c0t0d0s0.org

Before starting to rave to much about Mainframe Solaris, we should ask "Cui bono?". With all respect to the technical merits, i have my problems with this technology and with answering this question.. I´m still searching for the business case for this OS. In my personal opinion, it has only one purpose: Helping IBM´s sales reps to sell mainframes as they can say "Even Solaris runs on our new iteration of our zDinosaur". Yet another technology to help IBM with their nuclear submarine problem

But: I have no idea, why even the most underinformed CIO should do this. When i take the experiences with Mainframe Linux into consideration, the price/performance will be horrible. Why should you use a mainframe for a considerable amount of money with a performance on par with a small x86 server? This doesn´t look as a wise choice.

The next point: Software support ... there is not really a ISV support for Linux on mainframe besides of IBM, and i don´t really think that this will be much different with Mainframe Opensolaris. This Opensolaris isn´t a binary compatible implementation. You have to recompile your stuff, you have to requalify it, you have to redeploy it on a completly different platform.

As the Mainframe Solaris is still a Solaris, you have to keep the skills in your company. You have to backup it from the inside to make an consistent backup from a running system. Sorry, no savings here.

By the way, IBM´s zSeries in entirety leaves me with some questions: There isn´t a single widely accepted benchmark available for Mainframe Linux, and when zSeries is such a great consoldiation plattform, why isn´t there an AIX for this plattform? Such a move would be obvious. And i would like some more data about those mainframe consolidation projects: Consolidation hundreds of small old servers with light load, is a tedious job, but not an archievement. How many of them were development or testing servers ... and so on. Data you need for decision making.

I don´t see any advantage in doing such a consolidation project: Consolidation by virtualisation? Well, the best way to consolidate old Sun SPARC servers (maybe a couple of E250) ist to buy a new Sun SPARC server (perhaps a T5220 or a V490 depending of the task) . You have Containers, you have LDOMs von CMT-Systems to. You can use the same binary, and when your ISV doesn´t exist anymore, you can use the Solaris 8 Migration Assistant for example. Much easier than porting, less risk and vastly cheaper.

At the end: Even when i take out of consideration, that this technology months to years away from beeing ready for prime time, i don´t see any viable reasons to use Solaris for Mainframes. Okay, with the exception of political ones ("The Sun SR didn´t send me coffee mugs for years" )

Mithun from Sun ISV engineering made some very interesting studies about the performance of SAP on Xen. It´s a very interesting read and gives you some good insights into the challenges of virtualising I/O heavy tasks. He published a draft of his whitepaper on his blog.

Okay, there is a beautiful icing on the sulfur seas in hell. You find a video of an OpenSolaris kernel boot into something similar to the single user mode on a zSeries at youtube: Part IV and Part V. The boot starts at the end of Part IV.

I thought a little bit about the TPC-H benchmark published by IBM yesterday. There is something in it, that leaves some question. The p570 is a 8 socket system. You can build it by stacking 4 two-socket boxes with some special cabling. That´s one of the points behind buying a p570. Nevertheless, the configuration of the benchmark didn´t worked that way. They had 32 of this p570 building bloacks and used this boxes as 32 distinct systems making the p570 buildingblocks to an expensive volume server. By using the capability to build bigger systems ot of those building blocks you would have 8 instead of 32 systems to manage.

The questions: What´s the reason of using such a configuration? Is there a scalability problem within the p570 giving you less return for the socket in bigger configurations ? What´s the impact to loads with higher dependencies between the partitions? I would like to see the performance numbers for a system with 32 p570 buildingblocks in 8 systems with an otherwise equal configuration.

Wow, it´s benchmarketing time at IBM again. IBM Announces DB2 and POWER6 Combo Trounces HP and Sun by 2x and 3x Respectively in New Business Intelligence Benchmark. IBM you are soooo great .... you was able to beat our TPC-H 10 TB by a factor of 3. It´s really an technological archievement in 2007 to beat a TPC-H benchmark result generated on on 29th November 2005 ... exactly 2 years ago today. Come on ... in IT 2 years are a fscking long time ....

