Adventures in systems land

Yep, it’s a mouthful. I’ve just been booking some events and presentations for later in the year, and this one, which I had initially hoped to attend clashes with one, so now I can’t.

However, in case the snappy new title passed you buy, it is still the excellent IBM Technical conference it used to be when it was the IBM System p, AIX and Linux Technical University. It runs 4.5 days from 8 - 12 September in Chicago and offers an agenda that includes more than 150 knowledge-packed sessions and hands-on training delivered by top IBM developers and Power Systems experts.

Since the “IBM i” conference is running alongside, you can choose to attend sessions in either event. Sadly I couldn’t find a link for the conference abstracts, but there is more detail online here.

I must admit I’ve been a bit pre-occupied lately to post much in the way of meaningful content. For a frame of reference, I’m off looking at I/O Virtualization, NIC, FBA, Switch integration and optimization, as well as next generation data center fabrics. It’s a fascinating area, ripe for some invention and there are some great ideas out there. Hopefully more on this later.

I’ve also been looking at why we’d want to create a set of extensible interfaces that would allow virtual partitions to be used to extend the Power platform function, I have to say, the more I think about this the more interesting it is. I’d be interested in your feedback on the idea of creating a set of published interfaces to Power VM to allow you to add function running in a logical partition, or a virtual service partition to add or replace function that we provide. So, for example, maybe you want to add a monitor or accounting agent to function where we do not provide source code. We’d document the interface, provide a standard calling mechanism, a shared memory interface and so on. Then, you’d implement your function in an LPAR, probably using Linux on Power, or any other way you want.

Then, based on an event in an OS, Middleware, business application running in an LPAR under AIX, IBM i or Linux on Power generates a call to the OS, Hypervisor, or VIOS, instead of us providing the function, the hypervisor or VIOS would check to see if a Virtual Service Partition had been registered for that function, if so the call and event handling would be directed there instead of to the normal destination.

In this way we could also provide a structured way to extend the platform, where we currently would like to provide function, or customers have asked for it, but it hasn’t made our development list. Any comments? Good idea, bad idea, something else ?

I’ve been working on slides this afternoon for a couple of projects, and wondering why producing slides hasn’t really gotten any easier in 20-years since Freelance under DOS? Why is it I’ve got a 22 flatscreen monitor as an extended desktop, and I’m using a trackpoint and mouse to move things around, and waiting for Windows to move pixel by pixel…

Anyway, I clicked on the LIBSyn link for the RedMonk IT Management Podcast #10 from back in April for some background noise. In the first 20-mins or so, Cote and John get into some interesting discussion about Power Systems, especially in relation to some projects Johns’ working on. As they joke and laugh their way through an easy discussion, they get a bit confused about naming and training.

First, the servers are called IBM Power Systems, or Power. The servers span from blades to high-end scalable monster servers. They all use the Power PC architecture, instruction set RISC chip. Formally there had been two versions of the same servers, System p and System i.

Three operating systems can run natively on Power Systems, AIX, IBM i (formally i5/OS and OS/400) and Linux. You can run these concurrently in any combination using the native virtualization, PowerVM. Amongst the features of PowerVM is the ability to create Logical Partitions. These are a hardware implementation and hardware protected Type-1 Hypervisor. So, it’s like VMware but not at all. You can get more on this in this white paper. For a longer read, see the IBM Systems Software Information Center.

John then discussed the need for training and the complexity of setting up a Power System. Sure, if you want to run a highly flexible, dynamically configurable, highly virtualized server, then you need to do training. Look at the massive market for Microsoft Windows, VMware and Cisco Networking certifications. Is there any question that running complex systems would require similar skills and training?

Of course, John would say that though, as someone who makes a living doing training and consulting, and obviously has a great deal of experience monitoring and managing systems.

However, many of our customers don’t have such a need, they do trust the tools and will configure and run systems without 4-6 months of training. Our autonomic computing may not have achieved everything we envisaged, but it has made a significant difference. You can use the System Config tool at order time, either alone, with your business partner or IBMer, and do the definition for the system, have it installed and provisioned and up and running within half a day.

