StorageRap

Claus, someone should smack you up for bad math! And the HBP smackups continue

Claus Mikkelsen at HDS wrote in his most recent blog post:

Having a 700% improvement in workload throughput is equivalent to having 105,000 RPM drives (very crude arithmetic and workload assumptions, but you get the point; don’t beat me up on this!).

What??  "don't beat me up on this"  Claus, what sort of lame disclaimer is that??  If you are going to write something stupid - and you know it when you are writing it, don't beg for mercy like a stoolie.  The math checkers in the storage blogosphere will find out and then decide if they want to give you a heaping load of sh%& for it. 

But I'm going to cut you slack because you are promoting wide striping, an excellent technology that doesn't get enough attention.  So, thanks.  We're really good at wide striping in 3PAR arrays and we appreciate the fact that HDS is trying to help people understand how well the technology can work - even if the explanation you provided is screwed up. While I'm at it, let me give you props for this line too:

I’ll defy anyone to manually provision in a way that will outperform the wide striping we do with HDP

A page from the 3PAR hymnal! - except you don't have to be using thin provisioning on a 3PAR array in order to get wide striping.  Automated provisioning in 3PAR arrays provides wide striping that performs much better than can be achieved with manually tuning. Not only that, but the utilization levels with 3PAR arrays are very high - especially for mixed workloads, where customers often want to store data for different applications on different RAID levels or tiers. 

With HBP (HDS Bloated Provisioning) - if application data is stored on different RAID levels you need different pools for each RAID level, which means you have to divide your disk resources between pools, which means your wide stripes aren't as wide and the performance advantages of wide striping are diminished. The other problem with using multiple pools is that utilization tends to be lower because disk resources are leveraged unevenly across different subsets of applications.

Nigel Poulton, who is a pretty good guy for a dyed-in-the-wool HDS cheerleader, and I have been videoing back and forth about HBP and 3PAR's thin provisioning differences.  I seem to recall him saying that you could setup an HDS array with a single pool.  Really Nigel - would that be s serious recommended best practice? All data stored in one RAID level?

Tony Asaro, in his blog,  quoted Nigel as saying:

For a start it maps perfectly with the internal workings of the USP V and VM.

Which was my point - Hitachi's engineer's did it to make it easier for themselves as opposed to fitting it to customer requirements.  Which leads me to Nigel's metadata fixation where he assumes that all metadata processes obey the same immutable rules of coding. They don't. That's because processes that are core design concepts usually are more efficient than bolt-on afterthoughts.  

Allegro - crushing it in eastern Europe

Allegro is an online auction company in Poland and they are dominating the market in eastern Europe.  Four guys from their technology team came to 3PAR HQ last week on a visit to several of their strategic vendors and they were nice enough to take the time to let me interview them.  They take advantage of lots of open source software, and believe in running their operations on robust, flexible and scalable products from companies like 3PAR, Brocade and Cisco.  The audio for this video is pretty soft, so you will probably need to crank up the volume to hear it.

Yes my dear, thin provisioning allocation size matters

Why use thin provisioning technology if it turns out that it's not efficient?  That's the question for Hitachi's Dynamic Provisioning, with its 42 MB allocation unit size.

The allocation unit is the amount of physical storage that is commited to a volume when new data is written to disk.  Allocating an amount of storage that is close in size to a typical write means that utilization levels can remain high, giving customers the biggest bang for the buck.  That's why our allocation units at 3PAR are 16 KB. 

It's hard to imagine what Hitachi was thinking when they came up with 42 MB allocation units. The amount of physical storage commited for each new write is in the range of 5000 times more than what is needed for a typical 8KB write. Yikes.  Of course many applications write more than 8KB at a time, but how many come close to 42 MB?  (almost none).  The whole thing is just bizarre. 

There are some hints about why Hitachi did it this way.  In a recent comment on my blog, Hu Yoshida mentioned the management burden to the system of tracking small allocation units.  Apparently Hitachi's engineer's didn't get the requirements quite right on this one and decided to leverage the customer's experience against their develoment effort. 

Oops, correcting my HDS bloat shrink blog

I'm probably not alone when I say that I figured HDS' zero page reclaim was something more than it actually is.  After I posted my bloat/shrink video a couple days ago, Hu Yoshida at HDS posted a pretty clear entry explaining that it is a fat to thin migration function. My apologies for not getting it right - I should have - and so I try in this video below, once again, to explain what it is.

