Corsair's Force SSD Reviewed: SF-1200 is Very Good
by Anand Lal Shimpi on April 14, 2010 2:27 AM ESTAnandTech Storage Bench
Note that our 6Gbps controller driver isn't supported by our custom storage bench here, so the C300 results are only offered in 3Gbps mode.
The first in our benchmark suite is a light usage case. The Windows 7 system is loaded with Firefox, Office 2007 and Adobe Reader among other applications. With Firefox we browse web pages like Facebook, AnandTech, Digg and other sites. Outlook is also running and we use it to check emails, create and send a message with a PDF attachment. Adobe Reader is used to view some PDFs. Excel 2007 is used to create a spreadsheet, graphs and save the document. The same goes for Word 2007. We open and step through a presentation in PowerPoint 2007 received as an email attachment before saving it to the desktop. Finally we watch a bit of a Firefly episode in Windows Media Player 11.
There’s some level of multitasking going on here but it’s not unreasonable by any means. Generally the application tasks proceed linearly, with the exception of things like web browsing which may happen in between one of the other tasks.
The recording is played back on all of our drives here today. Remember that we’re isolating disk performance, all we’re doing is playing back every single disk access that happened in that ~5 minute period of usage. The light workload is composed of 37,501 reads and 20,268 writes. Over 30% of the IOs are 4KB, 11% are 16KB, 22% are 32KB and approximately 13% are 64KB in size. Less than 30% of the operations are absolutely sequential in nature. Average queue depth is 6.09 IOs.
The performance results are reported in average I/O Operations per Second (IOPS):
I've always loved the performance of SandForce's controllers, I've just been worried about their reliability. While we wait for the latter to prove itself over time, the performance is very good today. The Corsair Force is very competitive, as fast as any other SF drive and faster than nearly all other SSDs.
If there’s a light usage case there’s bound to be a heavy one. In this test we have Microsoft Security Essentials running in the background with real time virus scanning enabled. We also perform a quick scan in the middle of the test. Firefox, Outlook, Excel, Word and Powerpoint are all used the same as they were in the light test. We add Photoshop CS4 to the mix, opening a bunch of 12MP images, editing them, then saving them as highly compressed JPGs for web publishing. Windows 7’s picture viewer is used to view a bunch of pictures on the hard drive. We use 7-zip to create and extract .7z archives. Downloading is also prominently featured in our heavy test; we download large files from the Internet during portions of the benchmark, as well as use uTorrent to grab a couple of torrents. Some of the applications in use are installed during the benchmark, Windows updates are also installed. Towards the end of the test we launch World of Warcraft, play for a few minutes, then delete the folder. This test also takes into account all of the disk accesses that happen while the OS is booting.
The benchmark is 22 minutes long and it consists of 128,895 read operations and 72,411 write operations. Roughly 44% of all IOs were sequential. Approximately 30% of all accesses were 4KB in size, 12% were 16KB in size, 14% were 32KB and 20% were 64KB. Average queue depth was 3.59.
Once again, very little difference between Corsair's Force and OCZ's Vertex LE. SandForce's performance isn't as strong in our heavy downloading workload, the Corsair Nova (with the latest Indilinx firmware) actually does better.
The gaming workload is made up of 75,206 read operations and only 4,592 write operations. Only 20% of the accesses are 4KB in size, nearly 40% are 64KB and 20% are 32KB. A whopping 69% of the IOs are sequential, meaning this is predominantly a sequential read benchmark. The average queue depth is 7.76 IOs.
Here we're completely bound by read performance. I'm afraid the only way you'll get faster is via RAID or a 6Gbps controller in Crucial's case.
Facebook
Twitter
RSS
63 Comments
View All Comments
Chloiber - Wednesday, April 14, 2010 - link
Just to show you what I mean.I created an 512kb seq. write IOMeter test pattern which writes to a space of 1GB. When you use IOMeter for the first time, it creates that 1GB file to reserve the space. I then stopped the test as soon as the 1GB file was written and before the actual test even began. I then used 7-zip to compress the file, that's the result:
http://www.abload.de/image.php?img=compr7uv5.png
It's in german and it says to the right that the uncompressed size is 336MB (I paused at that point) and the compressed file size is 404KB. So the level of compression is nearly 0%.
I aborted then and did the above test again. This time, I let the harddisk write data for about 11 seconds (HD does about 100MB/s) so the complete 1GB file has been used.
I used again 7-Zip and this is the result:
http://www.abload.de/image.php?img=compr2165l.png
Uncompressed size: 138MB (paused earlier here), compressed size: 138MB. So it cannot be compressed at all.
That leads to the conclusion that IOMeter uses indeed a completely random pattern for its tests.
darckhart - Wednesday, April 14, 2010 - link
i didn't see listed physical dimensions. is this 7.5mm or 9mm height? also sata 3gb/s i assume?GDM - Wednesday, April 14, 2010 - link
Do you feel a noticable difference between this new Cosair Drive and say the Intel X-25M 160 GB? Benchmarks are nice, but I wonder how much of the speed difference can you really feel?shin0bi272 - Wednesday, April 14, 2010 - link
Ive noticed this quite a bit on reviews here. When a benchmark is low and the text of the result doesnt fit in the bar the text gets squished into the text of the name of the item being tested. Could you please move those results to the outside of the bar off to the right? Since the bar is so small you will have plenty of room out there to put the result and it will be legible. Other than that thanks for a great review and thanks for still including a spindle disk or two as well (though I do question the decision to use a 5400rpm drive unless you were trying to throw that in for laptop users or something).Kary - Wednesday, April 14, 2010 - link
Any chance of comparing the drives using compressed NTFS. I tend to do this to my SSD drive anyway and probably wouldn't see a difference on a drive that was trying to compress data internally that was already compressed).Oh, my drive is only 30GB and I needed the space..quad core CPU, figured I wouldn't notice a difference speed wise.
Lazlo Panaflex - Wednesday, April 14, 2010 - link
The Force is strong with this one.Exodite - Wednesday, April 14, 2010 - link
Ouch.I'm old enough to appreciate bad puns, well done Sir!
Lazlo Panaflex - Wednesday, April 14, 2010 - link
hehe..thanks. I couldn't resist ;-)Exodite - Wednesday, April 14, 2010 - link
Very nice review, it soothes some of my fears regarding these drives.I'm curious as to whether you know at this point if there's going to be reviews of the OCZ Vertex 2 and Agility 2 as well?
Seeing as these drives are based on the SF1500 and SF1200 as well it'd be interesting to see the performance difference from drives from the same vendor, using the different chips. There's the Vertex LE of course but it seems it's more or less the bastard child in this comparison.
Thanks in advance.
vol7ron - Wednesday, April 14, 2010 - link
I was curious if it's possible to overclock these SSDs either through the SF1200 or the RAM in some way or another?I know pencil modding has been dead in recent years. This is due in part to smaller components, but also to the fact that manufacturers have both (1) implemented in-place safeguards to reduce problems from overclocking and (2) started encouraging overclocking by providing more options through the BIOS.
I'm just curious if anyone's figured out how to do it on these SSDs. I know the average shouldn't - you typically don't want to fiddle with the sole thing that stores your data - but I suspect some tweaking could take place by enthusiasts to really up performance, if wanted. Anyone know a place to look into this?
vol7ron