When I first started in Power Systems, I didn’t take any classes, was not proficient in AIX or anything else Power related. I was able to get a server up and running from scratch and get WebSphere running business applications having read a couple of redbooks. Monitoring and debugging would have taken more time, another book. Clearly becoming an expert always takes longer, see the wikipedia definition of expert.

ps. John, if you drop out of the sky from 25k ft, it doesn’t matter if the flight was a mile or a thousand miles… you’ll hit the ground at the same speed

pps. Cote I assume your exciting editing session on episode 11, wasn’t so exiciting…

ppps. 15-minutes on travel on Episode #11, time for RedmOnk Travel Podcast

I’ve had a few emails asking me if I was going to write a log entry on this month announcements, and to be honest I wasn’t. They are an impressive list of products, branding and customer announcements. I wasn’t anything to do with them, given I’m no longer asked to do marketing/sales types presentations, I picked that time to go do the Machupichhu/Inca trail trip in Peru.

The April announcements though were a credit to the teamwork across the even more global IBM. Core Processor and server development teams in Austin and Rochester, worked with domain specialists in Poughkeepsie and Boeblingen. On top of this were the software development and test teams in India, China and and ever increasing number of places.

The new UNIX enterprise server, the Power™ 595 is an impressive beast if the charts are anything to go by. I’m hoping to get Nancy to take me across the building to the test bring-up to have an up close and personal look sometime this week. The new POWER6 “Hydro-Cluster” supercomputer, the Power 575, is very impessive using a new super-dense system, with a unique, in-rack, water-cooling system and with 448 processor cores per rack. Apprently it offers users nearly five times the performance and more than three times the energy efficiency of its predecessor, IBM’s POWER5+™ processor running upto a industry busting clock cycle of up to 5 GHz.

These Super-dense systems are starting to become a really interesting value prop. On Friday I got a link to the IBM.COM public website that included a video on our iDATAPLEX offering. It was there Saturday and has gone today, but it was there as this search in the current google index shows. The video doesn’t show any technical details but does give an interesting insight into this x86 based super-dense, Internet scale, behemoth of a server. I was hoping there was other public comment or blog entries I could leach off for discussion points, but the only search results return job postings

Anyone go to the iDATAPLEX session at IMPACT 2008 and want to comment ??

There’s an excellent analysis by Frank Dzubeck over on Network World today about the new Enterprise Data Center and that hoary old chestnut latency. I don’t know who briefed Frank, it wasn’t me, Jeff and I talked this afternoon and I asked, it wasn’t him, since the article covered also the z10 announcement, I have a good idea though

Frank covers ensembles, data center utilization and the some of the new data center fabric issues extremely well. He also makes the point, that I’d like folks to be clear about, that this isn’t the resurgance of the mainframe, or everthing back to a central server.

We’ve grown use to indefinite waits, or unbelievably fast response times from certain popular websites, but the emerging problem is around latency in the data center. How to deliver service levels and response times in an increasingly rich and complex systems environment. It’s OK to build a data center or server subsystem focussed around a single business model, something like Amazons EC2 or S3, or Googles search and query engines; it’s another to integrate a vast array of different vendors IT equipment bought at different times for different business applications and services and integrate them all together and orchestrate them as business services. While MapReduce may or may not be as good as, or better than a database, not everything is going to be run in this fashion.

Fibre channel over ethernet is a going to happen, 10Gb ethernet opens up some real options in terms of both integrating systems, and distributing services. It will be almost as fast to connect to another server as it is to talk between cores and processors within the same server. This disclosure from IBM Research today shows the way to the next generation of interconnected infrastructure, working at 300-Gbit/second, the bus goes optical making the integration of rich data systems video, VOIP, total encryption of data, secure key based secure infrastructure services, integrated with more traditional transactional systems a real possibility.

The opportunity isn’t to take the same old stuff and distribute it because the fabric is faster, it’s about better integrating systems, exploiting new ways of doing things. Introducing a common event infrastructure, being more intelligent about WAN and Application routing, having a publish/subscribe/consume model for the infrastructure and genuinely opening it up and simplifying it.

Of course, there a re lots of blanks to be filled in, but the new Enterprise Data Center is taking shape.

IBM announced today our new Enterprise Data Center vision. There are lots of links from the new ibm.com/datacenter web page which split out into their various constituencies Virtualization, Energy Efficiency, Security, Business resiliency and IT service delivery.

To net it out from my perspective though, there is a lot of good technology behind this, and an interesting direction summarized nicely starting on page-10 on the POV paper linked from the new data center page or here.

What it lays out are the three main stages of adoption for the new data center, simplified, shared and dynamic. The Clabby analytics paper, also linked from the new data center page or here, puts the three stages in a more consumable practical tabular format.

