OCZ’s Vertex Limited Edition Review & SSD State of the Union
by Anand Lal Shimpi on February 19, 2010 12:00 AM EST- Posted in
- Storage
Random Read/Write Speed
This test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random writes that you'd see on an OS drive (even this is more stressful than a normal desktop user would see). I perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time.
I've had to run this test two different ways thanks to the way the newer controllers handle write alignment. Without a manually aligned partition, Windows XP executes writes on sector aligned boundaries while most modern OSes write with 4K alignment. Some controllers take this into account when mapping LBAs to page addresses, which generates additional overhead but makes for relatively similar performance regardless of OS/partition alignment. Other controllers skip the management overhead and just perform worse under Windows XP without partition alignment as file system writes are not automatically aligned with the SSD's internal pages.
First up is my traditional 4KB random write test, each write here is aligned to 512-byte sectors, similar to how Windows XP might write data to a drive:
The OCZ Vertex LE does ridiculously well here, outperforming even Intel's X25-E. The Crucial RealSSD C300 does ok, a bit better than the Indilinx drives but no where near as good as the Intel based offerings. The reason being that the C300's controller doesn't actually attempt to reorganize unaligned writes on the fly. Look at what happens to 4K random write performance if we only write to 4K-aligned addresses:
Not only does the Vertex LE jump in performance to over 160MB/s, but so does the RealSSD C300. The Intel and Indilinx drives also get a small boost, but nothing huge by comparison. Modern 4K-aware OSes write data in 4K aligned addresses, which matches up perfectly with the 4K page size on all of these SSDs. You can also guarantee higher performance in older OSes like Windows XP by re-mapping the LBAs on the fly but that requires additional overhead. These newer drives forgo performance under Windows XP, for significantly better performance under Windows Vista/7 and Mac OS X 10.5/6. It makes sense given that Intel's X25-M was designed back in 2005 - 2007 while these newer controllers were more recent endeavors.
Random read performance is great on the C300 but a bit lower on the Vertex LE. None of these drives are posting bad figures here though. For the price the Kingston SSDNow V+ doesn't appear to deliver its worth.
Facebook
Twitter
RSS
83 Comments
View All Comments
v12v12 - Tuesday, February 23, 2010 - link
"To calm your fears, OCZ is selling the Vertex LE with a 3 year warranty."Umm 3yrs is CRAP! It's the industry standard among ALL HDs... again, how many times do I have to catch Anand-staff soft-wrist-slapping these con-artist manufacturers?! Who's "assured" with a 3yr warranty vs what? I haven't seen any manu offering lower? So how's that a selling/assurance point... let alone if it's even VALID to list in this article?
What you should have said (if at all) was:
"To calm your fears, OCZ is selling the Vertex LE with a STANDARD 3 year warranty (just like everyone else)." Hahaha.
I just don't get how you can continue to soft-scold (more like a notation) these manufactures when you and I KNOW it's crap. Well Okay I DO know; you're smart and running a business/review site (pro-business) and you don't wanna bad mouth these guys like you OUGHT to do. So instead you'll give them wrist slaps at the end of all the journalist-sensationalism in order to wash over the apparent chicanery of these businesses, so they'll keep sending you beta/new samples... Yes I know how the POLITICS of "business" works these days; sucks for the avg-minded consumer who totally misses keystone issues like this for all the hype and grandeur laced commentary... Sigh, the consumer-cattle loses again.
OWC Grant - Tuesday, February 23, 2010 - link
FWIW to this discussion thread and wasn't covered in the brief mention, the OWC Extreme Enterprise comes with an enterprise class level warranty...FIVE years. So, based on pricing and other similarities, will leave it up others to decide what the best value/performance ratio is in SSDs.kunedog - Tuesday, February 23, 2010 - link
Let's also not forget that he *never* acknowledged the near-immediately stratospheric pricing of Intel's G2 X-25M, right after he praised its affordability:http://www.anandtech.com/storage/showdoc.aspx?i=36...">http://www.anandtech.com/storage/showdoc.aspx?i=36...
