFL for 7x24 >support. (I found that on a web site, and I asked our Red Hat representative to make sure.) I >couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per >engine for the mainframe. > >He specifically mentioned the ability to pick up a Linux guest running under VMWARE and moving >it to another box running VMWARE. So far VM cannot do that. That's VMOTION. We haven't looked at it, but from the little I've read about it, it has some serious restrictions. (I don't remember them all, b ut I believe one was the configuration of the host boxes had to be very similar, and there are distance limitations) If you can live with those restrictions, it works well, though I think there are edge cases with the transaction being processed during the migration. > >Ideas on what value z/VM adds would be appreciated! VMWare also doesn't support 802.1q VLAN tagging. ie VSWITCHes., which me ans less ability to separate different servers for performance or security re asons. /ahw > >Alan Ackerman >Alan (dot) Ackerman (at) Bank of America (dot) com > = ===
Re: Value added by z/VM versus VMWARE
On Tue, 4 Nov 2008, Dean, David (I/S) wrote: > Why would anyone want to take a cherry pie and spread crap on top? > > No offense intended. > > David Dean > Information Systems > *bcbstauthorized* Hum, that parses strangely because we normally say that software "runs on top" of hardware. So the cherry pie is Intel and the crap is z/VM? . One thing that I've always been intrigued by would be something my manager said that IBM actually has. A "frame" into which one could slide a "processor" card. Said "card" could contain a i, p, x, or z processor. The cards would be able to communicate across the backplane (ala hipersockets?). Having such a thing, eEspecially if there were "control" software which could direct execution to a specific "node" (so that a z program could invoke an x program) might be interesting. IMO, the newest Intel chips (CPUs) are fairly nice. Still not as "elegant" or reliable as the z. But reliability costs money and z reliability (at least around here) is becoming "too expensive". Once again "good enough" is destroying "excellent". -- Q: What do theoretical physicists drink beer from? A: Ein Stein. Maranatha! John McKown
Re: Value added by z/VM versus VMWARE
Why would anyone want to take a cherry pie and spread crap on top? No offense intended. David Dean Information Systems *bcbstauthorized* -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Gary M. Dennis Sent: Tuesday, November 04, 2008 12:59 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Value added by z/VM versus VMWARE If z/VM supported virtual x86 systems, that support would make the platforms extremely competitive and, potentially, cause a sea change in the source of computing resource for x86. Considering the average CPU utilization for x86 desktop systems (less than 15% by some estimates), such support could make for a good match; guest systems that do practically nothing and a virtualization system with a remarkable ability to allocate resources among a large number of guests. On 11/2/08 2:12 PM, "Paul Raulerson" <[EMAIL PROTECTED]> wrote: > That's what > confuses me- the two platforms, mainframe and x86 are hardly > competitive to each other. --. .- .-. -.-- Gary Dennis Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Value added by z/VM versus VMWARE
If z/VM supported virtual x86 systems, that support would make the platforms extremely competitive and, potentially, cause a sea change in the source of computing resource for x86. Considering the average CPU utilization for x86 desktop systems (less than 15% by some estimates), such support could make for a good match; guest systems that do practically nothing and a virtualization system with a remarkable ability to allocate resources among a large number of guests. On 11/2/08 2:12 PM, "Paul Raulerson" <[EMAIL PROTECTED]> wrote: > That's what > confuses me- the two platforms, mainframe and x86 are hardly > competitive to each other. --. .- .-. -.-- Gary Dennis
Re: Value added by z/VM versus VMWARE
Sure- and it does a good job doing that too. On Intel x86. That's what confuses me- the two platforms, mainframe and x86 are hardly competitive to each other. Or perhaps they are in some minds. But something sure had to go down twisted to get that kind of comparison running again. :) -Paul On Nov 2, 2008, at 9:39 AM, Nick Laflamme wrote: On Nov 1, 2008, at 9:58 PM, Paul Raulerson wrote: I am very confused indeed by this whole conversation -VMWARE and z/ VM solve different solutions. And they are both extraordinarily good at what they do. IBM is positioning z/VM as a platform for virtualization, for hosting Linux applications and for other guest OSes. Which, from what I hear, is how VMWARE is being positioned. Bring together those light applications, those occasionally used Linux daemons. This reminds me of personal computer market space twenty-five to thirty years ago: people bought Apple ][s because it had Visicalc. Then Lotus 1-2-3 sold a few IBM PCs. Applications sold hardware. Both z/VM and VMWARE are selling virtualization for Linux applications. Are shops going to invest in Z platform or in WinTel platform to support Linux application virtualization? All of us can point to things either platform doesn't support, but to some managers, the question is regrettably simple: "OK, where do we put the next applications that can be virtualized?"
