* Posts by ByteMe

24 publicly visible posts • joined 14 Aug 2013

Rubrik to hit enterprise with double whammy

ByteMe

Modesty will get you nowhere

This guy's ego is astounding. Now Bipul thinks HE's Kevin Durant. A company that's only been around for 2? years, with something like $50-$75M run rate, claims they're the successor to multi-billion dollar firms with decades of experience. I look forward to their over-hyped IPO followed by the inevitable death spiral.

DataCore drops SPC-1 bombshell

ByteMe

Is SPC-1 still relevent with massive cache systems?

I agree that the question shouldn't be, "Is this just running out of cache?" The real question should be, "Is SPC-1 still a relevant benchmark test when storage and HCI systems are now much different and all can use massive amounts of DRAM cache?" SPC-1 was designed back when traditional arrays were entirely spinning-disk based and DRAM for cache was limited due to its high price. Most all of today's storage platforms leverage "YUUGE!" amounts of cheap and fast DRAM as well as multiple, if not all, SSDs. Somebody needs to start thinking-up a new benchmark test.

Lost little X-IO lays off ~75 staff in Colorado as it shutters factory

ByteMe
Thumb Up

Is that honesty I hear?

That was the most honest CEO response to failure that I've heard in a long time. Kevin DeNuccio of Violin Memory needs to read this.

A tiny Violin plays as EMC tops all-flash array revenue chart

ByteMe

Never underestimate EMC

There is one axiom in the storage industry: "Never underestimate EMC". Even they know they're not selling the best AFA product (see latest internal executive e-mails) but that doesn't stop them from dominating the AFA market. I've never been a fan of their storage products, but I always hold EMC in the highest regard from a sales execution standpoint. Well done.

EMC mulled a Pure Storage buyout amid patent sueball tennis

ByteMe

Taking the high road?

I love how these characters - from any IT vendor - suddenly claim to "take the high road" only once they're caught being absolute douchebags. Suddenly they're above it all and don't have a spec of dirt on their soul.

When Michael Dell met Chris Mellor

ByteMe

Don't insult NYC that way

"Don Basile of Violin Memory was a true New Yorker." Hey now. Not all people from New York are arrogant ass-clowns who wreck every company they touch. Many of them are lovely people.

Are you in the 1%? The 1% of sysadmins who need specialized flash?

ByteMe
WTF?

Thank You Captain Obvious

Thank you for telling us what we already know. Was this a piece to just kick Violin Memory while they're down? Or, was it to try and make Pure Storage look good after its financials debacle? Either way, it was a waste of my time.

Dog walkers, the San Andreas fault ... and the storage industry

ByteMe

Re: Think data, not storage

You're joking, right? Even for small shops, moving data is very painful and expensive. It's not just the migration of the data itself, it the coordination of the event. Project management, application owners, sysadmins, project timeframes, maintenance windows, possible outages, and the evil that is Professional Services. I'd argue that in many cases, the OPEX cost of all the people and time involved in storage migrations is more expensive than the new storage itself. IT staff often don't think about that, but CIOs and CFOs do.

Pure as the driven IPO: Upstart tells SEC it's go for stock market debut

ByteMe

Not a great time for IPO

Not a great time to IPO. There is a U.S. Presidential election looming on the horizon. Presidential elections have historically made the stock market very skittish until elections are over. As AC mentioned above, Pure Storage is burning through the cash and are not likely to get another round of funding, so they have to go public. Yet they're grossly over-valued and expenses are clearly way too high. Once they're public, there will be enormous pressure to get spending under control and get expenses down.

Where is the cash going? Likely R & D for a hyperconverged appliance which they've hinted at before. Seeing as how they don't currently have a scale-out cluster technology, this could take years to bring to market. By the time they deliver something, it could be too little too late as there are a LOT of competitors in that space already.

Should be fun to watch.

Is Nexenta exposing a vast core storage market vulnerability?

ByteMe

Can't argue...

