AnandTech Storage Bench 2011 - Light Workload

The performance between the top two isn't nearly as close in our light workload. Here the Vertex 3 is 20% faster than the 510 on average:

AnandTech Storage Bench 2011 - Light Workload

The culprit is, once again, read performance:

AnandTech Storage Bench 2011 - Light Workload

OCZ manages a 51% performance advantage if we just isolate the reads in our benchmark. The Vertex 3 behaves like a next-generation drive and the SSD 510 has the random read performance of an X25-V.

AnandTech Storage Bench 2011 - Light Workload

Once again the 510 does quite well when we look at pure write performance. At least based on our 2011 Storage Bench the major weakness here is random read performance - the 510's random write performance is seemingly sufficient for this workload.

AnandTech Storage Bench 2011 - Light Workload

AnandTech Storage Bench 2011 - Light Workload

AnandTech Storage Bench 2011 - Light Workload

AnandTech Storage Bench 2011 - Heavy Workload Performance vs. Transfer Size
Comments Locked

128 Comments

View All Comments

  • aarste - Wednesday, March 2, 2011 - link

    Those graphs on the TRIM test look nothing remotely close to ATTO, which I use. I checked HDTach as well and it wasn't that, but close.

    What app was it?
  • mino - Wednesday, March 2, 2011 - link

    Please, be so king and include a fast HDD (say a WD Velociraptor) in EVERY SSD benchmark.

    While most readers here understand the difference between SSD and HDD, including a single fast HDD would make the article useful also as a reference/datapoint when talking to not-so-techy people.
  • strikeback03 - Thursday, March 3, 2011 - link

    Then people would complain because the numbers are so small as to be unreadable
  • nerex - Wednesday, March 2, 2011 - link

    Maybe I missed it, but i didn't see any discussion of the power usage of the new drives- according the intel press releases, the new drives use 380mW/100mW active/idle and the G2 drives only use 150mW/75mW active/idle.

    This means the new drives would actually be worse on laptop battery life, correct?
  • DigitlDrug - Saturday, March 5, 2011 - link

    Hi Anand,

    +1

    Power consumption figures would be great for us laptop users!

    I find it interesting that a number of these drives report consumption of up to 3watts and others are in the mw range when browsing the Egg.

    Some clarity on power consumption would be a great addition.

    As always, great review!
  • ClagMaster - Wednesday, March 2, 2011 - link

    The Intel SSD 510 is not a bad drive but it cost more than a Vertex 2 or 3.

    The Intel Toolbox, and extensive compatablity and reliability testing are major pluses.

    The SSD is still an extravagance for desktops though I can see its a no-brainer for laptops because of power conservation. Unless the cost per gigabyte is less than $0.80/gigabyte, the performance gain does not offset the mechanical harddrive.
  • neotiger - Wednesday, March 2, 2011 - link

    I.e., an epic FAIL product priced at a premium to competing products that are far superior.

    What misguided priorities from Intel. People shell out the big bucks for SSD's for their RANDOM IO performance, NOT sequential IO. So the geniuses at Intel decided to release a "next gen" product that actually has WORSE performance than the last gen product. Really?

    I'm speechless. The really sad part about this fiasco is that most people will still buy this piece of crap over far superior competing products just because it's Intel.

    Just like NetBurst all over again.
  • strikeback03 - Thursday, March 3, 2011 - link

    Did you actually look at the real-world results? the 510 is almost twice as fast as the G2 160GB in some tests.
  • poohbear - Wednesday, March 2, 2011 - link

    nice review, but you're talking & comparing the Vertex 3 and this new drive, but where's the vertex 3 on the market? its not even released, its months away from release if im not mistaken? the C400 will be released before it, so what's the point of comparing tech today with tech months away from release (and in the SSD world months is a very long time!)
  • sor - Wednesday, March 2, 2011 - link

    FWIW, we've deployed literally hundreds of X25-E drives, and our failure rate is well over 1%, closer to 2%. Usually they drop link, try to renegotiate at 1.5Gbps, and fail, so it's more likely the controller than a wear-out issue.

Log in

Don't have an account? Sign up now