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. 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 excellent. The M3/Pro already had great random read performance to begin with but M5 Pro takes that one step further. We are looking at figures similar to Vertex 4 here.

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

At queue depth of 3, the M5 Pro is noticeably faster than its predecessors. The difference is 30MB/s (~18% on average), although Plextor still cannot match the performance of SandForce or Indilinx Everest 2.

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

Increasing the queue depth to 32 yields great results. Performance has significantly improved since the M3/Pro. The M5 Pro is on par with SandForce and Everest 2 based SSDs here.

Sequential Read/Write Speed

To measure sequential performance we ran a one 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 performance remains unchanged from M3 Pro.

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

Sequential write is up when compared to M3 Pro, but for some reason, the M3 is still even faster than the M5 Pro. 

Inside the M5 Pro and Test Setup AS-SSD Incompressible Sequential Performance
Comments Locked

37 Comments

View All Comments

  • BryanBend - Friday, August 31, 2012 - link

    http://www.amazon.com/Plextor-Series-PX-128M3P-2-5...

    Just noticed price drop on Amazon just a few minutes ago $84.99 matching Newegg on the 128 M-5, w/o adapter, drive only.

    Submitted a price match yesterday.. :)
  • teefatt - Tuesday, September 4, 2012 - link

    I just want to share my experience with OCZ Support Team,

    I posted the above matters to OCZ forum and got no solution from them after many email in and out in a week time. They want me to write an email to HP for help. They even deleted my reply and make the post like I did not reply their request or reply their mail. Furthermore, they blocked my post. They wanted me to send them a personal email instead of on the public forum.

    They moved my post to ForumOCZ Support ForumCompliments, Complaints, & SuggestionsVertex 4 512GB BSOD in RAID 0 setup.
    or

    http://www.ocztechnologyforum.com/forum/showthread...

    That's why I totally agree with the post here on the first page:
    http://www.anandtech.com/show/5719/ocz-vertex-4-re...

    "It's still a drive from OCZ, a company that has repeatedly and blatantly used its customer base as unpaid beta testers, and lambasted them when they dared to complain about it. No thank you. The fastest drive in the world is of no use to me if it's causing my computer to BSOD constantly. I'll be spending my money and that of my many clients on drives with proven track records for reliability and excellent customer service, both sadly lacking in OCZ products."

    I will walk away from this OCZ unreliable SSD. Luckily I am able to return the drives and asked for refund instead of following their steps to do the beta tester.

    Think twice before you buy it.

    Thanks you.
  • stalker27 - Tuesday, September 4, 2012 - link

    Kristian Vättö, you need to learn your gibies!

    119,2 Gibibytes (GiB = 1024 MiB) is 128 Gigabytes (GB = 1000 MB)
  • paulobao - Monday, September 10, 2012 - link

    Hi,

    I'm new here and not much of an expert in this stuff!
    Just a silly question but, since I would buy one SSD tomorrow for my Tecra R80 laptop (and I'm for the M3Pro): what to expect from the 512 GB version of the M3Pro (speed, power consumption, etc) when compared to the little brother (256 GB) ?

    I want reliability in my first SSD (and some spped too---:-))

    Regards,
    paulo
  • GullLars - Thursday, September 13, 2012 - link

    Small sequential transfers in ATTO seem to be mediocre on this drive. With just a small bit of the 256MB RAM used for read-ahead that could be fixed for reads. For small sequential writes 128-256KB of the RAM used for "unprotected" buffering (could be safe with caps, not necessarily supercaps) could put the write speed for all smaller transfer sizes close to the 340MB/s mark seen in 128KB seq write IOmeter test.
  • abhilashjain30 - Monday, July 29, 2013 - link

    Plextor entered the Indian markets with its range of SSDs by announcing its distributors for India. Plextor SSDs will be Distributed nationally by Mumbai based M/s Prime ABGB Pvt. Ltd. (http://www.PrimeABGB.com / http://www.OnlySSD.com)
  • abhilashjain30 - Monday, July 29, 2013 - link

    ** http://www.OnlySSD.com

Log in

Don't have an account? Sign up now