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). We perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time.

Desktop Iometer - 4KB Random Read

Desktop Iometer - 4KB Random Write

Desktop Iometer - 4KB Random Write (QD=32)

Random speeds show a small decrease in performance over the other OCZ drives, which is due to the combination of the slower M10 controller and A19nm NAND.

Sequential Read/Write Speed

To measure sequential performance we run 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

In sequential performance the ARC 100 seems to be more optimized for read performance as that is up compared to the Vector 150 and Vertex 460, but in turn the write speed has decreased slightly.

Desktop Iometer - 128KB Sequential Write

AS-SSD Incompressible Sequential Read/Write Performance

The AS-SSD sequential benchmark uses incompressible data for all of its transfers. The result is a pretty big reduction in sequential write speed on SandForce based controllers, but most other controllers are unaffected.

Incompressible Sequential Read Performance

Incompressible Sequential Write Performance

AnandTech Storage Bench 2011 Performance vs. Transfer Size
Comments Locked

54 Comments

View All Comments

  • StevoLincolnite - Tuesday, August 26, 2014 - link

    That's true to an extent.
    I have an OCZ Vertex 2 64Gb SSD which has been fantastically solid for years, if it died and I was able to get it replaced under warranty, I would throw it into a notebook and use the excuse to upgrade the SSD in my main desktop.

    That said, the main benefit of an SSD over mechanical that an end-user will notice is not actually the read/write speeds, but rather the 0-latency access times which makes everything feel super snappy and responsive, improved reads/writes are just diminishing returns from an end users experience perspective, hence why I have kept my old Vertex 2 for so long.
  • hurleydood - Wednesday, December 31, 2014 - link

    My old 128GB patriot SSD had a 10 year warranty, failed in 5 years. Patriot replaced it with a latest 240GB SSD they had in inventory. So expect replacements to be current spec.
  • Kristian Vättö - Tuesday, August 26, 2014 - link

    Only the 120GB Extreme II is cheaper than the ARC 100 and both have the same 3-year warranty. The Extreme Pro has a 10-year warranty but it is much more expensive.
  • Samus - Tuesday, August 26, 2014 - link

    The Extreme II is actually more expensive at all price points except the minimum capacity (120GB) and it isn't always faster, either. The only reason to consider it is for a laptop (where Barefoot 3 makes no sense) if price is a concern.

    However, I don't see any reason to get anything other than an MX100 for anything except high-performance applications. SleepDev, OPAL, PLP capacitors, solid reliability, lowest price of any SSD at mainstream capacities, and so on...
  • miandrew - Tuesday, August 26, 2014 - link

    Great article. I noticed that the SanDisk Extreme II consistently beats the OCZ ARC 100 and it has slumber power which helps in the laptop world. Nice that Newegg currently has the OCZ sale. So many choices...
  • jerrylzy - Tuesday, August 26, 2014 - link

    Why there's no trim validation now?
  • Kristian Vättö - Tuesday, August 26, 2014 - link

    I don't usually test TRIM anymore unless we are dealing with a new controller/firmware platform. The Barefoot 3 platform has shown to offer functional TRIM.
  • Witchunter - Tuesday, August 26, 2014 - link

    I read this like so: http://i.imgur.com/CMcHBs7.jpg.
    I agree that there's no need to test it again, but perhaps a reference could be helpful?
  • Kristian Vättö - Tuesday, August 26, 2014 - link

    Haha, a reference sounds like a good idea. I've been trying to streamline the review process to get through my backlog quicker, so that is why it might seem like I'm cutting corners, but I'll take this into account :)
  • Prodromaki - Tuesday, August 26, 2014 - link

    Kris, Samsung EVO 256 doesn't cost that much. Its newegg price is 140$. In EU(amazon) for some weird reason MX100 and the EVO are almost the same price(130$ vs 140$). Furthermore the Arc 100 costs ~160$, which definitely makes it a way worse buy than the two other value choices over here.

Log in

Don't have an account? Sign up now