Having spent over a decade in enterprise storage, both as a customer and selling it, I can't argue with the basic point of this story. Enterprise storage companies, with their 60 points of margin and massive sales organizations, are going to lose a huge piece of their business to server-based-storage. Call it HCI, SDS, server SAN, or whatever you want. This shit is happening. You hear it from customers and you can see server vendors positioning themselves for it.

Is Enterprise storage dead? Absolutely not. However, it's going to be squeezed into a niche where 1 copy of primary data lives. Ditto for all-flash-arrays. The rest will be carved-up between different flavors of server-based storage and will save customers a lot of money.

Fun times.

If flash storage achieves FaME, will it live forever?

ByteMe
WTF?

What is this, Fox News?

Author states that internal SSDs are much faster than networked flash arrays. "...A big jump in latency takes us to all-flash networked storage arrays accessed across Ethernet or Fibre Channel, with accesses taking many milliseconds." Who the %#!'s networked flash storage are you talking about? DIMM-type flash arrays like IBM FlashSystem and Violin Memory easily achieve 100-200 microsecond latency - at the host layer - under high workloads. Even the SSD-based "always-on" dedup arrays like Pure Storage and XtremIO can easily achieve 500 microsecond latency under average loads.

I understand the point of the article is to highlight the speed of putting flash closer to the CPU. Just don't lose your journalistic integrity in the process.

NetApp CTO Jay Kidd resigns and retires from the industry

ByteMe
Holmes

Same as the old boss?

No crystal ball required here. Val Bercovici will take over CTO role. While he's not exactly new blood, he may be smart enough not keep flogging the tired FAS horse and find something new for NetApp to sell. Rumor has it he's already shopping for new flash kit at Micron now that FlashRay has been shelved.

Pure Storage shoves channel growth ahead of IPO dream bid

ByteMe
WTF?

Pure replacing Tier-1? When has that ever happened?

I know Pure has done well, but let's be honest. They've been selling into the VDI / VSI space in the small-to-medium Enterprise space. They're not known for taking down VMAX replacements and running Tier-1 databases. This is why they've done so well with the channel partners who like taking-down easy deals.

If their IPO depends on channel taking down Tier-1 replacements, they're going to have a hard time.

Startups face logjam as the trickle towards the exit turns into flood

ByteMe
Unhappy

Buyer's market and acquisition is no guarantee of success

It's a buyers market and not a lot of buyers at that. Nobody is going to repeat the stupidity we saw with Data Domain and 3PAR acquisitions. With this many companies looking for a buyer and running out of cash, buyers can afford to wait for a good deal.

Even if one or two of these start-ups get acquired, it's no guarantee they'll last. NetApp is in pretty sorry state right now and needs to acquire something exciting. However, when it comes to acquisitions they're all thumbs. They've failed to make any acquisition pan out and the acquired talent jumps ship quickly due to the internal politics. They eventually mothball it because they can't figure out how to sell it.

I suspect some VCs will get their money back, but I'll be surprised if any of these companies see a huge payday.

Pure Storage preps for IPO: report

ByteMe
Mushroom

Burn baby, burn

Once Pure goes public and Wall Street sees their cash burn-rate, they won't look so attractive. Pure has been gobbling VC cash, chewing it up and pooping it out in the form of rediculously expensive marketing. Add the large R&D cost of re-designing their storage platform to use DIMM-type flash and not SSDs, their over-aggressive hiring of sales staff for an all-channel sales model, and expensive talent like Beepy. It doesn't look good.

Once they're public, they'll have to get their rediculous spending under control which negatively affects everything.

NetApp veep: 'We've shifted 750,000 all-flash arrays'. Er, really?

ByteMe

Zoom in please!

Could you please provide a photo that is closer to George's face? I can't quite count all the eyelashes or see all the plaque on his teeth.

Mind the product overlap gap, cloud ONTAP... make way for FlashRay – NetApp veep

ByteMe
WTF?

Reading this, I can't help but think that NetApp is tap-dancing and trying to figure out how to position this thing. First, the comment that FlashRay *might* have HA clustering sometime in the future is a red-flag that indicates its not fully developed and has long way to go. Which may explain why they're touting the use of TLC flash for a slower/cheaper platform for ONTAP replication. Who cares if it's a single controller if its just a backup/replication tier? At least they can start selling it and try and convince analysts this is what it was designed to do. NetApp is masterful in convincing analysts that everything it does was "by design" and well thought out. Emperor Palpatine could learn a thing or two from NetApp on how to sound like you have vision and foresight.