Zero page reclaim has been one of the stranger announcements this year - and it certainly doesn't top Storage Anarchist's announcement coup of IBM's XIV last year, but if there were awards, for this sort of thing there might be a category for zero page reclaim this year.

Crazed night for Steering Wheel Cam on the Solstice!

Blog readers are warned. This is a Steering Wheel Cam Society of America video and has nothing whatsoever to do with storage.

Equinoxes are nowhere when it comes to SWCSA activity. Check out this fresh video that includes the first ever SWC-PM as well as a great chase with a Vega and a Ferrari and a Prius mixing it up.

HDS' catastrophic storage management

Catastrophe theory attempts to explain how seemingly small, incremental changes to systems result in catastrophic results - such as bridge collapses. Sometimes it involves oscillating or resonating behaviors that get out of control.

When HDS released their version of dynamic provisioning, they created a system that can grow in ways that can cause problems for customers.  The allocation unit for dynamic provisioning is large compared to other thin technologies - and when lots of host systems start writing to unallocated block storage, the amount of available, physical storage needed to supply all those allocations can spike quickly. Can it become a storage catastrophe?  I don't know, but it certainly is the poster child for thin provisioning out-of-disk-space concerns.

In order to fix the over-allocation of storage by dynamic provisioning, they (sort of) released their zero page reclaim feature back in February to get back some of the allocation overkill. It's not exactly two wrongs making a right, but zero page reclaim is simply a bug fix for sloppy, bloated dynamic provisioning. It's interesting that several months after making the functionality available they announced it this week as if its something new.  I guess you can do that if you keep it swept under the rug well enough.

Reclaim technology is going to be a very big deal in the storage industry, but it will work much better when it is integrated with efficient thin technologies, such as those developed by 3PAR, to create a consistent, well-behaved, predictable environment - as opposed to one that requires customers to manage unpredictable allocation storms.

The long term issues with dedupe technology

Digital archivists struggle with the question of whether there will be equipment available to read data from media that was many years before. It's not a simple matter of keeping devices for decades because all interfaces, including things like computer I/O buses, network interfaces and even power cables need to be preserved.

Carter George at Ocarina has a good post today discussing what some of the implications of dedupe technology are for archival storage. He touches on software issues, metadata and legal topics that need to be considered.  If you have an interest in using dedupe for long term archival you probably need to be paying attention to what Carter is talking about here.

 

An interview with Frey Kuo from TheLadders.com

TheLadders.com, is a job board for people earning more than $100,000 per year. I recently spoke with Frey Kuo, Director of Information Technology & Operations at TheLadders.com about the technology they use and how 3PAR storage helps them manage the "hyper growth" they have been experiencing. 

Their "Chairs" Super Bowl ad is pretty clever. You can see the whole thing and other ads of theirs are their  Youtube channel.  Check them out.

DDUP juice is spilling everywhere: FTC beats out DOJ for antitrust ruling

The Data Domain acquisition saga continues to generate great soap singing.  People wanting to read about market size definitions for antitrust cases might find this article interesting. (OK, I linked to this piece back on June 2 too, but I STILL think its relevant)

You know you're hot when different government legal organizations are vying for position.  What's next? A ruling and then lawsuits, or just a cascade of lawsuits in all directions?  Whatever, this thing is going to go down as easy as the bull testicles on "get me out of here".(begins at the 5 minute mark in the video)

At this point EMC is screwed if they try to raise their offer as some have suggested if this deal comes down to a ruling about anti-trust. I have to say, the Netapp legal team seems to be doing a very good job of positioning what many observers believe is an inferior offer to EMC's cash-out option.

Then there is the VC angle. A really big win for Greylock and NEA.  For everybody wondering what all those crazy VCs were thinking when they invested all over the place in the storage industry 8-12 years ago - this is exactly what they were hoping for. It's good money when you can get it.

More storage industry drama, market share lies and storage in cages!

Its a juicy Monday in the storage blogosphere.

First the Data Domain board rejection of EMC, then the outing of HDS' market share spin.

Finally, this New York Times Magazine photo of 3PAR storage, (the yellow-fronted rack to the left of center) imprisoned in cages working 24 x 7:

There's a lot of change happening in the storage industry, but one thing doesn't change much - the competition is fierce.  3PAR is very happy to have an active role in the storage industry, pushing the envelope and making technology followers out of companies like EMC and HDS. We have a lot of storage in cages inside the worlds largest cloud computing data centers.

