Diggin' technology every day


Compellent gets Hyper efficient storage tiering

TechOps Guy: Nate

So according to this article from our friends at The Register, Compellent is considering going to absurdly efficient storage tiering taking the size of data being migrated to 32kB from their currently insanely efficient 512kB.

That's just insane!

For reference, as far as I know:

  • 3PAR moves data around in 128MB chunks
  • IBM moves data around in 1GB chunks (someone mentioned that XIV uses 1MB)
  • EMC moves data around in 1GB chunks
  • Hitachi moves data around in 42MB chunks (I believe this is the same data size they use for allocating storage to thin provisioned volumes)
  • NetApp has no automagic storage tiering functionality though they do have PAM cards which they claim is better.

I have to admit I do like Compellent's approach the best here, hopefully 3PAR can follow. I know 3PAR allocates data to think provisioned volumes in 16kB chunks, what I don't know is whether or not their system is adjustable to get down to a more granular level of storage tiering.

There's just no excuse for the inefficient IBM and EMC systems though, really, none.

Time will tell if Compellent actually follows through with going as granular as 32kB, I can't help but suspect the CPU overhead of monitoring so many things will be too much for the system to bear.

Maybe if they had purpose built ASIC...



Dell going after Compellent

TechOps Guy: Nate

I know this first made news a couple of days ago but I can't tell you how busy I've been recently. It seems like after Dell got reamed by HP in the 3PAR bidding war they are going after Compellent,  one of the only other storage technology companies utilizing distributed RAID, and as far as I know the main pioneer of automagic storage tiering.

This time around nobody else is expected to bid, it seems the stock speculators were a bit disappointed when the talks were announced as they had already bid the stock up far higher than what is being discussed as being the acquisition price.

While their previous generation of controllers seemed rather weak, their latest and greatest look to be a pretty sizable step up, and apparently can be leveraged by their existing customers, no need to buy a new storage system.

I can't wait to see how EMC responds myself. Dell must be really frustrated with them to go after Compellent so soon after losing 3PAR.


Compellent beats expectations

TechOps Guy: Nate

Earlier in the year Compellent's stock price took a big hit following lower expectations for sales and stuff, a bunch of legal stuff followed that, it seems yesterday they redeemed themselves though with their stock going up nearly 33% after they tripled their profits or something.

I've had my eye on Compellent for a couple of years now, don't remember where I first heard about them. They have similar technology to 3PAR, just it's implemented entirely in software using Intel CPUs as far as I know vs 3PAR leveraging ASICs (3PAR has Intel CPUs too but they aren't used for too much).

I have heard field reports that because of this that their performance is much more on the lower end of things, they have never published a SPC-1 result and I don't know anyone that uses them so don't know how they really perform.

They seem to use the same Xyratex enclosures that most everyone else uses. Compellent's controllers do seem to be somewhat on the low end of things, I really have nothing other to go on other than cache. With their high end controller coming in at only 3.5GB of cache (I assume 7GB mirrored for a pair of controllers?) it is very light on cache. The high end has a dual core 3.0Ghz CPU.

The lower amount of cache combined with their software-only design and only two CPUs per controller and the complex automated data movement make me think the systems are built for the lower end and not as scalable, but I'm sure perfectly useful for the market they are in.

Would be nice to see how/if their software can scale if they were to put say a pair of 8 or 12 core CPUs in their controllers. After all since they are leveraging x86 technology performing such an upgrade should be pretty painless! Their controller specs have remained the same for a while now(as far back as I can remember). The bigger CPUs will use more power, but from a storage perspective I'm happy to give a few hundred more watts if I can get 5x+ the performance, don't have to think once, yet alone twice.

They were, I believe the first to have automagic storage tiering and for that they deserve big props, though again no performance numbers posted (that I am aware of) that can illustrate the benefits this technology can bring to the table. I mean if anybody can prove this strategy works it should be them right? On paper it certainly sounds really nice but in practice I don't know, haven't seen indications that it's as ready as the marketing makes it out to be.

My biggest issue with automagic storage tiering is how fast the array can respond to "hot" blocks and optimize itself, which is why I think from a conceptual perspective I really like the EMC Fast Cache approach more (they do have FAST LUN and sub LUN tiering too). Not that I have any interest in using EMC stuff but they do have cool bits here and there.

Maybe Compellent the next to get bought out (as a block storage company yeah I know they have their zNAS), I believe from a technology standpoint they are in a stronger position than the likes of Pillar or Xiotech.

Anyway that's my random thought of the day