Violin’s bankruptcy

by Robin Harris on Friday, 6 January, 2017

Violin Memory, one of the early entrants with an all-flash array, filed for bankruptcy last month. The company continues to operate under Chapter 11, but this is a sad outcome for a pioneer.

So much for first mover advantage
When I first met with Violin, the original team had a great idea and not much traction. The architecture connected the flash storage nodes with a mesh network to ensure dual-channel access and high-performance, with system visibility down to the individual flash dies.

This was at a time – 2008 – when most folks (other than Fusion-io) were looking to emulate disk drives with flash in a can. This seemed suboptimal because, after all, if we had invented flash in 1957 instead of disks, is that what flash drives would have looked like 50 years later? Of course not.

I thought then, and still do, that this was an innovative architecture. But innovation can be hard.

Architecture isn’t everything
I was critical of folks, like Pure, who put SATA drives behind a couple of controllers, and called it good. But this was a time to market strategy, so they could focus on software, not hardware. And software is a lot cheaper and quicker to build.

Which is, ultimately, what cost Violin their early lead. By concentrating on hardware, Violin found it hard to compete with feature-rich software implementations, despite Violin’s excellent and consistent low latency. Buyers were dazzled by IOPS, not latency.

The StorageMojo take
The race is not always to the swift, nor riches to the wise. By starting with software, other companies built an early lead, and now have the money and time to optimize hardware for flash.

It looks like a new race is starting, with NVRAM as the instigator. I’ll try to remember the lessons of Violin’s path.

Courteous comments welcome, of course. Happy new year to all. As for me, this new year has gotten off to an excellent start! Also, I’ve done work for Violin.

{ 2 comments… read them below or add one }

Lou January 6, 2017 at 9:33 am

I’d agree that the focus needed to be on software – but it wasn’t IOPS vs. latency for me. Instead it was (a) data reduction to make the flash affordable, (b) the non-disruptive upgrades (hardware and software), (c) the even though it was commodity hardware, the hardware wasn’t being just used as a RAID5 set underneath.

It’s like Skyera. It’s impressive that you can cram that much flash into a 1U box but I need to schedule downtime to replace a bad module? I need to schedule downtime for a firmware upgrade?

Timothy Huber February 10, 2017 at 6:47 pm

I was part of the original (pre-restructuring) Violin team, back when we had just a few (DRAM) appliances to test, no caching software, no Windows driver, and dwindling cash reserves. It took balls to build the hardware, but without a complete solution, it was a science project. Lesson learned the hard way.

Low latency and high bandwidth win benchmarks. Production ready solutions win purchase orders.

Leave a Comment

Previous post:

Next post: