One part of my job involves designing the virtualization model for our internal unified communications (UC) system deployments around the world. A critical task in this design is specifying which UC virtual machines (VMs) can share a Cisco Unified Computing System (Cisco UCS) server chassis or blade and which ones can’t. When migrating UC servers to a shared virtual environment, we need to make sure we carefully balance each VM’s needs for CPU, storage, network and memory. Read More »
This is my first year as an attendee at the Gartner DC conference. I’ve been here once before working demos on the tradeshow floor, but this year it’s purely about information gathering. Tradeshows floors are great. You get to wander around and chat with a captive audience of your industry peers, partners, and “frenemies” collecting pens and light up bouncy balls. Based on where the swag really ends up, I think the pen purchasers really need to start thinking about logo branded crayon packs. But there is so much to learn in the conferences even in the most unexpected sessions.
My primary take aways from the initial keynotes were that Hadoop is a strong early adoption application candidate for cloud in a non-virtual context (Hadoop in the data center was recently covered in Jason Rapp’s blog) , that commodity compute is the leader in cloud computing (I cried a little on the inside with this one), and that personnel development and team building/creation is one of the biggest factors in an IT success story.
For day one the celebrity keynote was from Captain Chesley Sullenberger which seemed out of place before listening to him. His talk about teamwork, process, and respect leading to his success in pulling off that harrowing landing on the Hudson spanned well from the people aspect of organizations, and was a very enjoyable listen.
These take aways seem to me even more critical as IT organizations have to quickly evolve their data centers to meet demanding business requirements, without expecting additional resources .
Gartner does a very nice job of interactive polling within their conference. For the starting keynote the audience poll (~2,000?) revealed that budgets edging up, but for the greatest number of attendees are mainly flat.
It seems that 34% of the audience has to deal with a flat budget, 20% of the attendees benefit from a marginal increase (<5%), and 14% experience a small decrease (<5%)
Talking about data center evolution, as a Cisco guy, I had absolutely to attend (by choice ) David Yen’s presentation. David is our Sr VP & GM in charge of our DC Technology Group, so he’s the big picture for anything Cisco in the Data Center. He is a Phd, with a very large experience in compute, applications and network, acquired through executive role at Sun Microsystems, Juniper and Cisco. David’s talk was about the evolution of the data center and the relevance of Cisco -You may want to check the blog from Giuliano Di Vitantonio, VP Marketing Data Center and Cloud with slides and videos “ The Evolving Data Center : Perspectives from the Gartner DC Conferences” In his presentation David Yen covered some of the background for the evolution of the data center model, and the gains to be expected in the fabric model we see through Fabric Path in optimization of the new East/West data patterns.
This all has a strong relationship to our Unified Computing System solution. Which as a server platform “loaded with features ” might be perceived at some disadvantage in comparison to commodity compute, we’re happy to see that in reality our customers have placed us at #3 in datacenter compute world wide, and #2 in the US for an implementation that is only three years into the market, thanks to providing strong management capabilities, system agility, and dynamic integrated network functionality, as well as great TCO. As proof points , you may want to check Bill Shields blogs on this topic, but also the Cisco Buil& Price website with promotions of the month.
This Conference gave me also the opportunity to discuss other “more technical ” topics such as security for cloud and virtual services.
So stay tuned, as I will be back in January for additional conversations.
On this week’s Engineers Unplugged, HDS’s Andrew Nielsen (@virtualkjell) and Cisco’s J Metz (@drjmetz) discuss a recent announcement and validated design, Hitachi UCP on Cisco UCS. Here are the basics:
Welcome to Engineers Unplugged, where technologists talk to each other the way they know best, with a whiteboard. The rules are simple:
Questions for Andrew or J? Follow the conversation on Twitter! Follow us @CiscoDC. Ideas for an upcoming show? Let me know!
Cisco at Garner DC Las Vegas : A pragmatic view and approach of the evolution of the data center in the era of clouds and network programmability.
