One of the things that we hear most often is that it’s hard to identify the problem being the application, server, or network.  We can now officially add to this list: Application, server, network, or virtualization layer. 

Virtualization is to IT sorta what light is to physics.  Is it a wave?  A particle?  Is it a software thing?  Is it hardware?  Virtualization is… virtualization.  It’s something different, something new, and something which is very very difficult.  Also like physics.

And when things go wrong with virtualization, they can go wrong very very badly. According to Network World:

Many VMware customers Tuesday were prevented from logging onto their virtual servers as a bug distributed in a software update effectively stopped the boxes from powering up….

"This certainly appears to be the most publicized bug for VMware so far, and I think it is damaging to VMware and virtualization as a whole. The hypervisor is the lowest software level on the server and if you have an issue like this, boom, all your infrastructure is down," says Gary Chen, a senior analyst with Yankee Group. "Software will always have bugs, but a widespread issue like this that affects all VMs is really damaging, especially at this point in time where virtualization is starting to take off. VMware is going to have to fix this fast, provide an explanation, and outline what they will do to strengthen their QA in the future."

The bug is preventing users from powering on virtual machines, though VMs already running continue to do so.  There is a workaround – set the date back, turn on the VM, reset the date – but that can be tricky when certain applications need accurate timing information  – banking records, for instance.

Of course the fact that it’s complicated means that it’s even harder for lay people to understand. I’ll bet you that even though the real problem is the virtualization layer, end-users who find this problem prevents them from working blame the network.

by Brian Boyko
Editor, Network Performance Daily

Apple hasn't made many overtures to business; the announcement that King Jobs had deigned to allow enterprise apps in his iPhone fiefdom took many by surprise. Apple's previous attempts at wooing enterprise customers, specifically the Xserve, seemed, in my opinion, more like a half-hearted reassurance to shareholders that they weren't completely ignoring the enterprise market.

Here's a telling point about Apple's attitude: Even though virtualization is one of the most important trends in enterprise computing, Apple makes the only operating system which cannot be run as a virtualized OS on generic hardware. It didn't allow Leopard Server to be run as a virtualized OS even on its own hardware until October 31st of last year.

While it's also true that Microsoft had - past tense - clauses in Vista EULAs which made it illegal to run Vista Home Basic and Vista Home Premium (but not Business, Enterprise, or Ultimate), as a virtual machine, those restrictions were eventually lifted in late January of 2008 - most importantly there was no deliberately imposed technical stumbling block that prevented those OS versions from being virtualized.

(One commentator, who I cannot remember, suggested that Microsoft's awkward anti-virtualization positioning was a move to prevent Apple from offering Parallels Desktop and a virtualized Vista pre-installed on new Apple consumer computers - but the ban has been lifted and Apple hasn't made any deal like that.)

Apple's MacOSX, on the other hand, checks to make sure it's running on Apple hardware, and will not run, otherwise. There are hacks to get around this, I'm sure, but they're much more difficult to pull off, may have stability problems - oh, and there's that whole "it's quite illegal" thing, too.

You can run MacOSX as a virtual server on an Xserve. But then it gets back to the application developers.

Enterprise application developers know today that they can pretty much choose their choice of platform. Have a Linux app but want to sell it to a Windows shop? Virtualization comes to the rescue. Windows applications on a Unix flavor? Again, same deal (though developers might have to pay for a copy of Windows to bundle with virtualized apps if the company doesn't already have a Windows virtual machine running.) But this incentive does not exist for the Macintosh platform. Who would develop a networked server application for the Macintosh platform knowing that you can only sell it to a company that made a big investment in Xserves? Especially since you can just code it for Linux or Windows and let Apple-only shops run it in virtualization.

Additionally, Microsoft has developed an optimized Windows Server 2003 version for virtualization - the Datacenter edition, and various Linux developers have scaled-down versions of the Linux OS for virtualization, including Ubuntu JeOS. We were not able to find a stripped-down version of Apple's Leopard Server. At any rate, running a "full" operating system in virtualization increases overhead and can impact server response times and, therefore, application performance.

Since there's this disincentive for enterprise application developers to develop for the platform, and a comparative performance hit on the platform that should cause network engineers to think twice about the platform, what, exactly is the utility of a MacOSX server?

