back to article Time to say goodbye to Risc / Itanium Unix?

Twenty years ago open systems was the battle cry that shook the absurdly profitable proprietary mainframe and minicomputer markets. The proliferation of powerful and less costly x64-based systems that can run Solaris, Linux or Windows is making more than a few Unix shops think the unthinkable: migrating away from Unix for their …

COMMENTS

This topic is closed for new posts.
  1. Steve Davies 3 Silver badge
    Boffin

    Throughput is key

    I've done some benchmarks on a couple of systems recently.

    The first was a Power 7 beast (there is no other word for it.) running AIX & Linux

    The other was a quad socket Intel Xeon (latest models) rig running Linux

    The application software was setup identically on the three configs.

    The Power 7/AIX managed 36000 messages per second.

    Running Linux on the same hardware gave us 26500/second

    The intel machine managed a paltry 14,240/second.

    sure the Power 7/AIX combo is expensive but the X86 world (in these particular circumstances) lags well behind the RICS System.

    Then add in the mix the LPAR management in the Power Range and it is one hell of a solution.

    IMHO, the X86 architecture is well past its sell by date. Intel recognised this. Itanic was not the answer. Simply die shrinking X86 to improve performance will not make up for the obvious shorcomings in the CPU Architecture.

    1. Steven Knox
      Meh

      Not quite

      "The application software was setup identically on the three configs."

      Then it was not optimized for two (if not all three) of the configs.

      Now if you want me to take your analysis seriously, please fill in the blanks on these equations:

      36,000 x 31,557,600*/(cost of Power7 hardware annualized over depreciation + annual power/cooling costs + initial cost of AIX annualized + annual support cost of AIX)

      26,500 x 31,557,600*/(cost of Power7 hardware annualized over depreciation + annual power/cooling costs + + initial cost of Linux** annualized + annual support cost of Linux)

      14,240 x 31,557,600*/(cost of Intel hardware + annual power/cooling costs + initial cost of Linux** annualized + annual support cost of Linux)

      That'll give you performance per unit of time per unit of currency. THAT will tell you which platform is better, because throughput is not key. Throughput for investment is key.

      The Power7/AIX system is just under 253% the performance of the Intel/Linux system -- which means that if it costs 253% of the cost of the Intel/Linux system, it's not as cost-effective overall. (Theoretically, of course -- in real life, you do have some overhead managing workloads across multiple servers which would have to be factored in.)

      * (= seconds/year)

      **(I hope that one was damned near zero -- otherwise you got ripped off ; )

      1. Anonymous Coward
        Anonymous Coward

        Hmmm

        Lots of good points, but that last one is not:

        >THAT will tell you which platform is better, because throughput is not key. Throughput for >investment is key.

        Sometimes, throughput is all that matters, irrespective of investment, because customers (hear banks, trading floors, etc) need to run their workload during a fixed time window which is incompressible. e.g. They have to run their jobs within a 4h hour window and saving $1M on an x86 system that runs in 5h is simpy not an option.

        THAT is why they pay a premium on the RISC systems.

        Of course, they would love to pay less...

        1. Steven Knox
          Boffin

          Missed the point.

          "Sometimes, throughput is all that matters, irrespective of investment, because customers (hear banks, trading floors, etc) need to run their workload during a fixed time window which is incompressible. e.g. They have to run their jobs within a 4h hour window and saving $1M on an x86 system that runs in 5h is simpy not an option."

          NO. You missed the point. It's not that throughput doesn't matter. It's that you have to get the throughput you need in _the_most_cost-effective_manner. In the scenario above, I wouldn't recommend getting a slower system, I'd recommend getting the most cost-effective system that performed the task needed. Let me give you two example cost scenarios that fit that scenario:

          1. Say the x86 system mentioned costs $500,000 while the RISC system costs $1,500,000. If you bought two x86 systems and ran them in parallel, assuming a 10% overhead for synchronization, you could have the jobs run in under 3 hours and still save $500,000.

          2. On the other hand, if the x86 system costs $4 million while the RISC system costs $5 million then it doesn't matter how many of each system you get because they're on the same price/performance curve. So you get the biggest that fits your budget, which would probably be the RISC system.

          All of this is before factoring in the cost of actually running and maintaining the systems, which could very well be the difference as well. This is also not to mention that you won't have 1 x86 system to pick vs 1 RISC system. You'll have multiple vendors, with multiple solution points per vendor.

          So even in the scenario you mentioned, throughput is only part of the equation -- and the the other major part, cost, can still be important enough to change the answer.

          1. Mark 65

            Re:Missed the point

            "NO. You missed the point."

            "1. Say the x86 system mentioned costs $500,000 while the RISC system costs $1,500,000. If you bought two x86 systems and ran them in parallel, assuming a 10% overhead for synchronization, you could have the jobs run in under 3 hours and still save $500,000."

            I'd say that in responding to the previous poster's banking example it is you that has unfortunately missed the point. These people aren't numpties sat there running sequential batches. I can assure you that where tasks can be run in parallel they are. However that only gets you so far after which you need to up the hardware and it is this fixed window issue that the original poster is referring to as if they could run a job more cost effectively then believe me they would as any spare cash goes in some fat bastard's bonus pool. Ergo throughput is still king no matter (within reason) what the cost is.

      2. Mark 65

        @Steven Knox

        In some applications throughput is key and should not be discounted.

      3. John Smith 19 Gold badge
        Thumb Up

        @Steven Knox

        Tricky to explain.

        Complex to carry out.

        Gives an honest answer at the end.

      4. pan2008

        bye Unix

        We are most probably migrating to a Windows Server set-up due to the shortcomings of a certain DBMS (won't mention names) running on Unix. The database people said that if we run this database on a linux, apparently it can run faster. It can run faster cause the x86 processors have better technology (I have no comment to make on this cause have never seen the benchmarks). That's last chance to salvage anything.

        But the bomb has been dropped, the Windows Server on the other DBMS offers 3-5 times the performance at a fifth of the price. I am sure with some tweaking can make little faster. You can't argue with figures like this.

      5. bazza Silver badge

        @Steven Knox

        You're right to suggest that some sort of performance metric should be calculated for a candidate IT solution, but you can't tell everyone what their metrics should be.

        Google apparently use a metric of searchers per Watt. Sensible - searches are their business, energy is their highest cost. A banking system is more likely to be measured in terms of transactions per Watt second; banking systems are sort of real time because there is an expectation of performance, but energy costs will be a factor too. But ulimately it is for the individual business to decide what is important to them. For example a bank somewhere cold might not care about cooling costs!

