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
Sequential Read/Write Speed
Using the latest build of Iometer I ran a 3 minute long 2MB sequential write test over the entire span of the drive. The results reported are in average MB/s over the entire test length:
Saturating the bandwidth offered by 3Gbps SATA, the Crucial RealSSD C300 and OCZ Vertex LE are the fastest you can get. However, pair the C300 with a 6Gbps controller and you'll get another 70MB/s of sequential read speed.
The Toshiba based SSDNow V+ does a bit better than the Samsung based OCZ Summit at 224MB/s. You're still better off with an Indilinx drive though.
Despite being based on an architecture that was first introduced in 2008, the X25-Ms are still able to nearly saturate the SATA 3Gbps bus.
The sequential write speed of the SandForce SF-1500 controller is just ridiculous. OCZ is able to virtually saturate the SATA 3Gbps bus at 252.7MB/s. In the past it would take us two SSDs or a whole crapton of hard drives to get that sort of sequential write throughput. The RealSSD C300 is a distant second place at ~200MB/s, which is still not bad. Kingston's SSDNow V+ actually does well at 192.5MB/s here.
The Intel drives are still banished to the bottom of the chart with their <= 100MB/s sequential write speeds.
Facebook
Twitter
RSS
83 Comments
View All Comments
mindless1 - Friday, February 19, 2010 - link
I meant the above within the context of it using a PCIe, otherwise the SATA600 link would clearly be a bottleneck.mckirkus - Friday, February 19, 2010 - link
I know what you're saying. But I'm wondering what PCMark scores look like when you remove drive IO as the bottleneck. If the best SSDs are scoring 20,000 would the same system with no disk bottleneck score 25,000? 30?In other words, with only SSD scores we're still not sure how close we are to removing the drive bottleneck in system performance. IMO this is an important question and the answer would give these SSD scores some context.
overzealot - Monday, February 22, 2010 - link
I just tried out PCmark on a 2gb ramdrive. My q6600 (stock) had 1 core maxed from about 20% through each test, and got a score of 362,471 in the HDD test. That's with DDR800 folks.I'm guessing all the results would be CPU bound so my system is really not the best place to test it.
overzealot - Monday, February 22, 2010 - link
Physical Memory: 4 GB (2GB Ramdisk, so really 2)Graphics card: ATI Radeon HD 5770
Operating System: Windows 7 Ultimate (6.1.7600) 64-bit
Full suite results:
PCMark 6,566.0 PCMarks
Memories 5,596.0
TV and Movies 4,326.0
Gaming 5,133.0
Music 6,085.0
Communications 5,948.0
Productivity 6,242.0
HDD 345,794.0
The scores for everything would be way too long, here's the HDD results:
HDD - Windows Defender 1,797,924,224.0 B/s
HDD - gaming 2,064,242,048.0 B/s
HDD - importing pictures to Wind 1,810,203,648.0 B/s
HDD - Windows Vista startup 2,053,050,752.0 B/s
HDD - video editing using Window 1,549,093,504.0 B/s
HDD - Windows Media Center 1,607,108,864.0 B/s
HDD - adding music to Windows Me 1,423,892,096.0 B/s
HDD - application loading 1,355,910,784.0 B/s
HDtach rates it at 3GB/s.
jimhsu - Saturday, February 20, 2010 - link
There will also be an I/O bottleneck unless the entire dataset can fit directly onto the CPU. The RAM/CPU bottleneck is the Von Neumann bottleneck which is a well known one in computer science (time/space tradeoffs). It's just what's the point at which the bottleneck ceases to become a user issue...srue - Friday, February 19, 2010 - link
"Despite early messaging to press, the 40GB Kingston SSDNow V Series Boot Drive will never get official TRIM support for Kingston. Luckily some adventurous folks have figured out a way to trick Intel’s firmware updater into thinking Kingston’s drive is worthy of such a gift."That first sentence upsets me because I purchased the drive believing TRIM support would eventually come. Granted, I probably would have done the same knowing what I know now, but I thought I was getting a better value.
Does anyone have a link to the trick mentioned in the second sentence?
Glenn - Sunday, February 21, 2010 - link
Here ya go.http://www.overclock.net/ssd/656984-how-get-your-k...">http://www.overclock.net/ssd/656984-how...our-king...
I did this last week and it works great.
srue - Friday, February 19, 2010 - link
I found the instructions on overclock.net.mschira - Friday, February 19, 2010 - link
So I think I would rather go with an intel X25-MBy the way, what do you guys reckon are two X25-M 80Gb connected to the Intel Motherboard Raid in Raid 0 faster than a X25-M 160Gb?
Cheers
M.
leexgx - Saturday, February 20, 2010 - link
RAID 0 = no Trim support (maybe get TRIM support)160GB SSD would require no fussing to keep the drive tidy (with windows 7 that is standard drivers in AHCI mode) it stay at its advertised speeds as long as the Chipset driver was not installed or the intel matrix driver was Not installed
i give up for the most part commenting about how pointless RAID 0 with an SSD is, all you get is more data rate speed that you not even notice (unless your messing with Very big files 5-10GB but you lose TRIM so it degrade fast if you Write that much data a lot, One drive would still be faster) SSDs are about 2x data rate (a lot focus on this to much when its random you should be looking at ), 30x random data rate faster or more and the IOPS is 50x faster then an HDD (normally)
RAID + SSD = Fast for about an week or month then it be slower then 1 SSD