Performance Benchmarks

Our evaluation routine for hard-drive based direct-attached storage devices borrows heavily from the testing methodology for flash-based direct-attached storage devices. The testbed hardware is reused. CrystalDiskMark is used for a quick performance overview. Real-world performance testing is done with our custom test suite involving robocopy bencharks and PCMark 8's storage bench.

CrystalDiskMark uses four different access traces for reads and writes over a configurable region size. Two of the traces are sequential accesses, while two are 4K rando accesses. Internally, CrystalDiskMark uses the Microsoft DiskSpd storage testing tool. The 'Seq Q32T1' sequential traces use 128K block size with a queue depth of 32 from a single thread, while the '4K Q32T1' ones do random 4K accesses with the same queue and thread configurations. The plain 'Seq' traces use a 1MiB block size. The plain '4K' ones are similar to the '4K Q32T1' except that only a single queue and single thread are used.

The first interesting comparison in the table below is between the My Book with the 5400 RPM HelioSeal drive and the G-Technology G-Drive with Thunderbolt over USB 3.0 that employs a 7200 RPM HelioSeal drive. While the 1 MB sequential access traces show the 7200 RPM drive in better light, the use of a bridge chip supporting UASP helps the 5400 RPM My Book pull ahead by a huge margin in the high queue-depth sequential access trace.

HDD-Based Direct-Attached Storage Benchmarks - CrystalDiskMark

The second interesting comparison is between the My Passport and the LaCie Porsche Design Mobile Drive. The Seagate Backup Plus, though being based on the same internal drive as the LaCie Porsche Design Mobile Drive, was evaluated with an older version of CrystalDiskMark / different testbed, and its results are only presented here for the sake of completeness. Going back to the comparison, we find that the different bridge chip configuration, as well as differences in caching and hard drive firmware, make each of the units perform better than the other under different use-case scenarios. That said, the LaCie Porsche Design Mobile Drive performs better overall for this set of artificial benchmark traces.

Moving on to the real-world benchmarks, we first look at the results from our custom robocopy test. In this test, we transfer three folders with the following characteristics.

  • 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 (the same that we use in our robocopy tests for NAS systems)

The test starts off with the Photos folder in a RAM drive in the testbed. robocopy is used with default arguments to mirror it onto the storage drive under test. The content on the RAM drive is then deleted. robocopy is again used to transfer the content, but, from the storage drive under test to the RAM drive. The first segment gives the write speed, while the second one gives the read speed for the storage device. The segments end with the purge of the contents from the storage device. This process is repeated thrice and the average of all the runs is recorded as the performance number. The same procedure is adopted for the Videos and the BR folders.

The performance numbers show that the My Passport 4TB performs better than the LaCie Porsche Design Mobile Drive 4TB for reads, while the situation is reversed for writes (which is similar to the behavior we encountered in the CrystalDiskMark traces). The G-Technology G-Drive with Thunderbolt 8TB betters the My Book 8TB consistently even over the former's non-UASP USB 3.0 interface. The Seagate Innov8 is nowhere in the picture because of the Archive HDD inside, but its use-case (bus-powered high-capacity DAS) is quite different compared to the My Book. Readers interested in looking at all the graphs in one shot can choose the 'Expand All' option in the dropdown menu.

Photos Read

High-performance external storage devices can also be used for editing multimedia files directly off the unit. They can also be used as OS-to-go boot drives. Evaluation of this aspect is done using PCMark 8's storage bench. The storage workload involves games as well as multimedia editing applications. The command line version allows us to cherry-pick storage traces to run on a target drive. We chose the following traces.

  • Adobe Photoshop (Light)
  • Adobe Photoshop (Heavy)
  • Adobe After Effects
  • Adobe Illustrator

Usually, PC Mark 8 reports time to complete the trace, but the detailed log report has the read and write bandwidth figures which we present in our performance tables. Note that the bandwidth number reported in the results don't involve idle time compression. Results might appear low, but that is part of the workload characteristic. Note that the same CPU is being used for all configurations. Therefore, comparing the numbers for each trace should be possible across different DAS units. The general trend we observed in the robocopy benchmarks is seen here also. Readers interested in looking at all the graphs in one shot can choose the 'Expand All' option in the dropdown menu below.

