Sun Bashes Linux on (IBM) Mainframes 519
dagbrown writes: "An article linked from Sun's front page, entitled
"Linux on the mainframe: Not a good idea" by Shahin Khan, Sun's chief competitive officer, has the interesting theory that Linux on mainframes makes no sense because, among other things, the VM/Linux combo isn't a very good match. What do the folks on Slashdot think?"
It makes sense... (Score:2, Funny)
this isnt about linux its about IBMs success (Score:2, Insightful)
Maybe not, (Score:2, Informative)
Sun is not Linux's friend (Score:3, Insightful)
Besides, Sun will attack IBM at any chance it gets.
Re:Sun is not Linux's friend (Score:3, Insightful)
In other words, FUD is bad, even if it's pro-Linux or pro-BSD. Embrace and Extend into open source is debatable. Closed source isn't so much the enemy, imo, as the crap that a few companies have pulled with it.
--
Evan
Re:Sun is not Linux's friend (Score:5, Insightful)
Well, I've come to the realization that Linux is not a threat to Sun. Instead, companies like Dell, HP, Compaq, and IBM are the real competition. What's the catch? They all compete on hardware implementations. They compete on prices and features. Would I still buy a Sun server with Linux? Yes, for the same reasons I prefer Sun servers with Solaris: the hardware has benefits beyond whatever OS happens to be running.
Is Sun good for Linux? Yes, because Sun can provide an absolutely top-notch hardware platform on which to run Linux. All Linux needs are some hardware RAS support features and device drivers, which Sun is probably capable of providing, and better C-compilers for RISC architectures, which could be improvements to GCC or a port of Forte C to Linux.
It is not Sun vs. Linux. I'm convinced of that. Rather, the Linux community should be asking "What can Sun do for us?" rather than "What does Sun have up its sleeve?" These same questions should be applied to all the first-class hardware vendors. The more hardware that Linux runs well on, the better it gets for Linux. It's win-win.
What about Microsoft? Well, that's another war on another front over different principles. Sun is an ally in this war, unambiguously.
Re:Sun is not Linux's friend (Score:2)
I disagree (Score:4, Interesting)
Running Linux on an IBM mainframe doesn't defeat the entire purpose of using open standards like Linux. You still get the man years of free testing, free software, interoperability, and speed. Or rather, IBM gets them. And by tying software you can't charge for to hardware you can, IBM will have come up with a business model for selling Linux systems for incredible sums of money. Quite an ingenious plan - selling Free Software.
Sun's just pissed they didn't think of it first.
Re:I disagree (Score:3, Interesting)
I am pretty sure, whatever kernel IBM chooses to use on their linux mainframes will be THOROUGHLY tested and rigerously tortured and beaten to death until they know exactly how it's going to act. There will probably be a guideline to read for do-it-yourself people on how to make the most stable kernel for the mainframe you have.
Running linux on the mainframe has TONS of advantages, and they will become more pronounced as it gets more popular and more used.
Sun, give me a break, we know you have a big mouth but scaring everyone doesn't work all the time.
Re:I disagree (Score:4, Informative)
The other thing that seems to have improved AIX 4.3.3 a lot is the benchmarking. Dueling with Sun isn't a bad thing all the time. AIX 4.3.3, with the latest patches applied, has an excellent, capable, and very tunable TCP stack. It has also had a number of features backported to it from AIX 5.1. AIX 5L 5.1 has a lot more of the cool TCP features in it, and is even with Solaris 8 in those regards.
In the past, compiling has seriously sucked under AIX. However, the IBM VisualAge C++ compilers for AIX are cool. They will compile just about anything, and if you cannot compile it then the programmer should probably go back and adhere to the various C/C++ standards. Generally I have the same trouble compiling certain software under either Solaris or AIX. Sometimes I even break down and install the GNU compiler collection...
Right now, IBM has two machines that support virtual machines, or in mainframe/IBM terminology, logical partitions (LPARS). LPARs are supported in hardware on the pSeries 690 running AIX, and on IBM zSeries running z/OS or z/VM. LPARs are hardware-based, and if a processor, memory chip, or other system component dies it is able to prolong an outage by deallocating it. Currently AIX is not able to dynamically add resources to an LPAR without rebooting the LPAR, but that is coming. Otherwise, LPARs are totally independent instances of the OS. And the reboot to add resources takes an LPAR about thirty seconds (yes, 30). The LPARs do share a few things, like the system clock, and a management workstation for console access, but they are isolated in hardware.
On the pSeries 690, the boundaries of the LPARs are 1 processor/1 GB memory. So you have to allocate whole processors and whole gigabytes of RAM to an LPAR. While this sounds like it's not such a great idea (and it isn't the best), it's okay. Any more granularity can be handled by the built-in AIX Workload Manager, which is able to manage OS-level resources like memory, processor time, disk I/Os, etc. in percentages based on users, groups, and process names. That isn't something Sun has, and often you don't need partitions on a machine, but instead just need to keep two pieces of software from fighting for resources (or need to cap a group of users to low memory or low CPU usage). Workload Manager is very handy in that regard. The IBM mainframes running z/OS or MVS can do timeslicing, where an LPAR can have 10% of all of the CPU time on the box, or 5% of RAM, etc. You can also create situations where you overcommit the resources on the machine but define priorities, to guarantee levels of service. So maybe you have three LPARs, and one can have up to 80% of the CPU if it's busy, and the other two can have up to 30% of the CPU, but LPAR 1 has priority (so it gets its 80% anytime it needs it). This is where the pSeries 690 is going, it just isn't there yet (IBM took all the guys that made MVS capable of this stuff and pointed them at AIX).
I really know nothing about Sun's Dynamic System Domains. I do know it is similar in certain ways to the concept of LPARs, but isn't as flexible as the MVS/mainframe LPAR scheme. The OS instances are still isolated from each other in hardware. The two are probably nearly even when it comes down to it.