As expected a lot of talks, sessions and interest this year about the reality of the cloud deployment and hybrid cloud at Gartner DC Las Vegas.
Cisco is now perceived as a very credible player in cloud – In fact a quick electronic poll from the audience during one of the key notes speechs ranked Cisco as the number 2 amongst the vendors.
As a proof point of Cisco influence in the cloud computing evolution, both David Yen , Cisco SVP & GM Data Center Group, and John Manville Cisco SVP , Global Infrastructure for IT, presented Cisco vision and achievement in terms of infrastructure and foundation for cloud : Network programmability , and convergence infrastructure are at the core of the efforts driven by these Cisco executives and solution teams to deliver robust infrastructures for both our customers and Cisco IT organization.
If you are interested to know more about these sessions, stay tuned. I will post in the following days on this same blog the slide decks from David and John ,as well as two short and very interesting videos that I did these days:
-One one hand a short dialog between Giuliano Di Vitantonio, Cisco VP Marketing Data Center and Cloud, and David Yen.
-On the other hand a summary of the presentation by John Manville (see introduction blog from Omar Sultan Living with the Programmable Cloud)
Along the same lines , I also invited a panel of bloggers and tweeps , who attend Gartner DC to share with us their reaction to these presentations and their view on the current challenges faced by the IT organizations.
A story came out today showcasing the platform built to power Xerox Managed Print Services (MPS), and it’s hard to describe better example of how Cisco’s data center technology comes together to help unlock the full potential of cloud computing. In the lead-up to this release and the webcast that we’re airing this Thursday, I had the pleasure of working with Tom Force who leads up the architecture team at Xerox that built the MPS cloud. What I heard him describe illustrates some of the fundamental differences in UCS that come into play for cloud builders:
- Fabric-centric design. MPS is a cloud based service and hosts over a hundred applications. Many of these are multi-tier apps and they benefit directly from the fact that every server in a UCS environment is connected to a single high performance, deterministic, low latency fabric. This eliminates hops between servers and opens up the platform to support intense E/W traffic within the servers that collaborate to deliver services. Contrast this to traditional architectures that put layers of switching between servers with in-chassis blade switching modules. The performance gains were noticed and communicated by Xerox customers to Tom, and that is the end result that really matters
- Form factor agnostic design. In UCS a server is a server is a server regardless of the shape of the box. The Xerox MPS cloud leverages blade and rack servers as and where they make sense and the architects and administrators can manage them all in one abstracted pool of resources. No other platform so fully eliminates the concerns of what shape the sheet metal is.
- A unified control plane exposed via XML API. The MPS cloud is orchestrated with vCloud director. The deep integration between UCS Manager and cloud platform SW enables automated discovery and configuration of new compute resources as they’re added to the system. This creates the true elasticity and automation that a cloud of the magnitude of Xerox MPS demands. Programmable pools of abstracted computing and network elements is what separates a robust cloud from one built on a brittle, manual infrastructure foundation.
- UCS Manager Service profiles: Simplification of server image types and elimination of configuration drift as applications move from development through test, staging and deployment was a big win for the Xerox IT team. Having a infrastructure that can be reliably and accurately provisioned and maintained, both in the primary and remote DR sites is another area Tom cited in our conversations.
- UCS Central: this is recently released technology that allows customers like Xerox to manage multiple UCS domains across the data center and across geographies.
- I’m sure i’m forgetting something but I’ll go with 5 unique attributes for now.
**Fictional rendering of Tom Force
This Thursday, the Xerox team is joining us for a dynamite webcast we’ve pulled together to talk about UCS and laying the right foundations for cloud. James Staten of Forrester, who is THE MAN on cloud, helps us kick it off and we also have architects from FICO joining to talk about their private cloud design. If you’re in the business of looking at infrastructure strategy for cloud computing this is one you don’t want to miss.
Check also Xerox case study