Performance Consistency

Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal fragmentation. 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 (Logical Block Addresses) 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 dropdown selections 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 SSD370 256GB
Default
25% Over-Provisioning

Despite the custom Transcend firmware, performance consistency is an exact match with ADATA's SP610. I'm suspecting that the reason for low steady-state performance might be the hardware because the SM2246EN is a single-core design. Most controller designs today are multicore because today's NAND requires a lot of management and with multiple cores the NAND management can be dedicated to one or more cores, which leaves the rest of the cores available for host IO processing. In Silicon Motion's case, the one core has to take care of everything from host IOs to NAND management, which translates to lower overall performance as the controller can't keep up with everything that needs to be done.

Transcend SSD370 256GB
Default
25% Over-Provisioning

 

Transcend SSD370 256GB
Default
25% Over-Provisioning


TRIM Validation

To test TRIM, I filled a 128GB SSD370 with sequential 128KB data and proceeded with a 30-minute random 4KB write (QD32) workload to put the drive into steady-state. After that I TRIM'ed the drive by issuing a quick format in Windows and ran HD Tach to produce the graph below.

And TRIM works as expected.

Introduction, The Drive & The Test AnandTech Storage Bench 2013
POST A COMMENT

44 Comments

View All Comments

  • Kristian Vättö - Tuesday, January 27, 2015 - link

    The MX100 and Crucial drives in general do well when they are empty, but once you have a dirty drive and mixed workload the performance suffers. Our 2015 Client SSD Suite will have a more thorough look at different performance metrics because I agree that the current suite, especially the random/sequential tests, don't show the whole picture. Reply
  • Kristian Vättö - Tuesday, January 27, 2015 - link

    The MX100 is only faster in synthetic Iometer tests when the drive has been secure erased. If you look at the Storage Benches, the SSD370 is faster in all except the Heavy Workload, where the MX100 is very marginally faster (not enough to really say it's faster). Reply
  • eddieobscurant - Tuesday, January 27, 2015 - link

    Great review, keep them coming.

    Just to let you know that there are some compatibility issues with amd chipset motherboards and this ssd.

    http://www.amazon.de/product-reviews/B00K9HID1C/re...
    Reply
  • Daniel Egger - Tuesday, January 27, 2015 - link

    Personally I'd rather have linked to the various English forums rather than amazon.de so most people here can understand what the problem is all about like:
    https://forum-en.msi.com/index.php?topic=183310.0
    http://www.tomshardware.co.uk/answers/id-2361429/p...
    http://www.overclockers.com/forums/showthread.php/...

    I'm actually one of the couple who had problems with the SSD connected to my ASRock H87M Pro4 and after wasting almost two days trying to get it work I sent it back.

    There's some speculation that the problem is caused by having 5V and 3.3V at the SATA Power connector as some PSUs and notebooks will supply it and can be resolved by using an adapter from a regular Molex connector instead. Of course I'm not able to refute or confirm that rumor.

    However it does definitely not speak for Transcend for letting such a problem slip through nor does it speak for Anandtech not properly researching whether other users have problem with a product, especially when the review is done so late after the release...
    Reply
  • Kristian Vättö - Tuesday, January 27, 2015 - link

    I didn't get samples until right before I left to CES, hence the late timing. Let's just say Transcend's marketing people aren't the easiest to work with when it comes to sampling... Reply
  • Daniel Egger - Wednesday, January 28, 2015 - link

    Kristian, my beef is *NOT* the late review but rather that this delay should have brought you the possibility to check other peoples experiences.

    The two most important factors (yes, even more than speed) in SSDs are compatibility and reliability, the first one is definitely compromised and the jury is still out on the second.

    With the still uninvestigated compatibility problem on the table there shouldn't have been any recommendation IMNSHO.
    Reply
  • bfragged - Tuesday, January 27, 2015 - link

    I had slow speed and weird connection issues on all the SATA ports of my ASrock Z77 Extreme4-M while using a 512GB Trancend SSD370. Swapped it into a HP laptop and it worked fine. Very frustrating though, you would think they would test it on a wide range of systems. Looks like there are multiple motherboards that have problems with it. I saw it mentioned that it may be a compatibility issue with some SATA chipsets. Reply
  • Daniel Egger - Wednesday, January 28, 2015 - link

    Try using a Molex to SATA adapter rather than connecting it directly to the SATA connector of the PSU. Reply
  • hojnikb - Tuesday, January 27, 2015 - link

    >The SSD370 is available in capacities from 32GB to all the way to up to 1TB. I decided to leave out the 32GB and 64GB units from the specification table as I suspect these are mostly OEM-focused models because (to be honest) there isn't a significant retail market for drives smaller than 128GB anymore.

    Looks like these models are not OEM after all, as they can be found in lots of EU online shops
    Reply
  • KAlmquist - Tuesday, January 27, 2015 - link

    Newegg sells the following sizes:
    64GB $60
    128GB $80
    256GB $105
    512GB $202
    Reply

Log in

Don't have an account? Sign up now