If you consider the hardware these things run on you will see that a pSeries 690 with 32 CPUs equals a Sun Starfire with 72 CPUs. What IBM is doing in this regard is cool -- they are actively attempting to put fewer components into a machine. More components == more likelihood of failure, and therefore you need more redundant components. More components == more heat, which leads to more failures. It also means more electricity for more components. You can also cluster the big machines using a derivative of the IBM SP2 technology (you can also cluster smaller ones, like pSeries 660s, which are a hell of a deal, price/performance-wise). So while Sun's machines can go to 72 CPUs, all you get are extra components and extra heat (and extra service calls)
IBM has been working with Red Hat for a while now. In fact, when Linux was ported to the S/390, there were two ports. I forget who the individual was that did one of the ports, but IBM had a team that did the other. There is an S/390 distribution of Red Hat Linux -- check any mirror site that is worthy (many don't carry it). It generally lags behind the i386 distribution, but only by a few weeks. Considering the market, hey, that's not bad at all. And IBM is doing a lot of work on Linux itself, from porting JFS to it, to adding a lot of what makes AIX a very scalable, very stable, very reliable OS. Check the IBM AlphaWorks site for examples. I am not sure what Sun is doing in that regards, or what Solaris can offer Linux as far as technology. That isn't an insult, it is just my unfamiliarity with Solaris.
And finally, every machine is stable & reliable with a good system administration team that is knowledgable. I have been doing AIX admin work for about two years now, and I love it (having come from a Linux admin background). AIX has always had excellent filesystem support (true logical volume management built right in with real journalling filesystems, while you have to buy it from Veritas for Suns), and that, for me, makes it very easy to work with. And if you work with an OS for a while you get to know how it does things. I cannot speak for the admins that deal with Suns. I don't work with Suns, but half of the machines where I work are Sun machines (the other half is AIX, with two mainframes, and a handful of Linux boxes). And those Sun sysadmins can make their machines as stable and reliable as my AIX boxes. So it just depends on what you're trying to do, what you already have, and often, how much it'll cost you, because more often than not the machines can do the exact same thing, except one will be thousands cheaper.
Re:I disagree (Score:4, Interesting)
As opposed to running on a Sun system, which lets you run on a ... oh wait a minute. Those alternatives from Sun are mostly expensive proprietary systems, too, aren't they?
You also get a system that lets you migrate from your existing Linux systems to the IBM system without having to learn the quirks of a different Unix variant. If you use a supported distribution, you don't even have to learn a new distro. And if/when you decide that IBM isn't where you want to be, you can switch to many other hardware platforms with nothing more than a recompile. Sounds like you still get the key freedoms that Free Software is supposed to provide.
Re:I disagree (Score:4, Interesting)
Sun's pissed that they can't run multiple instances of an OS on their E15K systems. You might get Linux running on it, and Solaris is the champ OS on the big Sun machines ... but they are not virtual machine systems. IBM's hardware design lets them run multiple operating systems in parallel on one machine, and even dynamically share processor between them. And then with the VM operating system loaded, you can create multiple virtual machines and run Linux in each one. And VM is very efficient at that. I once ran 6 instances of VM inside itself, nested all the way down. Surely you've heard of the case where IBM tested running 41,000 instances of Linux under VM. It can do that, though that many seems rather pointless. It does let you partition off the resources so you can give each service function you need to run with its own virtual machine, and thus it's own Linux. And on the larger S/390 and zSeries machines, you can even run OS/390 (of MVS legacy) in those virtual machines, and mix/migrate between them all one a single mainframe piece of hardware.
Now personally, I wouldn't do exactly that. That's an awfully big basket with an awful lot of eggs in it. IBM hardware is quite reliable, but not so reliable that you can depend on getting "five nines" on one single machine. Sometimes there are reasons to take the whole machine down. IBM comes from legacy enterprise worksystems and usually early morning Sunday can be scheduled for maintenance purposes. In these days of e-commerce, you don't have such luxury. If you want to be up all the time, you need redundancy, and that machine way back in the corner of the room where "all the servers are gone" isn't redundancy (virtual redundancy, maybe, but you need real redundancy). You need several machines.
That said, there are pluses to IBM's approach as well. If you need to add another class of service, or partition users apart from each other because one needs to do stuff that needs root access? Give them their own Linux virtual machine.
OTOH, well managed, rows and rows of racks with 40 1U servers in each one, running Linux or BSD or NT or W2K or whatever, can be just as effective, if not more so. You can put dual 1.X GHz CPUs in those 40 machines in one rack ... that's 80 CPUs. That's quite a lot. The IBM zSeries can certainly compete, as can the Sun E15K. But those are going to be physically big, and power hungry, machines, too. Take your pick. There's no simple best answer; certainly not for everyone. All this is about is marketing, anyway.
Re:I disagree (Score:3)
Partitioning != VM (Score:3, Informative)
System partitioning isn't the same as IBM's VM technology.
With your E15K, you're dividing up processors and memory between various partitions, each running an instance of the OS.
IBM's running multiple OSs as virtual machines on the same system.
With Sun, if partition A is really busy, and partition B is idle, you can't make use of those idle processors unless you re-allocate your partitions.
With IBM, the processes in VM1 can use all the processors of the mainframe, unless VM2 also needs processing time.
With either one, if one OS instance crashes, it shouldn't affect the other instances.
Re:I disagree (Score:3, Interesting)
Hello? You obviously have never used an E15K or even a E10K with *does* domains for over 5 years now. Want some companies who use this? Ebay for one done. And they would be crazy to use Linux on it.
Re:I disagree (Score:2)
Re:I disagree (Score:2)
Kind of, but orders of magnitude more expensive. So expensive they come with a repairman, know what I mean?
Re:I disagree (Score:2, Informative)
Re:I disagree (Score:2)
The mainframes will always lead the pack in bandwidth and thus are very good working with multi-GB to multi-TB datasets. When you have a high computational need such as Computational Fluid Dynamics or molecular modeling, a cluster of workstations or a dedicated beowulf is going to perform far better than the mainframe. When you look at mainframes like the Cray T3E, they really do have it all; but you pay through the nose. To replicate the processor performance of a Cray with commodity products would require about 1/10th of the money.