They are really not new, many of our customers will have discussed these with us many times before. In fact, there’s no coincidence that the new Enterprise Data Center vision was launched the same day as the new IBM Z10 mainframe. We started discussing and talking about these these when I worked for Enterprise Systems in 1999, and we formally laid the groundwork in the on demand strategy in 2003. In fact, I see the Clabby paper has used the on demand operating environment block architecture to illustrate the service patterns. Who’d have guessed.

Simplify: reduce costs for infrastructure, operations and management

Share: for rapid deployment of infrastructure, at any scale

Dynamic: respond to new business requests across the company and beyond

However, the new Enterprise Data Center isn’t based on a mainframe, Z10 or otherwise. It’s about a style of computing, how to build, migrate and exploit a modern data center. Power Systems has some unique functions in both the Share and Dynamic stages, like partition mobility, with lots more to come.

For some further insight into the new data center vision, take a look at the presentation linked off my On a Clear day post from December.

Feb. 12th Datamation announced their product of the year awards, the IBM Power Systems p570 server won enterprise server of the year, up against the IBM System x 3950 M2 Server, the HP MediaSmart Server, and the Dell PowerEdge 2970.

Details on all the award winners are here.

Thanks to James Governor at Redmonk or @monkchips on twitter, for the pointer. In this pretty direct interview, Linus Torvalds says something I got into trouble for about 7-years ago. Linus says “An OS should never have been something that people really care about… it should be completely invisible”.

I gave the keynote presentation at the OS/390 Expo and Performance Conference, I think in either 2000 or 2001, during the presentation I made exactly the same point, only about Linux. Yes, Linux was great, yes, we were going to do some pretty innovative things with it, but if in 5-years time we are still wrrying about scalability, driver compatibility etc. then we’d missed the point, we shouldn’t really have to care about the OS.

Unfortunately in the audience was the IBM Account Executive for a large multi-national company, and the CEO from that company. Rather than come and ask questions afterwards, they took one point from a 75-minute presentation and complained about me to my then VP, Carol Stafford. Carol “invited” me into her office, I had to explain the remark, and context, Carol understood and took care of things.

So it’s with a wry smile I read the Torvalds article, and then sat up and wondered, do we still care about the OS, or has the stack become more important?

Trying to find a reference book on AIX 6, I looked at the latest list of Redbooks for Power Systems, these are the ones listed in the RSS feed since the start of October 2007.

Continue reading ‘Catching up on IBM Redbooks’

via James Governors del.ico.us feed, I read a pretty disappointing blog post on Don MacAskill CEO and Chief Geek of SmugMugs, SmugBlog.

Reading some of his past posts it’s easy to accuse Don of being a bit of a Sun fanboy. He recently ran a server bake-off to get some new servers for SmugMug, and decided to go with Sun, fair enough. I can’t dispute that Sun have a good offering in the web space, and being based out on the West Coast, get a lot of face time and word of mouth endorsements with many of the startups, especially in the web 2.0 space.

I know how important this can be. Back in 2000, I hung out a lot at the Silicon Valley World Internet Center and then, late in 2005, early 2006 worked out of the IBM office in Palo Alto with a number of key virtualization partners to get some direction and development work started.

What troubled me was not the Don had chosen Sun for his servers, but his comment “One of the attendees, who spends obscene, ungodly amounts of money with IBM, can’t even get engineering staff on the phone. Apparently, IBM has a big sales force who’s trained to buffer customers away from the engineers.”

“shurley shome mishtake”? My whole career before I joined IBM, was littered with experiences with sage and helpful IBM engineers. Either through the numerous user groups, or best of all, when the products broke, and after talking to level-1 and level-2, you’d get through to the level-3 folks. I remember to this day having a discussion with someone called, I think, Linda Iannella, who worked up in Kingston in the mid-1980’s. She knew code like no one I’d ever spoken to, when I asked how she was so sage, she replied, “I work on this code 10-hours a day, every day”. Adrian Walmsley, a former IBM UK employee was probably the most influential, and I’m delighted to have worked with him later on.

Have things changed so much that you can’t get in touch with the technical team at IBM anymore, or was Don’s experience atypical? Is it a west coast versus east coast thing, or just becuase IBM is so big these days?

I have to admit, getting things actually done these days can be difficult at times if you approach a novice IBMer, but we have an excellent kStart team out in the valley working with some startups, and most of the blue coud work is being done in Almaden and SVL.

Let me know what your experience has been. Can I help ??