OCZ Vector (256GB) Review
by Anand Lal Shimpi on November 27, 2012 9:10 PM ESTTRIM Functionality
Over time SSDs can get into a fairly fragmented state, with pages distributed randomly all over the LBA range. TRIM and the naturally sequential nature of much client IO can help clean this up by forcing blocks to be recycled and as a result become less fragmented. Leaving as much free space as possible on your drive helps keep performance high (20% is a good number to shoot for), but it's always good to see how bad things can get before the GC/TRIM routines have a chance to operate. As always I filled all user addressible LBAs with data, wrote enough random data to the drive to fill the spare area and then some, then ran a single HD Tach pass to visualize how slow things got:
As we showed in our enterprise results, Vector's steady state 4KB random write performance is around 33MB/s. The worst case sequential performance here is around 50MB/s, which is in line with what you'd expect. Sequential writes do improve performance, but as with most SSDs you're best operating the Vector with a bit of spare area left on the drive (in addition to what's already set aside by firmware).
TRIM and another sequential pass restore performance to normal, but it also triggers the Vector's performance mode penalty:
At 50% capacity there's an internal reorganization routine that's triggered on Vector, similar to what happens on the Vertex 4. During this time, all performance is impacted, which is why you see a sharp drop in performance just beore the 135GB mark. The re-org routine only takes a few minutes. I went back and measured sequential write performance after this test and came back with 380MB/s in Iometer. In other words, don't be startled by the graph above - it's expected behavior, it just looks bad as the drive doesn't get a chance to run its background operations in peace.
Facebook
Twitter
RSS
151 Comments
View All Comments
Death666Angel - Friday, November 30, 2012 - link
In one of the podcasts (E10?) Anand talks about how SF controllers have less issues with these IO latency worst case scenarios. So it's not necessarily an Intel feature, but a SF feature and the graph might look the same with a Vertex 3 etc.Also, it may behave differently if it were filled with different sequential data at the start of the test and if the test were to run longer. I wouldn't draw such a positive conclusion from the test Anand has done there. :)
jonjonjonj - Thursday, November 29, 2012 - link
did they have to name their 2 drives Vector and Vertex? they couldnt have picked 2 names that looked more alike if they tried. i have to image this was done on purpose for some reason that i can think of. now that ocz has its own controller are they retiring the vertex or will they just use barefoot controllers in vertex ssd's going forward?deltatux - Sunday, December 2, 2012 - link
While it is great that the OCZ Vector is able to compete with the Samsung SSDs in terms of performance, but OCZ's past reliability records have been iffy at most, they fail prematurely and RMA rates have been quite high. I've known countless people suffering issues with OCZ drives.I'll wait for a bit before recommending OCZ drives to anyone again due to reliability issues if the OCZ Vector can meet the reliability of Corsair, Intel or Samsung drives. Until then, I'll keep recommending Samsung drives as they exceed in performance and reliability than most manufacturers.
rob.laur - Sunday, December 2, 2012 - link
If you check the review of the Vector on the hardwarecanucks website, page 11 you will see the Vector AND Vertex crush every other drive listed when filled with over 50% capacity. This is probably the most important bench to judge SSD performance by."While the Vector 256GB may not have topped our charts when empty, it actually blasted ahead of every other drive available when there was actual data housed on it. To us, that’s even more important than initial performance since no one keeps their brand new drive completely empty. "
jwilliams4200 - Sunday, December 2, 2012 - link
If you are talking about this:http://www.hardwarecanucks.com/forum/hardware-canu...
you will note that the Samsung 840 Pro is conspicuously absent from the list, so we do not know how the Vector fares against its most difficult competitor.
rob.laur - Sunday, December 2, 2012 - link
you are right and I wish they did include the 840 Pro but they didn't. Point is compared to all those other SSDs/Controllers, the BF3 clearly outperforms everything in the real world with actual data on the drive. The 840 Pro uses faster nand than the Vector yet both drives are pretty much equal. The toshiba toggle version of Vector cant come soon enough!jwilliams4200 - Monday, December 3, 2012 - link
The Samsung 840 Pro is significantly faster (about 33%) than the Vector for 4KiB QD1 random reads. This is an important metric, since small random reads are the slowest operation on a drive, and if you are going to take just one figure of merit for an SSD, that is a good one.rob.laur - Monday, December 3, 2012 - link
well according to most sites, the Vector beats it on writes and in mixed read/write environments especially with heavy use. Not to mention the 840 takes a long time to gets its performance back after getting hammered hard whereas the Vector recovers very quickly.jwilliams4200 - Monday, December 3, 2012 - link
First of all, the type of heavy writes I believe you are referring to are a very uncommon workload for most home users, even enthusiasts. Reads are much more common.Second, I have seen only one credible study of Vector use with heavy writes, and the Samsung 840 Pro does a better than the Vector with steady-state, heavy writes:
http://www.anandtech.com/show/6363/ocz-vector-revi...
I have seen nothing to suggest the Vector recovers more quickly. If anything, there is circumstantial evidence that the Vector has delayed recovery after heavy writes (assuming the Vector is similar to the Vertex 4) due to the Vector's quirky "storage mode" type behavior:
http://www.tomshardware.com/reviews/vertex-4-firmw...
jwilliams4200 - Monday, December 3, 2012 - link
My first link was meant to go to storagereview:http://www.storagereview.com/ocz_vector_ssd_review