Basically, people need to not worry so much about the raw numbers and take a minute to think about what they're intended to be doing.
I actually worked on Linux on a Mainframe... (Score:4, Informative)
All those impressive demos where they have 32 hojillion instances of linux running on a mainframe are meaningless. Sure, you can do it, but it doesn't do anything. If you try actually working with the setup, you'll be rebooting your machine 10 times a day, and those mothers take forever to freakin' reboot.
Hey - me too! (Score:5, Funny)
All those impressive demos where they have 32 hojillion instances of linux running on a mainframe are so meaningfull. Sure, you can do without it, but it will do everything. If you try actually working with the setup, you never have to reboot your machine -- instead of doing it 10 times a day, and those other take forever to freakin' reboot.
But who are you going to believe, ummm, me or ummmmm, that other guy.
Sheesh.
Re:I actually worked on Linux on a Mainframe... (Score:4, Funny)
I gotta hunt down and re-digitize the video that a set of students did back in 1992. At that time the UBC Computer Science GraFic lab had a stack of IBM RS-6000 computers running AIX (which I sometimes pronounced 'aches') which tended to crash far too often.
For their animation lab one group's video was an RS6000 shaking, smoking and melting down into a grave with (computerized) flowers sticking out of it and a gravestone blinking 888 (which the 3-digit LED display would do after a general system panic)
With later versions of AIX and some coddling from your's truely, I was able to make the IBMs a good bit more stable -- but never quite as rock-solid as the SGIs running IRIX -- and they never really outlived their reputation.
Then, of course, there was the obligatory IBM PC... Let's just say it was really good for running Castle Wolfenstein (the original).
Re:I actually worked on Linux on a Mainframe... (Score:2)
Re:I actually worked on Linux on a Mainframe... (Score:2)
Re:I actually worked on Linux on a Mainframe... (Score:2)
What about independent testing (Score:2, Insightful)
Activity and mud throwing may be a good thing. (Score:3, Interesting)
New title? (Score:2, Interesting)
Re:New title? (Score:2, Funny)
Re:New title? (Score:2)
For those not familiar with Terry Pratchett, that would be something like a 'spin doctor'.
For those familiar with Terry Pratchett; that would presumably be Sun speak for 'head liar'.
Every company should have one. Actually, come to think of it, every company probably does have one
Re:New title? (Score:3, Funny)
In our company, we have some many "chiefs", and not enough Indians. I'm working on a project, and I'm the only architect, system designer, programmer, QA, integration engineer. In another word, a one-man show. But I have to report weekly status to 5 chiefs, each one wants it in a different format.
The 5 are:
- Chief Technology Officer (boy, this is a high visibility project, even the CTO has to know the weekly status. This guy wants the status in MS Project format).
- Chief Product Strategist (What the heck, the guy is responsible of another product, but I don't know why he wants the weekly status of my project. But he makes sure that the CEO knows that he MUST get the status every week, so I can't get the CEO (of the division, that is) off my back. This guy wants it in Excel format, as he has a lot of product matrices in Excel).
- Chief Competitive Office (well, I never figured out his role, and will never figure out why he wants the status either. Ah, but he wants it in PowerPoint. He doesn't want to waste his time to recreate the information when he has to do presentation, does he?).
- Chief Project Management Officer (he can't even keep up with other real projects, but he still run after me every week for this stupid pilot project/prototype. Another MS Project format guy.).
- Chief Customer Service Officer (what the fuck, the project I'm working on is just a prototype, for god sake... This guy wants the status in his searchable database, so I just give him all files that I gave to the other 4 chiefs.)
Life sucks sometimes.
Can't blame em... (Score:5, Interesting)
Sun: A solution looking for a problem
Re:Can't blame em... (Score:4, Informative)
ok, I have to answer this bull alltoguether
I'm an IBM tech (not speaking for IBM, of course) and can tell all that the "proprietary Operating system" they are talking about is not really an OS, more like a virtual machine that handles all other oses. This virtual machine is n implementation of the S390 architecture that will handle several "virtual computers" at the same time by the use of multiple "virtual processors", each one used for a "virtual computer", with each having it's own PC, virtual memory handling and all.
Re:Can't blame em... (Score:2)
Yes you can, in fact until the Z/800 that was the only way to run S/390 Linux. You partitioned the mainframe into multiple partitions and then loaded as many linux images on the linux partition as you liked/it could handle.
Is this a suprise? (Score:2, Insightful)
If anything, this is a really good sign for the ever maturing linux operating system. Of Course sun would want to move people away from an open source, free operating system, over to their 'paid for' one. And if they can't do that by simply saing "don't use linux, use solaris", it makes a lot of sense for their marketers to simply say "don't use linux, its bad... and scary". It still cuts out a potential threat to them.
I figure if IBM says that IBM is ready for linux, i will trust that a lot more than solaris saying IMB isn't ready for linux.
Not that i have anything agasint sun, or solaris.. i respect sun and what its doen, and been through.. i just question the reasoning for this 'article'.
It would go better on SatireWire (Score:2)
IBM milking mainframe monopoly (Score:5, Informative)
With Amdahl checking out of the mainframe business it seems IBM has decided to raise mainframe prices significantly - it's actually charged more for the same performance in 2001 than in 2000! This is why IBM's mainframe revenues increased by a fair bit between 2000 and 2001 (while it's PC and Unix revenue dropped). Mainframe revenue accounts for about half of IBM's total server revenue...
CCO? (Score:4, Insightful)
Re:CCO? (Score:2, Funny)
Re:CCO? (Score:2)
Remember, everyone is innocent but a certain Gates; thus it matters not what one does, as long as he is else.
Misrepresented article.. (Score:5, Insightful)
Finding mainframe staffing is an obstacle in many organizations(6); combining mainframe and Linux staffing further complicates the matter. Running multiple Linux images still requires administration that needs to grow with the number of images being run.
This statement applies no matter what operating system you choose, you still have to find people who know the hardware. And as with all VM systems, you have to actively administrate each image. This statement is Linux agnostic.
