The SSD Anthology: Understanding SSDs and New Drives from OCZ
by Anand Lal Shimpi on March 18, 2009 12:00 AM EST- Posted in
- Storage
The Anatomy of an SSD
Let’s meet Mr. N-channel MOSFET again:
Say Hello
This is the building block of NAND-flash; one transistor is required per cell. A single NAND-flash cell can either store one or two bits of data. If it stores one, then it’s called a Single Level Cell (SLC) flash and if it stores two then it’s a Multi Level Cell (MLC) flash. Both are physically made the same way; in fact there’s nothing that separates MLC from SLC flash, it’s just a matter of how the data is stored in and read from the cell.
SLC flash (left) vs. MLC flash (right)
Flash is read from and written to in a guess-and-test fashion. You apply a voltage to the cell and check to see how it responds. You keep increasing the voltage until you get a result.
| SLC NAND flash | MLC NAND flash | |
| Random Read | 25 µs | 50 µs |
| Erase | 2ms per block | 2ms per block |
| Programming | 250 µs | 900 µs |
With four voltage levels to check, MLC flash takes around 3x longer to write to as SLC. On the flip side you get twice the capacity at the same cost. Because of this distinction, and the fact that even MLC flash is more than fast enough for a SSD, you’ll only see MLC used for desktop SSDs while SLC is used for enterprise level server SSDs.
Cells are strung together in arrays as depicted in the image to the right
So a single cell stores either one or two bits of data, but where do we go from there? Groups of cells are organized into pages, the smallest structure that’s readable/writable in a SSD. Today 4KB pages are standard on SSDs.
Pages are grouped together into blocks; today it’s common to have 128 pages in a block (512KB in a block). A block is the smallest structure that can be erased in a NAND-flash device. So while you can read from and write to a page, you can only erase a block (128 pages at a time). This is where many of the SSD’s problems stem from, I’ll repeat this again later because it’s one of the most important parts of understanding SSDs.
Arrays of cells are grouped into a page, arrays of pages are grouped into blocks
Blocks are then grouped into planes, and you’ll find multiple planes on a single NAND-flash die.
The combining doesn’t stop there; you can usually find either one, two or four die per package. While you’ll see a single NAND-flash IC, there may actually be two or four die in that package. You can also stack multiple ICs on top of each other to minimize board real estate usage.
Facebook
Twitter
RSS
250 Comments
View All Comments
Franco1 - Wednesday, March 18, 2009 - link
I've been waiting a long time for this review. It was certainly worth the wait! I would love to see some benchmarks with 2+ drives in RAID configurations via onboard and add-on controller cards. Maybe another follow up?Howard - Wednesday, March 18, 2009 - link
Looks like the Vertex is the drive to get, especially once the user base expands a bit.MagicalMule - Wednesday, March 18, 2009 - link
Thanks for the article. Everyone is critiquing grammar and all this nonsense it seems, but I really enjoyed the article.It was very thorough and very informative.
Keep up the good work. =).
futrtrubl - Wednesday, March 18, 2009 - link
You missed out a VERY significant step that causes the greater part of the slowdown associated with your scenario. After the block is read out to cache the block has to be erased before it can be written to again and as you pointed out earlier an erase cycle, and thus the entire read/modify+erase/write cycle, takes a relatively LONG time, much longer than a simple read/modify/write.Edward
DrKlahn - Wednesday, March 18, 2009 - link
I've worked in IT for 15 years and have played with very fast arrays and know a fair amount about storage. 2 months ago I replaced my Raptor boot/gaming drive with a GSkill Titan. In day to day use I have no stuttering. The only stutter I have seen was while installing a large patch, surfing with multiple windows/tabs open and using Outlook. It wasn't even a second. I did align the partition, turned off drive indexing and defragmentation, and turned on caching. In day to day use it simply kills the Raptor. Games and applications load in a fraction of the time. Vista boot time has decreased dramatically.This isn't a case of purchase justification. If the drive was a dud I would have moved it to a secondary machine, reinstalled the Raptor, and chalked it up as a bad decision. I simply have not run into any scenario in daily use that it performs worse than the drive it replaced and I have not seen any real stuttering in daily use.
Gary Key - Wednesday, March 18, 2009 - link
I have a GSkill Titan drive also and really like it. However, my experiences while positive overall, do not compare with yours when it comes to stuttering (yes, all optimizations have been done to the drive and OS). I still have significant stuttering problems when using multiple IM programs and having multiple windows/tabs open at the same time. I literally have to wait a few seconds when texting colleagues if more than two conversations are occurring at the same time as the system pauses, hitches, and stutters in this scenario. It is especially aggravating when on Skype and trying to text, speak, and transfer files at the same time. This does not occur on the Intel drive in my testing. Apparently, it is no longer a problem on the OCZ Vertex or Summit drives. Except for my example above, I would certainly use the Titan drive over my Raptor any day of the week.druc0017 - Wednesday, March 18, 2009 - link
great article, keep up the good work, cant wait to see more updates, thxmikeblas - Wednesday, March 18, 2009 - link
Is the Velociraptor really "World's fastest hard drive", as this article states? Faster than the Hitachi SAS drives?Gary Key - Wednesday, March 18, 2009 - link
We have changed those statements to "...fastest consumer desktop hard drive...", that was the original intent of the statement, just clarified now. :)7Enigma - Wednesday, March 18, 2009 - link
I think the majority of us understood that. People just like to nit-pick.