Re: Value added by z/VM versus VMWARE
I'm not even sure how they would wind up on a comparison, but roughly, if you need high I/O or transactional capabilty -- use z/VM. If you need a whale of a lot of CPU processing, use Intel. On Nov 2, 2008, at 9:34 AM, Barton Robinson wrote: Exactly, but the issue is to explain this to peter principal IT managers. Paul Raulerson wrote: I am very confused indeed by this whole conversation -VMWARE and z/ VM solve different solutions. And they are both extraordinarily good at what they do. Just at the 10,000 foot level, VMWARE is designed to virtualize PC hardware and z/VM virtualizes mainframe hardware. Dismissing this as just "two different hardware platforms" is rather disingenuous, though admittedly, it is a "true" statement. Then again, a nuclear powered aircraft carrier and diesel powered megaton oil tanker are both ships - just "two different hardware platforms." They hardly operate in the same realms though. Where everything starts to get different is the underlying hardware. And at that level, it gets very VERY different indeed. In some ways, VMWARE is more like an LPAR than a VM guest instance, but that difference is driven more by the hardware capabilities than by the design. -Paul On Nov 1, 2008, at 6:34 PM, Barton Robinson wrote: One thing that really bothers me about VMWARE. When I ask about performance to the people that measure, they tell me the VMWARE contract specifically states they are not allowed to talk about it's performance. A vendor that won't let people talk about performance must be very afraid details will be made public and don't really need to invest in improving it's performance. Since we can not provide facts to confuse management, it comes down to religion or companies providing their own facts. A professor from I think Stutgaart presented last year at the GSE/ IBM meeting pretty convincingly that VMWARE was about 20 years behind z/VM in almost any "fair" technological aspect you wish to evaluate. And I think he was wrong - I don't see sharing of resources in VMWARE even what z/VM had 20 years ago. VMWARE is much more like LPAR, so any argument you can use for z/VM vs LPAR works as well. I believe VMWARE is great for desktops where users may want to run applications that only run on different versions of windows or Linux. Now there is a company in California that is even virtualizing the desktops, give end users a small appliance, keyboard and monitor, and the software runs on a "virtualized PC", where all software runs on the central "virtualized PC" that then supports multiple users. They save a lot of money by only having one copy of MS Office to support multiple end users. (Does this sound like 3270 and mainframes to anyone else?) Alan Ackerman wrote: Another question from the same architecture person. What is the value add ed by z/VM over VMWARE for a Linux workload? (That's my wording, not his.) As usual, I don't know anything about what VMWARE can or cannot do. I'm s ure it can run fewer guests than VM, but not how many. VM has shared DASD and DCSSes and NSSes , but most Linux people don't see the value of those things -- disks are cheap and come wi th the PC, memory is cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli products to tie them together, report performance, provide high availabil ity, etc. I think the advantage on the mainframe is economy of scale. But how do yo u measure that? At present, you can save money on software and peripherals enough to cost -justify the mainframe. Reduced people costs are hard to quantify and scare the heck o ut of the midrange folks. But I wonder how long those software prices will last? Red Hat charges $1 8,000 per IFL for 7x24 support. (I found that on a web site, and I asked our Red Hat representat ive to make sure.) I couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per engine for the mainframe. He specifically mentioned the ability to pick up a Linux guest running un der VMWARE and moving it to another box running VMWARE. So far VM cannot do that. Ideas on what value z/VM adds would be appreciated! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
On Nov 1, 2008, at 9:58 PM, Paul Raulerson wrote: I am very confused indeed by this whole conversation -VMWARE and z/ VM solve different solutions. And they are both extraordinarily good at what they do. IBM is positioning z/VM as a platform for virtualization, for hosting Linux applications and for other guest OSes. Which, from what I hear, is how VMWARE is being positioned. Bring together those light applications, those occasionally used Linux daemons. This reminds me of personal computer market space twenty-five to thirty years ago: people bought Apple ][s because it had Visicalc. Then Lotus 1-2-3 sold a few IBM PCs. Applications sold hardware. Both z/VM and VMWARE are selling virtualization for Linux applications. Are shops going to invest in Z platform or in WinTel platform to support Linux application virtualization? All of us can point to things either platform doesn't support, but to some managers, the question is regrettably simple: "OK, where do we put the next applications that can be virtualized?"