Although z/VM can start and stop Linux images, it cannot dynamically add resources to match demand. As a result, a mainframe would need to size for peak demand just as the Linux farm would; high utilization is a myth.
Again.. Linux isn't repsonsible for the machine not being able to dynamically allocate resources to over-utilized images, it's a hardware/underlying OS issue.
Applications that run on Linux for Intel need to be recompiled and recertified for each new platform; thus the application portfolio to run Linux on a mainframe is small
Duh. It's a different architecture.
So, SUN isn't really bashing Linux, they're bashing their competitor, IBM. No real news here. SUN is very careful not to say "Linux sucks", because they have Linux offerings, they're just saying that customers should buy the SUN/Solaris solution for their high-end systems, not the IBM/Linux solution. I'm sure we'll see something from IBM soon.
--XaXXon
Re:Misrepresented article.. (Score:4, Informative)
Although z/VM can start and stop Linux images, it cannot dynamically add resources to match demand. As a result, a mainframe would need to size for peak demand just as the Linux farm would; high utilization is a myth.
This is total bullshit, check the IBM RedBooks on z/VM
Re:Misrepresented article.. (Score:2)
When the peaks happen at different times, the resources from one VM can be shifted to another VM and IBM has a solution to minimize the costs.
Absolutly! And if you're big enough to need a mainframe, you probably have tons of batch jobs that can be queued at low priority to take advantage of every little dip in demand.
FUDnews.. (Score:3, Insightful)
Next thing to do would be to ask someone that recently switched to linux on the mainframe, like ebay... hope one of the links below still works...
http://www.cio.com/archive/010101_et_content.htm l
http://abcnews.go.com/sections/tech/DailyNews/ib ml inux000517.html
http://www.zdnetindia.com/biztech/resources/ebusin ess/ecommerce/stories/45234.html
Makes sense to me (Score:2, Insightful)
There are however, notable exceptions, given the nature of mainframe processors, if all of your apps are written unoptimized for such a system, then you would want to unify them in a familiar abstraction, given a close enough match, this makes Linux a natural choice. Of course, why would you buy an expensive mainframe and not optimize for it?
To the naysayers slamming Sun as merely trying to boost SunOS, well, yeah, they are, but lets look at the situation.
1) Sun still has SunFire servers, which are QUITE powerful.
2) Solaris is no longer competing with HP-UX, since HP-UX is no more. Sun sells windows and linux based solutions. In other words, Sun has no reason to just blindly nay-say against Linux. As far as exploiting Linux for being a hot technology, well, they're doing that too. That's business for you, you gotta do what you gotta do.
In otherwords, the z800 isn't exactly slaughtering Sun's business, but you gotta have whitepapers to back up your statements when you're bidding to large customers. Saying "just cuz" isn't good enough. Sun's scoring one for the people who want to buy their products. It's not "slamming linux."
Re:Makes sense to me (Score:2, Informative)
I'll use tech that you are probably familar with. It's exactly like VMWARE for windows/linux. Except that the zSeries OS that runs the virtual machines runs at a much lower level then the VMWARE program and the HW is optimized for the execution of VMs. Unlike the x86 on x86 emulator that VMWARE does, the zSeries boxes run their VM's very fast. All the code that is executed runs native to the processors in the box, you have to recompile everything to run on them.
see this url for more facts on IBM's stuff. I'm not saying it's the answer, but this paper from SUN is FUD.
http://www-1.ibm.com/servers/eserver/zserie
Guy's got his facts wrong. (Score:2, Informative)
If the article is correct, then the z800's running zVM emulate Intel x86 architecture in order to run Linux. Heck, even poorly written native compiled code generally has advantages over such a set up.
That's not what IBM is doing at all. The version of Linux that runs on the 390 platform is natively compiled for that system and has been tuned to work with it. This is no different than Linux on any of the dozen or so other platforms it's been designed to run on.
Sun's FUD-slinger got his facts wrong more than half the time in that article, which in most places would get him grade of "F". I've been using and buying Suns for 16 years, and while I really like their products, I hope IBM takes every opportunity to point out what a nitwit he is.
The moral: Just 'cause it says "Linux" on the label doesn't mean it's running on an x86.
z/VM is *not* x86 emulation... (Score:4, Informative)
Sorry, but z/VM has nothing to do with emulation. z/VM is a low-level system that simply (or not so simply ;-) virtualizes the hardware by providing one or more virtual machines, each of which can run any native OS. As far as the client OS knows, it's running on the bare hardware. The z/VM layer provides the ability to flexibly divide the hardware resources between the VMs, and guarantees that each VM is completely isolated from all other VMs. In the case of Linux/390, the Linux kernel and applications have been compiled to run natively on the S/390 architecture. Check out this Linux for S/390 FAQ [marist.edu] for more info.
Re:Makes sense to me (Score:2)
No, you misunderstood. The VM doesn't emulate an x86, it emulates lots of smaller mainframes on one big mainframe. Like a beowulf cluster in one box. Emulating an x86 would be silly and slow.
Re:Makes sense to me (Score:2)
Minor nitpicking; AFAIK Sun does NOT sell Windows-based solutions. The only thing related to Windows Sun sells are certain software packages (Forte, StarOffice) that have Windows-version available along with Solaris and Linux-versions. Sun's products can certainly be integrated with Windows systems etc, but Sun doesn't sell such systems.
Re:Makes sense to me (Score:2)
Re:Makes sense to me (Score:2)
Re:Makes sense to me (Score:2)
Sun servers are not "SLOW" for the reason you give. Apache will still scale with the number of processors in a Sun server, regardless of whether each process is threaded. Also, Sun UltraSPARC processors ship with large caches that can hold most of an Apache server process, and the SPARC architecture is pretty much designed for C-language-programmed UNIX kernels and applications, such as Apache.
So, they are not "SLOW" as you claim but are actually quite FAST. For example, if you have a server with enough processors to delegate one Apache process per processor, the kernel can keep every processor busy with minimal context switching or threading overhead. And recent Solaris kernels are extremely good at keeping all processors busy very efficiently. Under really really high load, Solaris on SPARC is hard to beat.
