* Posts by Vaughn Stewart

16 posts • joined 31 Jul 2014

Tintri terminates 200 staff, cash set to run dry in a couple of days

Vaughn Stewart

Good Technology, An Unfortunate Ending

Disclaimer = Pure Storage Employee

This is truly an unfortunate outcome. At one point in time Tintri understood the challenges of disk-based SANs and envisioned the opportunity to radically change storage operations in support of a VMware (and latter Hyper-V & OpenStack) private cloud.

In some regards they took what NetApp established and advanced the innovation. For a brief period in time, there was no simpler storage to operate with VMware, yet Tintri never seemed to cross the chasm or establish escape velocity.

Personally, I believe Tintri suffered due to a lack of a direct competitor - one who would validate the market they were trying to establish. Tintri was unique and ultimately undefined.

I sincerely wish nothing but the best for all who participated in the Tintri journey. Many friends and colleagues invested their blood sweat and tears to bring their technology to market.

- cheers,

v

Deleted

This post has been deleted by a moderator

Can NetApp's 4KB block writes really hold more data?

Vaughn Stewart

Re: Missing the point...

== Disclaimer: Pure Storage Employee ==

My understanding is all versions of 3PAR are 16KB. Can you cite HP documentation that AFA 3 PAR is 4KB?

-- cheers,

v

SolidFire's thin flash density eats more racks than HPE. What gives?

Vaughn Stewart

Re: Why are you picking on SolidFire? What about XtremIO, Pure, and Kaminario?

== Disclosure: Pure Storage Employee ==

Hey John, hate to do this to you mate but next time you "wonder about Pure Storage" you should disclose you work for NetApp.

Transparency is a good thing

-- cheers,

v

NetApp shrinky-dinks ONTAP 9: Will support 4:1 data reduction

Vaughn Stewart

NetApp should clarify the 4:1 claim

Disclaimer -- Pure Storage employee and former member of NetApp

I applaud the innovation I'm sure the engineering teams at NetApp have developed. With that said, I'd like to see NetApp elaborate on their 4:1 claims.

You may recall, NetApp has (and currently) claims Data ONTAP can deliver up to 933:1 data reduction (refer to http://www.netapp.com/us/products/storage-systems/all-flash-fas/all-flash-fas-software.aspx)

Customers lose when the storage storage industry hides technical details behind marketing claims. The Register should ensure that all vendors disclose the data reduction technologies that comprise their claims, wether they be 4:1 or 933:1.

Ideally the new 'data compaction' engine (a term that HPE also uses) will allow NetApp to publish results based on data reduction technologies (like dedupe and compression) versus their historic perpensisty to include point in time restores (snapshots) and dynamic provisioning and allocation mechanisms (like thin provisioning, zero removal, pattern removal and unmap) in their over stated data reduction results.

As data reduction is the new norm in storage, it's time to ensure The vendors speak a common language.

Nice work NetApp.

- cheers,

v

Pure Storage's coming high-end array: We have the details

Vaughn Stewart

Disclaimer: Pure Storage Employee

With the 'Love Your Storage Guarantee' from Pure Storage - even the estimated effective usable capacity is guaranteed. If the FlashArray doesn't deliver, we'll provide the customer with the capacity to correct the situation.

-- cheers,

v

Pure Storage to punt out supersized FlashArray system

Vaughn Stewart

Re: Replying to Vaughn Stewart of Pure

Nice quip mate ;)

The math form raw to effective usable should apply equally to all FlashArray //m configurations and models.

- cheers

v

Vaughn Stewart

Let's correct the math

Disclaimer: Pure Storage employee

Chris I'd like to correct the math behind the capacity. In the post you overlooked the 20 flash modules that sit behind the bezel of the controller chassis. Thus a FlashArray with two shelves is comprised of 68 flash models. With each at 8TB in size, one would end up with 544TBs of raw capacity for 1.5PBs of usable capacity. The formula for raw to effective usable applies a 5:1 data reduction ratio (which is lower than the average across our install base) to the remaining raw capacity following the allocation for RAID-3D and FlashCare.

-- Cheers

V

Don't take this the wrong way, Pure Storage – are you the next NetApp?

Vaughn Stewart

Re: All AFAs Equal?

Excellent recommendation.

NetApp wades into UK engineering pool, crowns first local techie officer

Vaughn Stewart

Kudos Grant!

=== Disclaimer: Pure Storage Employee ===

Grant is top shelf and the promotion is well deserved. I'm happy for him and my old NetApp mates in the UK.

- Cheers,

v

Seventh bigshot flings self out of EMC Federation window

Vaughn Stewart

Waiting...

I was startled to not find a comment linking me to these changes. One Anonymous Coward is definitely off his/her game. :)

Storage slump? Dunno what you're talking about, beams EMC

Vaughn Stewart

Slump or a time of transition?

Due to their marketshare, EMC is the vendor most impacted by the massive amount of disruption occurring in the storage industry. I expect they will be very successful transitioning their customer base from expensive legacy platforms, to modern, efficient and cost effective technologies. I'm confident EMC will be just fine in the long run.

Hyperconverged IDC shamans mumble mantras over market

Vaughn Stewart

Chris,

I would owe you one if you can get IDC to explain which EMC product is their hyper converged platform. A quick scan of the EMC website doesn't show they are in this market.

- cheers,

v

What benchmarks can tell you about your solid-state drives

Vaughn Stewart

== Disclaimer: Pure Storage Employee ==

Trevor

I think you hit the nail not head with, "...the holy grail of benchmarking is sticking as close as possible to the exact applications that will be deployed on the storage in question and as close as possible to the exact access patterns." - in other words, take a copy of your applications and run them on the new platform.

IO benchmarks miss the mark because applications 1). process data not just transfer IO 2). applications have multiple IO streams 3). application IO streams vary in IO size per process.

it as just as critical to test performance under load as it is with faults (failures) and data services like replication, snapshots, clones and data reduction technolgoies.

Nice insight - keep up the good work!

- cheers,

v

The triumph of VVOL: Everyone's jumping into bed with VMware

Vaughn Stewart

VVOLs offer more options

Anonymous is partly correct, disk-based arrays will likely have to provide either map a VVOL to a file (NAS), LUN or sub-LUN (SAN options); however, all-flash arrays are truly object-based regardless of the form of protocol access. As such these vendors will have options available to them to provide VVOLs as actual storage objects accessed via SCSI or file command sets.

While we are a ways off from the GA of VVOLs version 1 - VVOLs offer a ton of promise for cloud infrastructures and storage management over the next few years.

Biting the hand that feeds IT © 1998–2019