Data Center Networks Discussion of Networking-Based Technologies Designed to Optimize Data Centers

When Eight May Not Be Enough for Virtualization

Eight Is Enough was an American comedy / drama that ran from 1977 – 1981.  See http://en.wikipedia.org/wiki/Eight_Is_Enough if you are oddly curious.  You may not share my vintage or decided to be productive during those years, but the metaphor relates to interface requirements for VMware hypervisor implementations.   

The foundation for private or public clouds is virtualization.  This blog entry focuses on the network interfaces used to build a topology for VMware.  Specifically, VMware has the concept of port groups and vswitches ( http://www.vmware.com/technical-resources/virtual-networking/ [url reference if you want more detail]).  There are many reasons and combinations to choose from relative to this implementation.  I will comment on some of them next.

Read More.

Posted by Frank D'Agostino at 09:47AM PST

Frank P. D’Agostino - CCIE 3461
Distinguished Systems Engineer II
Cisco Systems
twitter.com/fdagosti

Cisco TechWiseTV Episode on Unified Fabric

I just wanted to give you a heads-up that we have an upcoming TechWiseTV on Unified Fabric.  If you have watched TWTV before, you know this Robb and Jimmy Ray are going to take a no-holds-barred look at unified fabric with equal parts humor and enlightenment.

In this latest episode…

Read More.

Posted by Omar Sultan at 10:46AM PST

Why Standards Matter…And When They Don’t

The year was 1992, Disney’s Aladdin was the top grossing movie, Garth Brooks had the top-selling album in the US, and I was a freshly minted SE.  Being a studious and diligent SE, I read up on all the gear sold by the integrator I worked for, and I decided that the Wellfleet BCN was the product of choice for our customers based on its hardware architecture and the impressive list of standards to which it laid claim.

And, then a funny thing happened…I learned that, while customers value standards compliance, what they value even more are networks that work and do what they need them to do.  And herein lies the inherent contradiction of networking standards and the constant tension between innovation and standards.

Ultimately customers look to us to address their problems: “I need my network to _________ (fill in the blank) so I can support the needs of my business—oh, and I’d like that ASAP, please” .  Luckily, our customer base is not shy, so when we see a trend, we move to address it and put solutions out there for our customers.  This is where innovation is critical—having the ability to continually move the ball forward to ensure networking continues to meet the needs of markets that are themselves continually evolving.  

But, ultimately, standardization is the end goal.  Without standardization, innovation cannot scale.  Time and again, we have seen that if a technology is balkanized, it stalls because no one wants to choose poorly (on a somewhat related note, I have a fine collection of HD-DVDs I’m willing to part with at a fair price).

Most of you are probably familiar with some version of the technology adoption lifecycle chart below, made popular by Geoffrey Moore in his seminal work “Crossing the Chasm”.

Read More.

Posted by Omar Sultan at 01:07AM PST

New Book Published from Cisco IT

Not sure if you’ve seen it yet but a great book for anybody trying to define what a “Green” data center means and take steps towards migrating to one.  I’ve known Doug Alger for about 4 years now, he is a Solutions Architect within Cisco IT.  Doug does is a rare breed, he has a strong facilities background but is employed by an IT operation.  Doug often jokes that if Facilities and IT departments had no issues in planning and management, his job would go away.  I was privileged to provide technical editing for this book and from what I know in the industry, I believe it is the best work today in providing a resource base to build upon.

Since there is no such thing as a Green Data Center today (in a purist sense), this book addresses what steps you can take and what standards are their to move towards one.  This is a great book to not just read once but refer back to in building your plan.

Read More.

Posted by Rob Aldrich at 12:44PM PST

Every cloud needs a net

Most enterprises have been exploring cloud computing to see how it might work for them.  Cloud computing offers the ability to run servers on the Internet on demand.  The storage, compute, and network functions are positioned and ready for use, so servers can be deployed within minutes, and paid for only for as long as they are in use.

An essential component of any cloud installation is its network.   When servers are deployed in a cloud, they need an external network to be usable.  The network services that they need are more than simple IP connectivity, and each customer of the cloud will need some customization.  Here are some key types of cloud network service.

Read More.

Posted by Ken Novak at 02:12PM PST

Virtual Computing Environment coalition -Can you list the benefits for your company ?

You probably didn’t miss the today announcement of the coalition  between Cisco, EMC and VMware designed to address the challenges of pervasive virtualization and private cloud computing .We met Mark Fulgham , Vice-President Data Center Solutions to get his point of view on the Virtual Computing Environment coalition , on the Vblock Infrastructure Packages approach .In this short extract , Mark Fulgham describes some of the benefits he sees for our customers. 

