Skip to main content

Intel's Virtualization Team Interviewed; Focus on Silicon not on Steel!

Brief Introduction

This I did a couple of weeks back and spoke to several Intel folks. Intel is virtualizing its 130 Data Centers worldwide and bring them down to 8 hubs! That is a massive undertaking and Intel has a few years to do that. Virtualization is forcing companies to start looking seriously at the core business. In the post-mainframe era we needed PCs to do work. The demands grew and both small and massive firms like Intel, IBM etc, grew bigger. More staffs and more PCs. Data Centers grew from a mere handful to full house! All this obviously led to areas that had nothing at all to do with your core business. So Intel decided, like any smart firm should, to put every useful Dollar/Euro/Yen back into the Silicon to keep up the pace in this continuously evolving and innovating market.

The people I spoke to were enthusiastic and had a common mission: Focus on your core strategy that is Silicon and not on Steel! It was good to see that even firms, of such depth and scale as Intel can have a company mission resonate across their ranks, from top to bottom!

Who did I speak to?

Travis Broughton, Enterprise Architect (His blog @Intel)
Ilene Aginsky, IT@Intel Enterprise Program Manager (LinkedIn Profile)
Brently Davis, manager, Intel's Data Center Efficiency Initiative (His Blog @Intel)

Who facilitated the interview?



Many thanks to:

Linda Bao
Joshua Lefkowitz




Here are the questions and answers

Me: Where are data centers located? Will the hubs stay in US or will they be distributed across the globe?


Intel: They will be distributed around the globe, according to our distribution of employees and manufacturing sites. We have a large population of design engineers in the US, so we will have a high density of servers here. However, we plan on hubs in Europe and Asia to support employees there as well.


Me: Why open up yet another channel to talk about virtualization when the market is already confused?


Intel: We agree that there is some confusion about the market. IT@Intel is bi-directional - we have the opportunity to learn from our fellow travelers as well as provide insight into what we're doing internally.


Me: This one is for Ilene: why talk about it to the web, the world already is into virtualization, what is so special about Intel's consolidation and virtualization?


Intel: Intel IT is interested in sharing best known methods and having a conversation with those out in the industry.


Me: Change management? Is it hard?


Intel: Change management is very hard, especially when you start moving virtual machines from one physical box to another. Keeping track of what is running where is a big obstacle to virtualization on an enterprise scale (on the client side it's not such a big deal - you've only got one physical box to worry about). On the other hand, virtualization can help with change management - you change the definitive system image one time rather than worrying about which boxes have been updated and which ones haven't.


Me: Will it lead to restructuring? Obviously, you are cutting down on servers, if there are lesser servers, you may not need many people, right?


Intel: Our plans are to focus more on standardizing than moving around people and responsibilities. We've outsourced a fair amount of the physical-touch part of data center management already (physical installation, repair, and removal of machines) so our IT headcount shouldn't be directly reduced due to those changes. There are two more likely outcomes: first, with lights-out data centers, service owners can reside pretty much anywhere in the world, even if their local DC is absorbed by a remote hub; second, we want to deliver more IT innovation and increase employee productivity (rather than merely keeping the environment running and stable), and we see this as a means to free up IT employees' time to work on delivering new capabilities.


Me: Globalization: Is it forcing intel to consolidate?


Intel: I don't know that it has caused us to consolidate, but it has certainly caused us to re-think some of our strategies. Ten years ago, we had about 6 major design sites. Now we have ten times as many. With fewer sites, it makes sense to provide each site with a full set of computing resources. At some point, though, the distribution of the resources becomes so fragmented that they can't be utilized efficiently. We reached that point several years ago and the current Data Center Efficiency initiative is an effort to reverse that trend.


Me: Are you using vendor specific virtualization OR your own (hardware assisted) or both?


Intel: Some of both. We have a grid/batch scheduler that we developed internally. We also buy off-the-shelf virtualization products that take advantage of features in our hardware.


Me: Do you have the C-level executive backing ? What are their true opinions about this initiative?


Intel: Yes. They seem to be very enthusiastic - and have been telling us to go faster. They encourage us to invest in silicon (servers) rather than concrete and steel (facilities), and this initiative is helping us along that path.



Comments

Popular posts from this blog

Security: VMware Workstation 6 vulnerability

vulnerable software: VMware Workstation 6.0 for Windows, possible some other VMware products as well type of vulnerability: DoS, potential privilege escalation I found a vulnerability in VMware Workstation 6.0 which allows an unprivileged user in the host OS to crash the system and potentially run arbitrary code with kernel privileges. The issue is in the vmstor-60 driver, which is supposed to mount VMware images within the host OS. When sending the IOCTL code FsSetVoleInformation with subcode FsSetFileInformation with a large buffer and underreporting its size to at max 1024 bytes, it will underrun and potentially execute arbitrary code. Security focus

Splunk that!

Saw this advert on Slashdot and went on to look for it and found the tour pretty neat to look at. Check out the demo too! So why would I need it? WHY NOT? I'd say. As an organization grows , new services, new data comes by, new logs start accumulating on the servers and it becomes increasingly difficult to look at all those logs, leave alone that you'd have time to read them and who cares about analysis as the time to look for those log files already makes your day, isn't it? Well a solution like this is a cool option to have your sysadmins/operators look at ONE PLACE and thus you don't have your administrators lurking around in your physical servers and *accidentally* messing up things there. Go ahead and give it a shot by downloading it and testing it. I'll give it a shot myself! Ok so I went ahead and installed it. Do this... [root@tarrydev Software]# ./splunk-Server-1.0.1-linux-installer.bin to install and this (if you screw up) [root@tarrydev Software]# /op

Virtualization is hot and sexy!

If this does not convince you to virtualize, believe me, nothing will :-) As you will hear these gorgeous women mention VMware, Akkori, Pano Logic, Microsoft and VKernel. They forgot to mention rackspace ;-) virtualization girl video I'm convinced, aren't you? Check out their site as well!