The ultimate function of the IT department is to provide delivery of the business critical applications in a speedy and reliable manner to the users who need them. Virtualization doesn't change that. It merely changes everything else.

The funny thing about a virtual server is that it is the living embodiment of the idea that the silos in IT have to break down and once different technical fields now have to work together.

Virtual servers are part of virtual networks - that is, there are multiple virtual servers on one actual piece of hardware, and they connect to each other - on the same hardware - using the same networking protocols that they would use if it was communicating with a server halfway around the world. But it's all on the same server, so here's the question: Who fixes it when it breaks? Who owns it?

After all, there's no actual fiber/copper/tin-can-and-string wiring going on, it's all entirely on the server. So is it the server team that is responsible for "intra-box" networking connections? Or is the network team responsible? Gumming this all up - virtual servers are software. Does that mean the application team should be the one responsible?

With virtualization, you really can't have a segregated IT department and continue to operate efficiently. Traditional models of which part of the IT department "owns" which part of the "application path" from server to user are now irrelevant.

We've been talking about the idea that server, application development, and networking teams have to merge into an application delivery team for quite a while now - we invited Jim Metzler to speak at NetQoS Symposium 2007 to talk about it, and he'll be back for NetQoS Symposium 2008, (which starts a month from today, actually).

I think virtualization has thrown everyone who works in the enterprise space - from network engineers to CIOs to vendors like us here at NetQoS. Everyone knew it was going to be big; I don't think anyone realized how quickly it would catch on. March's issue of CIO Magazine reports that 85 percent of CIOs are happy with the return on investment of virtualization - even though it can be hard to quantify exactly what the return on investment is with current tools.

Douglas Gourlay from Cisco has posted a comment on this site which probably explains some of the features of the Nexus 7000 much better than I possibly could. Please check it out.

Cisco just announced its Nexus 7000 switch will be available in the second half of 2008.

The Nexus is a rather large machine that boasts a number of improvements over the 6500 series switches. If you have recently made a large purchase of 6500 series switches for your enterprise, you have my sympathy.

Andy Greenberg covers the technical beat at Forbes.com and explains some of the benefits of the behemoth box in plain English. For example, the Nexus has Gigabit Ethernet support (as well as support for future delivery of 40Gb/s and 100Gb/s,) so that you can run your whole data center with just Ethernet.

The killer feature, according to Greenberg, is that the Nexus 7000 allows distant virtual servers to use parallel processing. In other words, the virtual server in San Juan can now take advantage of idle cycles on the virtual server in Philadelphia, and vice versa. But there's more to it than that. The Cisco NX-OS, the new OS for the Nexus 7000, is said to allow switches to be virtualized at the device level, doing for switches what VMWare did for servers - that is, it not only helps get virtualized systems into parallel processing clusters but network engineers can create "domains" which define particular combinations of "bandwidth, processing, storage, and software," according to an article in BusinessWeek.

In addition to the obvious benefits, using previously unused resources can do a great amount towards reducing energy consumption and costs.

For a real look at the Nexus 7000, Cisco has provided an interactive model of the Cisco Nexus 7000 on their Web site.

What are your thoughts on the Cisco Nexus 7000? Feel free to discuss it in our comments section.

By Brian Boyko

With all the (deserved?) hype over virtualized servers, and the consolidation of hardware in order to reduce underutilized servers or replace obsolete hardware, many are overlooking what might be, in retrospect, an obvious use of virtualization – the end-user client computer.

The benefits of virtualized desktops mostly deal with administration and reducing problems caused by user error.

First, virtual configurations are essentially files on the hard disk, and those files can be backed up and restored to the hard drive of the end-user. It’s not a secure form of data storage, but it can be a lifesaver when a malware infection strikes.

Second, it can shorten the “test and deploy” period for software updates, because virtual environments can be configured to be identical and even in a worst case scenario, where a deployed change manifests problems, you can restore from the aforementioned backup.

Third, multiple VMs can be loaded on one machine. This means that if a particular program hangs or crashes, or works fine but is a notorious RAM hog, the end-user can switch over and continue working on a secondary virtual environment until the IT team can get to solving the original problem.