Hands-on experience with Linux on a mainframe (Score:5, Informative)
I agree mostly with the article because I recently evaluated an IBM mainframe against an AIX SP2 and a Solaris 4-processor server. Most of the issues in the article, particularly performance, are right on.
The application we were testing was extremely processor and memory intensive. While there was a web component, the biggest problem was moving a large number of bitmaps in one format into the server, convert them from base 64 to a binary representation, rasterize them, and convert them to a "browser friendly" format such as JPEG, GIF, or PNG. We had to complete hundreds (> 200) of these operations per second.
I really wanted to use Linux because most of my staff is familiar with it and our customer felt warm and fuzzy about using IBM equipment. At the end of the day, however, the Linux mainframe only gave us 25% of the minimum speed that we needed for our process to be successful. IBM and a certain German Linux company tweaked everything they could but the performance wasn't there. The AIX vs. Solaris match was more evenly paired. My customer decided on Solaris because they offered a few advantages in Java tools that AIX didn't have. All vendor's boxes had equivalent processor and memory configurations.
I would like to spread the Linux credo as far and wide as possible. What we must understand is that, in order to make Linux a viable option in mission-critical applications (the kind of thing sitting on a mainframe), the performance and "hardening" of something like MVS must be present. Linux just isn't there yet.
Disclaimer: I'm under NDA so that's why some aspects of this posting are a bit vague. Drop me an email if you want more details regarding our experience but our conversation will be "off the record."
Have a nice wknd,
ERe:Hands-on experience with Linux on a mainframe (Score:3, Insightful)
You are talking about a different deployment than the one that is being attacked in the Sun article. What the latter is discussing are multiple images of Linux being hosted on top of a VM.
There is no reason why you should have been doing that in your case: you should have dispensed with the VM layer and just used Linux "native".
Basically the article is Sun bashing (perhaps righlty or wrongly, I don't know) the concept of "server farm in a box", which is completely different from your task!
Re:Hands-on experience with Linux on a mainframe (Score:2)
Re:Hands-on experience with Linux on a mainframe (Score:2)
Re:Hands-on experience with Linux on a mainframe (Score:2)
crush wrote:
What the latter is discussing are multiple images of Linux being hosted on top of a VM.
We tested running Linux in native mode and on top of VM on the z90. It was s-l-o-w anyway. By extension, running it in a VM partition would've made it slower.
My point is not to bash Linux; I like using it (and use it exclusively for 99% of my work, from notebooks to servers), but Linux just isn't ready for mission-critical applications running on mainframes. Sun is a lot closer to that goal.
For mission-critical stuff on mainframes, the kind of apps where you put your career on the line, MVS is still the way to go. Being a Linux chauvinist doesn't improve its performance or reliability on z90 hardware. I don't doubt it will get there; it just hasn't quite arrived yet.
Cheers,
ERe:Hands-on experience with Linux on a mainframe (Score:2)
Sounds like the wrong tools (Score:2)
Mainframe: I/O throughput, *massive* loads.
SP: *parallel* clusters, CPU, *fast* network.
You'd have been better with an S80... Sorry, "pSeries".
Re:Hands-on experience with Linux on a mainframe (Score:2)
That's what makes them expensive (well, that and the reliability).
Re:Hands-on experience with Linux on a mainframe (Score:2)
The FUD heard round the world... (Score:4, Interesting)
Now, Sun offers up the ultimate proof: Linux is just fine as long as it impacts the x86 world - but don't dare put it on a platform that affects us.
To be fair, IBM's offering is not perfect - yet. What Sun is preparing for is a future Linux and Big Iron combo that will be. They are afraid, and this FUD is the proof.
Pure crap (Score:3, Insightful)
What is it with these Sun guys? (Score:2, Funny)
One of the beauties of Linux is that it can be ported to so many different platforms easily. Sun uses it and then goes on to say IBM shouldn't? wtf? There are valid reasons to run Linux in multiple virtual machines. I even do it here on my PC.
Note to self: Must drink less coffee....
Linux not ready for Mainframes (Score:2, Informative)
Now, Sun comes right out and says this, and people start complaining? Sure, perhaps Sun is trolling for
You may think I'm biased: I work for Sun, after all. Don't get me wrong - I'd absolutely *love* to take one of the *THIRTY* E10k's I have sitting around me at the moment and install Linux on it. Or, rather - I'd love to TRY. But I don't have any real notion that any version of Linux, AS IT STANDS RIGHT NOW, will work as well as Solaris on that box.
Sure, Solaris isn't very user-friendly. GNU/Solaris (Solaris with GNU Tools) is better, but still not anywhere near what most Linux folks are used to when it comes to command-line fun. However, Solaris is *made* to work with Sun hardware. And it does, very well.
I doubt it highly that someone is going to go buy a US$4M E10k/E15k box and start porting Solaris tools and system utilities *just* so people can run Linux on those systems. Right now, the only reason people have installed Linux at ALL on those systems is for bragging rights.
If you want to outlay the cash and start-a-porting, I applaud you. I really do. But I won't hold my breath.
Yeah, right - Linux not ready for Mainframes (Score:2)
Sun doesn't have anything quite like it.
Their strategy (Score:2)
I think they want to utilize the benefits of linux however they do not want to allow Linux to creep into the larger servers where Sun dominates. And IBM which has AIX 5L (AIX w/linux compatibility) and now a special Linux for the mainframe it directly challenges their most valuable property, solaris which is valuable because all that software is made for it which makes people buy sun systems.
You find the program you need to run and then look at the systems running it, and unless you're already running AIX or HP-UX your first choice is probably Sun (and sun is usually always a choice). Now Linux comes in, becomes this pervasive server software and Solaris doesn't really look as hot as it did anymore.
FUD. (Score:2, Insightful)
They're working on that.
As for the rest, it's mostly FUD. The endian-ness is not an issue for 95% (wild ass guess) of apps that I have seen. Maybe except for DB2. You have to plan your maximum capacity in a discrete server farm just like you do in a virtual one. You also get capacity upgrade on demand with a phone call with the IBM hardware. They dont even have to send out a CE to do anything. Let's see SUN do that.
