Martins Blog

Trying to explain complex things in simple terms

The cause for and against the Exadata simulator

Posted by Martin Bach on December 8, 2011

I am on my way back from the best UKOUG conference I ever attended, unfortunately a lot earlier than planned. Before I start forgetting all these great moments it is time to write them up. To make use of James Morle’s words: if you weren’t there, you lose. I couldn’t agree more!

The Oak Table Network organised “Oak Table Sunday”, a hugely successful event on Sunday afternoon. This event featured some of the brightest Oracle minds, and thanks to a very relaxed atmosphere made it all a truly exceptional experience. I have to say that the audience was quite illustrious too-I didn’t recognise Paul Vallee from Pythian with his Movember moustache at first and to my great joy I finally met Piet de Visser again. After exchanging a few words with them I ran into so many people it was just great!

Unfortunately I couldn’t make it before the HA panel session, where Alex Gorbatchev, Dave Ensor, James Morle, Greg Rahn, Dan Norris, Graham Wood, Jonathan Lewis and Mogens Norgaard and all the others I just forgot to mention answered questions from the audience.

Inevitably, the Exadata discussion started. One member of the audience put forward the proposition that there should be an Exadata simulator. While everyone in the audience agreed, feedback from the panel was different. And I tend to side with the panel on this one. Sure, Oracle is very secretive about Exadata, but I expect a business reason behind it. As everyone who implements Exadata knows, Oracle wants to use ACS to provide support. Some customers however have decided not to treat Exadata as a black box and want to understand and ultimately support it themselves. Other consultancies such as Enkitec and VX Company develop a business model to provide independent support for Exadata implementations.

However, all of the involved parties (including Oracle!) struggle to find good, experienced, reliable and dedicated staff for Exadata support. Now why could that be? First of all Exadata is a lot less accessible. Unlike other Oracle software, it is not possible to experiment with Exadata without actually getting one. And renting lab time is probably a difficult thing to do as well. As Jonathan Lewis put it, you sometimes have a base plan of what you want to measure, and quickly develop different approaches to the same problem which require setup time. If the lab time is let’s say 48 hours, then spending a couple of hours on a test case takes valuable time away. Needless to say, lab time is in high demand and it might be that you have to wait a long time to be back.

Now the counter argument is of course that you couldn’t do this with a massive p-Series server either so the problem of testing your application on the new hardware has always been the same. Except that Exadata adds a secret sauce to the processing which you cannot get elsewhere ;)

So far I fully agree. There is no way you can try Exadata features without getting one, and if the initial assessment was wrong, your benefit of migrating to Exadata might be less than what you were hoping for. I do however disagree with the idea that a simulator makes that situation any better. You won’t be able to use a VM to find out if there is a performance benefit migrating to Exadata. First of all, your laptop or whichever other hardware you are using will not have the power to simulate a cell two hex-core X5670 and 24G of RAM. Neither will you have a F20 card used as flash cache in the real cell. Also, even at the low-end of the Exadata product range the system comes with three cell servers…

Having said that I do think that it would be very nice if cell patching could be practiced outside the really precious hardware for which getting downtime is probably very difficult. Every RAC DBA has applied a bundle patch in the past, or a PSU for that matter. That’s easy, and not different on Exadata. A cell patch however is a completely different thing, especially with the added twist that a completely broken cell can have a big impact on availability and processing power. So please Oracle, do something and let us test cell patches in software!

About these ads

11 Responses to “The cause for and against the Exadata simulator”

  1. Martin,

    I completely agree with you on the simulator problem. If you have licenses for Real Application Testing, you can run through an Exadata simulation, but I’m not sure how accurate it really is. Might be worth testing a workload against it, then running the workload on one of our Exadata racks to see how close the results are. Hopefully, Oracle can come up with something to allow users to test Exadata cell patches. I know that there were originally some VM images floating around with Exadata software on them, but the patching process is so tightly bound to the hardware that it’s practically impossible to run a storage server patch against them and expect it to work. Right now, we just test the patches as soon as they come out on our lab Exadata, and see what happens. Anxiously awaiting the certification on 11.2.0.3…that’s going to be a fun week!

