Does AFA matter?
Why does a system have to be "ALL FLASH" to be the measure? How about TOTAL FLASH shipped?
Sweet AFA: Pure sees flash of Big Blue as it drops to fifth behind IBM
It is only one quarter, but IDC’s latest enterprise storage numbers show IBM’s flash array revenues have overtaken those of Pure Storage, putting that IPO’d company in fifth place in the market. Stifel analyst Aaron Rakers has reported on IDC’s fourth 2016 quarter enterprise external storage revenues and we highlight the all- …
-
-
-
Tuesday 14th March 2017 06:32 GMT Lusty
Re: Does AFA matter?
They can have different tuning parameters, but then a mixed array could just as easily have several sets of parameters. They are just normal computers after all (except for the marketing joy that is 3Par ASICs)
No, the category was created because somebody with an interest paid for it to be created. That somebody was not one of the incumbent market leaders, who simply released their existing arrays in "all flash" configurations a couple of years later and became market leaders in the "new segment". OP is right, it's a pointless category that shouldn't exist. SAN performance can easily be measured so why would it matter if there are capacity disks present other than someone wanting to show themselves in a top right quadrant during powerpointless sales presentations.
-
Tuesday 14th March 2017 18:14 GMT Anonymous Coward
Re: Does AFA matter?
There is a big difference in architecture and how systems handle flash when it's built from the ground up for that purpose. Putting in Dell's VMmax, VNX (or whatever it was rebranded as), 3Par, Nimble or others in same category as IBM TMS or Pure is just idiotic. You may as well include all the flash put into servers.
If you want to see the growth of a company or specific solutions, you need to do an apples to apples comparison to see how or if they are really taking share. Luckily enough I haven't had to deal with the commoditization that is the infrastructure world for a while, but come on, this is just weak journalism.
-
Tuesday 25th April 2017 18:22 GMT Equals42
Re: Does AFA matter?
"There is a big difference in architecture and how systems handle flash when it's built from the ground up for that purpose."
Really? What part of it did they build from the ground up? Let's see:
1980s SCSI command set? Not until NVMe over fabrics is in the wild. Until then you're speaking SCSI.
Intel CPUs and DRAM? Nope. Same stuff in all the arrays except special ASICs from 3Par which are always late to the party... makes nice slides though.
Fibre Channel? Nope. Still works. Cisco and Brocade are pushing 32g FC for NVMe over Fabric.
Ethernet/FCoE/NFS/SMB? Nope. Not invented new for AFA.
Inline Compression/Dedupe? A lot of the AFA have those whether built from the ground up or not.
Scale out? Well that's not really an AFA feature and many of them fail that one.
Simple GUI or admin? Simplicity is nice until you need a feature. I agree some platforms are too complicated. It's a feature though not intrinsically tied to AFA.
SSDs or CFM? Most of them use SSDs and they should. My money's on SSDs. Going your own way on chips hasn't worked on for a long time. See Sun, DEC, SGI... Heck, the chipset landscape is cleared of competition. Where's Adaptec, AMI, LSI, National Semi...
Really it's just a storage array tuned for much faster backend access. It gives the manufacturers some new ability to tune their stacks instead of waiting for spinning rust to respond and lessen the need to buffer as much. There's great advances possible in AFAs but it's still just faster storage until we change the protocol. Even then, it's just faster. It's still retrieving the same old bits faster; not adding chocolate flavor to your bytes.
Does faster storage effect other things in the compute stack? Sure does. That still doesn't mean that it's fundamentally different from another array other than speed and with a neat bezel.
-
-
-
-
Monday 13th March 2017 20:21 GMT Anonymous Coward
Whither Hitachi?
There's no doubt Hitachi is still shipping an awful lot of Flash, albeit in mixed configurations with spinning disk and using Tiering to move data around. There's not much straight all flash configs for HAF, their proprietary flash modules that have no real services around them and still use all legacy management and configuration.
But they can't go any further with that technology and architecture--they are certainly stuck. Their OEM foray into AF last year was a failure, and they really desperately need to make a high tech acquisition today of something that can take them into a next gen platform with *good* software. They've made some good acquisitions in the past and integrated them, Sepaton and BlueArc. Looking at their 15% loss in Q4 revenue in 2016 and their bottom of the pack numbers in All Flash shipments, combined with their announcement that they were freezing storage investment last June, they aren't looking too good right now or for tomorrow. They must do something or continue their heavy revenue shrinkage.
-
Monday 20th March 2017 15:08 GMT Anonymous Coward
Re: Whither Hitachi?
I'm not sure that Hitachi will do another acquisition anytime soon. They've placed their bets on SVOS and have tightened up their array offerings, so adding another platform having another OS doesn't seem likely in the short term. Adding to that, letting go of Jack Domme who was their acquisition driver over the past many years, and moving back to the previous management style doesn't bode well for an acquisition. Before Domme, HDS had only acquired Archivas. It was Domme who drove the acquisitions of the other companies.
-
Biting the hand that feeds IT