You wouldn't want to use it as a compute farm, but as a database server or news server or something which is usually I/O bound. They ain't exactly ferraris, more like 18 wheeler big rigs.
Design (Score:3, Insightful)
Goes to show... (Score:3, Informative)
Linux isn't designed at all, which is good. Thats why its so flexible. There was already that debate [slashdot.org] a while back.
Oh please. Like your going to have an easier time compiling non-Linux software? Still think so given how open and portable most Linux software is? Is mainframe software as portable? Is there lots of free mainframe software to port? Thats almost as irrational as Microsoft's "Linux isn't free" TCO argument. Per that can-of-worms, because both systems have TCOs means NT itself *is* free?
Articles like this are interesting because Sun definitly has a conflict of interest with Linux. They need to appear as if they support it so new blood will buy SPARC hardware with Solaris, but they also don't want people 'liking' Linux over Solaris/SPARC.
Personally, I love Linux on SPARC. I would prefer Sun making Linux more 'Enterprise'-like instead of hawking Solaris as a big-brother. However, I understand that Solaris is a huge investment and one they probably will think is superior for years to come.
For their sake, I hope the Penguins don't squish them. But if they don't look both ways before crossing the street...
What do we think?!! (Score:2)
This is easy: anything posted on
How do you tell when a marketeer is lying? (Score:3, Insightful)
This piece was so full of FUD that I could scarcely believe it.
Then why did IBM have to port the TCPIP stack from the VM world into MVS, if VM is so far behind?
Linux is "designed for Intel"??? What about M68K, PPC, ARM, Alpha, SPARC and others? (See the Debian ports page [debian.org] for a more complete list.)
Yes, MVS (z/OS) is rock solid reliable. But the machines don't bust either. CPU recovery has been an integral part of the architecture for almost 30 years. If a processor breaks, another takes over with no application effect, or a spare is assigned. Someone on the ibm-main list today mentioned that the processors are themselves duplicated on chip, with comparison logic to ensure that both sides are computing the same thing. Does Intel even parity-check their processors?
Small? Install a copy of SuSE SLES in a S/390 LPAR (logical partition, a hardware implementation of VM that is delivered on EVERY S/390... no z/VM necessary) and see how much software was delivered with it. You wanted OpenSSH and OpenSSL, though SuSE didn't deliver it? Go to the web, download it, and do configure, make, make install. The big problem with application portability is the proprietary vendors that ship binaries only.
What an amazing assertion. Wish Khan had provided a reference.
Merde. Why run it on a closed proprietary SPARCstation? Or a closed proprietary Mac?
Khan makes a couple of decent points, particularly regarding z/VM skills. But the hyperbole is way out there, and it's hard to take him seriously.
The struggle for hearts and minds (Score:2, Interesting)
There was a stage during the '80s when I was working more as an industry analyst than as a developer when Sun and IBM between them had become two of the then only four serious pillars on which the future of computing rested at a conceptual level.
At that level, Sun was the embodiment of Unix, taking evnagelical responsibility for the cause, and it is reasonable to assume that within their own envorins they genuinely see themselves in that position still.
From my own biased perspective, I felt they abdicated that authority when they allowed their elegant Network-extensible Window System (NeWS) to be rolled by a tide of industry resistance that mobilised against the upstart Sun and behind the then clearly inferior X.
But I'm sure in Sun's hearts they still believe they are the ultimate repository of deep understanding on all things Unix and are being genuine and honest in the technical basis for this critique.
The real problem is thay they can't see beyond their own world view. They do not have places in their heart for deep understanding of either the VM nor the Linux view or the world, let alone the two in combination.
Still Sun struggles to find its own identity and focus, to say nothing of a sustainable business model for the future.
From NFS to RISC, to industrial strength Web servers and on to Java, Sun has been a major contributor to the direction of mainstream computing, but now seems to be edging closer to following the fall to oblivion of that other former pillar of hearts and minds, Digital.
It will be a worse than sad day when we finally have to convey Sun to history, especially if that comes before Java gets to really stand on its own feet.
Reading between the lines... (Score:3, Funny)
READ: Of course, with an infinite amount of money, every business problem is solvable at the highest profit for the problem-solver...
READ: But Sun is of the opinion that it's proprietary servers, running with proprietary hardware (such as the special disk drives with the "magic" secret partition table, and the memory chips with the notch moved 1/10 inch) and, of course, running proprietary Solaris Operating System is the best solution overall, especially if you have an infinite amount of money to throw at YOUR problem...
READ: Definitely, here, we have a blatant attempt at fitting an hexagonal peg into a pentagonal hole. Linux was conceived to run on discarded low-end hardware in order to satisfy teenage-geek impulses, which is quite a different thing than to run on the Big Iron dinosaurs IBM is well-known for.
READ: You just can't run JCL and CICS and MVS and CMS and Assembler on Linux. Cobol (even GNU-Cobol) will make the kernel break into hysterics.
READ: On the other hand, Solaris is designed to run (well) solely on Sparc architecture that made Sun famous.
READ: Of course, you don't have any of those virtual machine nonsense with Sun products: you simply plug in as many boxes as you need of machines. No more software headaches for your operators!!!
READ: Why do in software what can be done far more profitably (and piracy-immune!) in juicy, expensi^h^h^h^h^h^h^h profitable hardware?
READ: Of course, you can dynamically add and remove ressources from a Sun cluster with the use of specially trained monkeys and servoids, which is a better proposition than software hocus-pocusery within the deep, dark bowels of an IBM mainframe.
READ: Of course, Sun cannot take advantage of Parallel Sysplex clustering either, but that's more alphabet soup to muddy the waters and instill doubts into potential buyers.
READ: Again, Linux fragmentation is a terrible tragedy that will never happen to Solaris.
READ: Even if " nobody ever got fired for buying IBM ", we whish the same could be said about Sun.
READ: IBM is double-plus uncool amongst geeks. SUN is the hip thing to use in IT!!!
IMHO, this guy has no clue ... (Score:3, Interesting)
And Linux isn't designed to run in a virtual machine; implementation decisions that make sense on PC hardware don't fit well in a virtual machine(4). This is Linux. It's designed for Intel. It's not tuned for the mainframe hardware in which it's running.
First, let's check what his "(4)" reference points to:
(4) For example: Filling all available RAM with file buffers is great in a real machine (as it speeds I/O via caching with otherwise-wasted storage), but in a virtual machine doing that is bad (as it inflates the working set of the Linux guest, which is competing for real storage with many other Linuxes-leading to paging/swapping).
Uhh, I have never seen a VM implementation that did not give a RAM limit. So this guy is basically saying that a memory leak on one of your VM's will take down the entire mainframe. Somehow I doubt IBM's mainframe R&D staff would do this
Often the difference in Intel versus mainframe applications makes porting difficult(10)
(10) Intel uses something known as little endian; a mainframe uses something different. This is significant for certain applications and makes the port difficult.
I challenge anyone out there to name any significant piece of UNIX software that doesn't have a big-endian port
Just the way he phrased that last bit about endianness convinces me that this guy doesn't have a clue what he's talking about. I can't really know for sure though, since most of the stuff he talks about is beyond me. But, based on those few things he mentions that I'm familiar with, I'd say he's a typical manager who is loosely and incorrectly paraphrasing what some Enterprise developer told him, and decided to make a marketing advantage out of it.
Read between the lines!!
Why doesn't Sun worry about their own issues? (Score:2)
Sun should rather worry about their own licensing issues and their own problems with open source. Java's broken community licensing program and Sun's inability to evolve the platform more quickly has basically killed Java for open source applications (that's why Mono is being written around .NET, even though .NET is much less mature and comes from Microsoft). Sun keeps equivocating on Solaris, Linux, and which one is better in their not-so-humble opinion.
Sun should address their own issues before putting down IBM. I'm sure ten years from now, IBM is still going to be around. I'm not so sure I believe the same thing about Sun.
What do slashdoter's think? (Score:2)
Well, I can't speak for others, but I think sun sells a competative UNIX on mainframe solution.
Not a good idea? Maybe, but... (Score:5, Insightful)
I work at a big corporation which relied on IBM mainframes for its whole business for almost 30 years until the PC and the high-end Unix servers shook up the landscape for good. I'm from the PC (IT) camp, which has been separate from the Big Iron (DP) guys in the organization since the early days.
DP, once very powerful, has lost a great deal of influence in the 90s, although they still run most of the mission-critical stuff, and the main reason for this were the high-end Unix servers, most of them Sun boxen running Oracle. Believe me, there's no love lost between those two fractions in our company.
Our mainframe guys see Linux as an opportunity to get better integration with the IT world, which was abysmal until now (3270 terminal windows, IMS/DB, TSO/ISPF and such horrors) and to better position themselves against the Sun/Oracle camp which is after their budgets and their butts. Today, we have Linux happily running on our mainframes (still in an experimental phase, not in production), serving up http and Samba shares without a hiccup.
If we're talking about bringing Linux into the large corporations, the crucial influence of IBM cannot be overestimated. We were a died-in-the wool IBM shop (S/390, Token Ring, 3270PC, OS/2, S/36, AS/400, the whole enchilada) and successfully trusted our business to IBM for 30 years (paid through our nose for it, too, I might add). IBM has lots of credibility and trust, so if they say Linux is cool, our CTO listens. Microsoft, on the other hand, is viewed with some "new kid on the block" suspicion. Our management doesn't like downtime and security breaches, and the memory of the ILOVEYOU aftermath is still very vivid, for example. Plus, we migrated to NT4 late (about 28'000 systems, ended September 99) and now Microsoft is practically forcing us into another expensive upgrade cycle sooner than we wanted and with IT budgets cut short on account of the less-than-stellar economy because NT4 support is withdrawn in 2003.
We thus have the following situation: IT and DP are up against the Unix enterprise server guys, all this with the backing of IBM. The astronomically high cost of Sun/Oracle solutions is being questioned more and more, and technologically viable low-end solutions (x86 multiprocessor servers, Linux) begin to rattle the foundations from below.
I don't want to make bold predictions here, but if I were Sun, I'd be worried. To me, it looks like interesting times are ahead.
VM removes the need for load balancing software (Score:4, Insightful)
If you have a VM system with two virtual machines, and one of them is nearly idle, and the other virtual machine is very busy, VM will automatically take resources away from the less busy machine and devote it to the more busy machine.
This means that you don't need load-balancing software. VM is the load-balancing software.
Given the relatively low cost of hardware, some organizations find this trade-off acceptable to ensure appropriate service levels. Contrary to what many believe, consolidating a Linux farm into multiple images on a mainframe would not change the demand pattern. Although z/VM can start and stop Linux images, it cannot dynamically add resources to match demand.
Of course it can! The VM kernel will parcel out memory and CPU on demand.
As a result, a mainframe would need to size for peak demand just as the Linux farm would;
All computer systems need to size for peak demand. The difference is that with a mainframe, you can size one machine for the peak demand of the busiest of a large number of virtual machines, and get rid of the overhead caused by the load-balancing software, because you don't need it anymore.
high utilization is a myth.
VM systems can utilize 90-95% of the native computer resources. The overhead on a VM system is very, very small.
In Sun's defense (Score:3, Insightful)
Sun just wishes.... (Score:2)
And they aren't. And they're pissed about it.
Imagine for a moment that Sun has the hugely dominant market share in server revenues that it wished it had, and that cross-platform Java programming and their version of
Given the way they've been acting, I think that Sun - if it had the opportunity - might even turn out to be *less* ethical. Much of what they've done lately reminds me of a five-year-old screaming "my toys are better than your toys! And they're my toys! And you can't touch them unless I say so, and only if you'll play with them the way I want you to!"
I don't trust IBM any more than I do Sun when it comes to their motivations re Linux, but at least IBM has some class....
Max
I side with Sun on this one. (Score:3, Interesting)
So you are going to have to "engage" IBM Global Services to run the thing -- probaly a project manager @ $275/hour and a one or two consultants @ $200/hour.
