Server

• Fashionable Benchmarks

  Tue. May. 13, 2008
  by David Graves, Editor—Inside IT

  IBM blogger Elizabeth took the time to write about our stylish pink notebooks and went on to make the point that for servers, what really matters, is on the inside. Especially benchmarks and she cites VMmark specifically.

  We couldn't agree more.

  VMmark is a valuable tool to determine the performance of different hardware and virtualization platforms. Congrats, at the time she posted the IBM System x3850 was the #1 in this benchmark.

  As fashion is wont to do - now there is a new #1.  Can you guess the new "it" model for this issue???

  Check out the Stats: TOP 4-SOCKET PERFORMANCE RESULTS FOR VMMARK AS OF MAY 7, 2008

  Vendor	SystemVMware version	VMmark  (v 1.0)Score	Processors	PublishDate	ConfigurationPrice
  Dell	PowerEdge R900VMware ESX v3.5	14.23 @ 10 tiles	Intel Xeon X7350	May 2008	$28,802
  Dell	PowerEdge R905VMware ESX v3.5	14.17 @ 10 tiles	AMD Opteron8360 SE	May 2008	$23,135
  IBM	IBM System x3850 M2VMware ESX v3.5	13.16 @ 9 tiles	Intel Xeon X7350	Mar 2008	$30,729
  Sun	Sun Fire X4450VMware ESX v3.5	12.23 @ 8 tiles	Intel Xeon X7350	Apr 2008	$36,176
  HP	HP ProLiant DL580 G5VMware ESX v3.0.2	11.54 @ 8 tiles	Intel Xeon X7350	Aug 2007	$27,330

  - Both results for the PowerEdge R900 and R905 beat the previous #1, the IBM x3850 M2, by more than a full point (8%) in the overall score (which represents how well the VMs are performing).

  - Dell's results show that we're more than just "pretty in pink".  The PowerEdge R905, in addition to beating the IBM result by 8%, costs 25% less (and 36% less than Sun).

  - The same day this benchmark posted we had a major virtualization announcement - some external perspectives are here, here and here.  

  The fashion world just keeps spinning ‘round....

   

   

  digg del.icio.us email this 0 comment(s)

• TechCenter Chat on Tuesday: Managing the switch to OpenManage

  Mon. May. 12, 2008
  by Marc Farley, Inside IT Lead Blogger

  Our lovely and talented TechCenter Supergeeks will be around for an online discussion tomorrow (Tuesday) to help customers migrating from other server management tools to OpenManage.

  In a few weeks we are going to have a chat on iSCSI networking.  Stay tuned.

  -marc 

  digg del.icio.us email this 0 comment(s)

• My man Todd says we blew it

  Thu. May. 08, 2008
  by Marc Farley, Inside IT Lead Blogger

  Todd Muirhead in the TechCenter is a tech stud. Geekstud. U know? We were talking this AM and he said he thought we soft pedaled the R805 server in yesterday's Big V announcement. Says its the first server designed specifically for virtualization applications. 
  

  Who knows he might be right and he might just be full of Cabo Wabo, but here's his blog entry. 

  digg del.icio.us email this 0 comment(s)

• When it rains, it pours - fotos

  Wed. May. 07, 2008
  by Marc Farley, Inside IT Lead Blogger

  Yesterday John Mullen posted about the huge install at Purdue with 249 pictures from Tinkergeek of their Habitat for Computing effort.
  

  Today a customer of ours, Joe Cruz, from Wharton, posted about their own install fun.  Party on dudes!

  digg del.icio.us email this 0 comment(s)

• Purdue punches out supercomputer in near-record time

  Tue. May. 06, 2008
  by John Mullen, VP, Higher Education, Dell, Inc.

  I got my bachelors ME degree at Michigan State and understand what competition means in the Big Ten.  You crush it when you can.  Well, the folks at Purdue University's Rosen Center for Advanced Computing crushed it on Monday. With a huge team effort, they installed their new supercomputer - including unboxing the equipment - in just half a day. C|net called it an "electronic barn-raising."

  The supercomputer, named Steele, features 812 Dell PowerEdge 1950 dual-quad-core computer nodes and is predicted to have a peak performance of more than 60 teraflops, which means it could perform more than 60 trillion operations in one second, placing Steele in the top 40 on the current Top 500 computers list.  Tinkergeek has 249 photos of the install , which is probably some sort of record by itself.  You get to see them working on the raised floor, installing racks, rails, switches HVAC, power and network cabling.  My favorites are #s 79, 90, 152, 179, 200 and the last one - the rack with signatures of the team that worked on it - very cool.  They have a brisk stop action video too.  

  The HPCC will be used for research across a variety of disciplines, including engineering, biological, earth and atmospheric sciences, mathematics and physics. The leading researchers at Purdue pooled their grants and provided a majority of the funding for the cluster, which is housed at Purdue's Mathematics Building on campus.