Everytime i read a benchmark from IBM, i really looking forward to read their disclosure to see, what you can do in benchmarking, when you have nearly unlimited resources.

The configuration of IBM consists out of: 32 p6 p570 servers, each server had 32 GB of memory, resulting in 1 TB memory. Each of the systems had 96 36 Gigabyte 15k harddisks with 4 GB/s FC. A whooping amount of 3072 harddisks. A fully 10 GB enabled network.

The SF25K result was done on 1296 disk, with 10k rounds with 2 GB/s. The memory had a size of 288 GB. On a single system with a single operating system image The system used the old UltraSPARC with 1.5 GHz

Not that you can´t buy an system from Sun equivalent system from IBM. The venerable SF25k now has up to 1.15 TB per domain. And the M9000 class servers are a completly different story. But,dear IBM,when you want to make a statement of relative performance, the system should be at least somewhat similar.

So dear IBM, next time you want to showcase you system, don´t do it against a benchmark 2 years old. What´s the statement of such a press announcement: We are 3 times faster with our top of the line system with a benchmarking configuration than a 2 years old configuration. Big deal, IBM, really big deal ...

Alec Muffet did it again. He made another presentation lessing style, this time about Re-use 2.0 or how a different view to presentations can lead to an effective reuse of such communication like presentations and workshops.
I see one point weaking his conclusion: The reactions of the people hearing such an video/audio augumented presentation are unpredictable. How will the customer react, when you run a movie instead of a presentation. But nevertheless, Alec is right with his position. I think, i will adapt it in making and using video presentation where appropriate.

PS: I assume, the pirate copy is mine, as it was my notebook that was used in the first presentation slot to present it. I gave it only to my managers manager, really

Chris explains the difference between an engineer and a manager: A380? What A380?.

eweek reports in OpenSolaris Soon to Run on IBM Mainframes about the effort to port Opensolaris to mainframes:

David Boyes, president and chief technology officer of Sine Nomine Associates, an Ashburn, Va.-based consultancy that handled most of the integration and migration duties, told eWEEK at the Gartner Data Center Conference 2007 here that the new IBM-tuned version of OpenSolaris will be ready soon. He declined to be more specific.

Albeit a technological archievement, i think it will have the same future like Linux on Mainframe. It´s there, it´s used for some tasks, but it won´t put new customers to the mainframe. It´s simply cheaper and simpler to use a x86 or SPARC system and support by ISV is even more difficult. The USP of Mainframe Linux was the virtualisation, but this is hardly unique anymore.

Neat idea ... a virus aquarium ... an idea for the next christmas season:

Ubuntu was certified by Canonical on some new hardware from Sun. Now you can buy support for Ubuntu from Canonical for the Sun Fire T5220 and 5240 ( both UltraSPARC T2) and the Sun Ultra 24 (Xeon).

Just a thought: When almost every big player in systems market announces some virtualisation products making virtualisation a commodity, what is the justification for VMware´s market capitalisation of 27.36 billion US$ (11/26/2007) ?

Wenn Karlsruhe den Politikern irgendwann hoffentlich mal die Sammelwut austreibt, muss die Aufmerksamkeit mal auf die Firmen gelenkt werden, die allzu freizuegig mit Kundeninformation umgehen. Jens von Pixelfeuer (und Sun) schreibt in seinem Blog ueber eine sehr merkwürdige Pressemitteilung von ebay:Mein Kiel lob ich mir - Ebay wertet aus

Constantin wrote a neat tool: ooshrink. This tool shrinks presentation by doing some tricks on the pictures of the presentation. It doesn´t help me much for my own presentations, as i use Keynote for them, but it´s fscking useful for sending company presentations to colleagues or partners. (Disclaimer: Don´t do such tricks on you only recent version. Make more backups!)