Storage and server virtualization

HP looks to entice SMBs, hypes Hyper-V bundles

HP made some storage updates today as part of a larger announcement aimed at SMBs looking to cut costs, including new Hyper-V bundles.

Storage-related updates include:

• New application-integrated snapshot option for LeftHand iSCSI SANs. LeftHand already had application-integrated snapshots that supported VSS for snapping the LeftHand SAN, but not with the ability to run inside and quiesce an application. This update fills that gap; competitors like Dell EqualLogic and NetApp already offer this capability.
• New NAS interface for D2D data deduplication products. SMBs no longer need to license virtual tape drives to use HP’s low-end data deduplication product.
• New DAT 320 tape drive. SMBs still using tape, on the other hand, have the option of doubling the capacity on DAT tape drives to 320GB. HP claims the new drives also offer up to a 75% performance increase with a 50% lower power draw. Tape, especially for SMBs, is frequently declared dead, but there are still pockets of tape use in this market, particularly in remote and branch offices.
• Six new HP Virtualization Smart Bundles for Microsoft Hyper-V. Full specs on the bundles, which range from an entry-level tower server form factor to rackmount servers with networked storage, are available at HP’s website. These bundles are similar to the ones HP previously rolled out this year for VMware environments.

LeftHand product marketing manager Chris McCall says the Hyper-V bundles are not a counter strike against the new joint venture between VMware, Cisco and EMC. He says HP is supporting both hypervisors, even though VMware is deeply aligned wiht HP HP competitors Cisco and EMC. ”We’ve done bundles for VMware already because we’ve targeted market size — we did VMware first because they’re the market leader,” he said. “If Microsoft was, we would’ve done Hyper-V first. There’s nothing to read into there.”

VMware CTO drops storage hints in futures keynote

VMware Inc. CTO Steve Herrod (above) dropped hints about what’s to come from VMware’s vSphere and VMware Desktop Infrastructure (VDI) products in a keynote that opened VMworld’s Wednesday sessions.

Among the storage-related items:

• VMware is working with storage vendors to put virtual desktop root disks into high-speed cache on storage arrays for faster boot-up times.
• Based on a new OEM relationship with RTO Software announced today, virtual desktops can be given individual personalities while their operating systems are managed centrally. This will simplify patching, since each virtual desktop OS doesn’t need to be separately patched, while saving storage space by using a “golden” OS copy. Without the ability to have patches proliferate from the golden copy (which is the case when using space-efficient snapshot environments within storage arrays), users face a choice between patching each copy, potentially exploding storage capacity requirements, or redeploying virtual desktops.
• VMware and Visa demonstrated mobile device virtualization during the keynote. VMware is developing products that can let mobile devices run applications with data centralized at the corporate data center rather than residing on each endpoint device.
• VMware’s Distributed Resource Scheduler, which today VMotions virtual machines between physical servers based on power consumption and processing load, will also take into account disk and network I/O. “DRS will combine with tiering algorithms on the storage side to match the application with hardware,” Herrod said.
• Similarly, VMware’s vApp, which encapsulates multi-tier applications with policy information, will include disaster recovery recovery time objective (RTO) information as well as availability requirements in policy profiles.

Another topic getting a lot of buzz at the show this year is distance VMotion–stay tuned for more on that front.

Remote data protection vendors cozy up to Microsoft

Microsoft’s annual TechEd user conference kicks off today in Los Angeles, accompanied by the usual flurry of supporting news announcements from industry vendors. Today the theme seems to be remote data protection, whether file delivery to branch offices, or data backup and disaster recovery.

Riverbed Technology Inc. is the first wide-area data services (WAN optimization/WAFS) vendor to announce that it will support a new feature called Direct Access when it becomes available in Windows Server 2008 R2, due out in 2010. Direct Access will create “the equivalent of a VPN tunnel” for Windows 7 remote clients attaching to a Server 2008 R2 host in the data center. Another coming feature called BranchCache will allow files to be stored locally at branches for Windows 7 clients. BranchCache will be certified to run on Riverbed’s SteelHead appliances at the branch office, according to Riverbed director of product marketing Apurva Dave.

