Narayan Venkat, VP of product management at Violin Memory, recently published a guest blog post titled “6 Reasons Solid State Memory Is The Biggest Story In Computing” over at Forbes.com. The rhetoric in the article should be familiar stuff to regular readers here at the Denali Memory Report but Venkat makes a few new points about why he believes that Flash-based storage is faring better in data centers than in notebooks and other portable devices and he has a few perspectives worth discussing here. Venkat’s six reasons are:
- Latency
- Technology
- Inertia and The Innovator’s Dilemma
- Energy
- Big Data
- Volume Economics
I’ll comment on just two of these reasons and let you decide about the other four:
For latency, Venkat’s point is that time equals money in a corporate setting and nowhere is this equation more prevalent than in equities and futures trading. Microseconds lost mean millions of dollars lost, an equation that spans a 12-decade range. If Flash-based storage can give an edge in latency (and it does) then there’s a real dollar value that can be placed on it. If Flash-based storage vendors put together the right value proposition, it’s easy to see if it makes business sense or not.
Energy costs at some data centers now consume 30% or more of the centers’ operating budgets. If Flash-based storage can reduce energy consumption relative to high-RPM, short-stroke hard drives (and it does), then there’s another hard dollar cost that can be attributed to the asset side of the ledger for Flash-based storage.
Denali Memory Report 
I thought that article was just ” here is what I learnt in the 1 month in this industry since I come from the end user I must be the authority type article. His analogy of Flash memory with filling a flask through a hole in the wall was really really awful.. I suppose it could be equated to tunneling but weak..what was his point in Flash memory should not exist.
What I want to see from someone more knowledgeable and not say so full of themselves like say Knut or Avi Klein or Bob Selinger or Amber or James Myers or their equivalent from the Enterprise application space is what are the various enterprise applications where Flash could be used, how many of them use Flash, How many would benefit from a cache, how many could use and justify all Flash arrays, is it a dollar justification or ease of use? How does this industry move away from the commoditization set in by the nature of the flash industry thus far and move to a system view,
It is so incorrect and short sighted that the Violins , Pure storages, Tintris , Viridents and the Fusion IOs alone decide how not to write flash as much.. Its just common sense these are trying to get bought or IPOd they are focused on short term not strategy and they will never know as much about the flash as the Toshibas, intels Microns Samsung and Sandisk NEVER.. What strategy can they dictate except quote cliches like innovators dilemma??
True strategy would be to understand if infrastructure can be developed at a level of abstraction where most applications could be covered, in understanding if and when Flash makers could be persuaded to redesign Flash for enterprise or Hybrid or newer applications to allow lower latency so the pipe for error correction does not eat into the advantage of flash.
All in all just a terrible article
@the darthvaders of this world:
If there is a flash device, which costs me the same or even a little more than a comparable EMC/IBM/Netapp/Younameit superfast diskstorage with autotiering to oldfashioned SSDs, but is 10 times faster than these, needs only 10 to 30 percent of the power, 20 to 30 percent of the cooling and a fifth of the floorspace, WHY should I even THINK of buying a device, which uses the 50 year old technology of spinning rust ?
WHY should I think of a hybrid device using SSDs ?
I just don’t see ANY value in old diskstorage, if I can get a flashdevice of the same size at the same price.
I wouldn’t even think about what to buy, this is a nobrainer.
Herbert,
You do sound like a complete moron.. All HDDs are not replaced by ssds..Most ssds used in enterprise today are caches. Is it possible to continue to scale flash memory down? If it is will it hit the latency..if so how much better would the latency be compared to a disk going forward?
Darth Vader,
I’m in some of the largest data centers on the planet and the transition to Flash based storage is happening. A few months ago one of my customers replaced 2.5 racks of 15k short stroked drives with two enterprise class 3ru flash trays. Got over 5x the IOPs and savings in reclaimed data center footprint, reduced power usage, cooling requirements and maintenance costs. System paid for itself in months, not years on environmentals alone. You are correct in that currently most use is in point solutions like file system caching, data base, analytics and (not too surprisingly) very large VDI deployments but once the Flash vendors tie in the ability to provide spinning disk feature sets such as snap shots, replication and data reduction, they will move down into the mid-tier and traditional disk will become archive at best.