        I think that it is safe to conclude from IBM's sales figures that a fair proportion of businesses are analysing the performance metrics of x86, RISC, etc. and are deciding that a mainframe is the way ahead. IBM sell so much kit that not all their customers can be wrong!

    2. Matt Bryant Silver badge
      Stop

      RE: Throughput is key

      ".....sure the Power 7/AIX combo is expensive but the X86 world (in these particular circumstances) lags well behind the RICS System....." Congratulations, you found the perfect solution. For your application. To pretend that means you will see the same performance across all applications in all environments is either naive or deceitful.

      ".....IMHO, the X86 architecture is well past its sell by date......" Seems to be going quite well, though. By the way, did you stop to consider that RISC is at the point where future performance gains by anything more than die shrink are unlikely? Why do you think there is so little info on the IBM Power public roadmaps, it's because there is little more they can add to a geriatric design.

      1. Anonymous Coward
        Happy

        check out the new Power roadmap

        www.itaniumtopower.com

        1. Billl
          FAIL

          re: check out the new Power roadmap

          One generation and just stating the word "more" does not make a roadmap. IBM still has the worst roadmap of the three (Oracle, Intel, IBM). Of course, as many have said, they do not have as much need to be public with their roadmaps as Intel and Oracle. They've had trouble meeting the timelines of their roadmaps in the past (like Oracle and Intel), so it makes sense to be vague. This way they can say they've met all of their promises.

    3. Kleykenb

      vmware

      What is changing in the industry has more to do about 'virtualisation' than it has to do about 'architecture'. Many enterprises are going for virtualisation on VMware, and yes, VMware does only run on x86. Therefor we find that Windows and Linux are on the rise... not because they're perse so good , but because they are easy to virtualise, which cuts TCO. That said, Solaris CAN run as well on VMware but currently is not (yet ?) considered probably for the simple reason that most IT managers simply don't realise that it does run on VMware.

      Big iron RISC servers during an economy in trouble obviously are going to see a decline because of their cost. But when workloads need more than 4 CPU cores and the best in IO performance then Windows simply can't do what Solaris, AIX and HP-UX can do. Linux can do a lot but it also has it's limits, not in the least because Linux isn't an OS, it's a kernel. Build around it we have SuSe , Redhat, Ubuntu ... So choices need to be made because although these are very much alike, in an enterprise you want them to be IDENTICAL to keep down the cost of administration.

      So Big Iron isn't going away any time soon, what is going away is 'Midrange iron' and it's being replaced by VMware on Blades, but only for the 'small' workloads, essentially Tier 1.

      1. Destroy All Monsters Silver badge
        Paris Hilton

        "because they are easy to virtualise, which cuts TCO"

        Why and how does virtualization cut TCO?

        1. David 14

          Simple....

          Small Intel Linux server running an Oracle database requiring Enterprise Edition features:

          - single socket, quad core server = $2000

          - Oracle license for server = $200,000

          - annual maint costs for HW & Software= $44,000

          Actual CPU usage = less than 10%

          Virtualize, and you share a piece of hardware with other machines. So now you have the same server.. lets see:

          Server = $2000

          VMware = $8000

          Oracle = $200,000

          Maint Costs = $48,000

          Number of similar machines it supports = 5 or 6

          So about $250K in costs per server if physical... or about $50K per for virtualized.

          Pretty simple stuff!

          1. Jesper Frimann
            Holmes

            What ?

            Eh... you don't do this for a living I hope.. If you did, you would know that running Oracle under VMware means that you pay license for the whole physical machine, as Oracle doesn't count VMware as a hard partitioning technology as they do with all the UNIX virtualization technologies.

            Sooo... you whole example is flawed.

            // Jesper

            1. Anonymous Coward
              Anonymous Coward

              Running Oracle under VMWare

              only means paying for the whole physical machine if you're stupid enough not to haggle and threaten to port to MySQL. Oracle will wave the licence under your nose but will do a deal if you push back. If you need help, ask VMWare.

          2. cmaurand
            Linux

            But you shouldn't run a database in a virtualised environment

            Databases are I/O heavy. Even Microsoft's SQL Server bypasses Windows HAL and writes directly to hardware for performance reasons. Moving that to a Virtual environment is just dumb. I work for a company that has done that and there are myriad of problems that go along with it. Build a big honking server and put your databases on it. You can virtualize the rest of your kit. Much less expensive to do it that way and you won't have the inherent performance problems that come with trying virtualise everything to a shared environment.

  2. Bryan Hall

    License costs drive hardware choice

    Beyond IBM's chips - what RISC chips are out there that are remotely competitive with x64 chips for servers? Not some specific benchmark - but TCO including software.

    For years we were a Sun SPARC / Windows shop. About 4 years ago we dumped SPARC for x64 (AMD in that case). We still run Solaris / Windows, but on x64.

    Why? Performance per socket or core depending on licensing. Software licenses are MUCH more expensive to buy and maintain per unit than hardware. The RISC cores were just too slow to justify their costs.

    Instead of buying more licenses as loads increase, we just buy the latest / quickest hardware available - it is much cheaper to do so, especially for the socket license models where you can now have 8+ cores per socket.

    One of our big cost apps is Oracle Enterprise with Spatial and Label Security. The last go around we moved from a Sun SPARC v880 to a 16-core monster AMD box. This year we are dumping that and moving DOWN to a 12-core Intel box with TMS flash for all storage. The money we save in license renewals will pay for the new hardware. And we calculate that it will be about an order of magnitude quicker to boot. THAT is a no brainier upgrade - even for the US Govt.

  3. Alan Brown Silver badge
    Coat

    X86_64 was always a band-aid

    X86 was always the bottem end of the performance range (actual and per watt) - but what it is, is _cheap_.

    Power7 boxes might be faster, and so is AIX, but for the cost differential a company can have several X86 boxes and a couple of spares.

    Wintel boxes will always be slower until they can remove all the compromises which are required to still boot DOS. There are dedicated X86 systems out there which are a lot better optimised (but the price goes up)

    Linux is invariably faster with tuning - the defaults are for a wide range of operations, so I take performance comparisons like this with a bucket of salt (I've achieved speedups of 10-20X or more with appropriate tuning of boxes for the tasks they're performing) unless full details of the configurations and tuning mechanisms are provided.

    The _BIG_ advantage of Linux is portability. Source code written on X86 should compile and run happily on MIPS/ARM/Power/Big Iron/Itanic/Whatever comes along.

    Linux may not be Unix, but it's virtually identical in every respect that matters - and there is more/cheaper support than there is for the older *nixes. Because of that the market is really Win/*nix/VMS/Big Iron - and yes I still have VMS systems (brand new) in $orkplace for specific tasks because they're best suited to the task.

    Unix vs Linux is a strawman unless you start breaking the *nixes up into their component flavours and assess competition between them.

    I'm a happy Linux admin, but I also admin other Unixes, VMS and Windows(when I'm forced to). The point is that one should choose the software for the task then the hardware and OS it best runs on. Anything else is the tail wagging the dog.

    Right now I'm looking forward to the arrival of MIPS and ARM based systems for testing. If they work as I expect them to then we'll be achieving far higher throughputs per rack with far lower power consumption figures - speed isn't everything.

    Mine's the one with the fondleslab in the pocket, setup for remote X work.

    1. Anonymous Coward
      WTF?

      Ah ah ah

      I have to mark you down for that gem:

      >The _BIG_ advantage of Linux is portability. Source code written on X86 should compile and run >happily on MIPS/ARM/Power/Big Iron/Itanic/Whatever comes along.

      In your dreams!!

    2. bazza Silver badge

      Portability?

      >The _BIG_ advantage of Linux is portability. Source code

      >written on X86 should compile and run happily on

      >MIPS/ARM/Power/Big Iron/Itanic/Whatever comes along.

      Really? Maybe, provided you've got all the right libraries installed, the right versions of those libraries, the right GCC setup, and that your distribution's fs layout is along the same lines as the one used by the software developer, etc. etc. And then you may also have to worry about hardware architectural issues such as endianness. And then you have to wonder whether the software you have just compiled is actually running as the writer intended, or is there a need for some thorough testing?

      The idea of distributing a source code tarball and then expecting ./configure, etc. to work first time for everyone on every platform is crazy. Pre compiled packages are a joke in the Linux world too; deb or rpm? Why is there more than one way of doing things? There is no overall benefit to be gained.

      It is asking a lot of a software developer to maintain up-to-date rpms, debs and tarballs for each version of each linux distribution on each platform. Quite understandably they don't do it. If we're lucky the distribution builders do that for them.

  4. Anonymous Coward
    Pint

    IA64 itself is largely worthless

    Yes, largely worthless.

    Any value IA64 has is either part of the system into which it is built (especially in a really high end system), or is added by the OS, facts which TPM and many commentators (and HP/Intel) seem to struggle with.

    There are a few restrictions on AMD64-based systems in terms of scalability vs IA64 - Chumpaq's biggest AMD64 box maxes out at 48 cores and 512GB rather than the 32 cores and 1TB in the Intel equivalent; in both cases rather fewer cores and rather less memory than a high end IA64 system. (1) does this matter to any but a tiny minority of customers (2) Is this an instruction set restriction, a chip restriction or a system restriction? Afaict it's not the instruction set that's holding things back, it's the stuff outside The Chip Inside (tm). The system design and the supporting software. And now that Intel's AMD64 clones and HP's IA64 boxes now have basically identical memory interfaces and similar IO interfaces (QPI or whatever it's called this month), what exactly are the relevant hardware differences at a system level?

    As for the "IA64 has better RAS" fiction which used to be regularly trotted out: if TPM or Matt or anyone can find me a commercially relevant real world example where IA64 has significantly better RAS features than AMD64, I'll be amazed. Hint: in recent months even Intel VPs have realised this argument is largely worthless.

    Pretty much anything you can sensibly do on an IA64 system could in principle be done just as well and more cost effectively on a decent AMD64 system (or maybe even on an Intel clone) - IFF the relevant software (specifically, HP-UX, NSK, or VMS) was available. There are no technical issues making this happen (the OSes have already been ported more than once), only commercial ones.

    Why doesn't this happen? Your guess is as good as mine, but I'll bet it involves more politics than technology.

    Did IA64 even get mentioned in the recent Intel Investors Conferences (US and Europe)?

    @Steve Davies: you don't mention the OS which gave you the x86 result? Wouldn't be Windows would it by any chance? A Linux result on the same hardware would be interesting if that was the case.

    1. Steve Davies 3 Silver badge
      Unhappy

      X86 system

      Sorry to dissapoint you, the X86-64 system was running SLES11

  5. chairman_of_the_bored
    Devil

    One word missing - "enough"

    For years Unix vendors made a very good living out of claiming that their systems had higher throughput, reliability and stability than the alternatives. Unfortunately, Moore's Law has caught up with them: if the systems are designed properly, a white-box X86 solution is more than likely to be reliable ENOUGH, have throughput ENOUGH and (except if running Windows), stability ENOUGH that a 3-to-1 price disadvantage just can't cover. Brandishing selective stellar benchmark figures for a particular processor is almost irrelevant - there are very few organisations that can make use of the full unbridled power of a single-image fully-loaded Power 7 or Integrity server.

  6. michaelavis

    Use the right systems for the right workload

    Surely the best long term answer is to rationalise/standardise and get into a position where you can deploy different systems optimised for different workloads within a coherent environment of development, deployment and management tools.

    In other words, use a stack of OS, hypervisor, middleware and apps that can run on a range systems that could vary in CPU from blades, racks, appliances to large SMP systems offering different price, performance and RAS and don't worry about betting on a particular CPU.

  7. Malcolm Weir Silver badge
    Facepalm

    Is it just me, or...

    Does anyone else find the idea of "Linux vs Unix" as nonsensical?

    In my little world view, "Unix" is a generic term that encompasses a wealth of OS implementations, including: AIX, Solaris, IRIX, HP-UX, Mac OS X, BSD, and "Linux", amongst others (and, yeah, I get to work with old stuff). None of the above are interchangeable, and they all have strengths and costs and weaknesses... but I submit that the differences between Red Hat, Suse, Ubuntu are not qualitatively different from the differences between Solaris and Red Hat, Suse and AIX, etc. But throw someone comfortable with from any of those into VMS and watch them flounder...

    [ The differences change depending on viewpoint: from the perspective of a driver developer, all Linuxen tend towards looking the same, but very different from e.g. AIX; from the perspective of a developer using an X-based toolkit, they all tend to look similar with trivial differences in (e.g.) type faces right up until you get to integration with desktops. Etc. ]

    In sum, this article is really not talking about "Unix" vs anything, but proprietary hardware vs commodity hardware. Turns out the former is more expensive but tends towards "better", while the latter is cheaper.

    Gosh. Colour me surprised!

    1. Anonymous Coward
      Anonymous Coward

      Eh no.

      UNIX (note the capitalisation) is an adjective according to Dennis Ritchie and Ken Thompson.

      1. Anonymous Coward
        Flame

        re: Eh no.

        Eh, SHUT THE F*** UP!