Re: Value added by z/VM versus VMWARE
Exactly, but the issue is to explain this to peter principal IT managers. Paul Raulerson wrote: I am very confused indeed by this whole conversation -VMWARE and z/VM solve different solutions. And they are both extraordinarily good at what they do. Just at the 10,000 foot level, VMWARE is designed to virtualize PC hardware and z/VM virtualizes mainframe hardware. Dismissing this as just "two different hardware platforms" is rather disingenuous, though admittedly, it is a "true" statement. Then again, a nuclear powered aircraft carrier and diesel powered megaton oil tanker are both ships - just "two different hardware platforms." They hardly operate in the same realms though. Where everything starts to get different is the underlying hardware. And at that level, it gets very VERY different indeed. In some ways, VMWARE is more like an LPAR than a VM guest instance, but that difference is driven more by the hardware capabilities than by the design. -Paul On Nov 1, 2008, at 6:34 PM, Barton Robinson wrote: One thing that really bothers me about VMWARE. When I ask about performance to the people that measure, they tell me the VMWARE contract specifically states they are not allowed to talk about it's performance. A vendor that won't let people talk about performance must be very afraid details will be made public and don't really need to invest in improving it's performance. Since we can not provide facts to confuse management, it comes down to religion or companies providing their own facts. A professor from I think Stutgaart presented last year at the GSE/ IBM meeting pretty convincingly that VMWARE was about 20 years behind z/VM in almost any "fair" technological aspect you wish to evaluate. And I think he was wrong - I don't see sharing of resources in VMWARE even what z/VM had 20 years ago. VMWARE is much more like LPAR, so any argument you can use for z/VM vs LPAR works as well. I believe VMWARE is great for desktops where users may want to run applications that only run on different versions of windows or Linux. Now there is a company in California that is even virtualizing the desktops, give end users a small appliance, keyboard and monitor, and the software runs on a "virtualized PC", where all software runs on the central "virtualized PC" that then supports multiple users. They save a lot of money by only having one copy of MS Office to support multiple end users. (Does this sound like 3270 and mainframes to anyone else?) Alan Ackerman wrote: Another question from the same architecture person. What is the value add ed by z/VM over VMWARE for a Linux workload? (That's my wording, not his.) As usual, I don't know anything about what VMWARE can or cannot do. I'm s ure it can run fewer guests than VM, but not how many. VM has shared DASD and DCSSes and NSSes , but most Linux people don't see the value of those things -- disks are cheap and come wi th the PC, memory is cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli products to tie them together, report performance, provide high availabil ity, etc. I think the advantage on the mainframe is economy of scale. But how do yo u measure that? At present, you can save money on software and peripherals enough to cost -justify the mainframe. Reduced people costs are hard to quantify and scare the heck o ut of the midrange folks. But I wonder how long those software prices will last? Red Hat charges $1 8,000 per IFL for 7x24 support. (I found that on a web site, and I asked our Red Hat representat ive to make sure.) I couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per engine for the mainframe. He specifically mentioned the ability to pick up a Linux guest running un der VMWARE and moving it to another box running VMWARE. So far VM cannot do that. Ideas on what value z/VM adds would be appreciated! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
I am very confused indeed by this whole conversation -VMWARE and z/VM solve different solutions. And they are both extraordinarily good at what they do. Just at the 10,000 foot level, VMWARE is designed to virtualize PC hardware and z/VM virtualizes mainframe hardware. Dismissing this as just "two different hardware platforms" is rather disingenuous, though admittedly, it is a "true" statement. Then again, a nuclear powered aircraft carrier and diesel powered megaton oil tanker are both ships - just "two different hardware platforms." They hardly operate in the same realms though. Where everything starts to get different is the underlying hardware. And at that level, it gets very VERY different indeed. In some ways, VMWARE is more like an LPAR than a VM guest instance, but that difference is driven more by the hardware capabilities than by the design. -Paul On Nov 1, 2008, at 6:34 PM, Barton Robinson wrote: One thing that really bothers me about VMWARE. When I ask about performance to the people that measure, they tell me the VMWARE contract specifically