Cisco Blogs


Cisco Blog > Data Center and Cloud

Management implications of large scale data centers.

February 26, 2014 at 7:17 pm PST

As data center workloads grow we hear about new large-scale mega data centers being built.  According to a recent report Microsoft is planning on building a $9 Billion data center in Korea.

msdc

 

This photo shows one of Microsoft’s large-scale data centers in Dublin.

(courtesy datacenterdynamics)

 

 

atxdc

 

Cisco’s own Allen data center in Allen Texas is 38000 square feet.

You can take virtual tour of the data center.

 

 

As more of these large data centers are built, managing them efficiently will have to both from a facilities, and an IT point of view. The research firm, IDC has started tracking a category of software called DCIM or Read More »

Tags: ,

Cisco Nexus 1000V: Simplifying and Scaling Virtual Networking in Microsoft Private Cloud Hyper-V Environments

February 19, 2014 at 8:00 am PST

Windows Server 2012 R2 is central to Microsoft’s Cloud OS vision; the operating system platform delivers enhancements and new features in virtualization, management, storage, networking, and more.  Our Cisco server infrastructure solutions (UCS) as well as our management (UCS Director, UCS Manager, Cisco Intercloud) and network capabilities are purpose built for supporting Microsoft’s virtualization and cloud offerings.

Cisco Cloud Infrastructure
Figure 1. Cisco’s Microsoft Cloud OS Solutions and Capabilities

Together Microsoft and Cisco provide tightly integrated and flexible solutions that deliver on the benefits of a Microsoft private or hybrid cloud. Our R&D teams have spent, and continue to spend serious time together developing technologies, APIs, and solutions.  In our blog post today, let’s focus in on the networking side of things, specifically on our award winning Nexus 1000V offering for Hyper-V:

  • It’s all about simplifying and scaling virtual networking.  Nexus 1000V for Hyper-V helps to reduce the operational complexities associated with virtual machine-to-virtual machine networking and thus help customers gain more of the benefits of server virtualization technology and cloud.
  •  It maintains networking resiliency across your physical and virtual environments as you move to the cloud.  Protect your investment by future-proofing your network design with a flexible virtual networking platform.
  • Recognized with the 2013 Best of Tech Ed award in the Virtualization category, Nexus 1000V extends comprehensive networking capabilities to your Hyper-V environment. A distributed virtual switching platform with advanced networking features and integrated virtual services, Nexus 1000V delivers consistency across your physical, virtual and cloud environments.
  • Uses a consistent operational model designed to accelerate server virtualization and cloud deployments securely and transparently. Read More »

Tags: , , , , ,

New UCS Servers deliver innovative scaling options and record-breaking power

February 18, 2014 at 10:31 am PST

This week we’re announcing new systems at the upper end of the UCS server product line: some heavy-duty iron for heavy-duty times.   These are important new tools for our UCS customers:  the digital age is accelerating, IT needs more horsepower to keep up, and there is a lot at stake.

Cisco UCS Servers with Intel® Xeon® Processor E7 V2 Deliver Unmatched Customer Benefits from Cisco Data Center

Consider this: less than 10 years ago, some of the largest mainframes scaled up to half a terabyte (TB) of main memory.  What if I were to tell you that these latest generation UCS blade servers will scale to 3TB?   Sound like a lot?  It is.  And that’s just the two-processor version.   Connect two UCS B260 M4 blades with an expansion connector and they become a UCS B460 M4, a four socket server that will scale to 6TB.  Putting that into perspective: a spiffy new laptop might ship today with 8GB of memory.   Multiply that by 750 and you have 6TB.

Not too long ago, all the content Wikipedia would fit in this type of footprint (in 2010 it was just under 6TB with media.)   Here is a fun illustration of what this scale of data would look like on paper (just the ~10GB of text, not the images.)  Now remember, we’re not talking about fitting all that data on the local disks of the server – we’re talking about fitting it in main memory.   This is becoming crucially important in the field of data analytics, where “in-memory” is the key to speed and competitiveness.  Applications like SAP HANA are at the forefront of this trend. Today, at Intel’s launch event in San Francisco, Dan Morales (Vice President of Enabling Functions at eBay) joined us to talk about how they’re betting on this type of analytic technology to help them make the eBay Marketplace work better for buyers and sellers (and eBay shareholders.)   I’ll post a video clip of that soon; his description of the challenges and opportunities, at eBay scale, is worth a watch.