  8. Kiralexi

    Those systems offer a unique value

    Core performance on Power and Itanium has been consistently good or very good for most of the last decade, but that's never been what you pay for. Ever since the Pentium Pro, Intel has offered most of the core performance of RISC platforms at a fraction of the price. What you get with the proprietary UNIX boxes is a fast system that scales far higher than most commercial x64 solutions, with very high reliability and certain features (PowerVM, for instance) that are frequently worth the premium you pay. Judging UNIX systems by list prices is also silly, since most actual purchases involve big discounts.

    Core performance on all three major RISC platforms (Itanium, SPARC, Power) will probably make massive leaps in the next few years. Oracle's public performance targets are especially aggressive, although it remains to be seen whether they can make it happen.

  9. JEDIDIAH
    Linux

    Don't get out the bagpipes just yet...

    Migration away from proprietary RISC Unix hardware has been going on for a long time. A lot of this has been due to lackluster performance from the "market leader" (namely Sun). Over the years there has been some back and forth on this and you've had some shops realize that they might not need everything that proprietary RISC servers have to offer. The same also applies to big name proprietary Unix apps.

    Although for really big jobs and large environments, the "little iron" from the Unix vendors still does things that bulked up desktop PCs still can't. The RISC platforms don't stand still either. The situation is not nearly as simple as some pundits would like it to be.

  10. Dunstan Vavasour

    Longevity

    The single outstanding feature of applications deployed to SPARC/Solaris is their longevity. Time and again, the only thing which is driving migration is the impending withdrawal of hardware support. This never seems to be the case with either Windows or GNU/Linux. Why is that?

    1. JEDIDIAH
      Linux

      Longevity

      I've seen plenty of corporate systems that are out of support. Some part of the system has been de-supported long ago whether its the hardware, OS, or the app. How this goes over in large corporations is a mystery to me.

      The length of support issue is a universal one. It is not something where Unix has a magical advantage. Enterprise Unix vendors will gladly screw you over in that respect just as Microsoft or Apple would. It's not just a "small systems" or "PC thing".

      Your apps will be "obsolete" far quicker than your OS or hardware.

  11. cocknee
    Alert

    It depends....

    There is no right answer a best system. It all depends on so many different factors. The move to "commodity boxes" is driven by the same numpties that drove the Dot.com bubble, working in lots of industries, they all seem to be jumping on the Linux bandwagon away from the big-iron, without really considering the whole picture and consequences.

    Yep the X64 boxes are way cheaper than the RISC ones but what about the lack of features for partioning, virtualisation at the hardware and OS level that just isn't in Linux or X64 (or Windows)

    You have to consider where the business is now and where it needs to be in the next 3 years, balancing the hardware, licensing, performance and human costs.

    I moved a major operation from RISC to X64, because in 2006, the latter was so much faster. A major business model

    Old RISC: 4h:45

    New RISC 3h:15

    X64 (AMD) 1h:20

    but by mid 2010 I was recommending the move back to RISC as the workload and bandwidth required, X64 couldn't cope. Luckily the business was using an OS that ran on RISC and X64, no new skills or data.

    However a year later, the with the arrival of the E7, the rise of flash storage, the prevelence of integrated 10GbE, 8GbFC etc....................... tough call.

    Given that the business has a lack of human resources, I'd still stick with big RISC iron as less boxes is best for them and it doesn't make an iota of difference on licensing between the cores.

    The big challenge with X64 now is the sheer amount of cores, how do you partition a large box - Vmware and Xen have an overhead but also limit on resources per guest. Linux is very immature, though RH6 is starting to get some decent features that the big boys (AIX, Solaris, Tru64, HPUX etc) have had for years.

  12. Allison Park
    Go

    Unix is on the rise in our shop

    IBM continues to grow and be the torch bearer for Unix. Power7 is unmatched in the industry.

    Yes our x86 boxes are doing more than before but there are still serious issues with reliability...we see it being about 5 year mean time between failure which is about 100 failures per year...yes we have 500 x86 servers.

    scalability....we cannot put big workloads on it because each virtual machine can only scale to half of a nehalem chip. V5 will get scalabiltiy to 2 chips but we wont have that certified in production till next year. I/O is also a major bottleneck

    performance.....good perforrmance but we dont buy anything past 4 sockets. Its funny everyone says how x86 has such big revenue and box counts but that is because its cheap and we have to buy so many of them. I would rather buy a box that is twice as expensive but only have to buy 1/10th of them

    sparc and itanium are dead to us and off the approved platform list.

    x86(intel) and power are the standards.

    Its is ridiculous that people call Unix proprietary when you look at our "open x86" you find we have standardized on intel/hp/VMware/RedHat/Oracle its not only proprietary but a mess to support.

    cheers

  13. Daniel B.
    Boffin

    x86 is a steaming turd.

    The reason we're still using this ancient piece of crap is because:

    - Intel kept on cranking up the GHz to match the more power-efficient RISC chips,

    - AMD went ahead and jerry-rigged 64-bit support onto the crappy x86 processor.

    - Windows took over the desktop market, and it mostly runs on x86.

    Points 1 and 2 turned x86 into a crappy but capable trashware processor capable of mimicking what the good processor archs were doing. Point 3 menat that x86 took over the desktop market, while the RISC alternatives began dying off, with Apple being the last one to vacate the PPC arch. Intel tried to move on with Itanium, but it failed in its first attempts and AMD seized the day with their jerry-rigged x86-64. Ironically, competition killed the path out of x86, while lack of competiton was what stuck us to x86 in the first place.

  14. Fred Flintstone Gold badge

    Umm- isn't there more than just performance?

    One of the neatest tricks you can pull off with IBM irons is rip a full box out of a live stack, because its VM even has processors virtualised so it can use slices of them, and you can add capacity in pretty much the same way (read: no downtime).

    I'm admittedly not entirely up to date on high end systems, but the ability to scale up on demand or seamlessly fail over is IMHO another part of that equation. The discussion so far has only been about bang for buck, but keeping critical things running is another criteria..

    1. JEDIDIAH
      Linux

      There's plenty of extra hype everywhere.

      AIX has it's own warts. This includes it's "virtualization" technology and even it's "always up" hardware design. It's not all just a bed of roses.

  15. The Real Loki

    Oh dear

    Anyone who knows any of the history of the Operating System will know it's UNIX and not Unix!

    1. Gareth Gouldstone
      Happy

      According to Dennis Ritchie Linux IS UNIX

      http://en.wikipedia.org/wiki/Unix-like#Categories

    2. Anonymous Coward
      Flame

      re: Oh dear

      Oh dear, SHUT THE F*** UP! You pedantic prick! Nobody gives a shit! Unix Unix Unix Unix Unix Unix. I'm a Unix bigot. I'm cool with Linux (hey did you know it's Linux as in Lin-ux, not Line-ux?)

