Violin’s clean-sheet architecture

by Robin Harris on Wednesday, 11 April, 2012

Over 3 years ago StorageMojo saw that Violin Memory was “. . . on the winning architectural track.” Well, it took a lot of time and money, but Violin is making good on that early promise.

StorageMojo’s enthusiasm was kindled by Violin’s unique architecture. Here’s a short video that shows how Violin’s architecture addresses key problems with flash:

Full screen mode recommended.

The StorageMojo take
The industry is still in the early days of digesting the implications of fast persistent solid state storage. We’ve built up 50 years of cruft to deal with disk’s many issues. It will take a few more years for flash’s new options to ripple through the entire storage, server and application stack.

Take, for example, failover. If all apps and monitoring software could declare a failure in 10 seconds rather than, say, a minute, how much smoother would major apps run? How much better would be the perception of system uptime and response times be?

There are many other possibilities – what about metadata? – that flash and its successor technologies will affect. I’ll be offering more detail in my keynote at the Solid State Storage Symposium on Wednesday, April 25 in Silicon Valley. S4 is free and you can register here.

Courteous comments welcome, of course. The other flash company I liked in 2009 was Fusion-io, and they’ve done OK. And yes, Violin paid StorageMojo to produce the video white paper, but the opinions are my own.

{ 5 comments… read them below or add one }

Frank Fegert April 13, 2012 at 1:36 pm

Hello Robin,

nice piece on Violin. We evaluated a Violin 3×00 against a TMS RamSan 6×0 last summer. Even though Violins architecture seemed very sound and a bit more promising than TMSs, we decided to go with TMS instead. The reason was that – at that time – the FC attachment of the Violin arrays was way more complicated and lacked the dual controller configuration we’d usually like to see in a storage array. No doubt, Violins Solaris x86 based FC-head in front of the array would have done the job, it just left a bit of a DIY aftertaste one would not expect in that particular price range.

Best regards from Germany,

Frank Fegert

Robin Harris April 13, 2012 at 2:55 pm


I agree with your comments on the Violin 3000 model. The newer 6000 model would have fared better in your evaluation.



Jeff July 7, 2012 at 6:57 pm

Interesting. Commercial customers that are targets for Violin that need 1 million IOPS and wicked performance also need array based replication, snaps and clones. Violin is nothing but a direct attached block storage device that sits behind a beefy server.Way overpriced and hyped. In these economic times I find it unlikely anyone will rip out HDD and spend 400,000.00 for 10-15 terabytes of flash with no HA!. Long dismal road for Flash. VC’s will loose patience.

Taylor July 9, 2012 at 1:48 pm

Jeff, what about large database setups that use mirroring/replication for HA?

Doug Humphrey September 8, 2012 at 1:14 am

Hey Jeff –

Violin’s management suite provides replication, snapshots, and clones as well as encryption as of the v5.2 release. If you look at the TCO for owning this solution it is definitely not overpriced, and the forward looking companies that can see what these boxes bring to the table are definitely ripping out old-school HDD-based storage in favor of well architected flash solutions like Violin’s.

Leave a Comment

{ 2 trackbacks }

Previous post:

Next post: