Cisco Blogs


Cisco Blog > Data Center

Next Generation Data Center Design With MDS 9710 – Part II

Note: This is the second of a three-part series on Next Generation Data Center Design with MDS 9700; learn how customers can deploy scalable SAN networks that allow them to Scale Up or Scale Out in a non disruptive way.  Part 1 | Part 3 ]

EMC World was wonderful. It was gratifying to meet industry professionals,  listen in on great presentations and watch the demos for key business enabling technologies that Cisco, EMC and others have brought to fruition.  Its fascinating to see the transition of DC from cost center to a strategic business driver . The same repeated all over again at Cisco Live. More than 25000 attendees, hundreds of demos and sessions. Lot of  interesting customer meetings and MDS continues to resonate. We are excited about the MDS hardware that was on the display on show floor and interesting Multiprotocol demo and a lot of interesting SAN sessions.

Outside these we recently did a webinar on how Cisco MDS 9710 is enabling High Performance DC design with customer case studies. You can listen to that here.

Three Pillars of ReliabilitySo let’s continue our discussion. There is no doubt when it comes to High Performance SAN switches there is no comparable to Cisco MDS 9710. Another component that is paramount to a good data center design is high availability. Massive virtualization, DC consolidation and ability to deploy more and more applications on powerful multi core CPUs has increased the risk profile within DC. These DC trends requires renewed focus on availability. MDS 9710 is leading the innovation there again. Hardware design and architecture has to guarantee high availability. At the same time, it’s not just about hardware but it’s a holistic approach with hardware, software, management and right architecture. Let me give you some just few examples of the first three pillars for high reliability and availability.

 

Reliability examples in MDS

 

Picture6

MDS 9710 is the only director in the industry that provides Hardware Redundancy on all critical components of the switch, including fabric cards. Cisco Director Switches provide not only CRC checks but ability to drop corrupted frames. Without that ability network infrastructure exposes the end devices to the corrupted frames. Having ability to drop the CRC frames and quickly isolate the failing links outside as well as inside of the director provides Data Integrity and fault resiliency. VSAN allows fault isolation, Port Channel provides smaller failure domains, DCNM provides rich feature set for higher availability and redundancy. All of these are but a subset of examples which provides high resiliency and reliability.

 

Weakest link

 

We are proud of the 9500 family and strong foundation for reliability and availability that we stand on. We have taken that to a completely new level with 9710. For any design within Data center high availability  has to go hand in hand with consistent performance. One without the other doesn’t make sense. Right design and architecture with DC as is important as components that power the connectivity. As an example Cisco recommend customers to distribute the ISL ports of an Port Channel across multiple line cards and multiple ASICs. This spreads the failure domain such that any ASIC  or even line card failures will not impact the port channel connectivity between switches and no need to reinitiate all the hosts logins. You can see white paper on Next generation Cisco MDS here. At part of writing this white paper ESG tested the Fabric Card redundancy (Page 9) in addition to other features of the platform. Remember that a chain is only as strong as its weakest link.

 

Geschäftsmann hat Wut, Frust und Ärger im Büro

 

The most important aspect for all of this is for customer is to be educated.

Ask the right questions. Have in depth discussions to achieve higher availability and consistent performance. Most importantly selecting the right equipment, right architecture and best practices means no surprises.

We will continue our discussion for the Flexibility aspect of MDS 9710.

 

 

-We are what we repeatedly do. Excellence, then, is not an act, but a habit (Aristotle)

 

Tags: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

Breaking through Performance Barriers: Desktop Virtualization at Cisco Live

We’re halfway into Cisco Live!  Each year I find more and more attendees are coming to talk to us about running various desktop delivery models on UCS.  Some observations from folks I’ve chatted with:

More and more of you are asking about NVIDIA GRID solutions for graphics intensive use-cases.  I had several in fact, from the oil and gas industry who were especially interested in our C240 M3 solution with GRID – which conveniently we’ve been demo-ing here, remoted out of our San Jose lab.  If you’re not familiar with it, check out our solutions for both Citrix and VMware.

