Performance vs. Transfer Size

ATTO is a useful tool for quickly benchmarking performance across various transfer sizes. You can get the complete data set in Bench. ATTO illustrates the poor-ish read performance of the SSD 730 quite well. The SSD 730 is the slowest drive in this comparison and doesn't match the other drives until an IO size of 1024KB. Write performance on the other hand is average, although it should be noted that at the smallest IO sizes the drive is very slow for some reason. I'm guessing this is just a matter of optimization as enterprise workloads don't usually go to IO sizes smaller than 4KB.

Click for full size

Random & Sequential Performance AnandTech Storage Bench 2011
Comments Locked

96 Comments

View All Comments

  • CrazyElf - Thursday, February 27, 2014 - link

    Seeing that the SSD market is a low margin market, I get the feeling that Intel's strategy is to use it's existing reputation as a "reliable" vendor of SSD solutions and milk it so to speak. So that means little competition from a serious price to performance stand point, and more focus on product margins.
  • NCM - Thursday, February 27, 2014 - link

    I've reread the first page about 5 times and I still can't tell what controller is in this drive. There's reference to previous use of SF, but no indication of what's now in use.

    Did that info end up on the editing room floor?
  • Death666Angel - Thursday, February 27, 2014 - link

    From the text "Adopting the platform from the DC S3500/S3700", "The controller is the same 8-channel design as in the S3500/S3700 but runs at 600MHz instead of the 400MHz of the S3500/S3700.". From the table "Controller Intel 3rd Generation (SATA 6Gbps)".
  • NCM - Friday, February 28, 2014 - link

    @Death666Angel (!) Thanks for the controller parsing. A rather convoluted way for readers to arrive at an answer, but we get there in the end.

    In a related matter the reviewer writes: "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."

    However in none of the tables are the Sandforce drives identified. Apparently we're supposed to have memorized beforehand what controllers each drive uses. This is not some a mere quibble on my part. We have a couple of dozen workstations using SSD's, and because we work with a lot of incompressible data I do not buy drives with SF controllers.

    Please AnandTech: if you're going to bother making technical distinctions of this kind, make it clear where they apply.
  • Mr Perfect - Friday, February 28, 2014 - link

    That's strange, they used to label the drives in the charts with what controller was in them.
  • Kristian Vättö - Saturday, March 1, 2014 - link

    The controller is also listed in the table, although it's just "Intel 3rd gen" as to my knowledge it doesn't have any specific codename.

    As for the other feedback, the part you quoted it just a boilerplate that was we use in every review but I see that there's a need to update it.
  • Mipmap - Thursday, February 27, 2014 - link

    "to invest in custom client-orientated silicon." oriented

    "There wasn't much competition and given Intel's resourced" resources
  • Death666Angel - Thursday, February 27, 2014 - link

    Orientated/oriented is a preference thing. Neither option is wrong.
  • CalaverasGrande - Thursday, February 27, 2014 - link

    the meaning is conveyed either way, but I have always taken orientated in the same way I take "moneys'. While I understand the intent, it still sounds awkward and uneducated.
  • redmist77 - Thursday, February 27, 2014 - link

    Saying 'orientated' is as dumb as saying 'documentated' or 'adaptated.'

Log in

Don't have an account? Sign up now