OCZ Vertex 3 Pro Preview: The First SF-2500 SSD
by Anand Lal Shimpi on February 17, 2011 3:01 AM ESTSequential Read/Write Speed
To measure sequential performance I ran a 3 minute long 128KB sequential test over the entire span of the drive at a queue depth of 1. The results reported are in average MB/s over the entire test length.
This is pretty impressive. The new SF-2500 can write incompressible data sequentially at around the speed the SF-1200 could write highly compressible data. In other words, the Vertex 3 Pro at its slowest is as fast as the Vertex 2 is at its fastest. And that's just at 3Gbps.
The Vertex 3 Pro really shines when paired with a 6Gbps controller. At low queue depths you're looking at 381MB/s writes, from a single drive, with highly compressible data. Write incompressible data and you've still got the fastest SSD on the planet.
Micron is aiming for 260MB/s writes for the C400, which is independent of data type. If Micron can manage 260MB/s in sequential writes that will only give it a minor advantage over the worst case performance of the Vertex 3 Pro, and put it at a significant disadvantage compared to OCZ's best case.
Initially, SandForce appears to have significantly improved performance handling in the worst case of incompressible writes. While the old SF-1200 could only deliver 63% of its maximum performance when dealing with incompressible data, the SF-2500 holds on to 92% of it over a 3Gbps SATA interface. Remove the SATA bottleneck however and the performance difference returns to what we're used to. Over 6Gbps SATA the SF-2500 manages 63% of maximum performance if it's writing incompressible data.
Note that the peak 6Gbps sequential write figures jump up to around 500MB/s if you hit the drive with a heavier workload, which we'll see a bit later.
Sequential read performance continues to be dominated by OCZ and SandForce. Over a 3Gbps interface SandForce improved performance by 20 - 40%, but over a 6Gbps interface the jump is just huge. For incompressible data we're talking about nearly 400MB/s from a single drive. I don't believe you'd even be able to generate the workloads necessary to saturate a RAID-0 of two of these drives on a desktop system.
Facebook
Twitter
RSS
144 Comments
View All Comments
PubicTheHare - Thursday, February 17, 2011 - link
Anand,Would this be the drive to pair with a Sandy Bridge Macbook Pro, or do we still need to wait for native TRIM support in OSX?
I'm really eager to buy a Sandy Bridge MBP and do this if the V3P is the one to get. I can't recall which controller you recommended for Macs.
markjx1 - Thursday, February 17, 2011 - link
Why no mention of the fact this was originally slated for the SF-2000, and now its got the enterprise class SF-2500 with disclaimers of "hardware not final" all over the article?The truth is they had major problems with SF-2000 and nobody wants to talk about it - of all people I'd think you would have. Now go ahead and delete my post again.
markjx1 - Thursday, February 17, 2011 - link
Resorting to using the enterprise-class SF-2500 means I worry about cost competitiveness against other upcoming Gen3 offerings from Intel and Crucial/Micron.OCZ took a $25 mil bank loan recently so they need a winner. I worry about the "hardware is not final" disclaimers in the article. Sending these samples out for some buzz smells like buying time while they work out production dilemmas since originally they were going to use a different SF controller.
bplewis24 - Friday, February 18, 2011 - link
Why are you trolling? You have 3 of essentially the same posts on this page. We get it, you think he "sold out" for not mentioning that it's using a different controller.Brandon
vol7ron - Thursday, February 17, 2011 - link
Does this mean a higher QD, might improve performance.It looks like QD of 16 might be the sweet spot in terms of latency vs IOPS
DJMiggy - Thursday, February 17, 2011 - link
Thanks for the great article and thank you OCZ for making my Vertex 1 even more obsolete. That's ok though! Not a complaint! lol Just looking forward to my next upgrade!Rasterman - Thursday, February 17, 2011 - link
Since the drive is 400MB/s read, if you use two in RAID-0 are you going to get 800MB/s or the realistic max of 6gpbs of ~700MB/s?If you use RAID-0 X4 are you going to get 1600MB/s or ~700MB/s?
jwilliams4200 - Thursday, February 17, 2011 - link
With a decent RAID card, then RAID 0 of N drives will give you slightly less than N times the performance of a single drive.For on-motherboard RAID, you will also get approximately N times the performance of a single drive, but there is usually a ceiling to total performance on motherboard RAID. It is around 600 MB/s for ICHR-10.
myterrybear - Thursday, February 17, 2011 - link
I've been a loyal reader of this sight, but what realy myths me if you's use EVERY other controler but those found on the AMD platform .... especialy more so with a Sata 6.0 SSD like this it would match up well for those of us amd users whom have paid money to upgrade the motherboard to have that sb8xx controler onboard to utilize hard drives & other devices that run on the now becoming Sata 6.0 standard.Per Hansson - Thursday, February 17, 2011 - link
Hi, has the much talked about hibernation problem with the Sandforce drives been solved in the 2xxx series?Loosing Hibernation is pretty much a deal killer for me in a laptop :(
http://www.google.se/search?hl=sv&safe=off&...