    Andy

  2. Hi Martin,

    I’m following your blog, keep up the good work. Well I think that simulator will be also beneficial for getting familiar with all tools for administration of Exadata, like cellcli and gain confidence with the architecture, commands and tasks.
    I was browsing for Exadata trainings and found by accident found following blog post where they say that Exadata simulator really exists:
    http://odenysenko.wordpress.com/2011/05/03/i-have-passed-1z0-536-oracle-exadata-11g-essentials/

    Regards,
    Sve

    • Martin Bach said

      Hi Sve,

      the admin tools are really not a challenge at all, they can be picked up in no time or alternatively have a look at the Enkitec crew’s excellent “Expert Oracle Exadata” book.

      I’d be very careful-an official Exadata doesn’t exist outside of Oracle. Have a read of Andy Colvin’s comment below as well, we both conclude that a simulator would most likely produce a false sense of security and non-comparable results.

      Hope this helps,

      Martin

  3. Hi,

    I completely agree with you, just found the link and decided to share a thought on the topic. I’ve already ordered the book and I’m looking forward to have a chance in the near future to try it out for real.

    Regards,
    Sve

  4. There most certainly is an “Exadata Similator.” In fact there are full VM images that simulate and entire cell. Know how I know? :-) They are only withing the walls of Oracle though (that includes some trainging environments.

    Fact is, cellsrv is totally portable to any system that runs an RHEL5 derivation. The BMC layer needs ported for cellsrv HW management/monitoring functionality but there is a fine abstraction layer in place so that is a small porting effort as was proven in the race to switch from HP lights out management to Sun.

  5. Tim Hall said

    Hi.

    In my opinion, there are two perspectives on this:

    1) Will a simulator give me any indication of Exadata performance? Certainly not. The same way the performance of a VirtualBox RAC on your laptop is nothing like a real RAC from a performance perspective.

    2) Would a simulator be useful for functional testing of Exadata? Of course. Being one of those people who have never used Exadata I can assure you it would be nice to just play with the virtual Exadata to get an idea about how effective things like offloading, storage indexes, HCC are. You don’t need the real hardware to see these kicking in and analyze the impact of them on your load.

    The images are out there. It’s no effort to release them, like every other bit of Oracle software. Hell, if they only release them on Oracle VM it will actually force more people to try that product…

    Cheers

    Tim…

  6. vishal Desai said

    Oracle should come up with use/test for 30-45 days and buy policy.

  7. UKOUG 2011 Summary…

    This year’s UKOUG 2011 conference in Birmingham was so packed and multi-dimensional for me that I decided it’s going to take a few very different posts to describe my experiences without sending any unfortunate readers into a deep stupor, so the over…

  8. I think Tim is closest to my position here.

    It’s not about testing what performance you can expect and people aren’t looking for a full-scale test environment – that’s what Proof-Of-Concepts and lab visits are for.

    The fact remains that there is software involved here as part of the offloading process and so it’s difficult to write sensibly about whether specific workloads can be offloaded successfully without actually having access to the real gear. Contrast that with just about any other software that Oracle supply – I can get that, play with it, test it and work out whether it will be useful to me. I can help find bugs in it and so on. That’s the useful eco-system of experienced IT people that Oracle are missing out on.

    Let’s put it this way. From personal experience, there are many things to learn about how various aspects of the software might work for your applications that might be useful to find out before spending a lot of cash and aren’t always easy to establish in a short PoC. Or maybe that is the point here ;-)

  9. Oracle is not only withholding Exadata Simulator, they are also with holding Exadata Documentation. It would be so much nicer if they made the Exadata Documentation available to everyone. Everyone could understand Exadata slightly better by reading documentation. But even the documentation is not publicly available.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

 
Follow

Get every new post delivered to your Inbox.

Join 2,075 other followers

%d bloggers like this: