SandForce TRIM Issue & Corsair Force Series GS (240GB) Review
by Kristian Vättö on November 22, 2012 1:00 PM ESTAnandTech Storage Bench 2011, Light Workload
Our new light workload actually has more write operations than read operations. The split is as follows: 372,630 reads and 459,709 writes. The relatively close read/write ratio does better mimic a typical light workload (although even lighter workloads would be far more read centric). The I/O breakdown is similar to the heavy workload at small IOs, however you'll notice that there are far fewer large IO transfers:
| AnandTech Storage Bench 2011—Light Workload IO Breakdown | ||||
| IO Size | % of Total | |||
| 4KB | 27% | |||
| 16KB | 8% | |||
| 32KB | 6% | |||
| 64KB | 5% | |||
The Force GS does slightly better in our Light suite but overall its performance is average.
Facebook
Twitter
RSS
56 Comments
View All Comments
R3dox - Friday, November 23, 2012 - link
I see, but that doesn't really answer my question :P.Is there still a performance hit and do you just choose to test under normal rather than optimal conditions or is this a thing of the past?
Kristian Vättö - Friday, November 23, 2012 - link
I tested this quickly a while back but there was no significant difference in performance (small variation always occurs anyway):http://forums.anandtech.com/showthread.php?t=22721...
R3dox - Friday, November 23, 2012 - link
Thanks for the replies :).You say "AFAIK it affected performance with some older SandForce SSDs but when I started testing SSD and asked Anand for all the settings, he just told me to leave it on since it doesn't matter anymore".
But it's a clear difference on my old postville. Granted, the SSD is my boot disc during those tests, but isn't that their most likely use anyway? TBH I'd be interested to know why enabling those powersaving features apparently impact performance only when used as boot disc. When I say 'impact", I mean based on multiple runs, of course.
Lastly, it seems that C-states are the most impactful setting and that one isn't mentioned in the reviews. I suppose you've left those on as well?
JellyRoll - Wednesday, December 5, 2012 - link
that wasnt testing.Schugy - Tuesday, November 27, 2012 - link
Don/t buy MLC rubbish. SLC is really worth it.FunnyTrace - Wednesday, November 28, 2012 - link
Nice going SandForce.1) BSOD problem
2) AES-256 hardware doesn't work (seriously??? hardware doesn't work???)
3) TRIM has not been working properly (what, you failed to GC blocks properly?)
As a lot of people mention, these SSD makers want to use early adopters and PC building enthusiasts as guinea pigs.