From my experience of working with enterprise market users, I’ve learned that regardless of the fact that everyone uses similar building blocks for their data center, with similar requirements, there is a great concentration on the application which creates endless diversification in the deployment and need of application centric concrete data for CIOs to make a decision.
When moving back to our HQ earlier this year I was challenged on how to provide that information fast and effective.
Together with some of our marketing and architecture organizations individuals, the idea to “become an end-user” came up. Easier said than done…How does an engineering driven vendor do that?
I’ve targeted taking off-the-shelf components that typically compose enterprise data-centers to provide a complete solution and have them tested to provide the end-users some basic data points to consider (without/before any specific changes or tuning performed).
What do I mean by of-the-shelf? Just like groceries… bread will be there after it is baked and ready to be eaten… it does not require any last minute changes.
How far do we go with it? All the way – hardware, software and applications! Of-course the countless numbers of database applications (Oracle, SAP, MySQL etc.) and computing application (VMotion, GigaSpaces, RTI etc.) are and will be ones which are officially and published on official web-sites and distributions.
With all the hardware/software we wanted to add “off-the-shelf” soul :) …and we’ve formed this inside our architecture group: a professional team called the “Mellanox High-Performance Enterprise Team”.
Learning and defining the needs, identifying the components, quoting… educating myself and our IT on the need, brought me to a conclusion – buying HW is hard, especially when you know what you need, and you need to find it in the big pile of data and the promises provided.
Long story short, I planned and got a stand alone unit which includes the building blocks of the data center (servers/CPU, storage, management/switches/KVM) – all fired up and ready to go. In my next blog posts I will zoom in on the hardware components selection process and considerations (which are one of the most important steps) as well as the software applications picked and tested, and provide data about the challenges and results generated by the High-Performance Enterprise Team.
NOTE: End users, please feel free to provide your suggestions on what you would like us to run and report on.
Nimrod Gindi is Director of Corporate Strategy at Mellanox Technologies; he has been with Mellanox for the past 9 years holding various engineering and management roles, lately Mr. Gindi has been in charge of Business Development mainly in the USA financial market.