TRIM Functionality

Over time SSDs can get into a fairly fragmented state, with pages distributed randomly all over the LBA range. TRIM and the naturally sequential nature of much client IO can help clean this up by forcing blocks to be recycled and as a result become less fragmented. Leaving as much free space as possible on your drive helps keep performance high (20% is a good number to shoot for), but it's always good to see how bad things can get before the GC/TRIM routines have a chance to operate. As always I filled all user addressible LBAs with data, wrote enough random data to the drive to fill the spare area and then some, then ran a single HD Tach pass to visualize how slow things got:

As we showed in our enterprise results, Vector's steady state 4KB random write performance is around 33MB/s. The worst case sequential performance here is around 50MB/s, which is in line with what you'd expect. Sequential writes do improve performance, but as with most SSDs you're best operating the Vector with a bit of spare area left on the drive (in addition to what's already set aside by firmware).

TRIM and another sequential pass restore performance to normal, but it also triggers the Vector's performance mode penalty:

At 50% capacity there's an internal reorganization routine that's triggered on Vector, similar to what happens on the Vertex 4. During this time, all performance is impacted, which is why you see a sharp drop in performance just beore the 135GB mark. The re-org routine only takes a few minutes. I went back and measured sequential write performance after this test and came back with 380MB/s in Iometer. In other words, don't be startled by the graph above - it's expected behavior, it just looks bad as the drive doesn't get a chance to run its background operations in peace.

AnandTech Storage Bench 2011 - Light Workload Power Consumption
POST A COMMENT

151 Comments

View All Comments

  • SodaAnt - Wednesday, November 28, 2012 - link

    Its way too large for a msata drive, so it wouldn't fit anyways. Reply
  • somebody997 - Thursday, April 11, 2013 - link

    Why is there an mSATA connector on the PCB anyway? Reply
  • somebody997 - Thursday, April 11, 2013 - link

    The PCB is far too large for an mSATA drive anyway, so why have the mSATA connector? Reply
  • Anand Lal Shimpi - Wednesday, November 28, 2012 - link

    That's likely a custom debug port, not mSATA.

    Take care,
    Anand
    Reply
  • Heavensrevenge - Wednesday, November 28, 2012 - link

    Actually that connection is indeed a physically identically sized/compatible m-SATA connection. The problem is it's inability to actually plug in due to the SSD's general size or whether it's able to communicate with the typical m-SATA ports on mobos.
    http://www.pclaunches.com/entry_images/1210/22/tra... should give a decent example.
    Reply
  • vanwazltoff - Thursday, December 20, 2012 - link

    might be a sign of something else in the works from ocz like an msata cable to plug into it or something, maybe something even more awesome like double the band width by connected it to a ocz pci break off board. i guess we will see Reply
  • mayankleoboy1 - Tuesday, November 27, 2012 - link

    I have a Vertex2 256GB SSD.
    Is it worth upgrading to a Vector or a Samsung840 Pro SSD ?
    Reply
  • MadMan007 - Tuesday, November 27, 2012 - link

    If you've got a motherboard with SATA 6Gb/s you would probably notice a difference. Whether it's worth it is up to you - do you do a lot of disk-intensive work to the point where you wish it were faster? While I'm the difference would be noticable, it might not be huge or worth spending $200+ on. Reply
  • MrSpadge - Wednesday, November 28, 2012 - link

    Are you often waiting for your disk to finish tasks? If not it's not going to be worth it. Reply
  • Beenthere - Tuesday, November 27, 2012 - link

    It's going to take more than a nice type written letter to resolve the many product and service issues at OCZ - if they stay in business over the next six to 12 months.

    FYI- A five year warranty ain't worth the paper it's written on if the company no longer exists. In addition a five year warranty does not mean that a particular product is any better than a product with a one year warranty. For each extended year of warranty, the product price increases. So you're paying for something you may or may not ever use.

    In addition it's useful to read the fine print on warranties. Most state that you will receive a refurbished or reconditioned replacement if your product develops a defect. If you've ever seen some of the "reconditioned" or "refurbished" mobos from Asus or similar products from other companies, you'd never install them in your PC.

    People reach many untrue conclusions about product quality based on the warranty.
    Reply

Log in

Don't have an account? Sign up now