NetApp Rocks the SPC-1

This post…where do we start.  I’ve intentionally held off on posting about NetApp’s recent SPC-1 results for the past couple of weeks.  I needed some time to fact-check, do some research, and eat some popcorn while reading through all of the FUD that has gone around.  To understand, you need to do some quick homework and what I would consider “required reading”…

Here’s a link to the Full Disclosure report from June 18, 2012, directly from storageperformance.org, and here’s a link to a blog by Dimitris Krekoukias of NetApp outlining the details of the results.  Chris Mellor from The Register also has a pretty nice writeup comparing latency and $/IOPS, in addition to some all-flash-arrays.

It can essentially be boiled down to the following:

  1. HP thinks their 3PAR results are superior, but no one cares about a million IOPS if you’re delivering them at an arguably unusable latency (i.e. > 10ms).
  2. EMC “LOL’s” at our results, even though they have never posted results themselves.  Perhaps they’re too chicken to show what their real list prices of goods are?  Or perhaps they are too scared to participate in a test that truly levels the playing field to a point where they themselves cannot control the output?  It’s easy to throw popcorn from the bleachers.
  3. Opponents are obsessed with the idea that we only had 40% used capacity, when the number of IOPS per spindle at 84% used capacity versus 40% used capacity was PROVEN to be almost identical.

There’s plenty more, and we’ll cover as much as possible, but the reason I am writing this post is to make one thing CRYSTAL CLEAR

NetApp IS a tier-1 Enterprise Storage Array.  PERIOD.

(…oh and we also do SAN/NAS in the same box, not to mention the industry’s only true scale-out platform with Cluster-Mode)

 

I’m really tired of hearing the following…

  • NetApp is good for tier3 and Backup (as if to passively imply we aren’t good at anything else)
  • NetApp is good for SMB and mid-range NAS (as if to passively imply we’re not good enough for tier 1)
  • NetApp is not a true SAN, it’s just a NAS with SAN “bolted-on.”

Bolted-on?  More like Baked-In, which is more than can be said for the “Celeriion” Celerra-Clariion DART-FLARE relationship.  (Don’t get me started…I’ve resisted posting about this for the longest time, but maybe that scab needs to be scratched off.)

 

Usable Capacity versus Performance Degradation

There were a lot of claims upon release of the results that we “padded” the number of disks used, because everyone knows that the more spindles you have spinning, the more IOPS/disk you can drive out of the system.  Or can you?

Here’s the 2010 SPC-1 report, showing an older version of DataONTAP, smaller mid-range hardware, at 84% capacity utilization, and reflecting 567 IOPS/disk.

In the latest report from June 2012, we demonstrated the latest DataONTAP 8.1.1, running our flagship FAS6240 in a 6-node Cluster-Mode deployment, at 40% utilization, and reflecting 579 IOPS/disk.

Just because your disks don’t run as well and as efficiently in your RAID6/10 pools at full utilization doesn’t mean ours don’t either.

All this chatter about “you only used 40% capacity,” and that that somehow magically discredits the results, and no one paying attention to us saying that there was arguably no difference between 40% used and 84% used, AND ACTUALLY SHOWING YOU, rather than just posting speculative nit-picking, unsubstantiated FUD, is getting old.

Go run your own tests. Set it up the same way that ours was done if you want to, compare apples-to-apples, and come back and we’ll have a good chat.

Until then, thank you for your recognition of our success, whether direct or indirect.  :)

-Nick

0 0 vote
Article Rating
Subscribe
Notify of
guest
9 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
JeramiahDooley
JeramiahDooley
07/10/2012 13:54

Hey Nick.  Yes, the FUD gets old.  From every direction.  Every day.  Welcome to the club. [Disclaimer: I work for the VCE] The bigger issue I have with these benchmark tests (no matter what vendor does them) is that no one actually cares except the vendors.  In my 15 years as a customer, partner and vendor I’ve never once heard a customer say “Man, I totally decided to buy $vendor because of their SPC-1 score!” I’ve definitely heard people use the scores to justify the decision they made, and I suppose there’s value in that, but it didn’t change someone’s… Read more »

Nick Howell
07/10/2012 14:25
Reply to  JeramiahDooley

What a wonderful world we would live in if this were ALL that mattered.  If no sales teams had to “court” the customers, or deals weren’t made on the golf course, etc etc etc. I couldn’t agree with you more that, as an ex-customer, I never used these to research a potential supplier.  That said, I now use them heavily to counter CUSTOMER claims that opponent vendors program into their heads when they come to visit us.  I’ve personally handed the most recent report to several existing non-NetApp shops, and had discussions with them about perception, and what they THOUGHT… Read more »

JeramiahDooley
JeramiahDooley
07/10/2012 14:35
Reply to  Nick Howell

But again, the customer doesn’t care.  The majority of them don’t know how the benchmarks are run, or what the caveats are.  I’d venture to say that the majority of them don’t trust anything that any vendor tells them, because most of what they see is the rampant FUD being slung around.  You are using something that is technical in nature as a marketing exhibit to allow you to have a conversation with a customer to counter an argument that another vendor made about what you can and can’t do.  It’s amazing that customers believe anything we say about anything.… Read more »

JeramiahDooley
JeramiahDooley
07/10/2012 14:41
Reply to  JeramiahDooley

I’d also suggest that giving the industry and analysts fodder to discuss is part of the problem, not part of the answer. :-) But that’s just me.

Bsears
Bsears
07/11/2012 11:16
Reply to  JeramiahDooley

I bought my most recent car because it got 29 MPG instead of 27. As someone who makes something that benchmarks better than a competing product, you just have to hope that a certain segment of the consuming population will look at that use it as part of making an informed decision. Other factors are huge as well, but if I was a major shareholder in a big company that had a CTO who couldn’t make heads or tails out of such benchmarks or was known to not bother with them- i mean a data center IS such a small… Read more »

CJ
CJ
07/10/2012 14:35

> running our flagship FAS6280
6240 no? 

Nick Howell
07/10/2012 15:19
Reply to  CJ

Correct.  Let me fix that.  Thanks for the head’s up!

Jonathan Adair
Jonathan Adair
07/10/2012 17:05

 Enjoyed the color commentary! Thanks for saying what needed to be said.  

Keith
Keith
07/11/2012 11:19

Tier 1 SAN storage has in my mind been characterized by not having an active/active or active/passive controller personality.  So NetApp, Clariion/VNX, HP EVA, etc all did not float as Tier 1 because a controller would fail over when the code tripped it or the admin manually failed it over.  Symmetrix, Hitachi, 3PAR, etc get around this by having everything active with redundant paths that survive a controller failure without flipping this personality to another controller. Not sure how c-mode changes this when using block storage, would be interested to hear.  If i have 4 FC initiators, 2 per head… Read more »

9
0
Would love your thoughts, please comment.x
()
x
Login
Loading...
Sign Up

New membership are not allowed.

Loading...