As always when Microsoft expands into new areas, there’s the specter of the operating system vendor subsuming the value-add of smaller, more specialized players, which Dave admitted was a fear for Riverbed when it first heard about BranchCache. However, as with its Windows Storage Server product, Microsoft is pulling in partners for delivery, and Riverbed is prepared to sell BranchCache as part of “the complete picture for the branch,” which includes non-Windows and non-2008 Windows clients, Dave pointed out.

Also at TechEd, FalconStor Software Inc. will demonstrate a new product offering with partner Idera Software for backing up and single-instancing SharePoint documents. Idera’s SharePoint backup software will do the data protection; FalconStor’s File-interface Deduplication System (FDS) will do the data reduction. The co-marketed products will be available from both vendors.

Rounding out the remote data protection picture, Double-Take Software also indicated it’s on the Microsoft bandwagon today with the announcement that its GeoCluster integrates with Windows Server 2008 failover clustering and Hyper-V.

Finally, Sanbolic announced SQL Server 2008 clustering support and automation tools for the Melio clustered file system (CFS).

These announcements follow Sanbolic’s support for Hyper-V virtual servers, rolled out in January.

At that time, Scott Lowe, senior engineer for ePlus Technology, Inc. and a blogger on server virtualization, wrote that Sanbolic might be facing that old ‘coopetition’ bugaboo with Microsoft:

Clearly, Sanbolic wants to protect the value of Melio FS as Microsoft prepares to enter the clustered file system market with Cluster Shared Volumes (CSV), included in the R2 beta. It’s unclear to me whether CSV is going to be limited to virtualization only, addressing the “one-VM-per-LUN” issue, or whether Microsoft will also support CSV in other applications. By optimizing Melio FS for shared access to objects like virtual disk files and by extending support to run Melio FS in VMs on all the major platforms, Sanbolic hopes to establish Melio FS as a “de facto” standard in Windows-based clustered file systems.

Analysts: demand more from your storage vendor in virtual environments

A recent report by Andrew Reichman at Forrester Research showed that among 124 surveyed IT decision-makers, incumbent vendors and Fibre Channel still dominate the in-use storage systems supporting VMware deployments. But, according to Reichman and another analyst specializing in VMware, the Burton Group’s Chris Wolf, that doesn’t mean it’s necessarily how things should be.

According to the Forrester Report, users should “pick a vendor that offers thin provisioning, has deduplication on the road map, and has documented best practices in virtual environments.”

Some of these things, Reichman says, are harder to come by than you might think. “Especially clear best practices–it seems like vendors tiptoe around it, saying, ‘we can do whatever you need!’ and customers need more clarity,” he said.

Reichman also said he wanted more storage vendors to offer management console integration with VMware’s vCenter, the way Xiotech does with its Virtual View.

On the management console front, the Burton Group’s Wolf added that vendors who sell backup should be looking to consolidate VMware data protection features into the same software framework as array-based or network-based backup mechanisms.

“That integration is going to be important for backup products supporting a virtual environment,” he said.

Reichman’s survey found that most shops are sticking with an incumbent vendor for server virtualization deployments, and that that vendor is most often EMC. But Reichman also said that the survey is probably capturing the first wave of production deployments of VMware. As those deployments grow and become more complex, and as more storage vendors add new features to their products specifically to support virtual servers, users might be compelled to take a fresh look.

When they do, Reichman’s report urges users to consider Ethernet first rather than Fibre Channel, though he said Ethernet adoption may be driving primarily by Microsoft’s Hyper-V virtualization software rather than VMware, “which tends to either be protocol-agnostic or Fibre Channel-centric,” he said.

Wolf said there are a couple more virtual server-focused features he’d like to see vendors add as they try to market storage devices for virtual server support. One of them is array-level primary storage compression and dedupe, currently only offered in a handful of places like NetApp’s FAS systems, EMC’s newest Celerra products, and for nearline/archival file storage by startups StorWize and Ocarina. The other is more efficient deployment consolidation for things like patches on multiple virtual machine images.

“So you could deploy a patch one time and any dependent images automatically update as well–that’s the level of intelligence I’d like to see in the arrays,” he said.