      SHUT UP!

  16. Mikel
    WTF?

    Time to say goodbye to Unix

    Unix is from a different era - an era when it was OK to charge many thousands of dollars extra if the customer installed more RAM.

    These days you can have a system with 224162 cores, many terabytes of RAM, and pay nothing for software licensing whatsoever. Paying extra for adding a DIMM is a temporal anomaly.

    The Oracle thing is about to collapse. It's a database. Being able to provide a decent SQL database is becoming a hygiene issue rather than some special technology that needs special licensing.

  17. Mark 65

    Unwilling to move?

    "Organisations that have Unix skills are similarly unwilling to move to a new server architecture and operating system at the same time (although if they are using packaged software and migrating to a new version, this kind of transition can be done less painfully than actually porting home-grown applications from a Unix box to a Windows or Linux system)."

    The bank I used to work for moved their realtime risk system from Solaris/Websphere to Linux/JBoss due to the fact they could have many more machines to share the load and pay a lot less for the privilege.

  18. John Smith 19 Gold badge
    Thumb Up

    Some excellent points

    "The point is that one should choose the software for the task then the hardware and OS it best runs on. Anything else is the tail wagging the dog."

    Still, IMHO the best advice in business. Any other view is likely coming from con-sultant/con-tractor/reseller BS.

    And some remarkably restrained commenting as well.

    In reality companies have inertia. It takes a *very* strong management to say "We know that to cost justify our future plans we are going to migrate some of our *core* systems to a platform we have *no* current experience of (but we're going to acquire it)" and actually do it.

    IRL buying more (or an upgrade) of something is always easier than buying different.

    Some of those software licensing prices are quite incredible. I suspect COTB's comments is nearer the mark than a lot of people would like to admit.

    But I think scalability is *very* much under appreciated. It's understanding *those* issues *before* they become issues that separates the professionals from the amateurs.

    1. Steve Davies 3 Silver badge
      Mushroom

      Re john Smith 19

      I agree with you about this point.

      Some of those software licensing prices are quite incredible. I suspect COTB's comments is nearer the mark than a lot of people would like to admit.

      My finger points squarely at Oracle. AFAIK they have been raising prices for non Oracle H/W since their SUN takeover. Luckily our DB's run on Sun kit. Our main systems will remain on AIX for the forseeable future.

      As has been mentioned the H/W VM capabilities and the facility to easily add extra CPU's when the workload demands it is really great.

      If the likes of Intel/AMD get their finger out and make their h/w work like that if a Power 7/595 then I'll be pleased. Yes the costs for Intel/Linux/Jboss is less but there is no way that they can touch the P7/AIX/Websphere setup for raw throughput.

      As for those who insist on UNIX over Unix then {eat this}

  19. Randall Shimizu

    System throughput

    Despite all the changes with multicore. RISC systems still have a advantage due to a switched crossbar non-blocking architecture. This allows much greater overall system throughput. Not certain why the X86 companies never adopted this...?

  20. Anonymous Coward
    Anonymous Coward

    UNIX is determined by The Open Group

    Something is UNIX when it is certified so by The Open Group (www.unix.org). Many people believe that the various Linux distros are UNIX until a non-trivial application must be ported (either between then or to real UNIX, the problems are substanial).

  21. Anonymous Coward
    Pint

    @Steve Davies re SLES

    Not disappointed at all, just pleased to have more of the relevant facts. Thank you, for taking the trouble to try before you buy, and for sharing the summary here.

    SLES11 on IA64 vs SLES11 on x86, would that be a comparison worth seeing? Not for your requirements, but maybe for others to see...

  22. Jesper Frimann
    Headmaster

    Perspective...

    Actually I find this article kind of funny..

    Right now UNIX and it's bastard sibling Linux is perhaps at the hight of their might. I mean you find them in everything, music players (ipods) , smartphones, pads, 99% of systems on the top500 supercomputers, a solid part of the server marked, and last a rising presense in the PC marked.

    Sure it's sad that in the server marked is looking like AIX and Linux are going to be the only members from the UNIX'es left in the long run.

    // Jesper

    PS Sure you could talk about x86 versus the 'other processors', but in the OS war it's more and more looking like the UNIX family is the winner.

    1. Kebabbert

      @Jesper Frimann

      "...Sure it's sad that in the server marked is looking like AIX and Linux are going to be the only members from the UNIX'es left in the long run..."

      Maybe you missed it, but according to IBM executives, AIX will be killed off and replaced by Linux:

      http://news.cnet.com/2100-1001-982512.html

      Thus, it seems that IBM plans to let only Linux to survive. No more AIX. When AIX will be discontinued, most probably IBM will continue to support AIX for another 10 years. So dont worry, you will still have work.

      Pity that IBM will not port AIX to x86, though. When x86 outperforms POWER, IBM must port AIX to x86 or AIX will surely die. And preferably, IBM should open source AIX to ensure it to survive by the community when IBM kills it. And POWER will also die, because no one will buy POWER to run Linux on it, when they can run Linux on x86 faster and cheaper:

      http://www.anandtech.com/show/4285/westmereex-intels-flagship-benchmarked

      POWER is today only ~10% faster than x86, but costs 3x or more.

      .

      Regarding Solaris, there are no outspoken plans to kill it. Actually, Larry Ellison is planning increasing investments in Solaris, far more than Sun ever invested:

      http://www.informationweek.com/news/global-cio/interviews/222500081

      And Solaris source code is opened, so it can not be killed by Oracle.

      .

      Regarding HP-UX, I have not heard any plans to kill it. Of AIX, Solaris, HP-UX and Linux, there are only official, outspoken plans to kill AIX. It seems that your conclusion is not in alignment with IBM senior executives.

      1. Anonymous Coward
        Anonymous Coward

        "AIX will be killed off and replaced by Linux:"

        Mind, IBM (Steve Mills, senior vice president of IBM's Software Group) said that in early 2003 !

      2. SplitBrain
        Trollface

        Same old...Same old.

        Here you go again with the same old rubbish, that article you quote is from 2003! It was a very different market 8 years ago, one in which IBM was playing second fiddle to Sun even after the dotcom crash, it is now leading the UNIX market, IBM are not about to kill AIX anytime soon.

        You believe too much of what you read on the internet, including those useless benchmarks you keep quoting which as any seasoned SA will tell you mean absolutely diddly squat in the real world. They are PR/advertising, and nothing more than that!

        How dare you tell a fellow UNIX professional not to worry about having work, how patronising!! We all have our preferred OS, being Ex Sun mine is obviously Solaris and always will be. But times change and you need to accept other vendors do some things better. In IBM's case, their hardware is currently far superior to Oracle/Sun's, although as an OS AIX sucks for various reasons (Get rid of the ODM to start with as it's a frickin pain when it goes wrong) Solaris is a far more elegant "proper" UNIX, imho.

