The SSD Relapse: Understanding and Choosing the Best SSD
by Anand Lal Shimpi on August 30, 2009 12:00 AM EST- Posted in
- Storage
Used vs. New Performance: Revisited
Nearly all good SSDs perform le sweet when brand new. None of the blocks have any data in them, each write is performed at full speed, all is bueno. Over time, your drive gets written to, all blocks get occupied with data (both valid and invalid) and now every time you write to the SSD its controller has to do that painful read modify write and cleaning.
In the Anthology I simulated this worst used case by first filling the drive with data, deleting the partition, then installing the OS and running my benchmarks. This worked very well because it filled every single flash block with data. The OS installation and actual testing added a few sprinkles of randomness that helped make the scenario even more strenuous, which I liked.
The problem here is that if a drive properly supports TRIM, the act of formatting the drive will erase all of the wonderful used data I purposefully filled the drive with. My “used” case on a drive supporting TRIM will now just be like testing a drive in a brand new state.
To prove this point I provide you with an example of what happens when you take a drive supporting TRIM, fill it with data and then format the drive:
| SuperTalent UltraDrive GX 1711 | 4KB Random Write IOPS |
| Clean Drive | 13.1 MB/s |
| Used Drive | 6.93 MB/s |
| Used Drive After TRIM | 12.9 MB/s |
Oh look, performance doesn’t really change. The cleaning process takes longer now but other than that, the performance is the same.
So, I need a new way to test. It’s a shame because I’m particularly attached to the old way I tested, mostly because it provides a very stressful situation for the drives to deal with. After all, I don’t want to fool anyone into thinking a drive is faster than it is.
Once TRIM is enabled on all drives, the way I will test is by filling a drive after it’s been graced with an OS. I will fill it with both valid and invalid data, delete the invalid data and measure performance. This will measure how well the drive performs closer to capacity as well as how well it can TRIM data.
Unfortunately, no drives properly support TRIM yet. The beta Indilinx firmware with TRIM support works well, unless you put your system to sleep. Then there’s a chance you might lose your data. Woops. There’s also the problem with Intel’s Matrix Storage Manager not passing TRIM to your drives. All of this will get fixed before the end of the year, but it’s just a bit too early to get TRIM happy.
What we get today is the first stage of migrating the way we test. In order to simulate a real user environment I take a freshly secure erased drive, install Windows 7 x64 on it (no cloning, full install this time), then install drivers/apps, then fill the remaining space on the drive and delete it. This fills the drive with invalid data that the drive must keep track of and juggle, much like what you'd see by simply using your system.
I’m using the latest IMSM driver so TRIM doesn’t get passed to the drives; I’m such a jerk to these poor SSDs.
I’ll start look at both new and used performance on the coming pages. Once TRIM gets here in full force I’ll just start using it and we won't have to worry about looking at new vs. used performance.
The Test
| CPU | Intel Core i7 965 running at 3.2GHz (Turbo & EIST Disabled) |
| Motherboard: | Intel DX58SO (Intel X58) |
| Chipset: | Intel X58 |
| Chipset Drivers: | Intel 9.1.1.1015 + Intel IMSM 8.9 |
| Memory: | Qimonda DDR3-1066 4 x 1GB (7-7-7-20) |
| Video Card: | eVGA GeForce GTX 285 |
| Video Drivers: | NVIDIA ForceWare 190.38 64-bit |
| Desktop Resolution: | 1920 x 1200 |
| OS: | Windows 7 x64 |
Facebook
Twitter
RSS
295 Comments
View All Comments
zodiacfml - Wednesday, September 2, 2009 - link
Very informative, answered more than anything in my mind. Hope to see this again in the future with these drive capacities around $100.mgrmgr - Wednesday, September 2, 2009 - link
Any idea if the (mid-Sept release?) OCZ Colossus's internal RAID setup will handle the problem of RAID controllers not being able to pass Windows 7's TRIM command to the SSD array. I'm intent on getting a new Photoshop machine with two SSDs in Raid-0 as soon as Win7 releases, but the word here and elsewhere so far is that RAID will block the TRIM function.kunedog - Wednesday, September 2, 2009 - link
All the Gen2 X-25M 80GB drives are apparently gone from Newegg . . . so they've marked up the Gen1 drives to $360 (from $230):http://www.newegg.com/Product/Product.aspx?Item=N8...">http://www.newegg.com/Product/Product.aspx?Item=N8...
Unbelievable.
gfody - Wednesday, September 2, 2009 - link
What happened to the gen2 160gb on Newegg? For a month the ETA was 9/2 (today) and now it's as if they never had it in the first place. The product page has been removed.It's like Newegg are holding the gen2 drives hostage until we buy out their remaining stock of gen1 drives.
iwodo - Tuesday, September 1, 2009 - link
I think it acts as a good summary. However someone wrote last time about Intel drive handling Random Read / Write extremely poorly during Sequential Read / Write.Has Aanand investigate yet?
I am hoping next Gen Intel SSD coming in Q2 10 will bring some substantial improvement.
statik213 - Tuesday, September 1, 2009 - link
Does the RAID controller propagate TRIM commands to the SSD? Or will having RAID negate TRIM?justaviking - Tuesday, September 1, 2009 - link
Another great article, Anand! Thanks, and keep them coming.If this has already been discussed, I apologize. I'm still exhausted from reading the wonderful article, and have not read all 17 pages of comments.
On PAGE 3, it talks about the trade-off of larger vs. smaller pages.
I wonder if it would be feasible to make a hybrid drive, with a portion of the drive using small pages for faster performance when writing small files, and the majority of it being larger pages to keep the management of the drive reasonable.
Any file could be written anywhere, but the controller would bias small writes to the small pages, and large writes to large files.
Externally it would appear as a single drive, of course, but deep down in the internals, it would essentially be two drives. Each of the two portions would be tuned for maximum performance in different areas, but able to serve as backup or overflow if the other portion became full or ever got written to too many times.
Interesting concept? Or a hair brained idea buy an ignorant amateur?
CList - Tuesday, September 1, 2009 - link
Great article, wonderful to see insightful, in depth analysis.I'd be curious to hear anyone's thoughts on the implications are of running virtual hard disk files on SSD's. I do a lot of work these days on virtual machines, and I'd love to get them feeling more snappy - especially on my laptop which is limited to 4GB of ram.
For example;
What would the constant updates of those vmdk (or "vhd") files do to the disk's lifespan?
If the OS hosting the VM is windows 7, but the virtual machine is WinServer2003 will the TRIM command be used properly?
Cheers,
CList
pcfxer - Tuesday, September 1, 2009 - link
Great article!"It seems that building Pidgin is more CPU than IO bound.."
Obviously, Mr. Anand doesnt' understand how compilers work ;). Compilers will always be CPU and memory bound, reduce your memory in the computer to say 256MB (or lower) and you'll see what I mean. The levels of recursion necessary to follow the production (grammars that define the language) use up memory but would rarely use the drive unless the OS had terrible resource management. :0.
CMGuy - Wednesday, September 2, 2009 - link
While I can't comment on the specifics of software compilers I know that faster disk IO makes a big difference when your performing a full build (compilation and packaging) of software.IDEs these days spend a lot their time reading/writing small files (thats a lot of small, random, disk IO) and a good SSD can make a huge difference to this.