Users look increasingly to storage virtualization as data grows, analyst says

I had an interesting conversation today with TheInfoPro’s managing director of storage research Rob Stevenson about the results of his firm’s latest survey of 250 Fortune 1000 and midsize enterprise storage users. Fortune 1000 users surveyed by TIP cited block virtualization as having the biggest impact on their environment this year. TIP expects 50% of the Fortune 1000 to have virtualization in use by the end of 2009. All of this is in response to ongoing and relentless data growth.

“Impact” is difficult to define, as TIP doesn’t offer definitions or parameters to the open-ended question for users, instead letting the responses shape the definition. (Midrange users cited server virtualization as having the biggest impact, and we all know that there are good and bad impacts involved).

What really stood out to me, though, when I discussed the results (as well as the semantics of the word impact) with Stevenson, was how block virtualization is being used and for what purposes. My general impression has been that block storage virtualization has not lived up to its initial round of hype as a “silver bullet” for single-pane-of-glass management of an overall storage environment. I wondered, had that changed when I wasn’t looking?

According to Stevenson, while adoption for block virtualization has risen steadily even since this past February (number of respondents with the technology “in use” went from 21% in February’s Wave 10 to 23% in Wave 11), 23% said they’re using it with just 2% of the overall storage capacity.

Stevenson said the users in this case were petabyte-plus shops that in the past year or so have seen storage balloon from the single petabyte range to 2.5 petabytes or more, with no signs of stopping. These admins are scrambling to consolidate storage, move to new technologies that offer better utilization, and automate tasks. Where block virtualization comes in for most of them is performing data migration while moving to new technologies or systems — hence the relatively small proportion of data being managed by block virtualization devices from day to day.

Meanwhile, midrange enterprises are increasingly looking to maximize their resources on the server side.  Close behind that, though, come utilization improvement technologies for storage like thin provisioning and data deduplication.

It’s largely a matter of consolidating resources and improving utilization rates. “But the big Fortune 1000 shops have a bigger ‘legacy drag’ of data that they have to move,” Stevenson said. Hence the use of block virtualization tools.

Stevenson said continued data growth and an increasing amount of complexity to go along with it–storage managers are not only managing an average of 400 TB each compared to 200 TB each a year ago, but the number of LUNs to manage within that volume is also increasing. That drives a need for automated management. While the most popular use case for virtualization seems to be data migration, Stevenson said users are finding day-to-day data movement is also increasing, bringing these devices to the forefront once again for management.

Does this mean we could be seeing block virtualization tools proliferate once the midrange market reaches the petabyte level? (After all, as the old chestnut goes, a megabyte used to be a lot of data). That’s where Stevenson’s crystal ball grows, well, cloudier.

Right now, one tentative theory is that users whose data centers already have large amounts of data under management tend to also already have specialized staff. But as the midrange market comes up against a need to scale staff as well as technology, they may turn to service providers before turning to storage virtualization devices.

“In large data centers, we see the pooling of resources among multiple data center groups to balance workload, like moving storage networking to a networking team or data classification and archiving to server and application groups,” Stevenson said. “When it comes to midsize admins having to start ‘not doing things’, it’s probably not going to come with an increase in internal staffing–instead they may look to offshoring those tasks to cloud service providers.”

But that’s not to say large enterprises won’t be looking up at the clouds, too. ”We’re still working out the ‘competing futures’ if you will,” Stevenson said.

EMC’s Maui surfaces, then disappears

EMC blogger Storagezilla posted an interesting Flash animated video this morning about Maui, titled CloudFellas, in a post that has since been whacked. In the original post, ‘zilla alluded to ‘getting too far out in front of the boss’, so maybe that’s what happened (the post has been deleted from Google’s cache as well).

The video showed fun little animations about the spread of data to points around the world, and gave the example of a movie project where dailies from the set have to be sent to production houses for editing, then from the production houses back to the studio for vetting, and eventually out to movie theaters for distribution. Connecting multinational islands of data seemed to be a theme, as was scalability to petabytes, even exabytes.

