AnandTech DAS Suite - Benchmarking for Performance Consistency

Our testing methodology for DAS units takes into consideration the usual use-case for such devices. The most common usage scenario is transfer of large amounts of photos and videos to and from the unit. Other usage scenarios include the use of the DAS as a download or install location for games and importing files directly off the DAS into a multimedia editing program such as Adobe Photoshop. Some users may even opt to boot an OS off an external storage device.

The AnandTech DAS Suite tackles the first use-case. The evaluation involves processing three different workloads:

  • Photos: 15.6 GB collection of 4320 photos (RAW as well as JPEGs) in 61 sub-folders
  • Videos: 16.1 GB collection of 244 videos (MP4 as well as MOVs) in 6 sub-folders
  • BR: 10.7 GB Blu-ray folder structure of the IDT Benchmark Blu-ray

Each workload's data set is first placed in a 25GB RAM drive, and a robocopy command is issued to transfer it to the DAS under test (formatted in NTFS). Upon completion of the transfer (write test), the contents from the DAS are read back into the RAM drive (read test). This process is repeated three times for each workload. Read and write speeds, as well as the time taken to complete each pass are recorded. Bandwidth for each data set is computed as the average of all three passes.

Blu-ray Folder Read

The write workloads see the Extreme PRO v2 come out slightly better than the WD_BLACK P50 using the Haswell testbed. On the reads, we see the Hades Canyon / eGFX enclosure turning out to be better - this can be attributed in part to the capabilities of the testbed itself, rather than the PCIe tunneling chain. In any case, we don't see any significant gulf in the numbers between the different units as long as the observations are made within the USB SuperSpeed 10Gbps or USB SuperSpeed 20Gbps host configurations.We also instrumented our evaluation scheme for determining performance consistency.

Performance Consistency

Aspects influencing the performance consistency include SLC caching and thermal throttling / firmware caps on access rates to avoid overheating. This is important for power users, as the last thing that they want to see when copying over 100s of GB of data is the transfer rate going down to USB 2.0 speeds.

In addition to tracking the instantaneous read and write speeds of the DAS when processing the AnandTech DAS Suite, the temperature of the drive was also recorded at the beginning and end of the processing. In earlier reviews, we used to track the temperature all through. However, we have observed that SMART read-outs for the temperature in NVMe SSDs using bridge chips end up negatively affecting the actual transfer rates. To avoid this problem, we have restricted ourselves to recording the temperature at either end of the actual workloads set. The graphs below present the recorded data.

Performance Consistency and Thermal Characteristics

The first three sets of writes and reads correspond to the photos suite. A small gap (for the transfer of the video suite from the internal SSD to the RAM drive) is followed by three sets for the video suite. Another small RAM-drive transfer gap is followed by three sets for the Blu-ray folder. An important point to note here is that each of the first three blue and green areas correspond to 15.6 GB of writes and reads respectively. There is no issue with thermal throttling - even in the fastest configuration, both the P50 and Extreme PRO v2 show an increase of less than 5C after the workload processing. The P50 seems to have slightly better thermal performance for this workload set.

Synthetic Benchmarks - ATTO and CrystalDiskMark PCMark 10 Storage Bench - Real-World Access Traces
Comments Locked

81 Comments

View All Comments

  • repoman27 - Wednesday, October 7, 2020 - link

    According to the USB4 spec, host-to-host tunneling is possible via inter-domain links even when using a hub, but of course YMMV.

    Thanks for pointing out that Thunderbolt 4 hub, that's awesome! And way cheaper than I was expecting. It looks like a Goshen Ridge hub based on Intel's Thunderbolt 4 Compact Dock reference design to me. However, I'm a little worried that OWC's wording implies that it is not backwards compatible with Thunderbolt 3 hosts. That would seem insane, and it may just be an OS support issue at this juncture, but it sure sounds like it's for Thunderbolt 4 PCs only. Aargh!
  • CaptainChaos - Wednesday, October 7, 2020 - link

    It *might* work, and cost may not be prohibitive & worth a shot! I don't see networking mentioned at all on the product page. Also, aren't thunderbolt 3 cables required to be active to do 40GB speeds?
  • CaptainChaos - Wednesday, October 7, 2020 - link

    ... plus it's described as a hub and not a switch so expectations would need to be tempered accordingly!
  • repoman27 - Wednesday, October 7, 2020 - link

    IP over Thunderbolt is a thing, but you'll never see it advertised. Much like IP over IEEE 1394 (a.k.a. FireWire) was also a thing... that nobody knew about. Where we're going, we don't need Ethernet!

    It is a Thunderbolt 4 / USB4 hub, almost certainly based on the recently launched Intel JHL8440 chip. Per the USB4 spec, it contains a router which "includes a flat point-to-point, configurable switch necessary to create the internal paths between adapters", in addition to a PCIe switch as well as USB 3.2 and USB 2.0 hubs. It is also required to support Thunderbolt 3 interoperability and DisplayPort Alternate mode on all downstream facing ports. It's the real deal.
  • repoman27 - Wednesday, October 7, 2020 - link

    Oh, also, the max length for passive cables at 40 Gbit/s is 0.8 m, and FWIW Apple sells theirs for $39. Full featured active cables are available in lengths up to 2.0 m, but cost $129 (from Apple).

    And throughput for host-to-host communications will be limited by the available bandwidth of the PCIe link between the host CPU and Thunderbolt controller. For Thunderbolt 3 hosts, that tends to be a PCIe Gen3 x4 link which results in real-world throughput of about 22 Gbit/s after accounting for protocol overhead.

    So Thunderbolt isn't exactly going to be a panacea, but if you can live with those constraints, it is still a very fast interface.
  • CaptainChaos - Wednesday, October 7, 2020 - link

    i want one (or 2 - wonder if they can be cascaded?)! Should be interesting to see follow ons from this or other vendors for cost or features. I've been eyeballing the 2.5baseT switch recently released by QNAP but this might be a better option for me.
  • CaptainChaos - Wednesday, October 7, 2020 - link

    ... except that I guess I'd need to use a PC to bridge TB subnet to a 10 GB ethernet network :-(
  • Deprectuod - Saturday, October 10, 2020 - link

    It looks good!
  • xpclient - Tuesday, October 13, 2020 - link

    Hi Anandtech, can you do a performance comparison of 2 PCs networked via Thunderbolt 3 to Thunderbolt 3 standard cables (since it allows running 10Gbps Ethernet) vs networking using USB 20 Gbps (Gen 2x2) to RJ-45 10 Gbps Ethernet adapters between 2 PCs? Which is faster? I bet the Thunderbolt 3 connection will be faster due to the protocol overhead of USB.
  • Howard - Sunday, October 18, 2020 - link

    With the stupidity (or anti-consumerist behavior) so glaringly obvious, It's almost as if USB-IF want people to stick with Lightning for as long as possible.

Log in

Don't have an account? Sign up now