Random Read/Write Speed

This test reads/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.

I've had to run this test two different ways thanks to the way the newer controllers handle write alignment. Without a manually aligned partition, Windows XP executes writes on sector aligned boundaries while most modern OSes write with 4K alignment. Some controllers take this into account when mapping LBAs to page addresses, which generates additional overhead but makes for relatively similar performance regardless of OS/partition alignment. Other controllers skip the management overhead and just perform worse under Windows XP without partition alignment as file system writes are not automatically aligned with the SSD's internal pages.

First up is my traditional 4KB random write test, each write here is aligned to 512-byte sectors, similar to how Windows XP might write data to a drive:

4KB Random Write - MB/s

Here we see the first real impact of the SF-1200's final, shipping firmware. Random write performance drops down a bit, but not by a lot. However the SandForce controllers perform best when run in OSes that align across 4K boundaries:

4K Aligned - 4KB Random Write - MB/s

Here we see a dramatic drop. While the SF-1500 and SF-1200 (3.0.1) based SSDs manage over 160MB/s, the standard SF-1200 (3.0.5) can only push 44.2MB/s. That's still much faster than a HDD, but it ends up being slower than both a C300 and Intel's X25-M G2.

4KB Random Read - MB/s

The performance limitation only applies to small file random writes. Random read performance remains unchanged with version 3.0.5 of the SF-1200 firmware.

Sequential Read/Write Speed Random Data Performance
POST A COMMENT

60 Comments

View All Comments

  • johnlewis - Wednesday, April 21, 2010 - link

    Thanks for another great article. I'm patiently waiting for a (decent) 512 GB SSD in my budget so I can just throw everything besides media files on it; 256 GB might work, if I wasn't so damn lazy. Plus, I'd rather have a half full 512 GB drive than a 90+% full 256 GB drive. Reply
  • retnuh - Wednesday, April 21, 2010 - link

    90%+ full 256gb, I hear ya. I've been digging over as many SSD reviews as I can in the last couple days. I WANT to replace my 256gb 5400rpm in my notebook, but just can't quite squeeze everything into 200gb. Reply
  • gadgetguy10 - Wednesday, April 21, 2010 - link

    I am waiting until the price is at least down to $1 per gigabyte for a decent ssd. I figure I can get by with about 128gb of space. Reply
  • retnuh - Thursday, April 22, 2010 - link

    my problem is the ~120gb of development VMs, I can't get rid of them, but since I'm in vmware all day a SSD would be heaven sent for general performance. I'm keeping things pretty slim at ~190gb out of 256gb, but that 200gb mark is just too tight. I'd buy a 300gb agility 2 today if it existed. Reply
  • 529th - Wednesday, April 21, 2010 - link

    I thought the OWC controllers were discovered to have the SF 1200 controllers?

    Also, can we get a review on the 50g Vertex LE that are selling at New Egg, Thanks
    Reply
  • Anand Lal Shimpi - Wednesday, April 21, 2010 - link

    Those numbers are from the older OWC Mercury which used a limited run of SF-1500. The newer drives going forward are SF-1200 based. I'll be phasing them out of our graphs as a result.

    Take care,
    Anand
    Reply
  • dmayes - Thursday, April 22, 2010 - link

    When are we going to see benchmarks on the new intel driver that's faster than microsoft's driver and it supports trim with raid and we shouldn't go off of just prices MSRP but actual newegg prices and maybe even have a low to high # for example Intel X25-M Mainstream SSDSA2MH160G2R5 ($400 - $489). Also include the 80gb version specially since its around $215 - $225 Reply
  • Impulses - Thursday, April 22, 2010 - link

    I agree on the prices... Street prices of OCZ's Indillix drives are much lower than that Corsair Nova for instance, since OCZ ALWAYS has $20-30 rebates going on their drives (and they're just cheaper to begin with)... OCZ's Nova equivalent, the Solid 2, is like $300 flat after MIR.

    Intel's newer SATA drivers don't enable TRIM in RAID, just w/RAID... You can have a SSD w/TRIM support and two HDD in RAID on the same controller with said drivers (something you couldn't do before), but you still can't RAID two SSD and retain TRIM support. AFAIK they didn't dramatically alter performance either but if you've got a link to tests that say otherwise I'd love to see it... I haven't bothered to install them yet.
    Reply
  • eaw999 - Thursday, April 22, 2010 - link

    but you do have to admit it is strange that imsm 8.9 was used for the testbed instead of irst 9.6. 8.9 doesn't support trim at all! one has to wonder how this might affect (or not) the benchmark scores. Reply
  • dmayes - Thursday, April 22, 2010 - link

    "The SandForce SF-1200 controller used in the A-DATA S599 with Intel’s latest RST 9.6 drivers is the fastest 2.5 inch solid state drive for Windows users at this time. This combination is able to outperform every other drive we have tested to date in all around performance." Source tweaktown but they compared it to another 1200 drive instead of using the same ssd with both drivers. This is what intel says "Is there TRIM support for RAID configurations?

    Intel® Rapid Storage Technology 9.6 supports TRIM in AHCI mode and in RAID mode for drives that are not part of a RAID volume.

    A defect was filed to correct the information in the Help file that states that TRIM is supported on RAID volumes."
    Reply

Log in

Don't have an account? Sign up now