We also invite two customers, a CIO and a CTO to share their analysis of the Vblock Infrastructure Packages approach  

Read More.

Posted by Didier Rombaut at 05:11PM PST

Wishful Thinking: The Innovation Edition

I am an unabashed fan of social networking.  For the data center team, being able to get direct, unfiltered feedback from the market has been a boon for making sure we are tracking in the right direction.  I also thoroughly enjoy the online conversations on the various blogs and in Twitter.  There are a great number of people out there with a lot of good thinking on the data center and I highly encourage you to do a little googling to get plugged into these conversations.  There are folks out there with views diametrically opposed to mine (you know who you are) but they have well-reasoned, well-spoken opinions and you can’t help but respect them for that—and I honestly enjoy the back-and-forth.

And then I’ll come across something that will leave me scratching my head thinking “Really…that’s the best you could come up with?”  I was reminded about this when I recently ran across a diatribe on our “lack of innovation”.  So, as a company, I will readily admit that there are a number of things we need to work on (and are), but “lack of innovation”? Really?

Let’s deconstruct this a little bit.  Just for the sake of argument, let’s start with a definition.  My trusty Mac dictionary defines “innovate” as “make changes in something established, esp. by introducing new methods, ideas, or products,” so lets run with that.  So, what have we done along these lines in the data center space in the last 20 months or so (not meaning to brag, just trying to make a point): 

Read More.

Posted by Omar Sultan at 06:09PM PST

Could the Converged Network Adapter be the most important element in a Unified Fabric?

Many vendors are touting the benefits of IEEE DCB, FCoE, CEE, DCE, Unified Fabrics, and many other marketing monikers for equipment consolidation.  Each component of the technology is interesting, but maybe no more so than the Converged Network Adapter itself.   Why so?  Let’s take a look.

Read More.

Posted by Frank D'Agostino at 09:07AM PST

Frank P. D’Agostino - CCIE 3461
Distinguished Systems Engineer II
Cisco Systems
twitter.com/fdagosti

Cisco Nexus 4001I Switch Module for IBM BladeCenter

On my previous blog post “What exactly is a Nexus 4000?” there were many questions/comments around OEM blade server vendors and details of Nexus 4000 Series Blade Switches . Today, IBM announced the details of the Cisco Nexus 4000 blade switch for their BladeCenter H and HT chassis.

Nexus 4001 Switch Module for IBM BladeCenter will provide the support for Fiber Channel over Ethernet (FCoE) and the emerging IEEE Data Center Bridging (DCB) standards over 10 GbE for IBM Blade servers.

So IBM becomes the first blade server vendor to make Cisco Nexus 4000 available for their blade servers. You can find the Nexus 4000 blade switch IBM description at:

http://www.redbooks.ibm.com/abstracts/tips0754.html

and included in the IBM websites below:

http://www-03.ibm.com/systems/bladecenter/hardware/openfabric/fcoe.html

http://www-03.ibm.com/systems/bladecenter/hardware/openfabric/ethernet.html

and on the Cisco website:  http://www.cisco.com/go/nexus4000

Read More.

Posted by Kash Shaikh at 05:27PM PST

Cisco IT Data Center Experience

You know, our customers, even folks that are not our customers, are always interested what Cisco IT is up to.  Our IT strategy is intrinsic to our business strategy and folks are always curious to know what is working and what is not working.  Now, if you have every been lucky enough to hear folks like Rebecca Jacoby or Sidney Morgan talk, you know our IT org is a big believer in transparency and will happily share both our successes and learning experiences.  To that end, we have recently released the Cisco IT Data Center Experience.

The website takes you behind the scenes of Cisco’s global data center environment with a chance to hear from the folks responsible for long-term planning and strategy, architecture and operations and implementation.  There are over 30 videos on a broad range of topics—pretty much something for everyone.

Read More.

Posted by Omar Sultan at 09:56AM PST

Government Agency Upgrades Application Infrastructure with a Virtualized App Delivery Solution

Government Agency Upgrades Application Infrastructure…and by doing so provides a great proof point of  why old load balancers should be virtualized  (source: IDC) .

Faced with challenges of an aging application infrastructure and needing to scale application delivery state wide with security and performance, the Delaware Department of Technology and Information (DTI) deployed the industry’s only virtualized application delivery solution.

Read More.