  High-performance computing is helping to support research that benefits society and Purdue is one example of major universities using Dell technology to enhance their teaching, learning and research initiatives.

  digg del.icio.us email this 0 comment(s)

• Clusters by the numbers

  Mon. May. 05, 2008
  by Marc Farley, Inside IT Lead Blogger

  Gregory Pfister's excellent book, In Search of Clusters,  has a picture of fighting dogs on the cover.  I always thought it was a fitting image for a challenging technology that has perplexed so many for so long.  But, if you were going to write a book about clusters in Microsoft's Windows 2008, you might use Edward Hicks' The Peaceable Kingdom as cover art. 

  Failover Clustering from Micrososft is the latest High Availability (HA) technology in their server technology portfolio and brings clustering to customers that previously couldn't afford it. The big change is due to an integrated cluster validation tool that assures systems are cluster-ready.  Dell takes up it's part of the equation by providing tested, pre-validated configurations that make cluster setup and configuration a straightforward, step-wise process.  The beauty is that customers can deploy clusters now without having to know the details of how clusters work.

  Listen to a Jeff Johnson interview with people from Dell's HA engineering team talk about this important technology.

   

  digg del.icio.us email this 0 comment(s)

• Microsoft Systems Center goes hetero

  Thu. May. 01, 2008
  by Marc Farley, Inside IT Lead Blogger

  The biggest news from MMS this week was the announcement that Systems Center Operations Manager (SCOM) was adding heterogeneous platform support.  That's hot.

  The other biggie centered around Microsoft's vision of the Dynamic Datacenter.  Great steps toward simplifying IT.

  digg del.icio.us email this 0 comment(s)

• A new appliance-perfect server for OEMs

  Wed. Apr. 30, 2008
  by Rick Froelich, VP, OEM Industry Solutions Group

  This week we launched the OEM CR100 server, a short 1u form factor system built on PowerEdge technology, designed to help appliance vendors simplify IT for their customers. We’re really excited to offer this server exclusively to appliance OEM customers, who look to us for tier-1 stability, quality and global support for their appliance solutions.

  The CR100 is a rapidly deployable server that we can customize to the needs of our OEM customers. It comes in five different configurations that can be preloaded with their software and can incorporate customer-specific branding and packaging. With a long two-year lifecycle, the CR100 is backed by our End-to-End Appliance Program which includes the vital lifecycle management services, value-added logistics, Dell warranty and support services that our existing appliance customers have come to expect from Dell.

  I am confident that CR100 will help appliance vendors of all sizes —Secure Computing, McAfee and Connectbeam, to name a few— continue to grow their business with the confidence of knowing that their solutions are Dell-powered.

  digg del.icio.us email this 0 comment(s)

• Microsoft Management Summit is very hot and Dell is in the buzz

  Tue. Apr. 29, 2008
  by Ed Reynolds, Dir, Dell Systems Mgmt Mktg

  A Dell employee emailed from the Microsoft Management Summit this morning:

  I am in the opening keynote here at MMS. Being the featured hardware partner for SCCM is awesome. The room is PACKED and attendees are hearing Microsoft talk about how great Dell systems management is.

  Microsoft’s Bob Muglia, MS SVP, highlighted Dell’s preliminary bare metal deployment pack in his keynote. Hubba hubba and hey now.

  Many of our customers use Microsoft’s System Center and Dell’s OpenManage to manage their infrastructure. And who do you think offers the most comprehensive device management through Microsoft’s System Center Suite? (Dell does) And we’re not resting. This week we’re announcing the upcoming availability of the latest Dell Management Packs for Microsoft System Center Operations Manager that will give customers superior monitoring and control of Dell desktops, portables, workstations, rack and tower servers, blades, networked storage devices and even printers.

  Our new plug-ins and our roadmap to integrate Dell Services with Microsoft products means our mutual customers will continue to have industry leading tools to manage their IT infrastructures. All this talk about simplifying IT really means something.

  Thanks for the kind words this morning Bob!

  Technorati Tags: Microsoft,management summit,system center,openmanage,Dell,server management,infrastructure management
  digg del.icio.us email this 5 comment(s)

• How much can you turn off?

  Fri. Apr. 25, 2008
  by Marc Farley, Inside IT Lead Blogger
  Technorati Tags: ken brill,uptime institute,greenbiz,Blades,Dell,Energy conservation,Green benchmarks,Green technology,HP,Hardware,IBM,Open Source Systems (OSS),Power consumption,Power supplies,Sustainable IT

  GreenBiz radio has an interview with Ken Brill of the Uptime Institute.  Its a bit long, but all the text is there so you can speed read through it if you want.

  One of the more interesting things that Brill claims is that lots of energy can be conserved by turning off equipment that isn't being used.  Here's a quote from the interview transcript:

  KB: Well, the institute believes that IT could radically reduce its energy consumption, and it would save money in the process. And there are a number of things that people can do and we're gonna be talking about these at our upcoming symposium. But the first thing that people can do is to go through their data center and identify what is running that could just be turned off. Between 10 and 30 percent of the energy consumption in a typical data center is for servers and storage and other things that is no longer in use.  And it could just be turned -- I mean, as literally, as simple as turning the switch.

  Ken has some interesting things to say about blade servers too. Just like any other technology, there are important differences in blade server designs.

  digg del.icio.us email this 0 comment(s)