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.

Desktop Iometer - 4KB Random Read (4K Aligned)

Random read performance is very good on the Octane, matching the Samsung SSD 830 and the Intel SSD 320. Random write performance is no where near as fast as the Samsung, Crucial or SF-2281 based drives, but as we've seen in the past this can be enough performance for a desktop workload.

Desktop Iometer - 4KB Random Write (4K Aligned) - 8GB LBA Space

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:

Desktop Iometer - 4KB Random Write (8GB LBA Space QD=32)

Random write performance at higher queue depths doesn't scale nearly as well as the SandForce based drives. This doesn't really matter for desktop users, but I am curious to see how OCZ will position Everest in the enterprise space against SandForce. Perhaps that's where OCZ will focus its SandForce efforts instead and leave the consumer market to Indilinx.

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.

Desktop Iometer - 128KB Sequential Read (4K Aligned)

Sequential read and write performance is competitive, but not class leading. The Octane effectively performs like a Crucial m4 here, which isn't bad considering the m4 is a far more mature platform.

Desktop Iometer - 128KB Sequential Write (4K Aligned)

Background & The Drive AS-SSD Incompressible Sequential Performance
POST A COMMENT

75 Comments

View All Comments

  • pandemonium - Wednesday, November 23, 2011 - link

    Thanks for the article. That was quite interesting hearing about your personal interactions with OCZ and your perceptions. Of course, the number crunching data is always appreciated as well! Reply
  • Locut0s - Thursday, November 24, 2011 - link

    IMO they really only turned a new leaf with their SSDs and their decision to abandon memory sales. All of which was in the last few years. Reply
  • Beenthere - Thursday, November 24, 2011 - link

    I'm not sure they've ever "turned a new leaf"... ? Their SSDs also have issues which is why people should WAIT for 6 months or so to see how many firmware updates are required and if they actually fix all of the OCZ SSD Octane issues discovered. Reply
  • FunBunny2 - Friday, November 25, 2011 - link

    Yeah, and then get a huge discount at Newegg!! Reply
  • lancid81 - Thursday, November 24, 2011 - link

    Which SSD do you use for your personal computer at home Anand ? or i guess the
    real question is if you had to purchase an SSD with your own cash..which would you go for?

    Thanks for all the great reviews
    Reply
  • Anand Lal Shimpi - Thursday, November 24, 2011 - link

    My personal system(s) all use SSDs I recommend. It's a part of the review process to be honest. I put in months of use case testing on top of the normal review to help me formulate exactly these types of opinions.

    I've got both the Intel SSD 510 and Samsung SSD 830 in my main work computer at this point. If I had to spend money on one right now it'd probably be the Samsung.

    Take care,
    Anand
    Reply
  • jihe - Thursday, November 24, 2011 - link

    OCZ, now that's three letters I'd like to avoid at all costs. Reply
  • ppro - Thursday, November 24, 2011 - link

    I just post a link to this anadtech post and they removed the post on ocz forum... go and try... they even ban your account.

    NO OCZ anymore... awful customer support + BSOD on all series 3 OCZ drives
    Reply
  • Beenthere - Thursday, November 24, 2011 - link

    There have been lots of issues in both the OCZ and Corsair forums when they get over-protective of even mentioning a competitors brand/product. I understand the challenges and bickering that can occur in these forums but the moderation of these forums leaves a LOT to be desired IME and is often counter-productive to supporting the brand. Reply
  • TinHat - Friday, November 25, 2011 - link

    BeHardware - by Marc Prieur
    Published on November 16, 2011
    http://www.behardware.com/articles/843-1/component...

    Components returns rates - SSD's (page 7), Memory (page 4)
    If i'm reading this article right, I see from the stats provided by Behardware that OCZ still have very poor return rates for their SSD drives currently at 4.2%. In contrast Intel has a ultra low 0.1% return rate whilst Corsair (their nearest competitor) has only 2.9% fail rate. I appreciate this could be attributed to the controller bug nightmare that seemed to drag on forever but how do they explain why other competitor brands, using the same chip, seemed to have no problems at all? In addition to this why their memory return rates are the highest to date at 6%?

    If these stats are to be believed then OCZ product failure rates are still not very reassuring, especially when you consider the prices of their products and all the consumer hasstle when dealing with component failures. Intel and Kingston seem to be the better bet at this time.
    Reply

Log in

Don't have an account? Sign up now