Performance Consistency

Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal defragmentation. The reason we do not have consistent IO latency with SSDs is because inevitably all controllers have to do some amount of defragmentation or garbage collection in order to continue operating at high speeds. When and how an SSD decides to run its defrag or cleanup routines directly impacts the user experience as inconsistent performance results in application slowdowns.

To test IO consistency, we fill a secure erased SSD with sequential data to ensure that all user accessible LBAs have data associated with them. Next we kick off a 4KB random write workload across all LBAs at a queue depth of 32 using incompressible data. The test is run for just over half an hour and we record instantaneous IOPS every second.

We are also testing drives with added over-provisioning by limiting the LBA range. This gives us a look into the drive’s behavior with varying levels of empty space, which is frankly a more realistic approach for client workloads.

Each of the three graphs has its own purpose. The first one is of the whole duration of the test in log scale. The second and third one zoom into the beginning of steady-state operation (t=1400s) but on different scales: the second one uses log scale for easy comparison whereas the third one uses linear scale for better visualization of differences between drives. Click the buttons below each graph to switch the source data.

For more detailed description of the test and why performance consistency matters, read our original Intel SSD DC S3700 article.

  Transcend SSD340 JMicron JMF667H (Toshiba NAND) JMicron JMF667H (IMFT NAND) Samsung SSD 840 EVO mSATA Crucial MX100
Default
25% OP

Right from the start, things do not look too promising. Compared to the reference design with the same IMFT NAND, the IO consistency is considerably lower. The reference design manages around 1,000 IOPS minimum, whereas in the SSD340 the minimum performance is around 300 IOPS. Increasing the over-provisioning helps by a bit but the consistency is still poor compared to the other value drives (like the MX100). The older firmware definitely isn't doing Transcend any favors here – quite the opposite in fact.

  Transcend SSD340 JMicron JMF667H (Toshiba NAND) JMicron JMF667H (IMFT NAND) Samsung SSD 840 EVO mSATA Crucial MX100
Default
25% OP

 

  Transcend SSD340 JMicron JMF667H (Toshiba NAND) JMicron JMF667H (IMFT NAND) Samsung SSD 840 EVO mSATA Crucial MX100
Default
25% OP

TRIM Validation

To test TRIM, I first filled all user-accessible LBAs with sequential data and continued with torturing the drive with 4KB random writes (100% LBA, QD=32) for 30 minutes. After the torture I TRIM'ed the drive (quick format in Windows 7/8) and ran HD Tach to make sure TRIM is functional.

And it is. 

Introduction, The Drive & The Test AnandTech Storage Bench 2013
Comments Locked

57 Comments

View All Comments

  • KAlmquist - Tuesday, August 5, 2014 - link

    Back in the days of the JMF602 controller, I thought about buying one to store program files on (meaning I would be doing pretty much nothing but reads on the device and the write problem wouldn't matter). But the prices on the JMF602 drives never dropped to the point where this made sense. I eventually bought an Indilinx drive for about the same price as a J-Micron drive.

    It seems like history is repeating itself.
  • Per Hansson - Wednesday, August 6, 2014 - link

    You should be very glad you did not.
    I bought a 32GB JMF602B based Transcend TS32GSSD25S-M SSD in April 2008.
    This was before even the first Intel X25-M 50nm SSD was released so there was not much on the market to choose from if you wanted a "cheap" SSD
    Mind you cheap in this case was actually 1495SEK which translates to over $200!

    Performance is appalling, this is the type of SSD which you could not install Windows Vista or 7 on, because you would get "delayed write failed" errors during the installation, the SSD was simply so slow that the installation program timed out when copying the files...

    I'm using it for a Linux based firewall, IPCOP which is a 40MB ISO install, it took over 30 minutes to install!
    With a 2GB SCSI disk the same install is over in under 5 minutes, just for reference!

    Initially I gave this SSD a 2/10 score, because for my use it worked fine and I had not had any problems with it.
    But now just last week when rebooting the machine the vmlinuz boot file in /boot was corrupted.
    I can only conclude that the SSD has not refreshed the data in flash and that some bit flips has occurred, I made a HEX comparison of the file with a known good one and there where 4 errors in the file.
    Restoring the file from the original ISO made the system able to boot again, but it just goes to show what amazing crap this company makes!
    I sure would not take the bet that they have learnt anything in the last 5 years, especially so when they are probably using the crappiest flash they can find to get the price down, which they obviously have failed at when the MX100 is cheaper & performs miles better!
  • KAlmquist - Wednesday, August 6, 2014 - link

    That drive sounds bad. Even if one were to excuse Transcend for not refreshing the flash, the drive still should have detected the data corruption.
  • TonyCL6 - Thursday, August 7, 2014 - link

    For a SSD controller to be able to make crappiest flash a working SSD requires strong R&D capability in both hardware and firmware. That is the Midas touch solution/ technology that flash memory vendors and module makers are eager to have.
  • henrykale - Wednesday, August 6, 2014 - link

    It's an easy call to start promoting video testimonials with Modulates, then you can publish them to Facebook or your website or Twitter.
  • GraphicDesign - Thursday, August 7, 2014 - link

    May be this is a great notebook for me to work in my website. I 'm adding new designs, I like to work in photoshop cs, indesign, illustrator cs6. Please suggest me if this is perfect for my design profession. You can contact me www [dot] tunaman [dot] me. In my website you will find lots of Graphic design tutorial. Thank you!
  • cklee16 - Friday, September 26, 2014 - link

    Any idea if the updated firmware improved the performance of this drive?

    -K

Log in

Don't have an account? Sign up now