c0t0d0s0.org

For my non-german speaking readers a link to an english background article in the Register -Date bug kills VMWare systems:

Reg reader Duncan said VMWare's FAIL represented a "fantastic bug for a company trying to embed itself into the modern computing world." While another reader, Eric, said the "time bomb" contained in the update was causing a lot of panic among businesses.

"Customers were fuming this morning having planned downtime for weeks. Vmware have alot of answering to do on this and no doubt share price will take a hit again," he said.

Heise.de reports about a timebomb in the Update 2. The system denies the migration, creation and suspension of virtual machines with the message that the product has expired. That matches my opinion about VMware with all this big vendors introducing virtualisation solutions, but that´s a different story Well, Heise writes that the suggest workaround ist to set a date in the past and to disable the time synchronisation. But as virtual clocks are just a rough guess of the actual time, this doesn´t look as a viable workaround for me.

BTW: They have annother problem. The support website seems to suffer the slashdot effect started by the link on the heise website.

I don´t have a subscription for the Wall Street Journal, but the free preview says enough about this Fujitsu-Siemens divorce rumour: Siemens Set to Pull Plug On Venture With Fujitsu:

In a move that could set the stage for the sale or dismantling of a leading European maker of personal computers, Siemens AG has informed Fujitsu Ltd. that it wants out of their nine-year-old joint venture, people familiar with the matter say.

This revisits this rumour reported before from other news outlets. The rumour made it even into a german news broadcasting service today.

VMware announced a free version of their ESX server product. Well, this may be an effect of the 500 pound gorillas entering the business. Sun will announce xVM soon, Microsofts developed Hyper-V ... thus the market for it´s hypervisor may get narrow. At the end, the auxillary tools earn VMwares money, thus giving away the hypervisor is a clever move.

(Disclaimer: This article is my personal opinion, i´m not aware of the official opinion of Sun Microsystems regarding this rumours)

Well, this is a really interesting development: According to the german news portal heise.de with their article "Bericht: Siemens kündigt Vertrag mit Fujitsu"(on german) and a report on Reuters Siemens wants to get out of the joint venture (JV) with Fujitsu as the Siemens CEO doesn´t see FSC as a business unit that´s profitable enough to stay in the company.

This is interesting for Sun out of a simple reason: FSC is not just that notebook company. FSC is a distributor of the SPARC Enterprise Systems (M-Class and T-Class) and those systems are identical to ours. In Germany FSC has quite a market share.

Okay, according to the reports there is an agreement in the JV contract: Whenever someone wants to get out of the JV agreement, the leaving partner has to offer it´s stake to the other partner at first. But i don´t think, that Fujitsu will buy the part ... especially not when there are signs of a adverse global economic downturn. Thus it looks reasonable that they will offer the part to someone else will buy it interested in the well known Fujitsu-Siemens brand for desktops and notebooks. It would be further reasonable to assume that a new owner would concentrate on the x86 business and thus won´t take the SPARC business. And this would open an opportunity for Sun.

Well, i will go to bed now and think a little more about this development. But as usual: Interesting times ahead of us ...


PS: Maybe this was thee reason for announcing the Xeon based mainframe a few days ago ... this would give Siemens a opportunity to keep their mainframe business without the SPARC procs from Fujitsu.

This is the english translation of an article i wrote to answer an strange blog article in another german blog. While answering it, i found a case of "History Repeating".

In the actual installment of the Prozessorgeflüster (a reoccuring CPU technology article in the german computer magazine c´t) Andreas Stiller discusses the the first facts about the new manycore processor "Larrabee" from Intel. Stiller states in this article, that this processor was discussed to release with with 16 to 24 cores, but will release with 32 cores when it appears in 2009. To the surprise of many experts, the cores are well known. The cores are nothing more than Pentium P54C cores. Well, the P54C was announced 1994. This would be similar to a Niagara T1 on the basis of the SuperSPARC II, which was announced 1994 as well.

Annother interesting fact reported in the article: The Larabee xPU will use roundabout 300 watts. That´s much much more than a UltraSPARC T1 CPU. I know, Larabee is a GPU at start, but do you really believe that a manycore GPU with x86 compatible commands will stay on the graphics card for long time?

There is a small irony at this story. Sun learned many things about designing multicores when Sun developed the MAJC-5200 CPU and used it on the XVR1000 and XVR4000. The XVR4000 was the graphic card, that didn´t used something earthly like a PCI-bus, you plugged it directly onto the Fireplane Interconnect of the V880 instead of the CPU. Sun learned so much about multicore that some of the findings will reappear only in future incarnations like the Rock CPU (speculative multithreading e.g.)

The funny (and "history repeating" part): Intel start s to use it´s first manycore design on a graphics card as well. Like we did ... in 2002.

There was a small company called Plattform Solution. This company developed a Mainframe clone based on Itanium procs. And big IBM sued the small PSI. This could be a story of hate, legal dodges and the game of sueing and counter sueing. But the story ended differently: The big IBM simply simply swallowd the small PSI as reported by Computerworld for example.

Well ... where leave this the mainframe market. IBM took it´s nearest competito out of the game. This can lead to two developments in the future. You might think (and some industry analysts indeed do) that IBM will use the technology of PSI to build a new class of cheap mainframes. My personal opinion to that: Dream on and pigs might fly. IBM would canibalize it´s high margin mainframe business with such an offer and it needs the high margins to refinance the further development of the mainframe technology for a shrinking group of customers. And additionally: I heard on several occasions, that IBM uses laptops internally with mainframe emulation for test purposes. It would be easy for the large IBM to productize this emulation if they really want to do that. They don´t need to buy a company to do that (and more logical targets would be their own pSeries or xSeries and not an a somewhat strange Itanium server)

The more probable possibility is in my opinon a different one: They simply want to take out a competitor to protect their market share. And this would leave this acqusition as an interesting target for antitrust inquiries. But thats only my 2 cents, time will tell.

