Guest post by Txomin Barturen, Senior Consultant – CTO Office, EMC Corporation
SQL Server provides customers with a vast array of technology options to address a diverse range of data and reporting requirements including extremely high throughput OLTP environments to bandwidth and time-sensitive reporting and DSS systems. With choice comes the inevitable complexity of defining and building solutions. Customer IT teams are invariably dealing with Service Level Agreements (SLAs) from their in internal customers. Time and financial constraints often limit the ability of internal IT teams to spend significant amounts of time in defining, testing and implementing the broad range of environments that they need to deploy.
Jointly, Cisco and EMC have partnered with Microsoft to deliver a set of solutions that are pre-validated to deliver the requirements for customer SQL Server environments. These solutions implement the collective best practices for server, network and storage, ensuring that customers implement a known valid configuration without the guesswork.
Fast Track Data Warehouse
Dealing with data warehouse requirements requires that solutions be designed to meet the ideal balance between performance, DW size, and cost. Design guidance from the SQL Server team dictates that the total data warehouse size be finely balanced by storage system configuration, server system consumption rate (how fast the CPUs are able to process the data) as well as the interconnectivity between server and storage to deliver at the required rate. To match server configuration, the interconnectivity (including HBAs) and the storage infrastructure requires much design, calculation and testing across a number of disciplines.
Mileage (miles per gallon) is one of the important criteria while buying any automobile and once bought, it is highly desirable to hit the maximum advertised mileage withoutsignificantly changing the driving habits or the routes (highway vs city mpg). Well, I have not been able to achieve that yet, so being a geek, I focused my attention on a different form of mileage (throughput per switch-port) that interests me at work. So in this blog, I would explore a way to get more SAN mileage from the Cisco UCSFI (Fabric Interconnect)without significantly affecting the SAN admin’s day-to-day operations.
Just a bit of background before we delve into the details -- The I/O fabric between the UCS FI and the UCS Blade Server Chassis is a converged fabric, running FCoE. The usage of FCoE within the UCS fabric is completely transparent to the host operating system, and any Fibre Channel block storage traffic traverses this fabric as the FCoE traffic. So, a large number of over 20,000+ UCS customers, using Block Storage, are already using FCoE at the access layer of the network.
Now, the key question is what technology, FC or FCoE, to use northbound on the FI uplink ports to connect to an upstream Core switch for the SAN connectivity. So, what are the uplink options? Well, the FI has Unified ports and the choice is using the same uplink port as either 8G FC -or- 10G FCoE. [Note that when using the FCoE uplink, it is not a requirement to use a converged link and one can still use a dedicated FCoE link for carrying pure SAN traffic].
1) Bandwidth for Core Links: This is a very important aspect for the core part of the network. It is interesting to note that 10G FCoE provides almost50% more throughput than the 8G FC. This is because FC has a different bit encoding and clock-rate than Ethernet, and so 8G FC yields 6.8G throughput while 10G FCoE yields close to 10G throughput (post 1-2% Ethernet frame overhead)
2) Consistent Management Model: FCoE is FC technology with same management and security model, so it will be a seamless transition for a SAN admin to move from FC to FCoE with very minimal change in the day-to-day operations. Moreover, if the UCS FI is running in the NPV mode, then technically the FCoE link between the UCS FI and the upstream SAN switch does not constitute a Multi-Hop FCoE design, as the UCS FI is not consuming a Domain-ID, and the bulk of SAN configurations like zoning etc. need to happen on only the Core SAN switch, thus maintaining the same consistent SAN operational model as with just the FC.
3) Investment Protection with Multi-protocol flexibility: By choosing FCoE uplink from the converged access layer, one can still continue to use the upstream core SAN Director switch as-is, providing the connectivity to existing FC Storage arrays. Note that Cisco MDS 9000 SAN Director offers Multi-protocol flexibility so that one can Interconnect FCoE SANs on the Server-side with the FC SANs on the Storage-side.
On September 30th at Interop New York we announced the Cisco Nexus 3100 top-of-rack flexible switches. The show floor was buzzing with the news and the Techwise TV video below with Senior Product Manager, Jag Tamvada and self proclaimed Chief Networking Geek Jimmy Ray Purser discuss details of the switches.
With enough hype to rival even the most popular of Superbowl’s, Big Data experts will converge on New York City in just a couple weeks! But big data has good reason for all the hype as businesses continue to find new ways to leverage the insights derived from vast data pools that are continuing to grow at an exponential rate. A big reason for this is the ability to leverage Hadoop with the Hadoop Distributed File System and MapReduce functionality to analyze the data very quickly and provide incredibly fast queries that, although not even possible previously, can now be accomplished in minutes or less. We’ve only just begun to scratch the surface in terms of the financial returns made around Hadoop and the infrastructure to support Hadoop deployments but one thing we do know, it’s going to be big and it will continue to get bigger!
So how does Cisco fit into this picture?
Cisco is partnering with leading software providers to offer a comprehensive infrastructure and management solution to support customer big data initiatives including Hadoop, NoSQL and Massive Parallel Processing (MPP) analytics. Leveraging the advantages of fabric computing, the Cisco UCS Common Platform Architecture (CPA) delivers exceptional performance, capacity, management simplicity, and scale to help customers derive value more quickly and with less management overhead for the most challenging big data deployments.
Cisco UCS Common Platform Architecture for big data enables rapid deployment, predictable performance, and massive scale without the need for complex layers of switching infrastructure. In addition, the architecture offers unique data and management integration with enterprise applications hosted on Cisco UCS. This allows big data and enterprise applications to co-exist within a single management domain that simplifies data movement between applications and eliminates the need for unique technology silos in the data center. You can also check out my previous blog, Top Three Reasons Why Cisco UCS is a Better Platform for Big Data, to get an idea of what we’ll be sharing at the show.
Have you considered Cisco UCS for your Big Data projects? I’d like to invite you to come and hear more in a couple weeks at Strata Hadoop World in New York City. We’ll have a number of demos and experts on hand to answer all of your questions.
Companies today are facing an increasingly competitive environment and continue to look for points of differentiation in their markets. The SAN/Storage continues to play a vital role in enabling businesses to adopt new technologies and applications to help them grow. Software Defined Storage (SDS) / Software Defined Network (SDN) is positioned as one of the approach to gain efficiency and increase service velocity in the data center. SDS/SDN helps customers to keep up with the pace of change made possible by the virtualization of other data center resources and is a perfect complement to SDN.
EMC introduced their Software-defined storage, EMC ViPR — that offers a revolutionary approach to storage automation and management to transform existing heterogeneous storage into a simple, extensible, and open virtual storage platform.
Cisco is working closely with EMC to integrate Cisco MDS 9000 platform with EMC ViPR Software Defined Storage platforms. Cisco MDS 9000 provides industry leading performance, reliability, multiprotocol storage and supports extensive set of open API – those set of open API’s enable tight integration with EMC ViPR, as a result provide operational flexibility and agility by pooling storage assets, centralizing storage management, automating provisioning and delivering open API’s for our common customers.
To learn more, please view this video – where Rajeev Bhardwaj, Vice President of Product Management of Data Center explains the tight integration between Cisco MDS and EMC Viper and helps our common customers to simplify storage.