states they are not allowed to talk about it's performance. A vendor that won't let people talk about performance must be very afraid details will be made public and don't really need to invest in improving it's performance. Since we can not provide facts to confuse management, it comes down to religion or companies providing their own facts. A professor from I think Stutgaart presented last year at the GSE/ IBM meeting pretty convincingly that VMWARE was about 20 years behind z/VM in almost any "fair" technological aspect you wish to evaluate. And I think he was wrong - I don't see sharing of resources in VMWARE even what z/VM had 20 years ago. VMWARE is much more like LPAR, so any argument you can use for z/VM vs LPAR works as well. I believe VMWARE is great for desktops where users may want to run applications that only run on different versions of windows or Linux. Now there is a company in California that is even virtualizing the desktops, give end users a small appliance, keyboard and monitor, and the software runs on a "virtualized PC", where all software runs on the central "virtualized PC" that then supports multiple users. They save a lot of money by only having one copy of MS Office to support multiple end users. (Does this sound like 3270 and mainframes to anyone else?) Alan Ackerman wrote: Another question from the same architecture person. What is the value add ed by z/VM over VMWARE for a Linux workload? (That's my wording, not his.) As usual, I don't know anything about what VMWARE can or cannot do. I'm s ure it can run fewer guests than VM, but not how many. VM has shared DASD and DCSSes and NSSes , but most Linux people don't see the value of those things -- disks are cheap and come wi th the PC, memory is cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli products to tie them together, report performance, provide high availabil ity, etc. I think the advantage on the mainframe is economy of scale. But how do yo u measure that? At present, you can save money on software and peripherals enough to cost -justify the mainframe. Reduced people costs are hard to quantify and scare the heck o ut of the midrange folks. But I wonder how long those software prices will last? Red Hat charges $1 8,000 per IFL for 7x24 support. (I found that on a web site, and I asked our Red Hat representat ive to make sure.) I couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per engine for the mainframe. He specifically mentioned the ability to pick up a Linux guest running un der VMWARE and moving it to another box running VMWARE. So far VM cannot do that. Ideas on what value z/VM adds would be appreciated! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
> -Original Message- > From: The IBM z/VM Operating System > [mailto:[EMAIL PROTECTED] On Behalf Of Barton Robinson > Sent: 01 November 2008 23:34 > To: IBMVM@LISTSERV.UARK.EDU > Subject: Re: Value added by z/VM versus VMWARE > > > One thing that really bothers me about VMWARE. When I ask > about performance to the people > that measure, they tell me the VMWARE contract specifically > states they are not allowed to > talk about it's performance. A vendor that won't let people > talk about performance must > be very afraid details will be made public and don't really > need to invest in improving > it's performance. Since we can not provide facts to confuse > management, it comes down to > religion or companies providing their own facts. > > A professor from I think Stutgaart presented last year at the > GSE/IBM meeting pretty > convincingly that VMWARE was about 20 years behind z/VM in > almost any "fair" technological > aspect you wish to evaluate. And I think he was wrong - I > don't see sharing of resources > in VMWARE even what z/VM had 20 years ago. VMWARE is much > more like LPAR, so any argument > you can use for z/VM vs LPAR works as well. > > I believe VMWARE is great for desktops where users may want > to run applications that only > run on different versions of windows or Linux. Now there is > a company in California that > is even virtualizing the desktops, give end users a small > appliance, keyboard and monitor, > and the software runs on a "virtualized PC", where all > software runs on the central > "virtualized PC" that then supports multiple users. They > save a lot of money by only > having one copy of MS Office to support multiple end users. > (Does this sound like 3270 > and mainframes to anyone else?) > Firstly if you have multiple access software like Citrix where several users share the same copy of word, in general you need a license for each user. Its generally only one per concurrent user , but its still one per user. In fact the cost of licenses make Citrix some what expensive. You can buy a new IBM desktop PC, including a VISTA license (without monitor) for around a 1/3 more than a Citrix license. Given the cost of the citrix server the saving in capital is minimal. Of course you save in other