Sign in with
Sign up | Sign in

Storage Bench v1.0, In More Detail

60/64 GB SSD Shootout: Crucial, Samsung, And SandForce
By

SSD manufacturers prefer that we benchmark drives the way they behave fresh out of the box because solid-state drives slow down once you start using them. If you give an SSD enough time, though, it will reach a steady-state performance level. At that point, its benchmark results reflect more consistent long-term use. In general, reads are a little faster, writes are slower, and erase cycles happen as slow as you'll ever see from the drive.

We want to move away from benchmarking SSDs fresh out of the box whenever possible because you only really get that performance for a limited time. After that, you end up with steady-state performance until you perform a secure erase and start all over again. Now, we don't know about you, but we don't reformat our production workstations every week. So, while performance right out of the box is an interesting metric, it's not nearly as relevant in the grand scheme of things. Steady-state performance is what ultimately matters.

While this is a new move for us, IT professionals have long used this approach to evaluate SSDs. That's why the consortium of producers and consumers of storage products, Storage Networking Industry Association (SNIA), recommends benchmarking steady-state performance. It's really the only way to examine the true performance of an SSD in a way that represents what you'll actually see over time.

There are multiple ways to get there, but we're going to use Intel’s IPEAK (Intel Performance Evaluation and Analysis Kit). This is a trace-based benchmark, which means that we're using an I/O recording to measure relative performance. Our trace, which we're dubbing Storage Bench v1.0, comes from a two-week recording of my own personal machine, and it captures the level of I/O that you would see during the first two weeks of setting up a computer.

Installation includes:

  • Games like Call of Duty: Modern Warfare 2, Crysis 2, and Civilization V
  • Microsoft Office 2010 Professional Plus
  • Firefox
  • VMware
  • Adobe Photoshop CS5
  • Various Canon and HP Printer Utilities
  • LCD Calibration Tools: ColorEyes, i1Match
  • General Utility Software: WinZip, Adobe Acrobat Reader, WinRAR, Skype
  • Development Tools: Android SDK, iOS SDK, and Bloodshed
  • Multimedia Software: iTunes, VLC


The I/O workload is somewhat moderate. I read the news, browse the Web for information, read several white papers, occasionally compile code, run gaming benchmarks, and calibrate monitors. On a daily basis, I edit photos, upload them to our corporate server, write articles in Word, and perform research across multiple Firefox windows. 

The following are stats on the two-week trace of my personal workstation:

Statistics
Storage Bench v1.0
Read Operations
7 408 938
Write Operations
3 061 162
Data Read
84.27 GB
Data Written142.19 GB
Max Queue Depth
452


According to the stats, I'm writing more data than I'm reading over the course of two weeks. However, this needs to put into context. Remember that the trace includes the I/O activity of setting up the computer. A lot of this information is considered one-touch, since it isn't accessed repeatedly. If we exclude the first few hours of my trace, the amount of data written drops by over 50%. So on a day-to-day basis, my usage pattern evens out to include a fairly balanced mix of read and writes (~8-10 GB/day). That seems pretty typical for the average desktop user, though this number is expected to favor reads among the folks consuming streaming media on a larger and more frequent basis.

On a separate note, we specifically avoided creating a really big trace by installing multiple things over the course of a few hours, because that really doesn't capture real-world use. As Intel points out, traces of this nature are largely contrived because they don't take into account idle garbage collection, which has a tangible effect on performance (more on that later).

Display all 43 comments.
This thread is closed for comments
  • -1 Hide
    GhosT94 , January 5, 2012 4:13 AM
    what about ocz vertex 3 ?
  • 6 Hide
    acku , January 5, 2012 4:15 AM
    GhosT94what about ocz vertex 3 ?

    Read page 2.

    Cheers,
    Andrew Ku
    TomsHardware.com
  • 2 Hide
    Anonymous , January 5, 2012 5:02 AM
    Wow. Absolutely wonderful article. I did second guess my decision on SSD for my next build for a few. But honestly I'm just using it as a boot drive.
  • 1 Hide
    acku , January 5, 2012 5:19 AM
    kixofmyg0tWow. Absolutely wonderful article. I did second guess my decision on SSD for my next build for a few. But honestly I'm just using it as a boot drive.


    Glad to hear that!

    Cheers,
    Andrew Ku
    TomsHardware.com
  • 0 Hide
    xtreme5 , January 5, 2012 5:46 AM
    gr888888!
  • 0 Hide
    rossi004 , January 5, 2012 5:54 AM
    Ok, so I have the whole SSD for boot, HDD for storage and less intensive programs, but I have a practicality question:

    Is there a way to have files and programs automatically downloaded, installed, and run from the HDD without doing it manually every time if I have the SSD as the base drive?
  • 1 Hide
    james_1978 , January 5, 2012 6:37 AM
    rossi004Ok, so I have the whole SSD for boot, HDD for storage and less intensive programs, but I have a practicality question:Is there a way to have files and programs automatically downloaded, installed, and run from the HDD without doing it manually every time if I have the SSD as the base drive?