He mentioned the firmware problems and lack of stock once but never the pricing.
ONLY now, over 6 months later, do we see prices anywhere near what he predicted at release:
80GB for $220
http://www.newegg.com/Product/Product.aspx?Item=N8...">http://www.newegg.com/Product/Product.aspx?Item=N8...
160GB for $430
http://www.newegg.com/Product/Product.aspx?Item=N8...">http://www.newegg.com/Product/Product.aspx?Item=N8...
The 160GB comes with a free Apricorn USB enclosure, the same one "randomly plugged" here by Anand. It's a strange coincidence to see two sites decide to associate it with SSDs (why would you put an SSD in an USB enclosure?).
shin0bi272 - Monday, February 22, 2010 - link
I thought I saw a review on anandtech a few months ago about the corsair p128 which was supposed to be a great ssd. But its not included on these benchmarks. Its supposed to have 220mb seq read and 200mb seq write. yet its not included? why?OWC Grant - Monday, February 22, 2010 - link
Glad to see so much interest in SSD!As Anand was made aware, our earliest units went out to reviewers and we contacted him and other reviewers to get these units back upon learning of a firmware revision that became available early Feb. In direct communication with him, he noted that neither firmware version had any effect on the performance.
All other OWC SSD units in the field (and available with same day to 1 day delay shipping from OWC) do have the latest firmware revision.
So, we are not "a bit behind OCZ" in this regard.
Hope this clears up the matter...and that you get an OWC SSD for yourself!
smith11 - Monday, February 22, 2010 - link
There's something that I'm not getting...If there's 0.5x write amplification because of real-time compression, why wouldn't the effective capacity be a good bit higher than (the non-reserved part of) the physical capacity ???
GullLars - Monday, February 22, 2010 - link
When i was reading this test, i couldn't help but think on several occasions that a cheap RAID of 3-4 intel x25-V from ICH10R would beat many of the drives tested here, and at a lower price.4 x25-V in RAID 0 gives 160GB capasity, roughly 600 MB/s seq read (limited by ICH10Rs bandwidth), about 140-150 MB/s seq write, around 100.000 4KB random read IOPS (400MB/s) at higher queue depths, and about 40.000 4KB random write IOPS (120MB/s). At a price point around $400-450, wich is about the same as Intel x25-M G2 160GB costs...
I think it would be great if Anand could do a test with 4 x25-V in RAID 0 from ICH10R to demonstrate a budget concious enthusiast setup.
semo - Monday, February 22, 2010 - link
Hi Anand,Great article. Any word on PCI-e SSDs? Are you leaving them out because of high costs or other reasons?
Also, good to know that you have our backs if those SSDs start crapping out. Without people like you companies get away with it for a long time.
rubbertoe - Sunday, February 21, 2010 - link
Looks like Amazon is also selling the 100G version:http://www.amazon.com/gp/product/B0035RQZSG/ref=pd...">http://www.amazon.com/gp/product/B0035R...X0DER&am...
Can someone confirm this is the drive that was reviewed? With selling only 5,000 does anyone have any idea how they will be distributed into the retail channels?
RT
neoflux - Sunday, February 21, 2010 - link
The OCZ Agility uses Intel 50nm or Toshiba 40nm flash.The OCZ Solid 2 uses Intel 34nm flash.
The OCZ Vertex uses Samsung flash, but what SIZE?
And based on that size, if the controller is the same as Anand mentioned a few articles ago, is the Solid 2 faster or at least the same speed-wise as the Vertex?
I did find that the Solid 2 may actually have some sort of 'crippled' Indilux controller, but that was just some forum, not an article.
I have gone back through all the Anand articles and googled everything I could think, but could not find the answer.
Someone enlighten me as to the size of the flash and the speed compared to the Vertex?