costs, but when one of the Citrix boxes goes crank it hits many more users. Also Citrix does not cope well with demanding applications such AutoCad... In the VMWARE deployments we are looking at performance is is not a key factor. We have a large number of "small" servers that have a high waste factor. So typically these days each server will contain 2x72 gig drives (these are the smallest IBM will sell us) a 4 core CPU and 4 gigs of RAM. The server will be under used, but it will be kept serarate perhaps because the vendor product requires a specific version of JAVA, TOMCAT, Apache, MySQL or ORACLE, or for securty and audit. e.g. to limit access to a particular external supplier. Even if you can put four of these servers on a single VMWARE box then you have a significant reduction in waste, and VMWARE will allow you to migrate this workload without even letting the apps guys know what you are doing. Note zVM isn't currently an Option as we are firmly MS Windows, and as small VM/VSE site who has been neglected for years by IBM Mainframe folks turning this around would be hard. I guess if we invest seriusly in VMWARE it will by the IBM x Series supply chain that will be hit. > > > Alan Ackerman wrote: > > > Another question from the same architecture person. What is > the value > > add ed by z/VM over VMWARE for a Linux workload? (That's my > wording, > > not his.) > > > > As usual, I don't know anything about what VMWARE can or cannot do. > > I'm s ure it can run fewer guests than VM, but not how many. VM has > > shared DASD and DCSSes and NSSes , but most Linux > > people don't see the value of those things -- disks are > cheap and come wi > > th the PC, memory is > > cheap, etc. VM has automation capabilities, but Linux has > those too, and > > IBM sells all those Tivoli > > products to tie them together, report performance, provide > high availabil > > ity, etc. > > > > I think the advantage on the mainframe is economy of scale. > But how do > > yo u measure that? > > > > At present, you can save money on software and peripherals > enough to > > cost -justify the mainframe. Reduced people costs are hard > to quantify > > and scare the heck o ut of the midrange > > folks. > > > > But I wonder how long thos
Re: Value added by z/VM versus VMWARE
One thing that really bothers me about VMWARE. When I ask about performance to the people that measure, they tell me the VMWARE contract specifically states they are not allowed to talk about it's performance. A vendor that won't let people talk about performance must be very afraid details will be made public and don't really need to invest in improving it's performance. Since we can not provide facts to confuse management, it comes down to religion or companies providing their own facts. A professor from I think Stutgaart presented last year at the GSE/IBM meeting pretty convincingly that VMWARE was about 20 years behind z/VM in almost any "fair" technological aspect you wish to evaluate. And I think he was wrong - I don't see sharing of resources in VMWARE even what z/VM had 20 years ago. VMWARE is much more like LPAR, so any argument you can use for z/VM vs LPAR works as well. I believe VMWARE is great for desktops where users may want to run applications that only run on different versions of windows or Linux. Now there is a company in California that is even virtualizing the desktops, give end users a small appliance, keyboard and monitor, and the software runs on a "virtualized PC", where all software runs on the central "virtualized PC" that then supports multiple users. They save a lot of money by only having one copy of MS Office to support multiple end users. (Does this sound like 3270 and mainframes to anyone else?) Alan Ackerman wrote: Another question from the same architecture person. What is the value add ed by z/VM over VMWARE for a Linux workload? (That's my wording, not his.) As usual, I don't know anything about what VMWARE can or cannot do. I'm s ure it can run fewer guests than VM, but not how many. VM has shared DASD and DCSSes and NSSes , but most Linux people don't see the value of those things -- disks are cheap and come wi th the PC, memory is cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli products to tie them together, report performance, provide high availabil ity, etc. I think the advantage on the mainframe is economy of scale. But how do yo u measure that? At present, you can save money on software and peripherals enough to cost -justify the mainframe. Reduced people costs are hard to quantify and scare the heck o ut of the midrange folks. But I wonder how long those software prices will last? Red Hat charges $1 8,000 per IFL for 7x24 support. (I found that on a web site, and I asked our Red Hat representat ive to make sure.) I couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per engine for the mainframe. He specifically mentioned the ability to pick up a Linux guest running un der VMWARE and moving it to another box running VMWARE. So far VM cannot do that. Ideas on what value z/VM adds would be appreciated! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