CAPEX-friendliness with great performance, for small seat count environments is key.  Lot’s of folks asking about solutions that are optimized for 100-200 seats of Horizon or XenDesktop, that are completely self-contained, including compute, storage, broker and the infrastructure assets.  I’ve shared this brand new whitepaper on our C240 200 seat config with everyone I talk to – just a single rack footprint that includes the LSI Nytro MegaRAID Controller with 200 GB of flash for write-caching, plus 12 x 600GB SAS drives.  Here’s what’s been tested:

Hardware Components:

  • Cisco UCS C240-M3 Rack Server (2 X Intel Xeon processor E5-2697 v2 @ 2.70 GHz) with 384GB of memory (16 GB X 24 DIMMS @ 1866 MHz), hypervisor host
  • Cisco UCS VIC1225 Converged Network Adapter/Rack Server (Optional for 10GB Connectivity)
  • 2 x Cisco Nexus 5548UP Access Switches
  • 12 x 600GB SAS disks @ 10000 RPM
  • LSI Nytro MegaRAID Controller 8110-4i

The infrastructure/user file volumes are on the 1st 4 drives set up in a RAID 5 config, and the 2nd and 3rd groups of 4 drives (combined in RAID 10) are for XenDesktop MCS (Citrix) or Floating Assignment / Linked Clones (VMware).  Extremely cost-effective for 200 seats with great performance that doesn’t max out the system and has plenty of room to breathe.  Check out the Citrix and VMware configs of this “in-a-box” solution.

Flash – Flash and more Flash.  It’s hard to move around SF without seeing a Cisco UCS / Flash-Forward advertisement promoting UCS Invicta Solid State Systems.  Invicta is changing the economics of desktop virtualization with industry-leading wear life rating, expansive write-IOPS capacity, and superior manageability within the UCS fabric with UCS Director.  We’ve got a nice demo of 600 XenDesktop seats booting off an Invicta appliance, in under 9 minutes.

There you have it – great performance that goes beyond the traditional barriers associated with cost-effectively delivering desktop virtualization.  Definitely check out these three solutions if you have some time remaining at Cisco Live this week.

Tags: , , , , , , ,

How FCoE Helps Cisco Reduce Data Center Infrastructure

What a difference a networking cable can make in a data center’s infrastructure requirements and costs…especially when that cable uses Fiber Channel over Ethernet (FCoE) technology. An industry-standard, FCoE carries Fibre Channel over Ethernet links, which reduces the number of I/O adapters, cables, and switches in the data center.

Read More »

Tags: , , , , , , , , , , ,

“Is It Time To Become a Collaboration Technology Broker?”

It’s no coincidence that when choosing where to work, Type A personalities gravitate to organizations at the leading edge of their chosen field or that enable them to make a real difference. But gone are the days when you see “cell phone provided” in a job offer.  I don’t think I’ll choose my next employer based on what collaboration tools they provide, but I will make a point of measuring how seriously they take collaboration and how it fits into their operations. For me it will always be an important selection criterion.

They say “people don’t leave companies, they leave managers.”  I think people leave cultures that hinder them for ones that promise to set them free.

With so many disruptive technologies and deployment options, it can be difficult for IT teams to support broadening and challenging business needs. Increasingly, and often out of frustration around ‘Slow IT’, individual business units are acting as buying centers themselves; creating an issue of ‘shadow IT’.

Read More »

Tags: , , , , , ,

ANGA 2014: Igniting Growth for Service Providers

mckeownBy Mike McKeown – Director of Business Development for Service Provider Video at Cisco, EMEAR

It may be a month of bank holidays in Europe, but there’s no standing still for the video industry in May. We’re proud to say that it started with an announcement from Synergy Research (at the end of April) that we are the leading provider of video technology solutions to the industry.

How, you might ask, do you follow that?

With two of the industry’s most prominent events – firstly NCTA’s the Cable Show in LA and now ANGACOM in Cologne.

As with every year, NCTA provided a platform for the US cable industry to demonstrate and discuss the latest trends affecting some of the world’s largest cable operators.

On May 20th through 22nd, we’ll undoubtedly be having similar discussions at ANGACOM, but with a specific focus on Read More »

Tags: , , , , , , , , ,