Another way to understand what 3PAR announced yesterday is to think of the life cycle of storage. 3PAR clustered arrays now offer new methods for removing wasted capacity from storage and recycling it so you can make use of it again for more pressing needs.
First, lets start with Thin Provisioning, which is a way to match the consumption of storage resources with its demand. Non-thin provisioning storage makes you guess during installation what you will need storage resources for. Once the storage has been allocated to a volume in a thin provisioning system it is no longer available to be used by another application. Thin provisioning continues to work as the volume ages, but its effectiveness depends on how efficient the file system (or database) is choosing which blocks to write to.
There - that's the old stuff.
First is a technology 3PAR calls Thin Conversion. This is a way to make a block copy from a volume or system that wasn't thinly provisioned and put it on a 3PAR array so that it is thinly provisioned. In other words, it removes all the non-utilized space that was never written to - which can be a lot. This is a one shot deal that gives customers an immediate payback by not having to buy as much storage when they are refreshing their storage technology.
Second is Thin Copy Reclamation. It sounds a bit boring but storage admins familiar with the problem of trapping storage capacity in snapshot or remote copy pools know that this is actually a very big deal. It can make the difference between continuing to work with what you've got and being forced to buy more storage than you planned for. This is something that storage administrators are likely to use repeatedly, over the life cycle of the volume or array, to maintain the balance of resources in their 3PAR arrays.
Third is Thin Persistence. Like Thin Copy Reclamation, Thin Persistence is something that storage admins will use periodically through the array's life cycle to remove wasted storage. File system tools are used in conjunction with a 3PAR array to identify blocks that were previously allocated but have since been deleted by the file system. Thin persistence is designed to recycle these blocks.
Fourth is Thin Reclamation for Veritas Storage Foundation. This is also another full life cycle technology that was developed by 3PAR and Symantec where a storage protocol command is used to transfer deleted block information from a Veritas Storage Foundation file system to a 3PAR InServ array. Symantec is most definitely leading the way with thin-aware file system technology.
So there you have it - three new ways to keep storage thin and one new way to get onto a storage platform that offers you these important storage life cycle options.
Yawn.
Nothing special, nothing new. Nothing more than basic hygene for thin provisioning. Is, or soon will be, standard for every thin implementation on the planet.
Hardly worth wasting an ASIC on, if you ask me.
And how are those Flash drives coming along, eh? You know, the ones you vehemently insisted nobody needs? Sounds like your engineers have ignored your perspective...
Posted by: the storage anarchist | October 13, 2009 at 04:18 PM
Sour grapes Barry. Reach for a few more straws.
Posted by: marc farley | October 13, 2009 at 04:33 PM
Sour grapes? I have nothing to be bitter about!
Nope, I'm simply observing that there's nothing all that special about being able to reclaim unused space in thin devices.
Oh, yeah.
I am also reminding the audience that your track record about what is really important (and what isn't) ain't really all that good...tell us, if wide-striping is the be-all and end-all to storage performance, then why dost thine president bespeak of a future with Flash drives embeddeth in thine arrays?
Perhaps 'tis thou, good sir, with the sour taste in thine mouth?
Posted by: the storage anarchist | October 13, 2009 at 05:35 PM
There are many things that are important. Wide striping still is and is one of the reasons our products crush your in performance - and why EMC won't put them to the test. Your track record is the one in question - making false and misleading statements about anything you come across, and is why your writing is becoming irrelevant. Check out what I've been saying about EFDs. You are the one who gets it wrong most of the time, Barry.
Posted by: marc farley | October 13, 2009 at 07:20 PM
Hey, Marc!
Well, you have the thinnest array of the world, i read some articles,documentation and obviously your blog about new features just released by 3Par and your company has done a good job on them (IMHO). Above all i like the reclamation for Veritas Storage Foundation , it's very good because the Veritas layer is often used in enterprises to manage storage, good shot!
3Par has joined (and probably now leads) the small group of vendors than can provision thin LUNs with the ability to stay thin: HDS and Compellent are the others members coming to my mind now.
Probably we are going to talk a lot about different implementations of this features in the near future, but, as Chris Evans ( http://thestoragearchitect.com/2009/10/13/enterprise-computing-so-emc-wheres-your-thin-persistence/ ) reminds us EMC will not be at this party! ;-)
ciao,
Enrico
Posted by: Enrico Signoretti | October 14, 2009 at 07:56 AM