Demure Data Domain begs stockholders for the match of it's choosing

This morning in the Wall Street Journal.

In today's episode of storage soap.......

(DDUP) "But papa, I don't want to marry that man, he's a brute!"

(stockholers) "He's got a big dowry - a cow and 20 goats"

(DDUP) "Yes papa, but the alternative isn't bad, he'll give you the 20 goats and because he's a beekeeper - we'll bring you sweet honey for the rest of your life! "

(stockholders) "You think I should take the promise of honey instead of a cow??!! Oy vey!  I could do a lot with a cow."

(DDUP) "But if I go with him, you'll never see me again!  It will be the death of me!  Besides, what if old moneybags changes his mind? Nobody will want me -  I could be a widow the rest of my life?"

(stockholders) "Don't worry my dear, there's always someone else. Besides, its not you rejecting your beekeeper man, its me,  He'll still want you if he really loves you.  But you know what they always say, a cow is a cow! Still, I hear the desperation in your voice and it breaks my heart.  I need to think about this......"

3P's open rap to Data Domain Employees

3P got all excited this week when Joe Tucci from EMC made his public plea to Data Domain's employees in the San Jose Mercury News because he wanted to tell them something too.  He didn't have the budget to spend on a full page in the paper, but he has other ways to get his message across - like this Rap Blog.

Thin air for Atmos?

Storagemojo wrote yesterday about EMC's business model for Atmos and how it seems to be struggling.  Apparently, there is a special sales force supporting the Atmos business that doesn't necessarily coordinate its efforts with the larger, just-get-the-$$$-in-the-door sales force that sells most everything else EMC has.  EMC's marketing machine and its bloggers would have you think Atmos is the most important software on the planet, but apparently others in the company would just as soon commit fratricide.  Here's a quote from Storagemojo's post:

The dozen or so Atmos sales people - yes, they have a tiny dedicated salesforce - are finding the well poisoned almost anywhere they go. Issues such as performance, stability, quality and future support of Atmos are reportedly being raised. Perfectly fair questions for any v.1.0 product - but they’re usually asked by competitors.

 

Read Storagemojo's post and then tell me if you think Atmos is a technology to invest in for the long term, with the ADD prone EMC wondering what new distractions to chase after the Data Domain debacle ends.  If it were me, I'd probably look at using services from Nirvanix - a company that is solely focused on delivering cloud storage. 

Dedupified at CNBC: "Since when am I the expert on testicle stuff?"

Nate commented earlier today about a CNBC video he saw, along with a link.

I thought I'd share the DDUP parts here, which have their moments.  Especially when Mark Haines has an apparent freudian slip and asks, "Since when am I the expert on testicle stuff?" (occurs at 1:55).

The Wall Street Journal did much better, instead of being dedupified they found an actual storage analyst- Steve Duplessie - to share his succinct insights.

Thank goodness, the arcane world of storage is too obscure for most normal people.  Even the word "dedupe" appears to be a tongue tying transgression waiting to happen.  There might be some job security after all.

Cartoon Curtis Preston, surprise guest on the EMC/Netapp/DDUP Debacle

From the release posted this morning on Businesswire:

The Board of Directors of Data Domain (NASDAQ:DDUP) today commented on the unsolicited offer it has received from EMC Corporation (NYSE:EMC) to acquire all of the outstanding shares of Data Domain common stock for $30.00 per share in cash. Consistent with its fiduciary duties and in consultation with its financial and legal advisors, Data Domain’s Board is reviewing EMC’s offer. At this time, the Board is not making a recommendation with respect to the EMC offer. Data Domain requests that its stockholders defer making a determination whether to accept or reject EMC’s offer until Data Domain has communicated to stockholders its position regarding the tender offer from EMC. In accordance with Rule 14d-9 of the Securities Exchange Act of 1934, on or before June 16, 2009, Data Domain will communicate to stockholders its position regarding the tender offer from EMC. At this time, the Board is reaffirming the recommendation in favor of Data Domain’s merger with NetApp, Inc. (NASDAQ:NTAP) that is described in the Registration Statement on Form S-4 that NetApp has filed with the Securities Exchange Commission.

In this short video Cartoon Curtis Preston makes his debut with the League of Suspicious Avatars (LOSA):