StorageRap

Just in time groomin' behind the wheel

A SWCSA video talking about just in time grooming and 3PAR's reservationless approach to resource utilization in their InServ storage arrays. Thin provisioned storage and snapshots (3PAR's Virtual Copy software) are assigned storage resources at the time they are needed - and not before. That means that Administrators don't have to guess which pools to put disk drives in - or how to structure hypers and metas with 3PAR. 

Real Partnerships for Virtual Private Arrays

Earlier this week 3PAR rolled out the Cloud Agile Program with our charter partners, Attenda, DataPipe, Terremark and Verizon Business.   The mission of Cloud Agile is to bring 3PAR's efficient and scalable enterprise storage capabilities to a wide range of customers through cloud (utility) service partners. 

One of my favorite aspects of Cloud Agile is the concept of a virtual private array, which is the same idea as a virtual private server, but applied to storage. Customers of our Cloud Agile partners will be able securely manage their own thin slices of our arrays, taking full advantage of massive wide striping and thin provisioning. 

Poll Envy

The last time I checked I was in 16th place in the Storage Monkeys vendor blogger's poll.  This is crushing.  So I lashed out at Dave Hitz who is leading the poll and said he hadn't posted anything this year.  That was wrong - he actually has posted this year.  Not much, but he has.  Nothing for May and June when he and Manny Ramirez were both on the sidelines.

Who cares about Data Domain's customers?

Introducing Handlebar Cam - in honor of the TDF.

Chris Fricke commented here, wondering what's in store for existing DDUP customers.  Good question Chris, who gives a rip about you?  Would it matter if you had EMC gear already, as opposed to being a card carrying EqualLogic customer?  If you have anything to say about what happens to customers, let fly!

What Google's Chrome OS means for the storage industry

Google's announcement this week about their intention to create a web-based operating system  from its Chrome technology has huge implications for storage, as well as the whole IT industry.  Inexpensive, lightweight and always-ready is the big winner in client technology.

Whether Google eventually succeeds with its Chrome strategy is immaterial now that the cat is out of the bag - everybody now understands that a user operating system doesn't have to carry legacy desktop system baggage anymore.  The cost of supporting obsolete equipment and software can be dropped and those functions replaced by utility (cloud) services. Among the obsolete stuff that can be left out are lots of storage drivers.

So what happens to data storage when user operating systems are completely web-based?  To begin with most user data will be stored for clients by the cloud applications running as SaaS web services. The question of whether those are private or public cloud services depends on a number variables including privacy concerns, single sign-on integration and application service levels.  Public service providers can leverage their resources across a larger install base, which will give them an economic advantage, but they need to be able to handle the challenges of multi-tenancy with technologies such as virtual management domains.

Service providers will build infrastructures with the most flexible, scalable products available. In an environment when almost anything can be accomplished in an Internet instant, neither clients or service providers can afford much time for initial setup and service level changes. For storage administrators, this amounts to having autonomic storage that readies all the resources before they are needed to be provisioned.

The concept of reservationless storage is important. If storage resources are connected to an array, why should it be necessary to think about which pools or meta-structures to assign them to first?  A storage admin in a web-connected world probably doesn't have the time to plan, re-plan and change logical storage structures when they are in the middle of a services demand surge. When management wants to know why service levels are causing customer problems, the last thing they want to hear is that storage had to be re-distributed because previous plans had to be changed. Thin provisioning and wide striping implementations that require pre-work and re-work won't deliver the goods.

Best practices will move from being a human-managed effort to setting thresholds and warnings for an autonomic, self balancing system.  This vision is what is pushing development efforts at 3PAR, much of it is already available in 3PAR InServ arrays today.

Will EMC pay too much for Data Domain? What next for Netapp?

Will EMC pay too much for DDUP?  That's the question everybody is going to be asking for years.  It's an awful lot of money, but de duplication of backup and archive data is probably going to be a very big deal for years to come. 

I like Steve Duplessie's take on it:  he said Netapp should feel relieved because they would have been under immense pressure.  EMC, on the other hand, has a larger business and more ways to leverage their DDUP investment - such as their channel relationship with Dell. Of course, that would mean that Dell would have to agree to be even more dependent on EMC for their storage business. 

Netapp gets a consolation prize - the $57 Million break up fee which will be paid by Data Domain.  It's not a lot but I'm sure they can put it to good use.  The larger problem for Netapp is how they are going to replace DDUP in their plans.  Obviously there were things they wanted to do with DDUP that they aren't going to be able to do now.  It will be interesting to see what their next move will be. There are other de duplication companies available if they want to grow their business that way.  

Terrible storage video gets Worst First award from the SWCSA

The Steering Wheel Camera Society of America moved swiftly to give Kostadis Roussos of Netapp the undesirable Worst First Award for his recent storage smackup video.  Up to this point the SWCSA has not involved itself in best or worst dressed minutiae, but it could become necessary as a way to prevent further slumming of the commons.

OK, lets all go to the moon!

Sunshine at Ocarina had a blog post this morning about the role Nirvanix is playing with NASA's Lunar Reconnaissance Orbiter (LRO) that is orbiting the moon and taking high resolution images of it's surface to prepare for future missions to the moon. 

A week ago I net up with an old friend who works at NASA and he was talking about his work and what NASA was up to.  With the shuttle program ending next year, the push at NASA is to get back to the moon, not for short visits like the Apollo program made, but for extended work and research at a lunar research facility. 

Not everybody likes the idea of pouring resources into an extensive manned program when it would be possible to do a lot of work with robots. But why give robots all the fun when they don't even know what fun is?  More to the point, there is probably a lot to be gained by engaging international teams in this mission. One of the best ways to get a perspective on our earthly situation is to see it from space.  Moving beyond us-versus-them thinking and the resulting conflicts that destroy so much would be a very good thing.  Robots aren't going to help much on that front, so I say let's get on with this work and go to the moon together and find what whatever we find. 

Flash is the least compelling storage technology in ESG survey

Terri McClure at ESG recently blogged about the what technologies are most interesting to NAS customers, according to a survey they conducted last September and October. People following the storage blogosphere may have seen references to Terri's post in blogs written by Sunshine Mugrabi from Ocarina and and Stephen Foskett from Nirvanix

3PAR is not a NAS company, so the survey wasn't a perfect fit, but the results of the survey pertain to more than NAS companies.  There was one data point that I thought was particularly interesting - flash SSDs ranked at the bottom of all the potential technologies people might buy. Instead, survey respondents were far more interested in power, cooling and space efficiencies - in general, doing more with less.

I think Flash SSDs will become more popular over time after the prices become more reasonable, but until then customers are going to continue to look first for products that help them cut costs, as opposed to adding significant costs.  Most customers today are looking for ways to meet their performance objectives while reducing their costs. That's what thin provisioning, wide striped arrays from 3PAR are designed for.