We’ve talked about memory scaling, and Bruno Messina has a nice post that talks more about the scalability on these systems and UCS at large.   But dominating performance is the name of the game: behemoth processing performance is what we look for at this end of the server spectrum and Intel has not disappointed on this round of new technology.   The next generation of the Intel Xeon E7 family packs up to 15 cores per processor and delivers an average 2x performance increase compared to previous generation products.   Performance will be even higher on specific workloads, for example up to 3X on database and even higher for virtualization.   Cisco’s implementation of this technology has once again set the standard for system performance.   In today’s launch, Intel cited Cisco with 6 industry-leading results on key workloads.  As of this posting, the closest to come to that achievement that was Dell with 4.  HP ProLiant posted 1.  So hats off, once again, to the engineering team in Cisco’s Computing Systems Product Group.  Girish Kulkarni has a great summary of the performance news here.

 

New UCS Mission Critical Servers from Cisco Data Center

 

Our collaboration with Intel is one of the best technology combinations in the industry today.  Consider what we both bring to the party.  Intel: innovation in processor technology that drives Moore’s Law.  Cisco: innovation in connecting things across the data center and around the world.  UCS is an outcome of two blue-chip tech powerhouses investing in real innovation and the results have changed the industry.

In 1991, Stewart Alsop famously wrote:  “I predict that the last mainframe will be unplugged on 15 March 1996.”  He just as famously had to eat his words.  He munched on those twelve years ago, and while mainframes and RISC-based systems remain, there is an inexorable trend as the heaviest analytic workloads continue to shift to the type of scale-up x86-based systems we’re talking about today.   It only makes sense.  So while this will garner me plenty of comments from the architectural purists out there, I say “go ahead and plug a mainframe back in.”  It will fit right in your UCS B-Series blade chassis…

 

Tags: , , , , , , , ,

Cisco @StrataConf : Best Practices for Hadoop In Production-Panel Discussion

Hey data heads! O’Reilly Strata Conference kicks off tomorrow at the Santa Clara Convention Center. If you plan to go you better have tickets because the event is sold out.

Slide1

If you are attending the three days of sessions, keynotes, receptions and exhibits, please stop by the MapR booth for some face time with one of our big data partners and plan to attend their sponsored panel discussion which includes Cisco IT and other MapR customers facilitated by Mike Gualtieri from Forrester Research.

Best Practices for Hadoop In Production

“Mike Gualtieri, principal analyst at Forrester Research, Inc., will engage a panel of production Hadoop users – including Cisco IT, The Climate Corporation, The Rubicon Project, and Solutionary – to discuss the challenges and best practices for deploying Hadoop in production. Join us for an engaging conversation on tips and tricks in deploying Hadoop in production. 10:40am, Wednesday February 12 in Ballroom H” See more here.

Representing Cisco IT will be Distinguished Engineer, Piyush Bhargava. Piyush is Chief Architect for Data Architecture & Innovation and is responsible for finding new ways of harnessing value from data and for designing architectures to support data processing, analytics & data science needs.

_______________________________________________________

If you can’t make it to Strata Conference or are double booked during this time slot you can get the goods on this topic from a number of other sources.

  • First, check out the webinar Cisco and MapR produced with Mike that highlights the Cisco IT case study. Mike outlines the 7 Best Practices for Productionizing Hadoop, MapR follows with their best practices for data tables and Cisco IT covers their big data use case. If you want to skip to the Cisco IT use case, it starts at 34:00.
  • Then, take a look at my blog post on the Cisco IT big data platform success story. Cisco IT has standardized on Cisco UCS servers and fabric interconnects for its big data infrastructure and uses MapR for data tables.

tes3

For operational workloads, Cisco IT has standardized company-wide on Cisco Tidal Enterprise Scheduler with its unique set of adapters that include API integrations to MapR, Hive and Sqoop for big data workload processing.

Cisco Tidal Enterprise Scheduler for Big Data

  • Next, spend some time reading the Unleashing IT Big Data Edition. This special edition of Unleashing IT is all about big data and highlights our joint Cisco/MapR customer Solutionary who incidentally, will join Cisco IT on the Strata Conference panel discussion on Wednesday. This e-zine is packed full of big data thought leadership; best practices for infrastructure and operations; customer success stories and include our partners Intel, MapR and others.
  • Finally, peruse the Cisco big data website for all the latest on our solutions, partners, services and resources to help you make the best informed decision on moving your big data platform from development to production.

Big Data blogs I follow:
Raghunath Nambiar
Scott Ciccone

Tags: , , , , , , , , ,

Show Me the Money: Cisco UCS Success Stories in Microsoft Oriented Datacenters

February 7, 2014 at 8:31 am PST

Cisco continues to work closely on technologies and solutions around the UCS compute family so we can bring maximum value to you and your Microsoft oriented datacenters. The UCS family is well suited for Windows Server, Hyper-V and VMware based private clouds, and support for the key workloads of SQL Server, Exchange, and SharePoint. Recently I was inventorying our Microsoft oriented UCS case studies and came up with several that showcased UCS’s architectural strengths as well as good business value returns.

1Overview

Read More »

Tags: , , , , ,