AnandTech Storage Bench - The Destroyer

The Destroyer has been an essential part of our SSD test suite for nearly two years now. It was crafted to provide a benchmark for very IO intensive workloads, which is where you most often notice the difference between drives. It's not necessarily the most relevant test to an average user, but for anyone with a heavier IO workload The Destroyer should do a good job at characterizing performance.

AnandTech Storage Bench - The Destroyer
Workload Description Applications Used
Photo Sync/Editing Import images, edit, export Adobe Photoshop CS6, Adobe Lightroom 4, Dropbox
Gaming Download/install games, play games Steam, Deus Ex, Skyrim, Starcraft 2, BioShock Infinite
Virtualization Run/manage VM, use general apps inside VM VirtualBox
General Productivity Browse the web, manage local email, copy files, encrypt/decrypt files, backup system, download content, virus/malware scan Chrome, IE10, Outlook, Windows 8, AxCrypt, uTorrent, AdAware
Video Playback Copy and watch movies Windows 8
Application Development Compile projects, check out code, download code samples Visual Studio 2012

The table above describes the workloads of The Destroyer in a bit more detail. Most of the workloads are run independently in the trace, but obviously there are various operations (such as backups) in the background. 

AnandTech Storage Bench - The Destroyer - Specs
Reads 38.83 million
Writes 10.98 million
Total IO Operations 49.8 million
Total GB Read 1583.02 GB
Total GB Written 875.62 GB
Average Queue Depth ~5.5
Focus Worst case multitasking, IO consistency

The name Destroyer comes from the sheer fact that the trace contains nearly 50 million IO operations. That's enough IO operations to effectively put the drive into steady-state and give an idea of the performance in worst case multitasking scenarios. About 67% of the IOs are sequential in nature with the rest ranging from pseudo-random to fully random. 

AnandTech Storage Bench - The Destroyer - IO Breakdown
IO Size <4KB 4KB 8KB 16KB 32KB 64KB 128KB
% of Total 6.0% 26.2% 3.1% 2.4% 1.7% 38.4% 18.0%

I've included a breakdown of the IOs in the table above, which accounts for 95.8% of total IOs in the trace. The leftover IO sizes are relatively rare in between sizes that don't have a significant (>1%) share on their own. Over a half of the transfers are large IOs with one fourth being 4KB in size.

AnandTech Storage Bench - The Destroyer - QD Breakdown
Queue Depth 1 2 3 4-5 6-10 11-20 21-32 >32
% of Total 50.0% 21.9% 4.1% 5.7% 8.8% 6.0% 2.1% 1.4

Despite the average queue depth of 5.5, a half of the IOs happen at queue depth of one and scenarios where the queue depths is higher than 10 are rather infrequent. 

The two key metrics I'm reporting haven't changed and I'll continue to report both data rate and latency because the two have slightly different focuses. Data rate measures the speed of the data transfer, so it emphasizes large IOs that simply account for a much larger share when looking at the total amount of data. Latency, on the other hand, ignores the IO size, so all IOs are given the same weight in the calculation. Both metrics are useful, although in terms of system responsiveness I think the latency is more critical. As a result, I'm also reporting two new stats that provide us a very good insight to high latency IOs by reporting the share of >10ms and >100ms IOs as a percentage of the total.

AnandTech Storage Bench - The Destroyer (Data Rate)

The SM951 takes the lead easily and provides ~34% increase in data rate over the XP941. The advantage over some of the slower SATA 6Gbps drives is nearly threefold, which speaks for the performance benefit that PCIe and especially PCIe 3.0 provide.

AnandTech Storage Bench - The Destroyer (Latency)

The latency benefit isn't as significant, which suggests that the SM951 provides substantial boost in large IO performance, but the performance at small IO sizes isn't dramatically better.

AnandTech Storage Bench - The Destroyer (Latency)

Despite the lowest average latency, the SM951 actually has the most >10ms IO with nearly 2% of the IOs having higher latency than 10ms. I did some thermal throttling testing (see the dedicated page for full results) and the SM951 seems to throttle fairly aggressively, so my hypothesis is that the high number is due to throttling, which limits the drive's throughput momentarily (and hence increases the latency) to cool down the drive. 

AnandTech Storage Bench - The Destroyer (Latency)

However, the SM951 has the least >100ms IOs, which means that despite the possible throttling the maximum service times stay between 10ms and 100ms.

Performance Consistency AnandTech Storage Bench - Heavy
Comments Locked

128 Comments

View All Comments

  • 3DoubleD - Tuesday, February 24, 2015 - link

    While this drive looks great and all, after all the problems the 840EVO has had, it is hard to get excited about big benchmark numbers from a Samsung drive... you never know if they will stay that way. That said, this drive is MLC and not TLC, so less chance of similar issues as the 840EVO. Still, Samsung has a lot of work to repair their reputation with their customers.
  • theduckofdeath - Tuesday, February 24, 2015 - link

    Yeah, they only have a bit more than 1/4 of the market. Really suffering from that snafu... I think you're overreacting just a bit... :)
  • 3DoubleD - Tuesday, February 24, 2015 - link

    How could their past sales possibly have suffered from a problem that is ongoing and developing? How future customers react will depend on whether Samsung properly addresses the current issues. My comment is based on this fact.
  • theduckofdeath - Tuesday, February 24, 2015 - link

    I have an Evo 840 and since the performance restoration fix I have not seen any sign of performance degradation on my drive. And that fix was made in October last year.
  • theduckofdeath - Tuesday, February 24, 2015 - link

    And just to clarify hwo desperate your trolling attempts are. It took (a limited number of) users a year to realise there even could be issues. That's how rare and hard to notice it was, even though the Evo 840 is probably the most sold SSD ever.
  • K_Space - Tuesday, February 24, 2015 - link

    I am not sure if you are aware, however Samsung has released a recent statement to the effect that there remain issues with the 840 EVO drive and the above fix has not provided a permenant resolution:
    http://www.anandtech.com/show/8997/samsung-release...
    I have an XP941 and SD Extreme Pro 480; it'd sensible to see how Samsung deals with the current situation at hand which may tip me and other enthusiasts (? <5% of their SSD sales) one way or the other.
  • extide - Tuesday, February 24, 2015 - link

    Not really, Samsung has many other great drives, even older ones that are/were still great like the 830, 840 pro, etc. Couple teething issues on early TLC drives, thats pretty much what to expect ion this industry. The MAIN thing is that they are infact handling it, and not just shuffling it under the rug. IMHO thats far more important than anything else.
  • smilingcrow - Wednesday, February 25, 2015 - link

    "The MAIN thing is that they are in fact handling it"

    The MAIN thing for me is when they have HANDLED it and the solution sticks over time as only then would I trust one of their TLC drives again.
    If that fails I expect a product recall which they haven't offered on the vanilla 840 yet which seemingly still has no fix. No recall = NOT handling it.
  • 3DoubleD - Wednesday, February 25, 2015 - link

    Teething issues - OK, that's fine, as long as they fix them, and that's all I've been saying; however, the verdict is still out as to whether they have fixed them or not, and that was my initial point.

    The minute they apply a permanent firmware fix or, if a firmware fix is not possible, a recall, then they will have handled it and I'd feel future Samsung purchases were justified. This obviously applies most strongly for Samsung TLC products, but how Samsung responds to SSD issues in general should be of interest of any current and potential Samsung SSD owner (TLC or MLC).
  • cm2187 - Tuesday, February 24, 2015 - link

    What problems are you referring to?

Log in

Don't have an account? Sign up now