This is important because EMC has yet to formally tell us just what Maui actually does. When Hulk/Maui were first discussed during EMC’s Innovation day last fall, it was assumed that Maui was the file system for Hulk’s hardware. But it turns out Hulk is shipping with Ibrix as its front-end file system, and according rumors that were going around about Maui at EMC World in May, Maui is instead a layer of software that sits above local storage pools, which could serve as a global data repository for multinational companies, tying multiple data centers together.

This even jibes with the codename - Maui is an island in Hawaii as well as the name of the Hawaiian god that raised the Hawaiian islands from the sea. Raising islands (of storage), joining them together in a chain… 

Then there’s ‘zilla’s comment this morning in his original post: “the internal cloud currently stretches from the east coast of America right into China.” He also mentioned that the business plan is executing to schedule, which would mean Hulk and Maui will both be formally introduced in the third quarter.

NetApp CEO is cool with new VMware boss

NetApp has a strong working relationship with VMware, despite counting VMware’s parent EMC as its storage archrival. So NetApp CEO Dan Warmenhoven didn’t know what to make of the news when he heard VMware swapped CEOs from founder Diane Greene for former Microsoft exec Paul Maritz last month.

“When I first read the news about the change I was a bit shocked,” Warmenhoven said during NetApp’s earnings conference call Wednesday.

The next surprise for Warmenhoven came when he received a phone call from Maritz hours later. “I really want to thank Paul,” Warmenhoven said. “He placed a call to me before 1 p.m. the day he was announced as the CEO, and I’ve got to imagine that was a very busy day for him. When we did connect, he actually reaffirmed every part of the relationship we had prior, and even took some very visible actions to strengthen the relationship so we were very, very pleased. I think it’s going to be terrific.”

Warmenhoven called Maritz’s reaching out “very pragmatic,” considering there is a large pipeline of customers looking to implement VMware and NetApp storage. And with Microsoft entering the server virtualization market, VMware needs all the friends it can get. “He’s facing some significant competition coming up on the horizon, and he’s not about to jeopardize any close relationships he has,” Warmenhoven said.

Maritz has been doing a lot of reaching out in his early days as VMware CEO. Besides talking to VMware storage and server partners, he had to apologize to customers this week for a VMware bug that locked up their servers.

The great storage chargeback debate

“You need HOW MUCH for storage?!” That question has been heard by many of us currently submitting budgets for the next calendar year, quickly followed by “Are you SURE you need that much disk? Didn’t we just get disk last year? Where did they all go!? I want your house audited. Now!”

Okay, maybe not the audit part, but for most of us, getting the type of disk we need in the quantity we need it is an uphill battle. Add SSD, deduplication, and longer-term retention to the mix, and things are getting a bit hairy with my budgetary requests. I’m at such a point now with a few of my smaller clients, and when they get that “you’re crazy” look, I bring up the chargeback model.

I think I just heard a collective sigh from the interwebs.

I understand both sides of the chargeback dilemma: the accounting side, that has to somehow keep track of all this without keeping track of all this; and the IT side, that is constantly being painted as the cost center only because no one is taking ownership of their parts of the “plumbing.” People (read departments) will request outrageous resources when they don’t have to directly foot the bill. That part I get, but are they so vehemently against accounting for their infrastructure usage?

In my opinion, chargeback would actually lead to better data management habits — at least in the long term — because if you have to pay for everything out of your own budget, then you’ll be more careful about separating what you need from what you want. How many of our managers and accounting folks have processes in place to account for each department’s use of the “utilities” that make up IT and understand that IT isn’t the root of all expenses?

I had an energetic debate with a co-worker about this very issue. I took the stance that chargeback is the way to go. He offered a more community-oriented accounting method. We went back and forth, point and counterpoint, until concluding that it just depends on what your business environment will support and the level of organization that business has in place.

For instance, if you have a well-organized, project-oriented IT environment, and have a project portfolio ready for sizing, you can plan a community budget very well and effectively fund addition to your infrastructure through a single IT budget. The reality from <i>my</I> experience (read, SMB clients) is that most companies are not so well-organized, don’t have a project portfolio for the next 12 months, and will not be able to identify budgetary requirements for infrastructure improvements.

In these cases, chargeback (or, at the very least, departmental accounting) is key to being able to answer my opening question with confidence.

