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.

Iometer - 4KB Random Write, 8GB LBA Space, QD=3

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:

Iometer - 4KB Random Write, 8GB LBA Space, QD=32

Iometer - 4KB Random Read, QD=3

Faster than a Vertex 3 Pro & The Test Sequential Read/Write Speed
Comments Locked


View All Comments

  • seapeople - Thursday, February 24, 2011 - link

    I think the answer you are searching for is a bit more mundane than you desire. For example, when you load a map you are storage limited whether you have an SSD or not, and when you are fighting bad guys you are CPU limited whether you have a slow HD or not.
  • vol7ron - Saturday, February 26, 2011 - link

    While that's true, I'm not sure that's what he's referring to.

    If you're ever CPU limited, it's probably not just because of an SSD, it's just the fact that you need a better CPU. Generally, CPU limitations are apparent from memory access, not due to SSDs.

    I can understand what he's saying though as I'm still running a C2D and it gets to 100% during games. Not to mention, there does seems to be hang ups on Win7 64b startup, due to all the applications, widgets, and services that load; but that's less to do with the SSD and more to do with the CPU. The load time would be just as long w/o the SSD, it's just that there wouldn't be as much of a hang-up as the sluggishness would be constant.

    Having more cores in this instance would certainly help.
  • Nentor - Thursday, February 24, 2011 - link

    First paragraph:
    "What wasn’t impressive however was the price."

    There is not a word about price in the article about the V3Pro. Not even a slight indication implying a high price which made it seem affordable.

    Also this:

    ---I asked OCZ if this meant the drive I was testing wasn’t representative of final, shipping performance. OCZ stated very clearly that performance will not change between the drive I have today and the drive that goes on sale in the next 2 months.

    SandForce wouldn’t comment on any existing agreements and OCZ said it couldn’t get SandForce to confirm that the V3’s performance wouldn’t change between now and its eventual release.---

    What exactly does that mean? It comes down to not meaning anything at all to me.
  • ClagMaster - Thursday, February 24, 2011 - link

    I went half-way through this article and was frustrated with the complexity of the SandForce Controller capabilities and firmware games.

    It would seem SandForce is very Intel-like in its conduct. Why cannot they have 2-3 stinking controllers setup for maximum performance without these firmware games ? The hardware is willing but the businessmen are not.

    Last night I was about ready to purchase a 120GB SSD but decided this was an extravagance for my desktop for $220. I would rather have a good Western Digital Black 1.0 TB harddrive than this SSD. I get much more for my money. I still use Windows XP Home because of its efficiency and minimalist memory foot print. Are there any garbage collection utilities I can use for this still excellent OS? This is not clear from the vendor sights.

    Can anyone enlighten me as to what is available for Windows XP so these SSD's continue to operate in prime form ?

    I cannot believe consumers are willing to pay this kind of money so they shave off 15 to 20 seconds off boottimes.
  • 86waterpumper - Thursday, February 24, 2011 - link

    I agree whole-heartedly with you about the frimware games...that is def. lameness.
    With that being said, I don't think that ocz drives are really more expensive than other brands so I guess the solution for now is just to buy their drives instead of the competitions which is exactly what they want right? haha.
    I disagree though with you about ssd not being worth it. I know they are high, but shaving 15 to 20 seconds off boot time is huge in my book. I mean that is half the time in alot of cases. That has a coolness factor to it, but the main benefit I see is being
    able to multitask better, and having programs and games load faster. The boot time is just a side benefit really. Quietness and low heat and power draw are other nice features. Anyway I remember people were happy to pay the price for raptors not long ago, and they were this expensive and much less capacity than regular drives. They did not represent nearly the performance gap either.
  • Barbaniko - Thursday, February 24, 2011 - link

    How about Garbage collection on the Vertex 3?
    How would it hold up over time without access to winnows 7 trim command?
    I am interested in putting two of these in a Raid 0 configuration.
    Thank you.
  • arm3n - Monday, February 28, 2011 - link

    I second this request. Would love to get your take on these bad boys striped.

  • gstrickler - Friday, February 25, 2011 - link

    I've been searching for reliable information about the AES encryption on SF based SSDs. From the information I've been able to get from the manufacturers, this is NOT TCG "OPAL" compatible FDE, it's passive encryption that does not require any BIOS support, TCM, or boot time password. If that's accurate, then it's almost useless. It doesn't protect your data if your SSD is stolen. Therefore, it is of limited value.

    What that does do is protect the data from being recovered from the NAND Flash chips on a failed SSD, and executing a "erase" ATA command will change the password and make all your data, including bad blocks and reserved overallocation areas, inaccessible after the erase. Clearly, that has value to those reallocating a used drive, but that's about the extent of it's value.

    There is certainly some value in that, as securely erasing the data from an SSD can be challenging because of the LBA->Flash block remapping that SSDs perform. However, if it doesn't support "OPAL" FDE, then you must fall back to software FDE and the performance penalty for software FDE on an SSD is far more significant than it is for a HDD, and effectively eliminates much of the performance benefit of an SSD.

    Please check with SandForce and/or the SSD vendors and report if any of them support TCG compatible "OPAL" FDE. That information is vital to users who need to use FDE.
  • ac2 - Friday, February 25, 2011 - link


    The AES encryption bit sounds like one of those meaningless marketing bullet points...
  • iwod - Friday, February 25, 2011 - link

    The Anand SSD benchmarks 2010 and 2011 are the closest we get to real life measurements.

    And if those results are correct. Then our previous estimation of Seq Read Write become not important as we move faster will be incorrect. It turns out most of our time we are doing Seq Read Write. Therefore it is the Random Read Write has reach its tipping point and not providing any more Real World Improvement to users.

Log in

Don't have an account? Sign up now