Adobe Photoshop Light Read

Introduction and Product Impressions Thermal Aspects and Power Consumption
POST A COMMENT

35 Comments

View All Comments

  • fazalmajid - Monday, October 17, 2016 - link

    WD and Seagate both suck. The drives to get are HGST (formerly Hitachi, formerly-er IBM), despite the fact HGST is now owned by WDC. Reply
  • piroroadkill - Monday, October 17, 2016 - link

    Correct. Reply
  • Breit - Tuesday, October 18, 2016 - link

    I've got a total of 6 of these previous-gen WD MyBook 8TB model here and guess what: I took them all apart to see what's actually in them. In two of them there is actually a HGST Helium drive installed with a HGST sticker on it. The other 4 have an identical drive (same exteriour, same electronics, same name) but an updated sticker, which says WD instead of HGST. They look nearly identical to the HGST He8 drives, despite they are only 5400rpm. So I guess they are infact HGST drives, which is a good thing.

    Maybe buying them sooner rather then later might be a good idea, assuming WD will change the design in the future to bring costs down (the external WD 8TB drives cost ~$250, while the bare drives without external enclosures in the form of the WD Red costs around $300-350 for whatever reason).
    Reply
  • Samus - Monday, October 17, 2016 - link

    I see mostly Seagate 3.5" failures especially in the 7200.10-7200.12 series, and tons of WD Black and WD Blue 2.5" failures. I've only seen ONE WD Blue 3.5" desktop drive fail.

    The other point to note is Seagate drives fail catastrophically. My friend Mitchell works for a data recovery service in Chicago, and backs this up whenever we talk. Seagate drives they receive have a very low recovery rate compared to all other brands because many failures result in the platters being physically scratched (radial surface scratch) which nobody can recover because the media is ruined and there just isn't enough error correction to recover from surface defects on this scale.

    He is particularly fond of...you guessed it, Hitachi-designed drives. Most failures are controller related and are turned around 100% satisfactory using a donor drive.

    Hitachi Coolspins are as good as people rave about. It's ridiculous to trust your data on anything else if you can cope with the 4TB max capacity before the design changed to the joint Hitachi-WD developed Deskstar/Ultrastar models that come in larger capacities. The original Hitachi developed designed ended at 4TB, but are still sold at retailers because they are actually still in production.
    Reply
  • Wardrop - Monday, October 17, 2016 - link

    Interesting. Thanks for sharing. Reply
  • fanofanand - Monday, October 17, 2016 - link

    Count me in the camp that had a 7200.10 fail on me after 18 months of use. I won't buy a spinning platter again. Reply
  • BrokenCrayons - Monday, October 17, 2016 - link

    Hard drives are useful as infrequently used backup drives since modern SSDs have problems with long-term data retention. For instance, if you stick your backup drive at a relative's house like I do (~45 mins drive from my home) and forget about it, a modern SSD may not be the best solution based on what I've been reading about TLC. Reply
  • Michael Bay - Monday, October 17, 2016 - link

    But are they quiet? Price is indeed good. Reply
  • MrSpadge - Monday, October 17, 2016 - link

    Anecdotal experience is worth nothing when we're talking about statistics with single-digit yearly failure rates (as most normal HDDs have, server grade units score better). And you should not TRUST any single storage device, no matter how reliable you think it is. Reply
  • Samus - Monday, October 17, 2016 - link

    This. Backup backup backup. Cloud backup services are $50 a year for unlimited storage and protect you from every form of data failure (fire flood theft surge malware infections accidental deletion mechanical failure etc) Reply

Log in

Don't have an account? Sign up now