Traditional SAN storage may be easy to bill for, but what of virtualized storage? Take it a step further, how about Softricity/Microsoft’s Softgrid? (Softricity is the company Microsoft acquired not too long ago that allows for application-level virtualization as opposed to host virtualization.) How do you quantify and itemize a streamed, virtualized application?

Then there’s the question floating just below the surface of the chargeback debate: How do I, as a department, know you are giving me what I’m being “billed” for? That question opens a giant can of worms in my mind (and there are already creepy crawlies up there, no need to add worms to the mix).

The crux of what I’m getting at is: Are we as technologists — and storage pros specifically — asking for too much or too little when it comes to chargeback? Are there still companies out there that don’t see the light when it comes to chargeback and departmental accounting. Should we as storage pros be leading the way for other areas of IT to follow our example?

More server virtualization benchmark drama

Last time on As the Benchmark Turns, we saw NetApp pull a fast one on EMC. This week’s episode brings us into the torrid realm of server virtualization and Hyper-V.

It began with a press release from QLogic and Microsoft lauding benchmark results showing “near-native throughput” on Hyper-V hosts attached to storage via Fibre Channel, to the tune of 200,000 IOPS.

Server virtualization analyst Chris Wolf of the Burton Group took the testing methodology to task on his blog:

The press release was careful to state the hypervisor and fibre channel HBA (QLogic 2500 Series 8Gb adapter), but failed to mention the back end storage configuration. I consider this to be an important omission. After some digging around, I was able to find the benchmark results here. If I was watching an Olympic event, this would be the moment where after thinking I witnessed an incredible athletic event, I learned that the athlete tested positive for steroids. Microsoft and QLogic didn’t take a fibre channel disk array and inject it with Stanzanol or rub it with “the clear,” but they did use solid state storage. The storage array used was a Texas Memory RamSan 325 FC storage array. The benchmark that resulted in nearly 200,000 IOPS, as you’ll see from the diagram, ran within 90% of native performance (180,000 IOPS). However, this benchmark used a completely unrealistic block size of 512 bytes (a block size of 8K or 16K would have been more realistic). The benchmark that resulted in close to native throughput (3% performance delta) yielded performance of 120,426 IOPS with an 8KB block size. No other virtualization vendors have published benchmarks using solid state storage, so the QLogic/Hyper-V benchmark, to me, really hasn’t proven anything.

I talked with QLogic’s VP of corporate marketing, Frank Berry, about this yesterday. He said that Wolf had misinterpreted the intention of the testing, which he said was only meant to show the performance of Hyper-V vs. a native Windows server deployment. “Storage performance wasn’t at issue,” he said. At least one of Wolf’s commenters pointed this out, too:

You want to demonstrate the speed of your devices, the (sic) you avoid any other bottlenecks: so you use RamSan. You want to show transitions to and from your VM do not matter, then you use a blocksize that uses a lot of transitions: 512 bytes…

But Wolf points to wording in the QLogic press release, claiming the result ”surpasses the existing benchmark results in the market,” and claiming that ”implies that the Hyper-V/QLogic benchmark has outperformed a comparable VMware benchmark.” Furthermore, he adds:

Too many vendors provide benchmark results that involve running a single VM on a single physical host (I’m assuming that’s the case with the Microsoft/QLogic benchmark). I don’t think you’ll find a VMware benchmark published in the last couple of months that does not include scalability results. If you want to prove the performance of the hypervisor, you have to do so under a real workload. Benchmarking the performance of 1 VM on 1 host does not accurately reflect the scheduling work that the hypervisor needs to do, so to me this is not a true reflection of VM/hypervisor performance. Show me scalability up to 8 VMs and I’m a believer, since consolidation ratios of 8:1 to 12:1 have been pretty typical. When I see benchmarks that are completely absent of any type of real world workload, I’m going to bring attention to them.

And really, why didn’t QLogic mention the full configuration in first reporting the test results? For that matter, why not use regular disk during the testing, since that’s what most customers are going to be using?

On the other hand, QLogic and Microsoft would be far from the first to put their best testing results forward. But does anyone really base decisions around vendor-provided performance benchmarks anyway?