AnandTech Storage Bench 2010

To keep things consistent we've also included our older Storage Bench. Note that the old storage test system doesn't have a SATA 6Gbps controller, so we only have one result for the Vertex 3 Pro (and the C300). The SF-2500 controller does respectably here, but with a 3Gbps controller we're only marginally faster than other SSDs (which is why we've moved to a new storage platform for 2011).

The first in our benchmark suite is a light/typical usage case. The Windows 7 system is loaded with Firefox, Office 2007 and Adobe Reader among other applications. With Firefox we browse web pages like Facebook, AnandTech, Digg and other sites. Outlook is also running and we use it to check emails, create and send a message with a PDF attachment. Adobe Reader is used to view some PDFs. Excel 2007 is used to create a spreadsheet, graphs and save the document. The same goes for Word 2007. We open and step through a presentation in PowerPoint 2007 received as an email attachment before saving it to the desktop. Finally we watch a bit of a Firefly episode in Windows Media Player 11.

There’s some level of multitasking going on here but it’s not unreasonable by any means. Generally the application tasks proceed linearly, with the exception of things like web browsing which may happen in between one of the other tasks.

The recording is played back on all of our drives here today. Remember that we’re isolating disk performance, all we’re doing is playing back every single disk access that happened in that ~5 minute period of usage. The light workload is composed of 37,501 reads and 20,268 writes. Over 30% of the IOs are 4KB, 11% are 16KB, 22% are 32KB and approximately 13% are 64KB in size. Less than 30% of the operations are absolutely sequential in nature. Average queue depth is 6.09 IOs.

The performance results are reported in average I/O Operations per Second (IOPS):

AnandTech Storage Bench - Typical Workload

If there’s a light usage case there’s bound to be a heavy one. In this test we have Microsoft Security Essentials running in the background with real time virus scanning enabled. We also perform a quick scan in the middle of the test. Firefox, Outlook, Excel, Word and Powerpoint are all used the same as they were in the light test. We add Photoshop CS4 to the mix, opening a bunch of 12MP images, editing them, then saving them as highly compressed JPGs for web publishing. Windows 7’s picture viewer is used to view a bunch of pictures on the hard drive. We use 7-zip to create and extract .7z archives. Downloading is also prominently featured in our heavy test; we download large files from the Internet during portions of the benchmark, as well as use uTorrent to grab a couple of torrents. Some of the applications in use are installed during the benchmark, Windows updates are also installed. Towards the end of the test we launch World of Warcraft, play for a few minutes, then delete the folder. This test also takes into account all of the disk accesses that happen while the OS is booting.

The benchmark is 22 minutes long and it consists of 128,895 read operations and 72,411 write operations. Roughly 44% of all IOs were sequential. Approximately 30% of all accesses were 4KB in size, 12% were 16KB in size, 14% were 32KB and 20% were 64KB. Average queue depth was 3.59.

AnandTech Storage Bench - Heavy Multitasking Workload

The gaming workload is made up of 75,206 read operations and only 4,592 write operations. Only 20% of the accesses are 4KB in size, nearly 40% are 64KB and 20% are 32KB. A whopping 69% of the IOs are sequential, meaning this is predominantly a sequential read benchmark. The average queue depth is 7.76 IOs.

AnandTech Storage Bench - Gaming Workload

SYSMark 2007 Final Words
Comments Locked

144 Comments

View All Comments

  • FCss - Thursday, February 17, 2011 - link

    "My personal desktop sees about 7GB of writes per day." maybe a stupid question but how do you check the amount of your daily writes?
    And one more question: if you have a 128Gb SSD and you leave let's say 40Gb unformated so the user can't fill up the disk, will the controller use this space the same way as it would belong to the spare area?
  • Quindor - Thursday, February 17, 2011 - link

    I use a program called "HDDLED" for this. It shows you some easily accessible leds on your screen and if you hover over it, you can see the current and total disk usage since your PC was booted up.
  • FCss - Thursday, February 17, 2011 - link

    thanks, a great software
  • Breit - Thursday, February 17, 2011 - link

    isn't the totally written bytes to the drive since manufacturing be part of the smart data you can read from your drive? all you have to do then is noting down the value when you boot up your pc in the morning and subtract that from the actual value you read there the next day.
  • Chloiber - Thursday, February 17, 2011 - link

    Or you can just take the average..
  • marraco - Thursday, February 17, 2011 - link

    Vertex 2 takes advantage of unformated space. So OCZ advices to leave 20% of space unformated , (although to improve garbage collection, but it means that unformated space is used)
  • 7Enigma - Thursday, February 17, 2011 - link

    Comon Anand! In your example you have 185GB free on a 256GB drive. I think that is the least likely scenario that paints an overly optimistic case in terms of write life. Everyone knows not to completely fill up their drive but are you telling me that the vast majority of users are going to have 78% of their drive free at all times? I just don't buy it.

    The more common scenario is that a consumer purchases a drive slightly larger then needed (due to how expensive these luxuries still are). So that 256GB drive probably will only have 20-40GB free. Do that and that 36 days for a single use of the NAND becomes ~5-8 days (no way to move static data around at this capacity level). Factor in write amplification (0.6X to 10X) and you lower the time to between 4-25 years for hitting that 3000X cap.

    Still not a HUGE problem, but much more relevant then saying this drive will last for hundreds of years (not counting NAND lifespan itself).
  • 7Enigma - Thursday, February 17, 2011 - link

    Bah I thought the write amplification was 1.6X. That changes the numbers considerably (enough that the point is moot). I still think the example in the article was not a normal circumstance but it seems to still not be an issue.

    <pie to face>
  • mark53916 - Thursday, February 17, 2011 - link

    Encrypted files are not compressible, so you won't get any advantage
    from the hardware write compression.
  • 7Enigma - Thursday, February 17, 2011 - link

    Hi Anand,

    Looks like one of the numbers is incorrect in this chart. Right now it shows LOWER performance after TRIM then when the drive was completely full. The 230MB/sec value seems to be incorrect.

Log in

Don't have an account? Sign up now