Last night (1/5/12) at a DEMO Enterprise event in San Francisco Fusion-io unveiled a one billion IOPS (I/Os per second) storage system. A billion IOPS!
The machine was built using 64 Fusion-io ioDrive2 Duos connected to eight HP ProLiant DL370 servers.
This came sooner than we anticipated. It was only in July 2008 that the million-IOPS barrier was broken by IBM using 41 Fusion-io devices.
On Monday December 13 SandForce introduced SSD controllers designed specifically for cloud computing applications.
You might wonder what is so different about cloud applications that they need an SSD controller of their own. SandForce makes some interesting points:
The SSD guy usually argues that NAND flash (as an SSD) fits into the memory/storage hierarchy for two reasons:
An SSD is usually a very good alternative to adding more DRAM to a system, but this is not always the case. Users need to look carefully at the SSD they plan to use to make sure they are getting the most for their system spend. Continue reading “DRAM vs. SLC SSD – Which Makes More Sense?”
One of the SSD Guy’s favorite subjects is caching and SSDs. This is because I wrote a book on processor caches in the early 1990s, and the advent of SSD caches in storage systems hearkens back to the technology detailed in that book.
Caching works well whenever there are two layers in the memory hierarchy since the fast expensive layer can replicate data in the slow inexpensive layer to accelerate the processor’s performance. Continue reading “SSDs and Caching”
There’s a lot of “Fear, Uncertainty, and Doubt” – FUD – circulating about SSDs and their penchant for failure. NAND flash wears out after a set number of erase/write cycles, a specification known as the flash’s endurance.
While some caution is warranted, a good understanding of how SSDs really behave will help to allay a lot of this concern. Continue reading “What Happens when SSDs Fail?”
The SSD Guy has been asked a number of questions lately about SSDs and RAID. Most of these center around the difference in failure behaviors between SSDs and HDDs – HDDs fail randomly (if ever), while SSDs fail relatively predictably due to wear.
Oddly enough, SSD failures due to wear make them a little friendlier than HDDs. The wear mechanism is managed by the controller in the SSD. SSDs have spare blocks, and the controller manages those blocks, so the controller understands exactly how much wear the SSD has undergone and how much room is left before the SSD will start to have difficulties. Continue reading “SSDs and RAID”
One of the thorniest issues in SSD design how to manage erasing blocks that are no longer in use. That’s saying a lot, because NAND flash presents so very many difficult challenges like wear leveling, bad block management, error correction, and write amplification.
The difficulty stems from the fact that all of today’s software was written for HDDs which don’t behave like the flash in an SSD. An HDD can over-write existing data with new data. In a flash SSD, a block must be erased before being over-written and this can take a half a second – a huge amount of time in the world of computing. Since the software doesn’t accommodate flash’s “erase-before-write” needs, the controller inside the SSD must take care of this bit of housekeeping. Unused and unerased blocks are moved out of the way and erased in the background. This is called the “garbage collection” process. Continue reading “SSD Garbage Collection”
The SSD Guy attended TechTarget‘s Storage Decisions Conference last week in San Francisco. Dennis Martin of Demartek gave a very good presentation called Making the Case for Solid-State Storage.
Demartek tests a lot of systems based on various forms of storage.
I really liked an expression that Mr. Martin shared to compare SSDs to HDDs. He said that SSDs cost dollars per gigabyte and pennies per IOPS, while HDDs cost pennies per gigabyte and dollars per IOPS. This is a really good way to think about the strengths and weaknesses of these two technologies. There is every reason to use a mix of both. Continue reading “Sometimes SSDs Don’t Improve System Speed”
An article in the Storage Newsletter caught The SSD Guy’s eye when it ran in July. The article consisted of a press release followed by an editorial comment:
While hard drives still have the cost advantage, it appears it’s becoming akin to sticking with a horse-drawn buggy in an age of automobiles by arguing that the upfront cost for a car is so much more than the cost of a horse. At some point, it just doesn’t make sense to ride a horse. How soon until the IT world gets there?
SSDs vary widely in performance. This is something that becomes amazingly clear when a number of these devices are put through a battery of tests.
Calypso Systems ran the SNIA SSD Performance Test Specification (PTS), outlined in an earlier post in this blog, on seventeen SSDs and a single HDD. The results appear, in miniature, in the graphic for this post. Continue reading “Not all SSDs are Created Equal”
