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.

Corsair Neutron XT 240GB
Default
25% Over-Provisioning

Performance consistency has never been Phison's biggest strength and that continues to be the case with the S10 controller. The consistency is actually worse compared to the older S8 controller (i.e. Corsair Force LS) because the variance in performance is so high. I'm pretty sure the issue lies in Phison's garbage collection architecture as it doesn't seem to give enough priority for internal garbage collection, which results in a scenario where the drive has to stop for very short periods of time (milliseconds) to clean up some blocks for the IOs in the queue. That is why the performance frequently drops to ~1,500 IOPS, but on the other hand the drive may be pushing 70K IOPS the second after. Even adding more over-provisioning doesn't produce a steady line, although the share of high IOPS bursts is now higher. 

For average client workloads, this shouldn't be an issue because drives never operate in steady-state and IOs tend to come in bursts, but for users that tax the storage system more there are far better options on the market. I'm a bit surprised that despite having more processing power than its predecessors, the S10 can't provide better IO consistency. With three of the four cores dedicated to flash management, there should be plenty of horsepower to manage the NAND even in steady-state scenario, although ultimately no amount of hardware can fix inefficient software/firmware. 

Corsair Neutron XT 240GB
Default
25% Over-Provisioning

 

Corsair Neutron XT 240GB
Default
25% Over-Provisioning


TRIM Validation

To test TRIM, I filled the drive 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 Drives & The Test AnandTech Storage Bench 2013
POST A COMMENT

56 Comments

View All Comments

  • hojnikb - Tuesday, November 18, 2014 - link

    So pretty much, we're gonna have to wait another year or so to get 3D nand products (ie. mx200). Reply
  • Chrispy_ - Tuesday, November 18, 2014 - link

    Corsair *knows* you're going to test steady state.

    If the drive isn't good at steady state, why risk mass exposure with a bad review when a simple firmware update could make a big difference?

    First impressions matter, and the Neutron XT is now an underwhelming drive unlikely to be able to compete with the MX100s on price.
    Reply
  • ol1bit - Wednesday, November 19, 2014 - link

    I'm on my 3rd SSD.
    1st was Intel 74GB (first one would lock up, got Intel to replace it then was good).

    2nd was Corsair Force Series GT CSSD-F120GBGT-BK, and if my system got to busy, SSD would lock up HD light on solid, hard reset required, tried new drivers, everything and honestly I gave up on this drive, never fixed.

    3rd is Samsung 840 pro 250GB Uber fast, no lockups ever. I'm sticking with them for the foreseeable future!
    Reply
  • zmeul - Wednesday, November 19, 2014 - link

    any word on pricing? Reply
  • dj christian - Thursday, November 20, 2014 - link

    On the Performance Consistency page.

    "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."

    Which third one? All show log data and the last one doesn't show linear data.
    Reply
  • editorsorgtfo - Saturday, November 22, 2014 - link

    My A10-7850K / G.1 Sniper A88X build-in-progress is perfect for an M.2 (NGFF) SSD on a PCIe 2.0 x4 adapter card. The mobo's single PCIe 3.0 x16 slot is ripe for a Radeon R7 250, for Dual Graphics use, and its other x16 slot is PCIe 2.0, running at x4, ready for a bootable SSD to be installed.

    As for adapters, a Bplus M2P4A, a Lycom DT-120, or a (not-yet-released) ASUS Hyper M.2 X4 would fit the bill nicely.

    The LSI SandForce SF3739-controlled cards, such as the ADATA that was shown at Computex 2013 and the Kingston seen at Storage Visions 2014 back in January, or the Kingston HyperX using the Marvell 88SS9293 Altaplus PCIe 2.0 x4 SSD Controller displayed at Computex 2014, or Phison's, or Hynix's controller-in-the-works, etc. have yet to be released to the retail market. Don't they know the world's enthusiasts are just itching to spend their dosh on those gems?!

    Kingston trotted out their native PCIe expansion-slot HyperX "Predator" unit at the 2014 CES show in January, with a SF3739 controller. That's actually the unit I want! So, it's "hurry up and wait" at my house! LOL
    Reply

Log in

Don't have an account? Sign up now