The free lunch of the ever increasing per-core performance will come to an end. Ars Technica writes in Intel: an expensive many-core future is ahead of us:

Intel has bad news for software developers. It's been hinted at already, but now the company has stated explicitly: it's not enough for software developers to be targeting dual, quad, or eight cores. No, the future holds tens, hundreds, or thousands of cores, and developers are going to have to bite the bullet and write programs that will scale to such systems.

With their article they refer to a blog post on the Research@Sun blog: Unwelcome Advice. So ... please no more questions if CMT is the right solution. It´s the only solution when even "throw-tremendous-amount-of-money-to-frequency-increases" Intel doesn´t think that the other way is future-proof.

Robin from storagemojo wrote an interesting comment about the The Hitz report (Dave Hitz´s declaration in the Sun/NetApp lawsuit):

The NetApp/Sun patent battle continues. I don’t see how NetApp can win this, given the Supreme Court’s Teleflex decision, which makes prior art a question that can be appealed all the way to the Supreme Court.
But the company is doggedly pursuing the battle, and Dave Hitz’s recent declaration - which he hoped would remain private - has been unsealed.

Sometimes i have the strong impression that Linux is the landfill for old filesystems. Linux is now the proud home of AdvFS. as HP contributed the old Tru64 Unix file system to Linux. But: Does Linux really need yet another filesystem? Beside all the other ones ?

The Oracle DB got even more expensive as stated in the new pricelist (dated June 16, 2008): From $15,000 for the Standard Edition, $40,000 for the Enterprise Edition and $20,000 for RAC to $17,500 for Standard Edition, $47,500 for the Enterprise Edition and $23,000 for RAC. The core mulitpling rules haven´t changed. More reasons to think about Mysql for matching workloads.

I really think this is benchmarketing at full throttle. IBM published an new TPC-C record for non-clustered systems. Okay, TPC-C is meaningless, but it´s fun to read the disclosures. Before i start: I hope you remeber the saying "TPC-C is a function about the number of disks, not a benchmark of the complete system".

A configuration with IBM Power 595 Server Model 9119-FHA yielded a TPC-C throughput of 6,085,166 transactions. That´s impressive. Even more impressive: This benchmarketing configuration used the small number of 10.992 disks with 73.4 GB capacity (The second on the list, an HP Superdome, reached 4,092,799 with just 6000 disks ). Ten thousand disks ... sounds like a real-world configuration

PS: It´s a disclosure with an availability 6 month in the future again, the maximum amount of time allowed under the rules of the TPC.

Mellanox made the silicon available for 40 GBit/s Infinimand: 40gig InfiniBand arrives. This is an interesting development as this gives Infiniband a nice performance advantage over Ethernet. In the race for the dominant interconnect for single fabric datacenter this really important.

x86 got 30 years old now. This is interesting as Mom and Dad tried to kill this baby several times. The kudos for keeping this architecture afloat must be credited to a completly different company: AMD. Imagine the market, if AMD didn´t introduced 64 bit to the x86 world? Okay, SPARC would have it much easier. But this is a different story. Enterprise computing by Intel would be Itanium. Not a desktop processor kept afloat by heavy wizardry. And they tried to kill off x86 as early 1982 with iAPX 432 (does anybody remember this proc?

Albeit it´s a cash cow for Intel, they are not really responsible for the success. I really thing x86 is the predominant architecture by pure accident. How would the market look, if Linus bought a Amiga with 68040 or an early Mac with PowerPC instead of the 386? What would have happened to x86 without AMD decision do develop the Sledgehammer architecture? Back in 1992 nobody thought of x86 as the dominant gaming plattform. Today it´s normal to use an x86 compatible processes as a data feeding device for graphic cards.

Sometimes the accident is the most powerful tool to shape the market.

I´ve wrote on some occasions in the past that the marketing of IBM is really innovative (vicious voices tend to say, it´s their last core competency). But they seem to have a lack of ideas recently.

To understand the copycat moniker i should give you some upfront informations: Perhaps you know the Sun Try&Buy program. You can do such a T&B for a multitude of systems. You can get a system for 60 days to test it. You buy it, when it matches your requirements, but you can send it back, when you don´t want to keep it (whatever your reason is). No strings attached. You just have to send it back in a proper condition. Another marketing program was the "Buy a UltraSPARC T1 server, we pay the electric power for the system for the first year". We have this T&B for years now and the electric power promo is a really old one....

Well IBM Germany announced a new program today: Consolidate at least two servers from another vendor, and you get a p520 for a test for ... wait ... 60 days. And in a different offering they pay your electricity bill for the new server for ..... surprise, surprise ... one year in case of a server consolidation:

Zusätzlich übernimmt IBM im Rahmen eines neuen Energieeffizienzangebots bei einer Serverkonsolidierung auf System p mit POWER-Prozessor ein Jahr lang die Energiekosten für den Betrieb des neuen Servers. Das Angebot ist bis zum 20. Juni 2008 gültig.

But there are some strings. For example you have to write a test report and IBM is allowed to publish it:

Testbericht: Jeder Teilnehmer erklärt sich bereit, innerhalb von vier Wochen nach Ende des Testzeitraums einen selbst erstellten Testbericht an IBM zu liefern. IBM ist berechtigt den Testbericht zu veröffentlichen.

Furthermore there is only one type of system in the programm: Just the p520 is covered by this program.

That´s such a cheap copycat .... IBM marketing used to be more innovative in the past ...