New article: 8 socket commodity servers

Article: 8-Socket Commodity Servers: Flourish or Perish?
By: David Kanter (dkanter.delete@this.realworldtech.com), March 10, 2010 12:38 am
Room: Moderated Discussions
Michael S (already5chosen@yahoo.com) on 3/9/10 wrote:
---------------------------
>David Kanter (dkanter@realworldtech.com) on 3/9/10 wrote:
>---------------------------
>>Yesterday was an odd day in RWT history. We had three articles go up in a single day - probably a record.
>>
>>The first two were Russian translations of articles on Larrabee and Hot Chips.
>>
>>The third article is a biref look at 8 socket servers. This includes a bit of analysis
>>on why 8 socket servers were not successful previously, and some reasons why this may change.
>>
>>The article was first posted through exectweets here:
>>
>>http://exectweets.com/2010/03/08/eight-socket-servers-have-big-potential/
>>
>>
>>I subsequently put it online at:
>>http://www.realworldtech.com/page.cfm?ArticleID=RWT030810232808
>>
>>>
>>
>>Enjoy - I am hoping to return to this topic sooner rather than later.
>>
>>David
>
>Just read the first paragraph and I already have a couple of questions/disagreements.
>
>1. 2-4 socket systems are a sweet spot? Tell me by which >definition of sweet spot
>4 socket is part of it and 1 socket isn't? In reality, >4-socket is a small constantly
>shrinking niche rather than a part of sweet spot.

Realistically 2S is the sweet spot. The incremental cost is low relative to a 1S server, and the form factors are often similar. I'm not sure I see a real point to buying a 1S server instead of a 2S server for the most part. 4S isn't cheap, but it's readily available from many vendors.

Perhaps I should have said 1-4S.

>2. IBM X4 is higher performance at 8 sockets than >NEC/Unisys? Where is a proof?
>IBM could have marginally higher performance at 4S and IBM >used to have higher
>performance at 8-16S during Tigerton times. But current >Xeon-MP is Dunnington, not
>Tigerton. It seems very likely that with Dunnington IBM is >slower than NEC/Unisys,
>otherwise they wouldn't avoid apple-2-apple comparisons.

Frankly, I had a hard time finding much information about Unisys' or NEC's architecture...which tells me something right there.

My estimate of performance was based on historic trends, lack of direct information and also general comments from 3rd parties. I did not have specific benchmarks in mind.

>3. AMD scaling to 8 socket was poor in the past. It's >still not great right now
>but Shanghai was a huge improvement and Istanbul is >slightly better yet. No, I wouldn't
>buy 8-socket Istanbul for anything I do. But, unlike a >year ago, I wouldn't say
>that buying 8S Opteron is plain stupid and never makes >sense. More so, by now it
>makes sense significantly more often than buying 8S Xeon.

Why would you buy an 8S opteron system when you could buy a 4S Magny-Cours? You could get 800MHz more frequency, but it seems like your overall performance may be worse in quite a few cases.

David
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
New article: 8 socket commodity serversDavid Kanter2010/03/09 10:27 AM
  New article: 8 socket commodity serversVincent Diepeveen2010/03/09 01:46 PM
    number of sockets is wrong metric (was: New article: 8 socket commodity servers)longtimelurker2010/03/14 05:13 AM
      number of sockets is wrong metric (was: New article: 8 socket commodity servers)EduardoS2010/03/14 05:34 AM
      number of sockets is wrong metric (was: New article: 8 socket commodity servers)Wes Felter2010/03/14 10:33 AM
        Magny-CoursMax2010/03/14 04:56 PM
          Magny-Coursanonymous2010/03/14 06:33 PM
            Magny-Courslongtimelurker2010/03/15 02:54 AM
      number of sockets is wrong metric (was: New article: 8 socket commodity servers)Vincent Diepeveen2010/03/14 11:31 AM
        number of sockets is wrong metric (was: New article: 8 socket commodity servers)longtimelurker2010/03/14 01:37 PM
          number of sockets is wrong metric (was: New article: 8 socket commodity servers)Vincent Diepeveen2010/03/15 11:36 AM
      number of sockets is wrong metric (was: New article: 8 socket commodity servers)David Kanter2010/03/14 11:56 AM
        Bad mathDavid Kanter2010/04/01 01:24 AM
      number of sockets is wrong metric (was: New article: 8 socket commodity servers)slacker2010/03/14 02:51 PM
        number of sockets is wrong metric (was: New article: 8 socket commodity servers)Michael S2010/03/15 05:05 AM
          number of sockets is wrong metric (was: New article: 8 socket commodity servers)slacker2010/03/15 01:02 PM
            Memory interfacesDavid Kanter2010/03/15 01:17 PM
              Memory interfacesslacker2010/03/15 09:08 PM
                Patents on tiny components vs. large, complex thingsmpx2010/03/15 11:41 PM
                  Patents on tiny components vs. large, complex thingsRichard Cownie2010/03/16 05:58 AM
                    Patents on tiny components vs. large, complex thingsMS2010/03/17 05:42 PM
                      Patents on tiny components vs. large, complex thingsa reader2010/03/18 08:45 PM
          Serial Port Memory TechnologyDavid Hess2010/03/21 03:32 AM
  New article: 8 socket commodity serversMichael S2010/03/09 03:13 PM
    New article: 8 socket commodity serverstheluketaylor2010/03/09 05:32 PM
    New article: 8 socket commodity serversJesper Frimann2010/03/09 10:35 PM
    New article: 8 socket commodity serversDavid Kanter2010/03/10 12:38 AM
      New article: 8 socket commodity serversTim2010/03/16 08:44 AM
  New article: 8 socket commodity serversanon2010/03/09 06:59 PM
    New article: 8 socket commodity serversDavid Kanter2010/03/09 11:06 PM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell green?