Add to this the INSANELY expensive hardware and software maintenance charges every year and you are talking about a serious amount of cash for little benefit
When you consider the alternatives, it makes even less sense. You can buy 100 Sun E220's or 2-processor intel 4U servers for the cost of one mainframe that lets you emulate 20 Linux boxes.
Mainframes have been on the wane for the last 20 years for good reason -- they are too friggin expensive!
Really? (Score:2, Funny)
Re:Interesting read. (Score:2)
Re:Interesting read. (Score:2, Interesting)
You make money by shrewd marketing, not by building a quality product i.e. Yugo's inception, Microsoft, Sun, etc.
But there are exceptions to that rule, build a quality product and market it "just good enough" like Cisco, and the market is yours. This idea failed with DEC/Compaq assuming the Alpha will sell itself.
Re:Are you kidding?! (Score:2)
No, it's marketing (Score:2)
Re:Of Course not! (Score:2, Funny)
And if you buy some sun machines to do the same thing you have to
The add that the server can't dynamically create more utilization capacity (extra hardware) dynamically. If anyone out there were selling a box that could do that, I'd buy it in a heartbeat. First we'd need some good nanobots, or maybe a replicator.....
Re:Of Course not! (Score:5, Insightful)
can keep it running, slap in new processors, new
memory, and then suck them into a running
partition.
It seems that most of the criticisms of Shahin
Kahn's article are based on ignorance. It's a
fair assessment of the liabilities of using
mainframe hardware for typical modern web service
applications. IBM tried to save the mainframe
from declining market share in a very ingenious
way, and Linux and IBM have benefited from it,
but that doesn't mean that it is competetive
with Sun's hardware offerings for the same
application environments.
Not all of Kahn's objections to VMs are valid,
however. The robustness arguments are good, but
the performance ones are short-sighted. While
s/390 Linux may not be tuned today, you can be
confidently assured that it will be soon -- even
if IBM has to fork the kernel to do it.
Re:Of Course not! (Score:3, Interesting)
Actually IBM's regular mainframes can. When you buy one of the higher end zSeries servers you get a box fully populated with ram and cpu's. If your liscense is for something less than the max # of cpu's and you later need to add capacity all you do is call IBM and they happily take your money and dial into your mainframe, they set a couple registers in the controller board and viola near instant hardware upgrade.
Re:Of Course not! (Score:2)
Re:Benefits of the mainframe (Score:2)
A 1000 processor Cray T3E 1200 would smoke your pathetic little mainframe :). And you wouldn't have to use crap like JCL. However, there's this little problem called cost of ownership. If supercomputers and mainframes were cost-effective there wouldn't be the huge push for commodity clusters, blade servers, and so on. There are probably applications where mainframes are cost-effective, but there are problems like almost nobody coming out of college with mainframe knowledge.
-Kevin
Re:They're probably right. (Score:2, Insightful)
With regard to the linked benchmarks, somehow I bet the benchmarkers at Tom's didn't compile parallel. Of course there is not going to be a speed improvement if you don't run a parallel make!
As someone who builds a small embedded Linux system from scratch (including gcc and glibc), a dual processor system is VERY nice. It cuts down the compile time by at least 30-40%. make -j2 is your friend with two processors.
Re:Solaris (Score:2, Insightful)
They are both Unix(-like), both solve the same problems but Linux does it cheaper and allows you to look ath the source code.
Actually, the price of Solaris is not really that expensive unless you are using a system with very many CPUs. A single user copy if you download it is pretty much free [sun.com]. It is the hardware needed to run it on that is expensive. Also, the solaris source code is available [sun.com].
I doubt Sun really cares that badly about the success of Solaris so much as they care about the failure if IBM. As far as I can tell, this article is mostly pushing the fact that a cluster of low end Sun boxes running Linux will be better than an IBM mainframe running Linux.
You can have access to a mainframe running Linux.. (Score:2)
Re:Linux on anything is good. (Score:4, Insightful)
The economy and most business models are not a 100% research and development, not-quite-stable environment.
Don't tell a large business "Well, it will get better the more people who use it". They'll spit in your face. They need to know what works, and what works now, and what will continue to work in the future.
Right now, Solaris works. Linux-bigots will sit and say "Well Solaris doesnt provide useful GNU utilities and is a boar when it comes to performance!" Well, yes it is, but it's been around forever, and when Sun says they can make it work, they will MAKE it work. You can't sit around and play with something for awhile in a 100% production environment, and rely on tools which have a sketchy (in a business-model sense) support base. It just cant, and wont, happen.
Just my $0.02.
Re:Linux on anything is good. (Score:2)
I wish I were joking, but this really does seem to be the way it is at all too many places, not that I would have any direct experience with THAT *cough*ATGDynamo*cough* [atg.com].
Re:Not really bashing linux (Score:2)
He obviously doesn't address what you point out, but I think the argument against the VM-ized version is valid. The benefits of Free Software obviously do not apply when the underlying system is closed.
I wonder if Linux still suffers the horrible performance issues when running natively verses when running on top of a VM (or atleast, the issues pointed out in the article).
Re:Not really bashing linux (Score:2)
He obviously doesn't address what you point out, but I think the argument against the VM-ized version is valid. The benefits of Free Software obviously do not apply when the underlying system is closed.
On the other hand some people will tell you that a small in-house team of hire'n'fire developers can make better progress on some things (like Intel's C compiler) than "Open Source" projects. Contrary to the mantra that "Open" development is always better for performance issues the advantage of Free Software have to do with Freedom: improved performance is a frequent desirable epiphenomenon.
I wonder if Linux still suffers the horrible performance issues when running natively verses when running on top of a VM (or atleast, the issues pointed out in the article).
The same general problem would still occur. However LPARed S/390 definitely doesn't suffer the same performance hits as you would expect.
Ps: Before anyone flames me I consider Free Software to be wonderful and desirable, but I don't believe that it is always more efficient or accurate or perfect as a result of that development process: it /can/ be, but it is not an immutable outcome