A possible unintended side-effect, however, is decreased network performance – virtual machines simply don’t run as fast as full-fledged installs, and if you have the ability to back up every end-user’s configuration to the network, eventually you may find yourself having to do so. Those with consolidated data centers and a lot of traffic operating over a WAN might not find the prospect of backing up hundreds of computers, including operating system, drivers, applications, and data, so appealing.

Kept on the LAN, however, servers dedicated to doing backup should not be as daunting. Those servers can be maintained via SSH from the WAN, and would not need that much hardware. You could probably repurpose some of those underutilized servers you have lying around – the ones that became redundant when you rolled out virtualized servers.

As readers can see, we’ve changed our “daily links” to twice-a-week Tuesday and Thursday links. This way we can provide a bit more commentary on each link instead of just listing them with little to no analysis. We invite our readers to give their opinions on this new format, and we’ll be looking to incorporate changes. One important note – if you have a link that you’d like to submit, please use the “submit a story” link on the left column of this page – we’ve been inundated with comment-spam and we wouldn’t want to accidentally delete your suggestion.

ZDNET: AMD versus Intel: CPU wars roadmap

George Ou at ZDNet graphs out the next two years of projected developments in CPU design over the next two years from Intel and AMD.

According to Kanter, the big reason for AMD's problem was Intel's manufacturing lead. While Intel was producing 65 nm processors all of last year, AMD was outputting 90 nm parts and barely got their first 65 nm product out by the end of the year. The significance of this is that 90 nm manufacturing with small 200 mm wafers produces less than half the number of wafers compared to a 65 nm process on 300 mm wafers. That means that while the price wars of 2006 put a damper on Intel's profits, it tore in to AMD financials because of higher chip fabrication costs.

Obviously the processing speed of the server will have an impact on request times, and if more data can be processed on the server side from more users, there will be more demand for Web-based apps – which could impact both application development and demand on network resources. Additionally, more computer cores means that there’s more room for virtualization… which you can read more about below.

Ars Technica: Buying OEM versions of Windows Vista: the facts

Ken Fisher has information about buying OEM versions of Windows Vista – you can get Vista Home Premium for $119, vs. retail at $239, but OEM versions cannot be reused with new motherboards.

OEM software is also tied to the motherboard it is first installed on. Unlike the retail versions of Windows which can be transferred to a new computer, OEM versions are not transferable. What about upgrading hardware? Microsoft says that anything is fair game, except the motherboard. Replacing the motherboard in a computer results in a "new personal computer," which the company considers to be synonymous with a transfer. It's not permitted with an OEM edition of Windows.

VMWare: Convert Physical Machines to Virtual Machines – Free!

Okay, imagine this scenario – you want to move to virtualization, but you have no idea whether or not you can switch over from a real server to a virtual one. Secondly, you’ve spent hundreds – if not thousands – of man-hours configuring and tweaking all the server’s settings for performance optimization, and you really don’t relish doing that again, multiple times.

VMware Converter quickly converts Microsoft Windows based physical machines and third party image formats to VMware virtual machines. It also converts virtual machines between VMware platforms. Automate and simplify physical to virtual machine conversions as well as conversions between virtual machine formats with VMware Converter.

Additionally, for the home user, being able to clone their existing installation of Microsoft Windows and then use it in the free (as in beer) VMWare player in Linux is a major stepping stone towards Linux migration.

• Network Performance Daily: Identifying the Source of Network Delay
• EFYTimes.com - Cisco Introduces Visual Quality Experience Technology
• EETimes.com - For telcos, all about access
• ITSM Watch: MRO Software Launches Web Resource
• IT Skeptic: VOIP is not cheating anyone. It is simply the future arriving

Continue reading "Daily Links: Network Delay, VQE Technology, Online Network infohub, VOIP is the future" »

• Network World: The four most trendy Linux developments
• IT Service Management - Practical Insights: Assuring the “Service” in Service Management – Part 2
• Network World: Naïve users who hog (or bring down) the network
• SearchNetworking: Five wireless myths debunked (Registration Required)
• ZDNet/George Ou: The truth about the IPv6 transition
• Data Center Central: The Rising Specter of Virtual Server Sprawl

Continue reading "Network Performance Daily Links 2006-11-15" »