AnandTech Storage Bench 2011, Light Workload

Our new light workload actually has more write operations than read operations. The split is as follows: 372,630 reads and 459,709 writes. The relatively close read/write ratio does better mimic a typical light workload (although even lighter workloads would be far more read centric). The I/O breakdown is similar to the heavy workload at small IOs, however you'll notice that there are far fewer large IO transfers:

AnandTech Storage Bench 2011—Light Workload IO Breakdown
IO Size % of Total
4KB 27%
16KB 8%
32KB 6%
64KB 5%

Light Workload 2011 - Average Data Rate

Performance improved a bit with the latest OCZ firmwares in our light workload, but not enough to substantially change its position. As we mentioned in our initial review, the Vertex 4 seems best suited for the truly intense, heavy multitasking workloads. 

Once again the issue is small read IO performance, which you can see from the chart below:

Light Workload 2011 - Average Read Speed

...and once again write performance is very good:

Light Workload 2011 - Average Write Speed

Light Workload 2011 - Disk Busy Time

Light Workload 2011 - Disk Busy Time (Reads)

Light Workload 2011 - Disk Busy Time (Writes)

AnandTech Storage Bench 2011 Final Words
Comments Locked

60 Comments

View All Comments

  • hasseb64 - Sunday, August 5, 2012 - link

    This OCZ firmware review biz has to stop. Let them get ONE chance to deliver a FINALIZED PRODUCT (review it 1 time, and then it is enogh). We consumers should not accept a half finished product.
  • jwilliams4200 - Sunday, August 5, 2012 - link

    The solution to that is simple. Just do what I do. Never buy OCZ.
  • peevee - Monday, August 6, 2012 - link

    EXACTLY!
    OCZ is a sketchy business. We remember upder0the-table downgrade of Vertex 2. We remember blue-screening Vertex/Agility 3s. Now this.
    OCZ employs incompetent firmware engineers. 15 months later after I purchased my Vertex 3, and the latest firmware is still unstable.
    Now all modern SATA III SSDs are fast enough for desktop use. The main differentiators are reliability and quality of support. And at these metrics OCZ is the worst of the worst. They still cannot upgrade firmware on a system drive from Windows, they still don't work with Mac at all, they still will require you to "Sec erase" your drive with your system (and then spend hundred hours to reinstall and reconfigure everything again) every time they update firmware, they still don't allow you to go to an old firmware (although some on them crash less for some users then their new firmwares) and require you to have working internet connection for update utility to redownload firmware every time... And blame problems on everybody else (while other drives simply work). This company is so bad it should simply die. I don't know why Tom's pays them so much attention, OCZ's reputation is beyond repair at this point.
  • vishwa108 - Sunday, August 5, 2012 - link

    It is never a good moment when the bull being lead by its nose-ring is claiming to be leading the bullring. This OCZ Independence Day saga have had many a worshipful scurrying to atone his altarboy days of their “independent” review and now, after “Version 1.5”, the worship is still akin to the fruit of The Choir Boys At Practice being heard louder than ever.

    First it was OCZ Zist und Zat soon to be followed by photocopied scans of “the reviewers” bottoms and then it was Marvellouski, quickly buried by another version of Amerikana 1.4 – only to end up with some vacuous advice of the, “Don’t go beyond half und you be OK, ja?”, variety. All for a good course/cause in buggery no less. No wonder Amerikans are being offered either the feast of Uncle Tommy und hist Kobbling Kabin Krew or another Mormon extravaganza with the mesmerised numpty vessels ringing louder than ever whenever the word, “War”, is messaged. What? OCZ are not of Yankeeland but rather of those who will soon be receiving their just rewards from across The Straits? Makes you ‘fink, ain’t eet. Perhaps the truth ought to be tried once in awhile – with all holes barred, of course.

    It is self benevolent to realise that Truth is merely another word for Freedom because the freedom that was gifted is about another/others and is not about self – when the gift was taken back. When truth is of self, you can’t even get it out of the blighter after a severe bout of torture. Hands up those who would like to disagree – especially when it is via a freed versioned 1.5 of some SSD doo-dah.
  • ssddaydream - Sunday, August 5, 2012 - link

    what is wrong with you?
  • shunya806 - Sunday, August 5, 2012 - link

    welcome to our website:
    http://commonprosperity.org/simpletrading@hotmail.com

    Dear friends, do you want to have some different things?
    Whether you want to give your relatives and friends,
    take a few different exotic gifts? Whether you want to
    buy some cheap benefits of thing? So please, let us begin now!

    Click on our website
    http://commonprosperity.org/
    simpletrading@hotmail.com
  • mark53916 - Monday, August 6, 2012 - link

    What happens to the lifetime and reliability of the OCZ Technology Vertex 4
    drives with firmware 1.5 when the drive is only running at 1/2 capacity?

    We already know that the performance is improved, but there may be other
    advantages to operating with reduced capacity. These two come to mind:
    1. The drive endurance may be improved
    If it turns out that either the drive endurance is improved if the
    drive is only half used I would be very happy.

    2. The data retention time for powered off devices may be improved.
    Increased powered off data retention time at reduced capacity
    won't affect me much since I couldn't afford solid state for my monthly
    backups even at the full capacity price, but people who have to
    keep around old system disks for long periods would benefit
    if the powered off data retention time were increased

    In addition, I find that the per byte price for SLC drives seems to be about
    10 times what the cost is for MLC drives [even though the manufacturing techniques
    seem to indicate that manufacturing cost is slightly less than 2 or 3 times
    as much for SLC compared to MLC.
    I'd gladly spend 2x the price per byte and run at 1/2 capacity until I actually
    need the additional capacity, even without increased drive endurance or
    powered off retention time, just for the improved performance.
  • FunBunny2 - Monday, August 6, 2012 - link

    SLC and MLC are the same parts, just binned and then programmed for either 1 or 2 bits. That's it.
  • robalm - Sunday, September 16, 2012 - link

    I decided to upgrade from my old Intel x25-m g2 80gb to a new fast ssd.
    It became an OCZ Vertex 4 128gb (1.5) but now I saw this review and this:

    "Small filesize sequential read performance needs work. Thankfully most sequential reads in client workloads tend to be in the sweet spot for the Vertex 4, but there are some applications That do a lot of small sequential IO (eg web browser cache accesses). '

    Have I made ​​a stupid upgrde when it come to web browser performence?
  • ryrynz - Monday, December 15, 2014 - link

    My Vertex 4 128GB had a sudden death. Seems to be fairly common for these drives.
    MAKE SURE YOU'RE BACKED UP. If you get some sudden reboots you know your controller
    is on the way out.. one time it'll happen and poof.. no drive detected, you've been warned.

Log in

Don't have an account? Sign up now