Total Pageviews

Tuesday, October 16, 2012

Cloud Computing and the Cult of Intel and x86

So firstly apologies, I have been a bit lazy of late on my own personal ramblings, and have been cut and pasting rather than being original, well that is going to change...

Over the last couple weeks I have observed a worrying trend in my interactions with clients and on the Twittersphere i.e. the cult of x86 and it's hold over the world of Cloud Computing...to quote a recent Twitter interaction, after asking a recent follower (you know who you are) for their views on cloud on z, I got the following response:

"Technically magnificent - totally impractical - won't run Intel Binary products. Chocolate teapot. (PS - I love Z and wish it were not so)"

 Well you can imagine my response!!!  For those with no imagination it went something like this:

 If cloud = intel and x86, then agree. What about Linux? (RHEL & SLES), we are seeing adoption for a Linux cloud on z

I met with a large global outsourcer recently who has an x86 based cloud offering (which is losing money by the way) and we positioned DBaaS to them based on Linux on z.  Well after much mudslinging and a verbal battle they begrudgingly agreed that databases don't usually play nice with x86 virtualization and that there may be an alternative, especially since the approach we proposed was approx 40% cheaper!!!

It amazes me in this cash strapped times, that when you present a solution that is patently cheaper and has numerous other benefits such as industry leading security, availability and scalability, that you still get push back.  So let’s explore why we get pushback for Cloud on the Mainframe:
  • Mainframe as a word has a dark meaning, in some languages it is a substitute word for old, in others it translates to proprietary.  Well my response to this is:
  •  $5bn of R&D investment since 2010, and $1bn in the latest EC12 alone does not equal an ‘old’ platform and as for proprietary how does a server that runs 7 different operating (2 of which are Linux) systems and 13 databases sound?
  •  Skills are hard to find – well there is some truth in this, but only because the box runs so damn efficiently that you don’t need and any army of IT Staff!!! I met with an energy supply company that has over 2 million active customers who has a mainframe team totalling one sys prog the other week and they only have their core billing system running on z, so nothing important…
  • x86 is what everybody else is doing – well where do I start, have you heard the one about the lemmings? Or the one about the PC manufacturers who thought that Apple would never get a hold in the home computing space…I can go on but you get the picture.
So let’s be clear for all those x86 cult members who have found their way to the darker recesses of the blogsphere, namely here, read this whitepaper:

http://www-03.ibm.com/systems/z/advantages/virtualization/platformmatters.html

And then contact me on Twitter at @StevenDickens3

Friday, October 5, 2012

Details of zTechnically Speaking in the UK

2012 zTechnically Speaking is a stream in the November IBM Smarter Computing conferences
which you and your colleagues in your organisation are invited to register and attend.

Roger Fowler/ Iain Neville from the IBM UK Hardware Technical Team will be covering the
recently announced zEnterprise zEC12 hardware which is a key part of IBM’s Smarter Computing
revolution. It is a great opportunity for anyone who wants to understand these recent announcements.

At the Manchester and Edinburgh events Jeff Biamonte will give an insight on zEnterprise chip design,
manufacture, direction and futures. Jeff is the Manager for the System z Processor Design & Verification
Group based at the IBM  Poughkeepsie, USA manufacturing plant.

At the London event Howard Rogers from Tesco will provide an insight to their 2012 zEnterprise
hardware refresh  replacing all their Escon connections with Ficon while keeping their legacy Escon equipment.

Speakers from IBM's z Software technical team will explain how recent IBM software announcements enable IBM middleware to exploit the new zEC12 technology to deliver data analytics and cloud services, with even greater security. 

During the breaks and lunch there will be a chance to see live zEnterprise systems and talk to experts
from IBM Software and Hardware Groups.  These events are planned to start around 9am and finish around 4:30pm. Agendas will be sent to registered attendees nearer the time.

I look forward to meeting you at a z Technically Speaking stream. These events are very popular so please register today to secure a place at your preferred location. There is no charge for these events so please feel free to invite a colleague, but remember these will be very popular and places are limited.

These are the scheduled events with the webpages for you to register:

Thursday, 1 November – DoubleTree by Hilton Hotel London 

Tuesday, 6 November – Manchester - The Lowry Arts and Entertainment Centre

Thursday, 8 November – Edinburgh - Sheraton Grand Hotel and Spa hotel


These are the webpages to Register for each event if you choose use cut and paste.

Please ensure you cut and paste both lines to work in your Browser

LONDON REGISTRATION
https://www-950.ibm.com/events/wwe/grp/grp019.nsf/v16_enrollall?openform&seminar=BCBCJDES&locale=en_GB&lang=&S_TACT=102JH7WE&MATTACT=102JH7WE&CONT=43242.0

MANCHESTER REGISTRATION
https://www-950.ibm.com/events/wwe/grp/grp019.nsf/v16_enrollall?openform&seminar=92FD54ES&locale=en_GB&lang=&S_TACT=102JH7WE&MATTACT=102JH7WE&CONT=43242.0

EDINBURGH REGISTRATION
https://www-950.ibm.com/events/wwe/grp/grp019.nsf/v16_enrollall?openform&seminar=9CFAS4ES&locale=en_GB

Thursday, October 4, 2012

Workload Placement and the economics of Cloud

Had a very interesting meeting with a global outsourcer yesterday where got under the covers of their rate card for private cloud so thought I would share some observations.

My presentation on workload characteristics was entirely focused on how all workloads are different and therefore require different platforms.  Whilst presenting, this point was widely acknowledged and accepted.  Then when we get into the general discussion about the suitability of z as a cloud platform the discussion focused on how can IBM make z just like other platforms so it is easy to size. 

Now I fully understand that z is a different religion and understanding how our I/O based approach relates to cloud is not easy to articulate or fully understand from an x86 standpoint, but when you acknowledge that all workloads are different can you not acknowledge that platforms differ to?

An analogy I used after the meeting was:

Imagine you commute to work by train and a colleague commutes to work by bike, which form of transport is better?  Obviously a lot of factors come into play, some of which could be:

  1. What is the weather like generally for each commute?
  2. How long are the commutes?
  3. How close do you both live to a train station?
  4. Which country do you live in?

If you live in Oslo next to a train station and your office is also next to a train station and the distance between the two is 50-miles, then the answer is clear.

If you colleague lives in Holland and is 10-miles from the nearest train station, and the commute is 10-miles on a bike, then the answer is clear.

Why can't the same principle apply to workloads?

If you take a look at Oracle as a Service on a private cloud as an example, then the answer is a train, and let me explain why....

  • Oracle does not play nice with VMWare... the default position of Oracle is don't virtualise our database unless you do it on our virtualisation software
  • Oracle typically charge for a license per every two cores of x86
  • A typical Oracle license will cost £25K over 3 years

So if you have 288 cores of x86 for instance then you need 144 licenses or put another way you need to give the Larry Ellison yacht Fund £3.6m over 3-years.

Now imagine a weird and wonderful black magic platform existed where you could handle the same workload on a 12 core machine, which need 12 Oracle licenses, which had no problems with its virtualisation layer supporting Oracle.  The math goes someithing like this:

12 cores = 12 licenses = 12 x £25,000 = £300,000

Or put another way Larry has to wait another year to buy that racing yacht.

Or to go back to my original analogy still want to ride to work?