However, Ty goes on to state it will absolutely compete with Pure and XtremeIO. That implies it will be HA, user faster MLC flash, and have higher performance. ONTAP integration is only going to get in the way of that.

So, for now, I'm still not buying this deranged story. Only time will tell what FlashRay is actually designed to do.

NetApp's running with the big dogs: All-flash FlashRay hits the street

ByteMe

Reeks of Desperation

Nate, your spot-on about it being released too early. A single controller? Only 7.8 TB useable? This reeks of desperation. NetApp's revenue's have been flat as of late (which is better than most storage vendors) and they're loosing customers to flash start-ups. This press release is a classic EMC-esque move to "freeze" existing ONTAP customers to prevent them from purchasing a non-NetApp flash solution. What is the key selling point of FlashRay? ONTAP integration! It clearly has no revolutionary features to make it stand-out in the all-flash-array crowd. What it DOES have are features to keep exisitng ONTAP customers on-board and not jump ship.

Violin's arrays play in Concerto - but they can't hit the dedupe notes yet

ByteMe

Interesting...

Interesting announcement. I was expecting deduplication just because its so common in the flash space. Why is that taking so long? However, replication definitely helps. I'm also curious about the application-integrated snapshots. NetApp SnapManager was cool, but we couldn't manage it at scale. If Violin can do something similar for SQL and Oracle, and make it manageable, that would help them stand out.

EMC's DSSD rack flashers snub Fibre Channel for ... PCIe

ByteMe

I have to agree with Hapkido. Very misleading statement. The inherent read latency of MLC NAND flash itself is around 100us (published numbers vary). With an all-flash-array you can easily achieve sub-millisecond response times at the host layer using 8 Gbps FC.

Scott Dietzen said it best. Moving flash closer to the compute is BS because NAND flash itself is the largest bottleneck, not the interconnect. The last thing storage teams need right now is yet another storage interconnect technology to support and troubleshoot.

CDOT relatively crap for flash, hyperscalers crap for constant storage

ByteMe
Thumb Up

Nice to see a legacy storage vendor who actually admits that swapping HDDs for SSDs does not make them a flash player. Doesn't take a genius to figure out the same is true for EMC, HP, IBM, etc...

However, until FlashRay shows-up and actually demonstrates it can do something, NetApp is going to lose market share to flash startups. The EF550 isn't going to win a lot of races (even if they did win against XtremeIO....once....). And don't be fooled by Jay Kidd's comments about not being worried about flash startups because they have big customer accounts. NetApp can't afford to lose *any* accounts right now, and losing lots of small-to-medium customers to flash startups will definitely hurt their bottom line.

How flash storage raced from glory to despair in 2013

ByteMe
WTF?

"EMC had its XtremIO product on limited availability but went GA late in the year. Rumours are that it's now the the AFA volume leader."

You must have heard that rumor directly from EMC because that half-baked POS isn't selling in our channels. Even loyal EMC customers have turned their noses up at it.

Toshiba tweaks SSD model: She's flashy, but she's not dense ENOUGH

ByteMe
Thumb Down

SSDs getting slower, not faster

Yikes. Under real workloads, this SSD wasn't that fast to begin with (see review below). Now writes are even slower? This is a perfect example of how all SSDs will get slower as they're forced to move to the more-dense next generation flash. As Toshiba and Samsung race to 19nm or smaller technology to extract bigger die yields (i.e. more profit), SSD manufacturers are going to be forced to transition to it. Doesn't sound promising.

http://www.storagereview.com/toshiba_px02sm_series_enterprise_ssd_review

New 64TiB Violin byte bucket is a load of Tosh: 19nm flash in a 3U box

ByteMe
Meh

Re: IBM / TMS FlashSystem 820?

Violin uses PCIe and VIMMs are fully hot swappable.