Thursday data center tidbits: arguing against virtualization, NASA data goes free range

Vern Burke, SwiftWater Telecom
Biddeford, ME

First up today is a question I ran across asking if there are any circumstances that argue against server virtualization in the data center. The only thing I can think of is the requirement for specialized hardware. If your applications require specialized hardware, keep them on their own server, otherwise, get virtualizing!

The next piece is about NASA discovering that they’ve been selling excess PCs without properly cleaning sensitive data off them. And everyone is in a panic over cloud computing being a tremendous security threat? The biggest security threat is leaving your data in the care of people who have no focus on the security of it.

Data center doof of the week goes to Tumblr for managing to kill a database cluster AND kill their network for a day for the sake of scheduled maintenance. Squeaky red noses are enroute!

Tuesday data center tidbits: PayPal doesn’t pay, scary virtual servers

Vern Burke, SwiftWater Telecom
Biddeford, ME

First up today is the piece about the recent 3+ hour data center failure at PayPal. Yet another self inflicted injury by a major company who should know better. Just in case the message isn’t clear, it might be a good idea to actually TEST your failover procedures BEFORE things actually fail. (Hmmmm, I wonder where you’d put the parking brake in a data center )

Next is the piece about the “scary side” of virtual servers. Everyone is having major angst over theoretical security “problems” when all of the issues I see are failure to follow the same well established best practices that work just fine for physical machines. It’s far easier for an attacker to compromise a virtual server with bad sysadmin practices than to invent a totally new hypervisor attack. Oh, and if you can’t trust your data center admin to do his job without having to be physically roadblocked by other departments, you have worse problems than virtualization.

Email or call me or visit the SwiftWater Telecom web site for green data center services today.

Monday data center tidbits: solar powering the data center, cleaning up after yourself virtually

Vern Burke, SwiftWater Telecom
Biddeford, Maine

First up today is a piece about solar power efficiency and whether it is practical to run a data center from 100% solar (it’s worth noting that all of the “100% solar” data centers that I’ve seen are very tiny). It’s going to take a long time before photovoltaic solar power is efficient enough to run a large load like a data center but any load you can shed is a benefit to the bottom line, not to mention shading the data center roof to cut down cooling costs.

Next up is the piece about virtual machine ghosts in the data center. There’s no substitute for paying attention and keeping control of what you’re doing, this isn’t rocket science. These people would have to do exactly the same thing with physical servers, why is it such an awful strain to do it with virtual ones?

Email or call me or visit the SwiftWater Telecom web site for green data center services today.

Is your workload a good candidate for #cloudcomputing? Adjust it if it isn’t!

I was just reading an article on what not to virtualize in your data center. I’m going to extend this question to IaaS cloud computing and show why this is the wrong idea.

Cloud computing as a whole and IaaS (infrastructure as a service) gain their efficiency by improving the percentage of utilization on the physical machines running the cloud. What was once a sea of terribly under utilized machines at 5% or less has now become a lean, mean, pack of highly efficient servers at 70%-90% utilization.

Unfortunately, some workloads have also pursued high efficiency (conventional) server configurations. This leads to a condition where the current standalone server isn’t a good candidate (in it’s current configuration) to place in a cloud environment, due to the fact that it may exceed the resources provided by the cloud virtual machine. So, does this mean we can’t cloud these workloads? Not at all.

Doing this means that we have to take a bit of a step backward. Instead of the entire workload crammed into one machine, which was the most efficient way to use a standalone server, clouding this workload means splitting it up.

The example given in the article is a high load web server that sucks up a standalone physical server’s entire I/O capacity. Instead of trying to cloud a clone of that, simply cloud a bunch of clones and load balance them.

Spreading out the work this way allows the cloud to efficiently spread the work out on it’s physical machines. This also gains you the easy ability to adjust for changes in demand. Now, instead of trying to cram more resources in a single (virtual) machine, simply create another clone and add it to the load balancer when you need more capacity and delete a clone when you need less. Also, you gain the big advantages of fault tolerance of the cloud, as well as the easy ability to run clones of the web server on clouds in different data centers. Now you have a level of fault tolerance and disaster recovery that your old standalone server could never match.

The end result here is that there is almost nothing that can’t fit in the cloud if you can break yourself from the current common wisdom that condensing things is best. Spread out, diffuse, and stop shoehorning things into tight packages.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services.

Vern

Growing the cloud. #cloudcomputing

We’re growing the cloud again! SwiftWater Telecom is pleased to announce the latest features and products for our cloud computing service!

Self provisioning: Just fill out a simple form to register as a customer, place your order online, and your virtual server is automatically created for you, fast and easy!

Control panel: With our new user control panel, you’re in full control of your virtual server. Start, stop, reboot, add features, statistics, control of your service is yours!

More supported systems: In addition to CentOS (5.5) Linux, we now offer Ubuntu Lucid Lynx (10.04)(server and desktop variants) and Debian Lenny (5.0.5) Linux as well! Don’t see your operating system here? Ask us to add it!

Add to this watchdog services that keep your virtual server up and running as well as powerful packages (high reliability web site, business server, etc) combined with multiple green energy efficient data centers and you have an unbeatable combination!

Visit us to learn more about cloud computing or to get started and place an order today!

Vern

Cloud computing and data centers, the numbers add up just fine.

I was just reading an article about the government’s 1200 data centers with only 7% server utilization and one claiming the government’s cloud computing numbers don’t add up. For probably the first time ever, it’s not the government that’s slinging the fuzzy math.

First, Vivek Kundra revealed the state of the government’s data centers. How in the HECK do you get that far off track? Is someone really setting the “build new data center” trigger at 7% utilization? I’m assuming that since this is the case, little or no other efficiency measures are in place in these data centers either. What an absolutely phenomenal waste of money and energy, even by that icon of inefficiency the federal government’s usual standards.

