Sign in with
Sign up | Sign in

Examining Steady-State Performance

Marvell-Based SSDs From Corsair, Crucial, OCZ, And Plextor: Tested

Conducting “fresh-out-of-the-box” testing in Iometer saves time for exploring other performance aspects. For this round-up, we want to investigate steady-state performance during worst-case operating conditions, including writing over a full drive with 4 KB random writes. Because the drive is already packed with data, the controller does not have any empty blocks available. Writing sequential data to the packed drive forces it to perform garbage collection operations. This strenuous test is important because it confirms the existence of efficient SSD garbage collection.

Torture testing our Marvell 88SS9174-based SSDs results in similar scores for all drives. Though reads are not impacted, sequential write performance simply tanks—and then fails to recover. 

This is not the first time we've witnessed this sort of behavior from an SSD. It also occurred with OCZ's Octane. However, we previously interpreted this as an indicator of an SSD overly dependent on foreground garbage collection. It would have been more accurate to describe these results as a “un-recoverable” operating condition.

Marvell-based SSDs enjoy low scores when we test maximum response times during 4 KB random writes. This supports claims of background garbage collection for the m4, M3, M3 Pro, Performance Pro, and Octane.

How do we reconcile these results with the elegant recovery curve demonstrated by Marvell-based drives like the Vertex 4? If everything is working optimally, that'd be the type of behavior we'd expect from a drive employing background garbage collection.

The answer is that the threshold where it becomes difficult for an SSD to perform background garbage collection also makes subsequent graceful recovery highly unlikely. Metaphorically speaking, beating an SSD into the corner of the ring causes it to return in bad shape the next round. If we only re-run our random write torture test for a few minutes (rather than a sustained 20 minutes), the drive is able to recover.

In a way, this isn't necessarily the best way to approach background garbage collection if you're looking to preserve performance in the future. However, it's the preferred technique for extending SSD endurance, simply because fewer blocks of data are moved around over time.


Practically, none of this should dissuade you. Even in our torture test, issuing a TRIM command to the SSD results in performance recovering. Because that's not an option in RAID arrays, these SSDs aren't the best choice for combining for additional performance. Random writes will eventually trash the performance of a couple of Marvell-based drives in RAID.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 40 comments.
This thread is closed for comments
Top Comments
Other Comments
  • 10 Hide
    hellfire24 , May 1, 2012 6:39 AM
    crucial FTW!
  • 1 Hide
    Anonymous , May 1, 2012 7:49 AM
    Shoulda tossed in a V4 128gb for entertainment value...ah well. :p 
  • -7 Hide
    uruquiora , May 1, 2012 9:14 AM
    hellfire24crucial FTW!

    hmm , my M4 has 10x more BSOD than my vertex 3... Each i boot my pc and work with it i prepare myself for a BSOD with my M4...
  • 3 Hide
    joytech22 , May 1, 2012 11:27 AM
    uruquiorahmm , my M4 has 10x more BSOD than my vertex 3... Each i boot my pc and work with it i prepare myself for a BSOD with my M4...

    That is what we in the I.T industry like to call: "Faulty Hardware".
    If you considered that normal all this time, I have some bad news for you..
  • 6 Hide
    chesteracorgi , May 1, 2012 1:00 PM
    With the price of SSDs coming down, Toms should start introducing 256 GB + drives into its reviews. It's nice to have the 64 & 128 GB reviews, but for power builders the 256 GB is becoming mainstream.
  • 2 Hide
    Cyclops21 , May 1, 2012 1:23 PM
    Any tests planned on the Sandisk Extreme models. They were a Tom's recommend buy but I still haven't seen any benchmarks on Tom's.
  • -2 Hide
    cknobman , May 1, 2012 1:51 PM
    I'd still say for most boot and program drives SandForce is the way to go as it has a significant performance edge.
  • 4 Hide
    Onus , May 1, 2012 1:54 PM
    I've only installed 6-7 SSDs, with mixed results. Two with Sadforce controllers died within months or weeks (the RMA of one is yet to be tested). Given that the slowest SSD beats the pants off the fastest magnetic HDD, I have quickly reached the conclusion that reliability has to be the #1 criterion for SSDs, and I'm not sure Sandforce is there yet.
  • 0 Hide
    zodiacfml , May 1, 2012 2:13 PM
    Awesome. SSDs time is now!
  • 7 Hide
    ramon zarat , May 1, 2012 2:34 PM
    uruquiorahmm , my M4 has 10x more BSOD than my vertex 3... Each i boot my pc and work with it i prepare myself for a BSOD with my M4...

    You must be joking... The list of forum thread complaining about SF controller instability is endless. The M4 actually has a very solid reputation. I've been running 2 128GB M4 in 2 different PC for the last 8 months. Not a single BSOD. They still both benchmark the same speed as day 1. Actually, the M4 was and might very well still be the best choice for balance between price, performance and reliability in the whole SSD market. In my book, there are only 3 manufacturers really worth mentioning when it comes to SSD: Crucial, Intel and Samsung.

    Your unit is simply defective. That can happen to any manufacturer. RMA it and be happy.
  • 6 Hide
    daysyang , May 1, 2012 3:54 PM
    ^ agree... my M4 has been nothing but awesome.
  • 1 Hide
    Pawessum16 , May 1, 2012 4:50 PM
    When are you going to update your SSD charts? Some of the SSD's on the 2011 chart don't even exist anymore, and it's missing all the cool new drives released in the past couple of months.
  • 4 Hide
    americanherosandwich , May 1, 2012 4:55 PM
    Hah, I just got done reading this, too:

    Crucial M4's still kicking butt.
  • 2 Hide
    g-unit1111 , May 1, 2012 5:04 PM
    daysyang^ agree... my M4 has been nothing but awesome.

    So has mine, but at $70 I am thinking I might ditch my Intel 320 for a Plextor M3. I've always been a fan of Plextor drives and it's good to know that the move to SSD hasn't changed their quality at all. Tempting, tempting...
  • 2 Hide
    eddieroolz , May 1, 2012 5:14 PM
    Godo to see my choice of SSD be proven in tests. I have high hopes for my Crucial m4.
  • 1 Hide
    inflexion , May 1, 2012 6:07 PM
    Nice review. I just picked up another Crucial M4 today on for $110 USD to my door.

    Thanks for the great content!
  • 2 Hide
    Anonymous , May 1, 2012 6:33 PM
    Where the heck can you get the M3 64gb for $70?
  • 0 Hide
    rohitbaran , May 1, 2012 11:31 PM
    I wonder if there are any reliability stats on SSDs available. They are fast for sure, but how about reliability scores, based off drive performance over a year or so?
  • 0 Hide
    slomo4sho , May 2, 2012 1:11 AM
    rohitbaranI wonder if there are any reliability stats on SSDs available. They are fast for sure, but how about reliability scores, based off drive performance over a year or so?

    I couldn't agree more. Having a fast drive means nothing if it dies or corrupts your data.
  • 0 Hide
    10tacle , May 2, 2012 3:36 AM
    Where are you guys seeing the 64GB M3 for $70? I have yet to find it anywhere for under $100. In fact, the best price I can find from reputable E-tailer is $120. I'd snap one up in a second as dedicated Intel SRT cache drive.
Display more comments