Inside System Storage -- by Tony Pearson

Tony Pearson Tony Pearson is a Master Inventor and Senior IT Specialist for the IBM System Storage product line at the IBM Executive Briefing Center in Tucson Arizona, and featured contributor to IBM's developerWorks. In 2011, Tony celebrated his 25th year anniversary with IBM Storage on the same day as the IBM's Centennial. He is author of the Inside System Storage series of books. This blog is for the open exchange of ideas relating to storage and storage networking hardware, software and services. You can also follow him on Twitter @az990tony.
(Short URL for this blog: ibm.co/Pearson )
  • Add a Comment
  • Edit
  • More Actions v
  • Quarantine this Entry

Comments (5)

1 vskinner commented Permalink

I watched it last night. Very interesting. Is it wrong to say I felt a little bit sorry for the humans playing against him? I also found the host interacting with the computer to be hilarious. More humor than I expected!

2 TonyPearson commented Permalink

<p>Valerie, I don't think it is wrong to feel bad for the humans.</p> <br /> <p><br /> I remember back when IBM had DeepBlue compete against Garry Kasparov. In 1989, Garry won easily all games. In 1996, Garry had three wins, two draws and one loss, so he won again. In 1997, Garry had only 1 win, 3 draws and two losses, losing the match. Garry was notably upset.<br /> </p> <p><br /> Now, in this case, we have two champions of Jeopardy! They have already played practice rounds against WATSON, so they know what they are getting in to. Remember the first place gets $1 million, second place gets $300K and the third place gets $200K. The humans will be donating half their earnings to charity, and then party with the rest, so I won't feel bad for either of them. I suspect that they might be more worried about how each human plays against the other human. Brad beat Ken in a tournament before, so will Brad feel bad if Ken does better than him? They are both smart guys, but maybe their egos might take a hit whomever comes in third place.<br /> </p> <br /> -- Tony

3 TonyPearson commented Permalink

<p>The full set of moves for each game in the Deep Blue match against Garry Kasparov in 1997 can be found here:<br /> </p> <br /> <a href="http://www.research.ibm.com/deepblue/watch/html/c.shtml">http://www.research.ibm.com/deepblue/watch/html/c.shtml</a> <br /> <p>---Tony</p>

4 BSamson commented Permalink

Tony- <div>&nbsp;</div> As a storage seller, how close is the Watson SoNAS implementation to our GA product?

5 TonyPearson commented Permalink

Bryan, <br /> There are three minor differences. <br /> <p><br /> First, Watson uses POWER7 versus GA product uses x86 CPU processors. IBM's General Parallel File System (GPFS) runs on AIX, Linux on POWER, as well as Linux-x86, so functionally identical across the board. It was easier for the folks in Austin to put together an all-POWER7 Watson than mixing in a few x86 machines inside. This allows all the frames to be identical.<br /> </p> <br /> <p><br /> Second, GA version of SONAS has separate NFS interface nodes from the storage pods so that all NFS interface nodes can talk to all storage pods. A storage pod is two storage nodes connected to a common set of disk. However, for Watson there is only one storage pod, so it was simpler to just run the NFS interface software directly on the storage nodes themselves.<br /> </p> <br /> <p><br /> Third, GA version of SONAS uses high-density 60-drive 4U-high drawers, or connects to an XIV disk for capacity. The Watson uses 12-drive drawers, each server connected to two drawers for a total of 21.6 TB raw capacity. The 3.5-inch 450GB 15K RPM SAS drives are the same in both cases.<br /> </p> <br /> --- Tony

Add a Comment Add a Comment