On top of this, we find that the TSA was planning to spend $600,000 to launch a blog. To launch a blog. To launch ONE blog. I’ll give you a moment to absorb that. It’s difficult for me to fathom the idea of spending $600.000 for ONE blog when you can grab a free copy of WordPress, slap it on a less than $1000 server, and, in an afternoon, have a perfectly top notch blog up and cooking. What is wrong with these people’s thought processes?

On the other side of the coin, we find an argument against the government’s cost saving numbers from dumping much of this horde of horrendously under utilized data centers in favor of cloud computing. The argument is that nobody is providing “detailed numbers” on precisely where the cost savings are.

The economics of cloud computing and virtualization are well established. Put the workload of 10 physical servers (a fairly conservative ratio) on one physical server, reduce your capital expenditure 90%, reduce your data center requirements 90%, reduce your power consumption and expense, and reduce your manpower requirement. These benefits of cloud computing are not vague or reasonably refutable.

So, is it a good reason to claim “the numbers don’t add up” unless you know down to the penny how much of the saving comes from power usage reduction versus manpower reduction? Should we poo poo this because we don’t know the precise percentage of saving between less IT equipment and less data center space?

Bean counting didn’t save us from getting into this mess and it’s grown to drastic proportions when you talk about a $600,000 blog. I see a lot of this going on in business adoption of cloud computing and virtualization also, pick nits over pennies when you’re bleeding $100 bills.

It’s time to embrace the savings of cloud computing, even if you can’t tuck all the pennies neatly in pigeon holes. Savings are savings and that’s the bottom line.

Let us show you the REAL savings, email or call me or visit the SwiftWater Telecom web site for cloud computing services!

Vern

Yes Virginia, you can virtualize almost anything with cloud computing.

This morning I’ve been reading from an article about virtualization not being a universal panacea. I do have to disagree some with Steve though. In this post, I’ll be talking about this from the standpoint of an IaaS cloud computing provider, but this should mostly be applicable to non-cloud virtualization as well.

Any application can benefit from a move to a cloud computing environment, whether that move improves performance or functionality of the application. Reduced complexity for the customer and disaster avoidance (quickly and seamlessly move virtual machines out of a data center threatened by natural disaster, for instance) should make this a no-brainer right from the go. What prevents this from happening more often than not are businesses that aren’t feeling enough pain around it to do anything until after the worst happens.

Far from being bad candidates for virtualizing, abandoned apps, obsolete apps, obsolete and oddball operating systems, and apps running on orphaned hardware are all prime candidates for cloud computing. It isn’t generally the application software or the OS itself that eventually kills these apps, it’s the failure of irreplaceable hardware that drives the nail in the coffin.

Big cloud computing providers typically have a limited range of the more common operating systems available as virtual machine images but smaller cloud computing providers can usually supply a solution for almost any OS that can still be found on the net (and most of them can). From the standpoint of non-x86 antiquated hardware, many old platforms can be found as very good emulators now. This means that the OS can either be run directly in a virtual machine (for x86 hardware) or on top of an emulator in a virtual machine (for non-x86 hardware).

So now, many of these orphaned applications can take advantage of cloud computing without having to become “kill” applications. If the software is still performing a useful job, put it on a cloud and and dump the caveman hardware.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services (give m a challenge, nothing is too weird to cloud!)!

Vern

Saturday data center tidbits.

I was just reading today about 4 trends in the new data center. What caught my eye first was a quote in the section about I/O virtualization:

“Take into consideration VMware’s best practices recommendation that you assign 1G port per virtual machine (VM). With newer 24-core servers, you could theoretically run at least 24 and maybe as many as 50 VMs on a single piece of hardware, which in turn would mean needing 50 1G ports, Harbaugh says. “

Good grief. Would you REALLY assign a dedicated physical 1GbE port to every single virtual machine? After you find a server you can cram that many ports into, what’s the point?

The second “trend” from the article is the ability of servers to handle crazy amounts of virtual machines based on increasing numbers of CPU cores. As I’ve written before, the limit on virtual machines isn’t raw CPU power, it’s the amount of memory available. Spend the money on these gold plated CPUs and then find out you can’t cram enough memory in to use it.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services!

Vern

Monday data center tidbits.

I was just reading a bit about virtual desktops when this jumped out at me:

“* Hosted virtual machine-based desktops, where a VM on a server supports 125 desktops …”

Um, is anyone REALLY trying to cram 125 desktops on to one single virtual machine? I thought I’d seen some crazy ratios before but this would have to perform just awful.

Sometimes just because you CAN do something doesn’t mean you SHOULD.

Email or call me or visit the SwiftWater Telecom web site for cloud computing services .

Vern

Monday data center tidbits.

First up today is reading about virtual servers and virtual switches and the claim of each virtual server having it’s own virtual switch. I can’t imagine any virtualization platform requiring a virtual switch for every virtual server (the excellent Xen Cloud Platform that we use uses one virtual switch for every physical interface on the host server). This is either the result of horribly bad cloud engineering or a claim that just plain isn’t correct.

Next up is an article promoting cookie cutter data centers. It’s entirely true that you can get silly pouring tons of money into microscopic gains in efficiency, but if you’re just going to abdicate control for a “common design”, you might as well just give it all up to Google or Amazon. Yes, there’s a risk of being different just for the sake of being different, not better. There’s more risk to not being different at all.

The reality is, you don’t have to get crazy pouring tons of money into a data center to get great efficiency (I’m sitting in one of our micro data centers right now with a PUE of 1.22 ). The trick is knowing when to stop.

Email or call me for green data center engineering that doesn’t go overboard on your wallet.

Vern