        Here's hoping Oracle crank it up a notch with the T4's so Solaris/SPARC stick around for some time to come.

        Here's also hoping Kebabert starts to appreciate the good things other vendors can do, it's not all about SPARC/Solaris these days, as much as I wish it was.

        1. Kebabbert

          @Splitbrain

          You should calm down, or you will get a heart attack.

          But the trend is clear, POWER gets cheaper and cheaper. And x86 becomes faster and faster, and soon they will cross. Then why should anyone buy expensive POWER gear?

          1. SplitBrain

            @Kebabert

            Wow, thats the best you can come up with "you should calm down or you will get a heart attack", why don't you actually think about the points I have made and make an intelligent reponse to those. There are no "facts" or "benchmarks" to quote when it comes to making a response to my post so you may struggle I expect...

      3. Anonymous Coward
        Angel

        Kebabbert - stop with the Insanity please

        Kebabbert.....you cannot quote a misquote from 2003 as fact. In the same article IBM is saying that Linux will forever play catch-up to AIX.

        What has happened since 2003? Well AIX was 3rd in the market and has now not only passed Solaris and HP but is 50% of the Unix market. I think a lot has changed since Power4 and AIX 4.3.

        If anything HP-UX is in the biggest danger unless HP does something about database support. Solaris will need someone to actually buy a Exa-xxxxx before Larry wonders by he is bothering with solaris.

        1. Kebabbert

          @A.C

          "....you cannot quote a misquote from 2003 as fact..."

          Am I "misquoting" the official statements from IBM? How am I misquoting them? I am trying to explain to Jesper Frimann, that according to IBM, AIX will be killed off and replaced by Linux. How is this a misquote? Please cite me, and the article I linked to - and if you can point out any errors in my understanding of the article I will stop say false things. If you can not point out my misunderstandings, then maybe it is you who misunderstood the official statements from IBM?

          .

          .

          "...What has happened since 2003? Well AIX was 3rd in the market and has now not only passed Solaris and HP but is 50% of the Unix market. I think a lot has changed since Power4 and AIX 4.3...."

          So? It seems that you dont really understand me. I say that long ago, POWER6 was several times faster than x86 and it costed 5-10x more. Today, POWER7 is ~10% faster than Intel Westmere-EX but costs 3x more. Future POWER cpus will cost 1-2x more, but ideally will be cheaper than x86 or they will not sell.

          Yes, a lot has changed since POWER4. The trend is clear: AIX/POWER is not a high margin business anymore. IBM had to lower the price of their best CPU yet (the mighty POWER7) because IBM is afraid of the competition from x86 and Niagara. This means something.

          I predict that IBM's fear will increase, and future POWER cpus will be cheaper and cheaper. There will be a time in the future when IBM POWER can not compete with x86. x86 will catch up on POWER. You know that. I know that. This is true. The trend is clear, it will happen. Some time after, IBM will kill POWER, because IBM can not afford to loose money on expensive and slow POWER cpus, with a diminishing market share. That is when AIX will be discontinued.

          Do you really think that IBM will release a future POWER cpu that is many times faster than x86, so IBM can continue to charge 5-10x more? No. Those days are gone. x86 will be faster. And AIX does not run on x86. So AIX on POWER will be no more. This is true. Even IBM executives see this trend.

          Next year, the 22nm Ivy Bridge from Intel will arrive. It will be 40% faster (according to Intel) than today's Sandybridge. Thus, it will be faster than POWER7. IBM must make sure that POWER8 is much faster than x86, there will be no point in spending billions on R&D on a slower POWER8 cpu.

          So, AIX and POWER is soon obsolete. Itanium is obsolete (this is a pity). Better start to learn Linux on x86. The thing is, the managers dont understand that POWER and Itanium has much better RAS than x86, and that x86 is a piece of buggy shit. They just look at the cheapest performance / money, and x86 is the future. The managers will only consider OS that runs on x86.

      4. Jesper Frimann
        Facepalm

        I'll try to post again..

        Well my comment to this post seem to have been lost, so I'll quickly do a response again.

        "POWER is today only ~10% faster than x86, but costs 3x or more."

        What you meant to say is that low clocked 1.2Billion transistor 45 nm POWER7 chip introduced one and a half year ago is still 15 % faster than newest higest clocked 2.6 Billion transistor 32 nm Westmere-EX chip, right ?

        According to your link it's 15%, as for the price Anantech is comparing a HP blade versus a IBM rack server. That will never be a fair comparison.

        Try to have a look at what the HP blade costs compared to the IBM POWER blade of equal size.. let me enlighten you. The HP blade costs 75% of the IBM POWER blade, if you look at equal bare metal configurations.

        You can look that up on the HP and IBM online stores. Again that is not a factor of 3 in cost. And we are not even talking TCO yet, but only cost of the actual hardware.

        // Jesper

        1. Kebabbert

          @Jesper Frimann

          You are just evading the issue.

          I am claiming that POWER gets cheaper and cheaper, and Intel gets faster and faster. Then I gave some numbers. I said POWER7 is 10% faster than Intel. It might be 13% or 15%, so what? The trend is clear: POWER6 was several times faster than Intel before (on some benchmarks) and costed 5-10x more. POWER7 is only slightly faster, and much cheaper.

          Instead of disputing the exact numbers I suggest you discuss the issue instead: POWER is getting cheaper and cheaper, and Intel is getting faster and faster. This is true, it is a fact. Intel cpus are getting more performance at a quicker pace than IBM POWER is getting performance. The Intel slope is higher which means the lines will cross: Intel will catch up on POWER.

          Also, IBM has said officially that AIX will be killed. This is also true. It is a fact.

          .

          Now, here comes the guess part (these are not facts, but opinions):

          I predict that when Intel is faster, or fast as POWER cpus, then POWER need to lower the price even more. And finally when the price is too low so that IBM does not earn much money anymore, POWER will be killed off. Just like IBM killed of CELL cpu. And that is the time when AIX finally will be killed by IBM. AIX is soon no more high margin business.

          I am basing this prediction on IBMs official statements and I am extrapolating the clear trend (POWER getting cheaper, and Intel getting faster). In other words, I do have some substance in this prediction: it is not evil rumours without ground (not FUD). I am not FUDing.

          1. Jesper Frimann
            Headmaster

            *SIGH*

            You don't seem to get it.. Sorry but Keb, you don't really know what you are talking about. A processor chip is just a little bit of the total cost of a server. The TCO of POWER SERVERS is getting better. The machines of a specific class of servers, cost more or less the same, as it have done for the last what 6-7 years. So the whole premises for your little theory is.. well.. wrong.

            It's actually pretty simpel, the hardware of a p570 based upon POWER5 from 2004 cost more or less the same as a POWER 770 cost you today. The real difference is that a POWER 770 has a factor of 10 the raw capacity, and with it's enhanced virtualization capability perhaps even a tad more.

            Furthermore what you seem to forget is that the IBM revenue coming from POWER is going up, even though their $/capacity unit is going down and down. So I would presume that the profits are at least constant. So your statement is basically not making any sense.

            // Jesper

    2. Anonymous Coward
      Anonymous Coward

      Err...

      I think you're missing the point... UNIX is not Linux, Linux is probably the biggest rival to UNIX, to count them together as a whole misses the point that, in general, UNIX is run on very expensive propriatery RISC hardware and Linux is run on comodity x86 hardware. If you lump them both together you don't see the migration from UNIX/RISC to Linux/X86/Virtualised.

      The bang for buck of RISC processors/servers just doesn't stack up against a modern x86_64 server. A RISC server may be bigger and faster, but the cost is disproportionate and usually the extra capacity isn't used.

  23. Anonymous Coward
    Anonymous Coward

    Hmm...

    My former employer (top 5 global bank) are migrating off all proprietary unix (except for tactical essentials) and are replacing with Virtualised Windows/Linux (RHEL) and z/OS and z/Linux. The reasoning is simply that the bang for buck of the RISC processors running most modern UNIX OSes doesn't stack up against a modern x86_64 chip. This will be augmented with some of the new database appliances coming onto the market.

    If they need really big throughput in Linux it goes on a Z server, otherwise it's vmware.

    The UNIX guys really weren't very happy about this at all (why do people working in such a fast moving industry resist change so much?) as there was the typical unix guy suspicion of Linux. However they're coming round to the idea and can't really argue that much with the seer cost savings involved.

  24. Jim 59

    Linux etc.

    The author writes about Linux as if it were part of the Windows product suite, and not a tentacle of Unix. Linux is the most open unix of all, and has well and truly answered that 20 year old call for for "open systems!".

    The lower midrange market was there fore he taking in the late 90's. MS jumped right in there and had a great time for 5 years. Then unix sent in its Linux steamroller, which continues to rumble back and forth in the datacentre.

    The proprietory unixes have of course declined, driven by technology, but that's 10 year old news. This article focusses, oddly, on Itanuim/RISC, a minority platform if ever there was one. Yes, mainframes cost more than midrange, which costs more than x64. 'Twas ever thus. Only the old names changed - mainframe, mini and micro.

    1. Anonymous Coward
      Anonymous Coward

      Sigh...

      Please try to understand: Linux is not UNIX.

      GNU = GNU's Not Unix

      Linux isn't fully POSIX compliant, even Windows can be made fully POSIX compliant by installing SFU.

      1. Jim 59

        Unix/Linux

        Unix/Linux are technically very similar and historically intertwined. In the context of this article, they should be held the same, cutsey project names notwithstanding. The author has instead lumped Linux with Windows simply in order to make a point about the commercials. Far more interesting to group Linux more correctly with Unix, and ponder the evolution of the OSes from that viewpoint.

  25. S Watts
    Boffin

    Building large projects

    We build a large-ish project on both Solaris/SPARC and Windows x86.

    Event though the Windows build machine is a higher spec [1] than the Solaris box, and only builds a sub-set of the UNIX product...

    * On Solaris/SPARC the system build quicker, and builds in the background while other users can happily work uninterrupted (including multiple builds). This box is about 7 years old now, and has a rather dated toolchain.

    * On Windows/x86 the build takes longer, much longer, on a dedicated build machine which cannot be realistically used for anything else in the meantime. This box is about a year old.

    For serious jobs I still find that the SPARC/RISC architecture is far more usable than x86. Haven't tried x64 since the system is 32-bit and I really don't want to be responsible for porting to 64...

    [1] by simple processor/core count & speed, memory and disks.

  26. cmaurand
    Linux

    Its not DOS

    Windows NT/2000/XP/2003/Vista/7/2008 all have their roots in OS/2 not DOS. You're booting OS/2 there (you could really see it in NT 3.5) with broken security.

    1. ptime
      WTF?

      NT is not OS/2

      NT (and children) are actually VMS-based. Look it up. Strange but true. "Booting OS/2… with broken security" is uninformed nonsense.

      1. Anonymous Coward
        Thumb Up

        "NT (and children) are actually VMS-based"

        Commonly held misapprehension, not really true. When NT started life it had more in common with a DEC distributed realtime kernel called VAXELN (which had VMS as a development host, and some limited VMS compatibility) than it had in common with VMS itself. Source: Helen Custer, Inside Windows NT (and various other published and unpublished sources inside DEC and MS).

        As time went by Gates forced more and more NT OS code into kernel mode for "performance" reasons, and thus introduced all kinds of compromises to the original OS's security and stability.

        Today's NT may have good device support and lots of shiny features but in comparison with the original NT security and stability model, it sucks.

        NT wasn't technically a child of OS/2 although commercially it may have looked that way at one point, and at one time there was an OS/2 compatibility subsystem in NT.

  27. Anonymous Coward
    Linux

    "I still find that the SPARC/RISC architecture is far more usable than x86."

    FFS.

    You could sensibly make a comment like that IF, and only if, you were comparing Solaris on x86 with Windows on x86.

    Otherwise you are comparing differences in the software not just the hardware.

  28. Anonymous Coward
    Pint

    "Linux isn't fully POSIX compliant"

    You've presumably never heard about Lasermoon, provider of the world's first POSIX compliant LINUX, maybe 15 years ago or more. Unfortunately all the PHBs that used to bleat back then about the importance of "open systems" actually wanted Windows because they thought it was cheap, and Lasermoon went out of business.

  29. Beachrider

    AIX vs x64 Windows or Linux

    There is some Beavis and Butthead traffic going on that references a 2003 IBM document where IBM expects Linux to eventually replace all enterprise UNIX (it didn't just talk about AIX, no matter what anyone says). IBM said it in 2003. They did not say how-fast it would come.

    IBM Power 7 has taken a different product-path than Intel IA32 x64. Intel IA32 (~1980) is actually a OLDER than IBM Power (~1989). IA32 has seen major changes from its 16-bit bus origins to its x64 existence today. Power was RISC and 32-bit from the start, but IBM wasn't aggressive with advancing its technology in the 1990s. Since 2001, IBM has been much more active in getting its 64-bit architecture and higher-performance aspects rolling.

    #1 Power is more expensive then x64. I agree. As soon as you start talking about 8 cores-or-more, it isn't 3x. A single-socket 8-core x64 blade w/ Xeon 7500 is about $6K. A similar 8-core blade w/Power 7 is about $8K. Both can run Linux. The Power blade benchmarks out 15-20% faster. The Power blade even goes into the same enclosure and an IBM Xeon blade, if that matters.

    #2 Power virtualization hardware is quite competitive with VMWare. CPU overhead is lower on PowerVM and cross-client communication is better PowerVM. VMWare handles Windows and that is just a non-starter for PowerVM. VMWare also adapts Windows to virtualization in really nice ways. If you have Windows, then VMWare must win. If you have Linux or AIX, then PowerVM provides substantial management and resource sharing that matters in a sufficiently large shop.

    #3 Power 7 still has the giant-server business locked down, but at a substantial markup. This is where the 3x cost multiplier comes into play. If the application gets kludgey trying to run on x64 Linux, then running on Power 7 can be attractive (even at its cost premium)

    #4 Power 7 is nearing the end of its current server-cycle. Power 7+ is due out in the Fall. IBM sells servers, not chips, with this product. A lot of bloggers find IBM's not-as-public ways off-putting. They are off-putting. That doesn't invalidate what IBM is doing, though.

    ... I guess that I have said enough for now...

    1. Kebabbert

      @Beachrider

      I post links to IBM senior executives. Would you prefer me to not post links at all, so you could dismiss my posts as pure FUD and rumours? Well, IBM executives has said what I claim, I am only quoting them.

      POWER6 was several times faster than x86 but costed 5-10x more.

      POWER7 is 10% faster than Intel Westmere-EX and costs 3x more.

      What is your predictions about future POWER cpus? What does the trend tell you? That IBM will continue to lower the price of POWER? That POWER is soon not a high margin business anymore? And you know what IBM does with low margin business? IBM kills it. As any sane capitalist company with greedy share holders would do. IBM is an american company. IBM gets rid of low margin business, when IBM spends billions on R&D and can not get the expends back. x86 is the future. (Even though x86 is a buggy piece of shit, it is cheaper and soon faster)

      1. Jesper Frimann
        Holmes

        Again.. you just post numbers..

        You aren't making much sense...

        Again your claim that POWER is 3 times more expensive is a very broad and so absolutely not always, if ever, the case. Look at my previous post or try to look up some figures up yourself.

        Sure a POWER 780 is an expensive machine, but it's also a fast machine. For example have a look at this link to the best price/performance TPC-C benchmarks

        http://www.tpc.org/tpcc/results/tpcc_results.asp?print=false&orderby=priceperf&sortby=asc

        Then you'll find that the POWER 780 the 'higher end' version of the POWER 770 8 socket box, comes in at 13th place, with the best x86 windows result that doesn't use an enterprise database, being only 29% cheaper, even though the POWER 780 is basically a highend machine, with dual service processors, being able to hot repair of nodes and and ...

        So yes POWER and other UNIX'es are more expensive than x86.. but it's not like it was in the old days. Now it's two digit %'es not a factor that is greater than 2.

        You are saying that POWER is to expensive.. then you say IBM is killing off POWER development while POWER is having the best makedshare that it have ever had ?

        You are not making sense.

        // Jesper

        1. Kebabbert

          @Jesper Frimann

          The question is not the numbers, never mind them. It does not matter if it is 10% or 13%.

          The question is: POWER is getting cheaper and cheaper. And Intel is getting faster and faster. Soon, POWER will be very cheap, to be able to compete with Intel, and that is when POWER will stop being high margin. And why would IBM do low margin business, when POWER costs billions in R&D? Why should IBM not kill a low margin business when you get a off the shelf Intel CPU at a lower price, and higher performance?

  30. Beachrider

    Where do you get the FUD accusation..

    @Kebabbert I never said anything about FUD, so you aren't reading what I wrote. I did imply that the 2003 document was a long term prediction and that citing is as a fait accompli is superficial.

    If you keep it in the future tense, then it isn't superficial. Your choice.

    Your 10% number has been challenged with citations several times. It really is 15-20%. I infer from Jesper that giant servers (32+ cores) favor Power much more. He has examples.

    OPINION

    Power is behind x64 in manufacturing process (INTC has 22 micron NOW), but ahead of x64 in GHz (IBM has better heat control). IBM will get to 12+ cores per socket this fall. x64 has been battling with its more-complex ISA because it makes it harder to layout tighter/faster logic.

    IF you believe that x64's ISA will ultimately hog-tie improvements in 1-4 years, then you would favor Power (some do). IF you believe that INTC will 'overcome', then it is hard to see Power being viable in 7-10 years. INTC did get dragged kicking-and-screaming (by AMD) into doing that much needed x64 function-enhancement. INTC is also battling ARM for low-end Windows sales (ARM already is strong in handheld smartdevices). INTC's reputation for 'vision' and 'intensity' are key elements for success in this challenging time.

    IBM doesn't want to put Power in the commodity server business, so your warnings about IBM's appetite for low-margin sales are about-right. The hyperbole about them getting scared off the moment the bloggers find a disadvantage is not right.

    FWIW, my guess is that INTC won't find an easy way out of the heat dissipation issue with x64. In the worst-case scenario, they will go massively parallel (>16 cores/socket) on highly complex chips for large servers in the next 3 years. This worst case would keep the door open to Power on non-Windows environments. INTC also faces ARM on Windows, now that MSFT has opened the door on that. INTC is a very resourceful company, though. I don't count them out to find an imaginative approach.

    FWIW, my guess is that IBM will only push Power enough to maintain control of the high-end market. They probably can push GHz up faster than INTC, because of their heat-dissipation advantage. Power isn't going to break-out past the Linux/AIX market though (that was easy), so unless Linux makes major inroads on Windows, Power is playing in a facet of the marketplace.

  31. STZ
    Childcatcher

    Anybody thinking about the business users ?

    Great discussion going on here - all driven by hardcore IT experts with their respective OS preferences and a deep desire for even higher clockspeeds, combined with a remarkable pennypinching mentality ...

    Anybody asking about the concerns of those stupid business users - those who just understand their business but have no clue about the latest trends in IT ? Are they really screaming about more bang for the buck, sophisticated virtualization and cloud computing ... or wouldn't they come up with other priorities if they only were asked ?

    Things like I don't need even more complexity and I can do without the latest fancy stuff. Rather, I want my application to run reliable, I don't want my database to get corrupted, I don't want to get hacked, and I don't like hunting for even more of those expensive experts in pursuit of those rather simple goals.

This topic is closed for new posts.

Other stories you might like