Testbed Setup and Evaluation Methodology

Evaluation of DAS units on Windows is done with the testbed outlined in the table below. For devices with a USB 3.1 Gen 2 (via a Type-C interface) connections (such as the SanDisk Extreme 900 1.92TB that we are considering today), we utilize the USB 3.1 Type-C port enabled by the Intel Alpine Ridge controller. It connects to the Z170 PCH via a PCIe 3.0 x4 link..

AnandTech DAS Testbed Configuration
Motherboard GIGABYTE Z170X-UD5 TH ATX
CPU Intel Core i5-6600K
Memory G.Skill Ripjaws 4 F4-2133C15-8GRR
32 GB ( 4x 8GB)
DDR4-2133 @ 15-15-15-35
OS Drive Samsung SM951 MZVPV256 NVMe 256 GB
SATA Devices Corsair Neutron XT SSD 480 GB
Intel SSD 730 Series 480 GB
Add-on Card None
Chassis Cooler Master HAF XB EVO
PSU Cooler Master V750 750 W
OS Windows 10 Pro x64
Thanks to Cooler Master, GIGABYTE, G.Skill and Intel for the build components

The full details of the reasoning behind choosing the above build components can be found here.

Evaluation involves running synthetic benchmarks such as ATTO and CrystalDiskMark. We also process custom test-suites (transfer of a set of photographs and video files) from a RAM disk on the testbed. Finally, we also run PCMark 8's storage bench on the external device.

The power consumed by the bus-powered device is measured using the Plugable USBC-TKEY interposer. The USBC-TKEY was plugged into one of the Thunderbolt 3 / USB 3.1 Gen 2 Type-C ports enabled by the Alpine Ridge controller. While the USBC-TKEY acts as a transparent interposer for the host's port, it is connected to a Ubuntu system for data gathering purposes via its micro-USB port. The power consumption is tracked while CrystalDiskMark processes its traces.

The Extreme 900 turned out to be a very interesting DAS unit to review. In our initial trials on the Skylake testbed (specified above), the performance numbers turned out to be very inconsistent. While performance was definitely better than any USB 3.0 flash drive for most tests, there were a few with very disappointing numbers. Assuming that it was a compatibility issue for the ASM1352R with the Alpine Ridge controller, we tested out on our Haswell testbed with an ASRock PCIe card (sporting an ASMedia controller). The results were similar. To complicate matters further, it turned out that none of our testbeds could process the PCMark 8 storage bench on the drive. All attempts failed with a workload initialization error.

While trying out various trials, we decided to completely get rid of any partition information on the drive. Using 'diskpart', 'select disk X' and 'clean' commands, we reinitialized the drive and formatted it afresh in exFAT (the drives had originally come pre-formatted in exFAT along with SanDisk's software encryption app). After this process, the PCMark 8 storage bench started working without issues. Benchmark numbers from ATTO and CrystalDiskMark also became consistent from run to run.

Introduction and Usage Impressions Direct-Attached Storage Benchmarks
Comments Locked

31 Comments

View All Comments

  • Holliday75 - Monday, April 11, 2016 - link

    Do those $10 enclosures support RAID 0? I'm sure there are some on the market, but to support RAID 0, USB 3.1 gen2? Doubt there are many if any on the market.
  • littlebitstrouds - Monday, April 11, 2016 - link

    I've got this 2 bay 3.1 gen2 from Startech. Have two 480gb Sandisk Ultra II SSD's running RAID 0. I get 420 MB/s read and write with my Macbook Retina. I'm on the road, so I haven't tried them on my desktop, with true 3.1 gen2 support yet.

    http://www.amazon.com/StarTech-com-10Gbps-External...
  • ganeshts - Monday, April 11, 2016 - link

    Nice one.. it is not $10, but $95, but a good solution for sure.

    Unfortunately, it is not bus-powered or as compact as the Extreme 900. That said, it is definitely more flexible with the configurable RAID levels.
  • jameskatt - Saturday, May 7, 2016 - link

    I'd rather have a boring enclosure design that is as small and utilitarian as possible. No need for extra fins and doodads. Just do its job and stay out of the way.
  • digiguy - Monday, April 11, 2016 - link

    I wonder if we'll see at some point external enclosures capable of supporting PCIe SSDs that can saturate 10Gb/s and/or even use Thunderbolt 3 to transfer data up to 40Gb/s
  • name99 - Monday, April 11, 2016 - link

    "with a peak power consumption of around 8.1W. SanDisk suggests using USB ports capable of delivering up to 10W of power for optimal performance. It is obvious that using a port capable of delivering only the usual 5W will heavily hamper the performance of the unit.
    "

    I'm sorry but this is an unacceptable ending to a pretty good review.
    There is no such thing as a "usual 5W USB port". A USB2 port will give you 2.5W, a USB3 port will give you 4.5W. Hoping that you'll be lucky and get more is a recipe for tears.

    Next, since SANDisk provide an A-connector, what actually HAPPENS when you use a 2.5 or 4.5W port? I'm somewhat dubious of the claim that it will just "heavily hamper the performance". At the very least I'd like to see some testing of this, with verification that the device does not simply randomly disconnect when it wants to power-draw beyond the allowed limit. Even assuming it is well-enough engineered to run properly on these lower power-draws, how much of a performance hit are we talking?

    This is part of a larger problem that, especially in the context of external drives (and, to some extent, WiFi equipment) AnandTech lives in blissful ignorance of the real world. Sure your labs don't contain a single devices manufactured before January 2016, but in the real world, a substantial use case for external USB drives involves their being swapped between different machines. THIS is why it REALLY matters to know how well they can handle being connected to older ports.

    This is not just some weird corner case, like a person complaining "well you didn't test that new SATA SSD drive when you connect it to 2007 SATA-66 box, and I really care about that situation"; it gets to the actual fitness of purpose for I would guess many, if not a majority, of the use cases of this sort of external USB drive.
  • ganeshts - Monday, April 11, 2016 - link

    No disconnects. Checked with a traditional USB 3.0 port. Some sort of throttling going on, which reduces the speed.
  • DanNeely - Tuesday, April 12, 2016 - link

    All hyperbole from name99 aside; some degree of benchmarking at lower power levels needs to be done for all high power usb flash devices for the next few years. Not necessarily the full suite; but one or two tests suitable to characterize what the fallback performance levels will be for people not having the latest and greatest hardware to plug them into.
  • epobirs - Monday, April 11, 2016 - link

    Which is why the SIIG USB 3.1 Gen 2 single bay enclosure comes with a dual host port cable, Type A on both ends.

    I have a 480 GB Patriot Blast SSD in it and it does a pretty nice job of saturating the SATA bus. Things should get more interesting if and when somebody produces an SSD controller that avoids the SATA bottleneck and taps into USB 3.1 fully.
  • TheUsual - Monday, April 11, 2016 - link

    No 'The'? I don't think every device deserves a 'The' at the beginning of the review, just the very important, well known devices.

Log in

Don't have an account? Sign up now