Posted by Yogesh Rami at 09:21AM PST

Cisco UCS Gets the Nod From Oracle

So, we continue to see broad traction in the industry for the Cisco Unified Computing System.  The latest passenger on the UCS Bus is Oracle, which recently certified and validated the Cisco UCS platform for Oracle Enterprise Linux 5.3 and Oracle VM.  

As the picture illustrates, the test system was built around out UCS B-Series servers with EMC CLARiiON storage system with a mix of Fibre Channel drives and state- of-the-art Enterprise Flash Drives (EFDs) to further speed performance.  Its important to note that, because the Cisco UCS is architecturally consistent across form factors, the same system could be built with the recently announced C-Series rack servers.

We have published a white paper on the tested deployment that digs into a fair amount of detail on the setup and configuration of the system—highly encouraged reading for anyone that supports Oracle in an enterprise environment.  Please note, you will need to register to access the doc (any follow-up from us is on an opt-in basis).

One of the more interesting things  things that came out of the testing was the performance data. We ran the cluster through 24h hrs stress tests for both OLTP (order entry) and DSS (sales history). The results included:

• Very consistent CPU utilization: around 40 percent on all eight nodes
• No saturation levels of any subsystems (CPU, disk, I/O, or networking)
• Sustained FCoE-based I/O ranging between 1.8 and 2.0 GB per second, which could be further divided into 1.4 GB per second of Fibre Channel I/O and approximately 450 MB per second of interconnect communication
• No occurrence of I/O bottlenecks or wait times
• Excellent I/O service times for storage

We attribute much of this consistency to the UCS architecture and its intrinsic 10GB fabric as well as the use of the EMC CLARiiON storage with EFDs.  Note, this was not performance testing, there was no config optimization or the like done for this test, we were more interested in understanding how the system handled long-term sustained loads.  We are working on performance benchmarking, so stay tuned for those if you are looking for numbers to compare to other solutions out there.

Read More.

Posted by Omar Sultan at 09:49AM PST

The Internet Protocol Journal

One of the hidden gems at Cisco is the Internet Protocol Journal.   The IPJ describes itself as “... intended to serve as an informational and educational resource for engineering professionals involved in the design, development, and operation of public and private internets and intranets. It does not promote any specific products or services, but focuses on issues facing the network designer or operator. The journal carries tutorial articles (“What is…?”) as well as implementation/operation articles (“How to…”). It provides readers with technology and standardization updates for all levels of the protocol stack and serves as a forum for discussion of all aspects of internetworking.”

The quality of the content is quite good and a subscription is free.  One of the reasons I bring this up for our readers is the the current edition has a the first part of a two part primer by T. Sridhar on cloud computing.  For those of you looking to come up to speed, it is a good vendor-agnostic intro to the topic.

Read More.

Posted by Omar Sultan at 01:19PM PST

Of Cloud Computing and Virtualization

There still continues to be an immense amount of confusion around what exactly constitutes cloud computing.  As an example, over the last few days, there has been a spirited debate whether the Sidekick service Microsoft/Danger offered was a cloud-based service or not (I am not going to dig into that here, but I do happen to agree with Chris Hoff’s viewpoint).

A common question I get is if virtualization is an inherent and mandatory component of any cloud solution.  I bounced this question up to our CTO’s office to get their take on things.  Their perspective:

Cloud computing delivers IT resources on-demand and elastically, and many organizations would like to leverage these capabilities today. Compute virtualization established itself as a way to improve resource utilization, but has other characteristics that make it more broadly relevant to cloud.

To expound on this a bit further, Glenn Dasmalchi, technical chief of staff in the office of the CTO at Cisco, provides a summary of how cloud computing and virtualization are related, and what advantages are afforded to customers.    He also touches on the network play with the cloud-virtualization linkage.

Read More.

Posted by Omar Sultan at 10:49AM PST

Are You Getting Top Performance for Your Oracle Applications over the WAN?

With Oracle Openworld running this week it’s a good time to think about the performance of applications over the wide area network (WAN).  With the changing business environment IT organizations are re-architecting how they deploy enterprise applications. Oracle applications automate business processes and increase productivity, but in this new network-centric world their performance is being impacted by longer WAN links and inefficient Internet protocols resulting in reduced performance and decreased user productivity.

Globalization and outsourcing has created a workforce that is spread across the world. At the same time, to reduce IT costs resulting from the spread of regional systems, and to take advantage of large scale virtualized systems, organizations are centralizing their application and IT infrastructure in the data center. The result of this trend is that the distance from the end user to the application server has increased dramatically and the connection is often over links with limited bandwidth.

Read More.

Posted by Michael Leonard at 02:05PM PST