Re: Value added by z/VM versus VMWARE
Alan -- What Rob said. (Which I know that you know, but which bears repeating and deserves to be heard by your architect.) Don't make out like z/VM is a silver bullet, but be clear that z/VM is a powerful weapon in his arsenal. Also: I like to draw illustrations from other platforms. Even the most die-hard PC person recognizes that "embedded systems" are NOT THE SAME as desktops machines and xSeries servers. We've been doing "embedded systems" on VM for several decades: RSCS, VTAM, TCP/IP. Do you have any Visara systems? They are probably running embedded Linux and they don't work like PC Linux. Make a point to FIND someone at your shop who has a Linux based hand-held. (I myself flashed QPE Linux onto an iPAQ twice and would be using that device today had it not developed unrelated hardware problems (things like a worn out power button, etc).) See the web site http://www.handhelds.org/ for more information. Heck, anyone with satellite television at home is likely to find Linux under the covers of the receiver (if they are inclined to look). Linux on z/VM is "more normal" than the three examples I have cited. But z/VM brings added value in that DCSS, NSS, shared disk, VSwitch, and the rest of our bag-o-tricks are vital when you scale up the number of virtual penguins. DCSS is operationally just like CD-ROM. NSS is very much like a Linux kernel on a hand-held. You could do shared disk in SAN land. And VSwitch is ... shucks ... just an approximation of network switches "they" already are familiar with. None of this is foreign except that it is harder to achieve in a PC-only shop. I hope this helps. -- Rick; <><
Re: Value added by z/VM versus VMWARE
On Sat, Nov 1, 2008 at 7:26 AM, Alan Ackerman <[EMAIL PROTECTED]> wrote: > Ideas on what value z/VM adds would be appreciated! Starting point should be the presentations that Reed Mullen does at various events on the value of z/VM for running Linux workloads, and the comparison between z/VM and other virtualization options. Those presentations work both ways to explain technology of the other platform. When I explained System z virtualization to a PC-minded audience (http://www.rvdheij.nl/Presentations/nluug-2007.pdf) several people afterwards confirmed that learning about System z and z/VM made them understand why they did not make progress with VMware and Xen as fast as anticipated. Some people claim their hardware is so cheap you don't have to share it like we do on the mainframe. But when you look further you find that the cost of an extra box is not just the hardware but way more. At some point it does make sense to share, even when shareable hardware may be a bit more expensive. The cost of some infrastructure components grows faster that the number of discrete boxes (i.e. explodes). This is why the scale of virtualization makes a big difference (whether you have 4 or 400 servers in a box). z/VM provides a "virtual raised floor" that replaces handling of physical components by software. Such a configuration can be managed easier, and in many cases automated to reduce cost and improve quality. Maturity of System z and z/VM frees you from a lot of low-level issues, solutions like VMware at best replace them by different issues that are hoped to be easier to manage. Rob
Value added by z/VM versus VMWARE
Another question from the same architecture person. What is the value add ed by z/VM over VMWARE for a Linux workload? (That's my wording, not his.) As usual, I don't know anything about what VMWARE can or cannot do. I'm s ure it can run fewer guests than VM, but not how many. VM has shared DASD and DCSSes and NSSes , but most Linux people don't see the value of those things -- disks are cheap and come wi th the PC, memory is cheap, etc. VM has automation capabilities, but Linux has those too, and IBM sells all those Tivoli products to tie them together, report performance, provide high availabil ity, etc. I think the advantage on the mainframe is economy of scale. But how do yo u measure that? At present, you can save money on software and peripherals enough to cost -justify the mainframe. Reduced people costs are hard to quantify and scare the heck o ut of the midrange folks. But I wonder how long those software prices will last? Red Hat charges $1 8,000 per IFL for 7x24 support. (I found that on a web site, and I asked our Red Hat representat ive to make sure.) I couldn't find any prices on Novel SuSEs web site. We have other software with higher prices per engine for the mainframe. He specifically mentioned the ability to pick up a Linux guest running un der VMWARE and moving it to another box running VMWARE. So far VM cannot do that. Ideas on what value z/VM adds would be appreciated! Alan Ackerman Alan (dot) Ackerman (at) Bank of America (dot) com
