The Intel SSD 320 Review: 25nm G3 is Finally Here
by Anand Lal Shimpi on March 28, 2011 11:08 AM EST- Posted in
- IT Computing
- Storage
- SSDs
- Intel
- Intel SSD 320
Random Read/Write Speed
The four corners of SSD performance are as follows: random read, random write, sequential read and sequential write speed. Random accesses are generally small in size, while sequential accesses tend to be larger and thus we have the four Iometer tests we use in all of our reviews.
Our first test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random access 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. We use both standard pseudo randomly generated data for each write as well as fully random data to show you both the maximum and minimum performance offered by SandForce based drives in these tests. The average performance of SF drives will likely be somewhere in between the two values for each drive you see in the graphs. For an understanding of why this matters, read our original SandForce article.
Random write speed is improved compared to the 510 thanks to Intel's controller, but we're only looking at a marginal improvement compared to the original X25-M G2.
Many of you have asked for random write performance at higher queue depths. What I have below is our 4KB random write test performed at a queue depth of 32 instead of 3. While the vast majority of desktop usage models experience queue depths of 0 - 5, higher depths are possible in heavy I/O (and multi-user) workloads:
Random read performance has always been a strong point of Intel's controller and the 320 is no different. While we're not quite up to C300 levels, the 320 is definitely competitive here.
Sequential Read/Write Speed
To measure sequential performance I ran a 1 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.
Without a 6Gbps interface the 320's performance is severely limited. Compared to other 3Gbps drives the 320 is quite good here though.
Read performance is at the top of the chart for 3Gbps drives. I wonder how far Intel would've been able to push things if the 320 had a 6Gbps controller.
Facebook
Twitter
RSS
194 Comments
View All Comments
piquadrat - Monday, March 28, 2011 - link
Theoretically for working encryption you need bios with ATA password support. If you're out of luck there is also a way to mod existing bios and add appropriate extension, but skills and experience required.The thing is:
There is no evidence that BIOS password in intel's implementation is LINKED to AES password generated by internal cypher engine!!!
If not, this solution is no different than SF-1200 non-enterprice drives. You can enable ATA pass on OCZ Vertex2 but it is not used to hash internal encryption keys which effectively renders the whole AES thing USELESS (security wise).
wvh - Tuesday, March 29, 2011 - link
Thanks... But I'm even more confused now. ;)piquadrat - Tuesday, March 29, 2011 - link
Lets wait until some further details concerning intel's implementation make to the public. I'm sure that early adopters will test this feature thoroughly. Now all of this is mainly academic.danjw - Monday, March 28, 2011 - link
Have you forgotten the P67 fiasco already?neotiger - Monday, March 28, 2011 - link
So after all these delays Intel released a product that can just barely keep up with the LAST generation of competing products. Meanwhile, competitors are releasing new gen of products at significant performance increases.In other words, Intel just GAVE UP on the top end of the market and is now just trying to be the cheapest product.
Truly disappointing.
FXi - Monday, March 28, 2011 - link
$1069 for a product only guaranteed to work 3 (THREE) years. IF it fails after that time, you've paid over $350 a year for storage. The 300 works out to $190, almost $200 PER YEAR for storage.If Intel feels so confident that these things will last, do the same as the rest of the enterprise grade industry and give it 5 years of "we're positive it will work this long".
Watch the rest of the SSD market cry if Intel does this, but they won't. These things are bad enough if something goes wrong at year 2 or 3, but past that it's the wild west. And given the prices, that shouldn't be the case.
$1069 is a decent price. $999 would have been excellent, but either price is horrible when compared to only a 3 year guaranteed lifespan.
iwod - Monday, March 28, 2011 - link
Personally i think it is too expensive. But,1. It would still sell very well. Because 90% of users are still with SATA 3Gbps. And Intel Drives are the most reliable SSD out there, currently its pricing is not cheap, but competitive.
2. Intel aren't keeping up with production volume anyway for their 25nm SSD. ( Note most of the Intel 25nm NAND sold to other company are proberly Tier -2 Bin NAND )
Yeah, we are disappointed, but it is still going to do well.
Let's Hope Future Intel SSD will beat even the Sandforce 2200 Series.
Lingyis - Monday, March 28, 2011 - link
Reliability is a big issue! I'm not a super-techie, but as a user, having experienced 2 out of 3 Vertex drives that I ended up having to reinstall the OS (once Windows 7, once Mac on my wife's machine) within 6 months, I have reverted to using good'ol hard drives for myself.Intel's higher reliability might be good enough--but hard drives are still more reliable. (if anybody has hard statistics to back me up i'd highly appreciate it)
sean.crees - Tuesday, March 29, 2011 - link
I've personally had MUCH more issues with HDD's than SSD's. Though that likely has to do with the fact that the only SSD's I've worked with are my 2x 1st gen 80g Intel SSD's, and I've spent the last 15 years dealing with HDD's.My biggest issue with HDD's is exposure to heat. I've lost my A/C in the summer, and then subsequently lost all my data on my HDD's because it got too hot for them. You don't have this problem with SSD's.
Also, any tech device is going to have DOA's. Just because you got a bad batch, doesn't mean the entire industry as a whole is worse than older tech. And, OCZ has come a LONG way since their initial reliability issues with their 1st gen Vertex drives. They have listened to their customers, and listened to reviewers like Anand, and have implemented changes to make their products meet our expectations. This one simple act above all else is what pulls me away from the Intel camp to purchase a Vertex 3 for my next SSD.
jwilliams4200 - Tuesday, March 29, 2011 - link
Are you insane? OCZ is meeting expectations?How could you have missed that just in the last few months, OCZ has changed their products to be lower performing and less capacity than previously, without informing customers or even changing the product SKU? Or that OCZ uses Spectek flash instead of higher-tier Micron flash memory in some of their SSDs, but a customer cannot know which flash they got without opening the SSD and voiding their warranty?
OCZ are nothing but con men and spin doctors. If you think OCZ cares about their customers and treats them with honesty and respect, then you are awfully naive.
Besides, the statistics show that Intel is the most reliable SSD. Even without the statistics, it is easy to see why Intel is more reliable. Intel uses the highest quality parts, including getting the highest bin flash memory from their manufacturing lines, and Intel testing and quality control is a corporation wide thing. I doubt OCZ even knows the meaning of the words.