OCZ's Vertex 3 Pro: Second-Gen SandForce Perf Preview

Benchmark Results: 4 KB And 512 KB Random Reads

At low queue depths and small random reads, we see the Vertex 3 Pro suffer in IOPS.

The header of these two charts is the same, except for one important detail. The first employs a queue depth of one, and the second uses a queue depth of 32. Why are these figures important? Well, look what they do to performance.

Native Command Queuing, part of the SATA specification, was originally designed to improve the performance of mechanical disks by allowing the hard drive itself to optimize the order in which read and write commands get executed. Of course, the physics of a hard drive don’t apply to SSDs. However, the multi-channel architecture of a solid state drive enables it to similarly field multiple concurrent requests—though Intel claims the bottleneck isn’t the drive, but rather the host system itself. Today’s SSDs are consequently dependent on high queue depths in order to realize the specifications you see manufacturers quoting.

With a QD of one, the new Vertex improves on what we've already seen from SandForce, augmenting performance in situations unfavorable to the way modern SSDs run best: with lots of concurrent requests. Cranking queue depth up to the other (very unrealistic on the desktop, but much more plausible in the enterprise space) extreme of 32, the Vertex 3 Pro is suddenly pushing ~217 MB/s.

Once we move to larger random reads, we see OCZ's newest drive take the lead again.

Create a new thread in the US Reviews comments forum about this subject
This thread is closed for comments
35 comments
    Your comment
  • karma831
    Performance looks great but I don't think the price will be.
    1
  • Bigmac80
    This is why i haven't bought a SSD yet. One it's freakin expensive 2 not enough capacity 3 it's freakin expensive! It'll go down next year when the world ends in 2012.
    0
  • falchard
    Price is lower then last generation. A shrink in die size means cheaper manufacturing costs, lower power usage, and better performance. Thats what happens when every hardware company shrinks their chips.
    Considering this is going to have the same amount of space, its going to be a cheaper SSD.
    1
  • Scanlia
    500MB/s... wow
    1
  • aaron88_7
    These are for enterprise use, that's why they are priced so high. They have features average consumers don't need. In other words, you're wasting your money if you are putting these into your home computer.
    0
  • dragonsqrrl
    OCZ Vertex 3 Pro MSRP Pricing:
    100GB: $525, $5.35 per GB
    200GB: $775, $3.88 per GB
    400GB: $1350, $3.38 per GB

    Getting cheaper, but still far outside my price range given their relative capacities. Even taking their amazing performance into account, it's still going to be a difficult sell for all but the most passionate enthusiasts, pros with heavy server workloads, or hardcore idiots. You're definitely not going to be getting your moneys worth putting one of these into your gaming rig. Enterprise type applications experience the largest benefits from these types of drives, and it's probably the only application where the performance benefits balance out the higher costs.
    0
  • JohnnyLucky
    The article made it perfectly clear the drive is not a drive that will be offered to consumers, gamers, and pc enthusiasts. How is OCZ going to reduce prices for consumer drives? Reduce features? Cut corners? Replace high quality components with lesser quality components? On answer is OCZ will reduc features. I'd like to know what else OCZ is going to do.
    0
  • Anonymous
    Please add a TrueCrypt benchmark to your SSD evaluations, for two reasons. First, the difficulty of truly erasing data on a flash drive makes data security more important. Second, there are drives (like Sandforce) that use compression and may behave differently when storing encrypted (high entropy) data.
    1
  • nikorr
    About time
    0
  • Miharu
    Presently Plextor M2-M2S offer 370-420MB/s read for what... (64gb)150$-(128gb)250$. Vextor 3 price is out of the loop, it's too expensive. At this price I can buy 2 Plextor and put them in RAID 0.
    -1
  • alidan
    THANK YOU

    you finaly put normal hdds in a ssd review with tests, its nice to see the comparison.

    now i do hate to ask this... but until SATA 6 Gb/s hit the market big, can we get the drive also tested in a SATA 3 Gb/s configuration? this would be largely bennifitial to people to know. because im assuming that even with the 3's limited bandwidth, some operations will still be faster between the two
    0
  • sirmaster
    I just got a 256GB Mushkin IO SSD directly from the Mushkin store for $200.
    http://www.mushkin.com/Digital-Storage/SSDs/MKNSSDIO256GB.aspx

    It sold out pretty fast though.

    But it was under $1 per GB finally. It's not blazing like this drive but its about 250MB/s read and 180MB/s write with 20,000 IOPS. Considering it's 4x cheaper for the capacity compared to this drive I think it was worth it.
    0
  • dimar
    Didn't see the new Plextor drives when I was ordering Corsair Performance 3 128GB SSD at newEgg. Well... I'm pretty happy with it anyway. Hope the day comes soon when regular HDDs will be remember as much as music tapes today :-) and where 2TB 1GB/s SSDs are standard :)
    0
  • saint19
    uhmm where is the C300?
    0
  • Anonymous
    You have to multiply the power (watts) by the time it took in order to get a meaningful, comparable number (energy).
    1
  • Figaro56
    Why did the review have comparison against the other top SATA 6 drive out there today, EG, Crucial C300? Very odd.
    0
  • Figaro56
    I agree, where is the Crucial C300. Go to Anandtech, they show the C300 in their review. If you own a C300 you will happy to see that it is still a relevant SSD. The Vertex 3 doesn't blow it away.
    0
  • TeraMedia
    I second ChrisHF. Power is free. It's energy that costs money and raises temperatures inside a PC case. Please include either Joules (1 Watt = 1 Joule / second), Wh (3600 Joules) or kWh (3.6 M Joules) in your discussions about energy consumption. You always end up having to note that something uses more power but finishes faster... by graphing the relative energy consumption rather than the power consumption, you automatically resolve this confusion.

    Other than that, thanks for the article. If anything, hopefully the faster high-end devices will cause lower-end devices to reduce in price just like what happens with CPUs. I can only hope.
    0
  • dark_lord69
    I really like the performance specs but those prices are painful!
    1
  • hardcore_gamer
    The diagram of flash transistor is missing the SiO2 layer
    0