    You can move your personal folders to your HDD (my documents, my music, downloads, ...), so downloads will end up there automaticaly, but programs will go to your C drive (SSD) by default.
  • 0 Hide
    james_1978 , January 5, 2012 6:53 AM
    james_1978You can move your personal folders to your HDD (my documents, my music, downloads, ...), so downloads will end up there automaticaly, but programs will go to your C drive (SSD) by default.

    Ok, sorry, but actually you can move your program files by editing the registry:

    Moving only user files is far easier nevertheless, just using "move" in the folder properties...
  • 0 Hide
    james_1978 , January 5, 2012 6:57 AM
    james_1978Ok, sorry, but actually you can move your program files by editing the registry:Moving only user files is far easier nevertheless, just using "move" in the folder properties...

    "Add an url" didn't quite work for me :-)
    http://www.tomshardware.com/forum/6643-63-windows-boot-drive-user-files-program-files-normal
  • 0 Hide
    Soul_keeper , January 5, 2012 6:58 AM
    nice article

    Worth mentioning, plextor PX-M3S are micron based and use toggle nand
    I don't think they make a 64GB version however
  • 0 Hide
    exban224 , January 5, 2012 7:33 AM
    Are the tests on the m4 with the new firmware, if not then is you update the firmware the m4 is overall better. 120gb sandforce speeds anyone in a 64gb package.
  • 0 Hide
    ojas , January 5, 2012 9:48 AM
    Hey great in-depth article Andrew, really liked it!

    BTW: Intel lists different IOPS for its drives. They say, for example, that:
    Random Write (8GB Span)=21000 IOPS
    Random Write (100% Span)=600 IOPS

    Reads seem to be unaffected. What's this about?


    p.s. The graphs in any article (in general) aren't readable using the iOS app :(  have to open it in safari then use the reader...and some comments aren't displayed entirely...i'm using an ipod touch, maybe it works fine on a tablet? :o  Just thought i'd let someone know, didn't who develops the app...
  • 0 Hide
    Dacatak , January 5, 2012 11:43 AM
    What kind of flash does Super Talent use in their 64GB SATA III drives? They are hardly any slower than the higher capacity drives, which shows lower capacity doesn't always have to mean lower speed.
  • 0 Hide
    burnley14 , January 5, 2012 11:50 AM
    Confirms my good decision to buy the 64GB m4! :) 
  • 1 Hide
    john4real4ipok , January 5, 2012 12:58 PM
    my Nokia 2688 is hot and faitning
  • 2 Hide
    a4mula , January 5, 2012 1:12 PM
    http://www.hardocp.com/article/2011/08/07/nand_flash_faces_off_synchronous_vs_asynchronous/1

    Something that isn't even mentioned in the article is how full these drives were when benched. A fresh installed SSD with most of its capacity available will perform wonderfully. In real world scenarios where the drive is at 50% capacity however, the asynchronous drives performance falls off the map while the synchronous drives continue to perform well.

    Another issue that really could have been tackled here is RAID0 and performance per dollar of the 60/64GB drives vs their 128/256GB counterparts. I know there is a RAID0 scaling article already out there it would have been nice to see that incorporated here.

    Looking strictly at these benches it would seem as though a 256 m4 is the automatic choice. Maybe straight out of the box, not taking RAID0 into consideration that's the case. Once the drives start filling and considering the near 100% scaling of RAID I think you'd come to a different conclusion.
  • 2 Hide
    peevee , January 5, 2012 3:23 PM
    So, it is pretty clear that at the current flash density 64GB is both too slow (even slower than an old-tech HDD in some cases!) and too inconvenient (fits almost nothing you want to be faster).
    If you cannot afford at least 120GB, just wait and save money, with money saving and prices falling soon you will be able to buy it and enjoy your speed with almost everything except videos and backups/archives (for which HDDs are absolutely adequate).
    Or 240GB better yet.
  • 0 Hide
    BlackHawk91 , January 5, 2012 3:58 PM
    *&^*&, should have bought it back on Black Friday when it was $100 bundled with Batman: Arkham City, but didn't had the money at the time.
  • 1 Hide
    Reynod , January 5, 2012 4:09 PM
    Thanks Andrew.

    I'm getting a Samsung ... this looks to good to miss as a new boot drive, and I'll keep my Momentus XT for storage.

    I'm thinking of 2 of the Seagates in RAID0.

    Does that seem good value for the money ?

    cheers.

    :) 
  • 0 Hide
    jjb8675309 , January 5, 2012 4:10 PM
    I have had a single crucial m4 64 GB running for a little over a year now as a rock solid and fast OS/APP drive
Display more comments