Western Digital’s Black 1 TB NVMe SSD reviewed

Western Digital has a long and rich history in the storage market, but for a long time it wasn’t a player in the consumer solid-state storage space. The company first started to dabble in SSDs with its acquisition of Siliconsystems almost ten years ago, but that was a ticket into the business-focused market only. It wasn’t until the company’s much more recent and more expensive purchase of SanDisk that WD became truly ready to enter the mainstream SSD fray.

Freshly armed with SanDisk’s existing client SSD portfolio and the technologies and foundries of the SanDisk-Toshiba joint venture, WD wasted little time in getting SSDs carrying its own brand out the door. Its initial salvo was an unassuming set of re-badged SanDisk SATA drives, but the firm followed up with something more interesting: the Black PCIe SSD. The Black was an NVMe M.2 gumstick marketed as a lower-cost alternative to faster and more established NVMe product lines.

This year, however, Western Digital issued a new iteration of the Black SSD with a markedly different goal. Meet the WD Black NVMe SSD.

WD Black NVMe SSD
Capacity Max sequential (MB/s) Max random (IOps)
Read Write Read Write
250 GB 3000 1600 220K 170K
500 GB 3400 2500 410K 330K
1 TB 3400 2800 500K 400K

The naming scheme may not be crystal clear, so let’s break it down. The older Black is 2017’s “Black PCIe SSD.” It came in 256-GB and 512-GB capacities and was intended to be a low-cost entry point into NVMe PCIe drives. This year’s Black drive is the “Black NVMe SSD.” It comes in 250-GB, 500-GB, and 1-TB versions. WD touts the new drive as a high-performance player, unlike its more humble predecessor. The 1-TB version boasts particularly lofty performance numbers. That’s the one WD sent us to play with, so we’ll gladly put them to the test. As an aside, Western Digital will also be selling this exact drive under the SanDisk brand as the Extreme Pro M.2 NVMe 3D SSD, but only in the 500-GB and 1-TB capacities.

So what’s changed in a year? A lot. The 2017 drive’s blue PCB has been replaced with a more namesake-appropriate black one. Beneath the sticker are more significant changes. Marvell’s 88SS1093 controller has been booted out in favor of a new in-house design: a SanDisk-branded controller sandwiched in between the memory packages. The controller features the latest version of SanDisk’s proprietary nCache 3.0 pseudo-SLC caching scheme. Additionally, the controller is capable of bypassing nCache to write directly to TLC when the caches are too busy to service incoming writes. 

The drive’s NAND is  the same goodness we reviewed in Toshiba’s XG5 OEM SSD, but this time the cells are bundled up in packages bearing SanDisk’s name. We were very taken with the XG5 when we tested it and are still impatient for a retail version of the drive. Maybe the Black NVMe can scratch the itch in the meantime.

Western Digital warrants the Black drives for five years and rates the 1 TB version’s endurance at 600 terabytes written, matching the guarantees of the 970 EVO 1 TB that WD is so clearly gunning for.

The Black also matches the 970 EVO’s price. The WD Black NVMe is available at Newegg for $400 even. Despite carrying the same tag as Samsung’s latest, the Black unfortunately provides no hardware encryption acceleration features. But if the performance is good enough, we may be willing to relax our privacy principles. Let’s see what Western Digital’s new halo drive can do.

 

IOMeter — Sequential and random performance

IOMeter fuels much of our latest storage test suite, including our sequential and random I/O tests. These tests are run across the full capacity of the drive at two queue depths. The QD1 tests simulate a single thread, while the QD4 results emulate a more demanding desktop workload. For perspective, 87% of the requests in our old DriveBench 2.0 trace of real-world desktop activity have a queue depth of four or less. Clicking the buttons below the graphs switches between results charted at the different queue depths.

Our sequential tests use a relatively large 128-KB block size.



The WD Black languishes at QD1 with sequential reads. That’s not a good place to languish, since it represents performance typical for PC users. Otherwise, it seems to keep up with the 970 EVO 1 TB. The XG5 is faster across the board, so perhaps WD still has a thing or two to learn from the older SSD players about controller optimization. Random reads and writes come next.



Respectable. The WD drive is very responsive, especially with its random writes.

The WD Black is doing fine in our first round of synthetics, but has yet to set itself apart from the NVMe pack. There are plenty of benchmarks to go, so it still has time to prove itself. Let’s move on to sustained and scaling tests.

 

Sustained and scaling I/O rates

Our sustained IOMeter test hammers drives with 4KB random writes for 30 minutes straight. It uses a queue depth of 32, a setting that should result in higher speeds that saturate each drive’s overprovisioned area more quickly. This lengthy—and heavy—workload isn’t indicative of typical PC use, but it provides a sense of how the drives react when they’re pushed to the brink.

We’re reporting IOPS rather than response times for these tests. Click the buttons below the graph to switch between SSDs.


Yikes. Peak and steady-state both look pretty rough for a drive of this caliber. Let’s see what the numbers are.

The WD Black NVMe’s peak rate is half that of the XG5 and only a third that of the 970 EVO 1 TB. Steady-state performance isn’t quite as rough, but it’s still less than you want from a drive like this. We’ve reached out to Western Digital for comment, but this is likely yet another instance of a drive’s firmware and caching algorithms needing more time to recover from IOMeter test setup than our process gives. 

Our final IOMeter test examines performance scaling across a broad range of queue depths. We ramp all the way up to a queue depth of 128. Don’t expect AHCI-based drives to scale past 32, though—that’s the maximum depth of their native command queues.

For this test, we use a database access pattern comprising 66% reads and 33% writes, all of which are random. The test runs after 30 minutes of continuous random writes that put the drives in a simulated used state. Click the buttons below the graph to switch between the different drives. And note that the P3700 plot uses a much larger scale.


Scaling is not the WD Black’s strong suit. Its best performance is at QD4, but beyond that its graphs are SATA-like flat ground.


As you can see, most  other NVMe drives squeeze out more power until at least QD16. The WD Black just isn’t interested. To be fair, most consumer workloads aren’t nearly that parallel, and the Black remains quite competitive in the lower queue depths that client users should be interested in.

Our IOMeter synthetics proved a rough patch for Western Digital’s new gumstick. But we’re exiting the quagmire of IOMeter for the greener pastures of real-world tests. Maybe RoboBench will be the Black’s cup of tea.

 

TR RoboBench — Real-world transfers

RoboBench trades synthetic tests with random data for real-world transfers with a range of file types. Developed by our in-house coder, Bruno “morphine” Ferreira, this benchmark relies on the multi-threaded robocopy command build into Windows. We copy files to and from a wicked-fast RAM disk to measure read and write performance. We also cut the RAM disk out of the loop for a copy test that transfers the files to a different location on the SSD.

Robocopy uses eight threads by default, and we’ve also run it with a single thread. Our results are split between two file sets, whose vital statistics are detailed below. The compressibility percentage is based on the size of the file set after it’s been crunched by 7-Zip.

  Number of files Average file size Total size Compressibility
Media 459 21.4MB 9.58GB 0.8%
Work 84,652 48.0KB 3.87GB 59%

RoboBench’s write and copy tests run after the drives have been put into a simulated used state with 30 minutes of 4KB random writes. The pre-conditioning process is scripted, as is the rest of the test, ensuring that drives have the same amount of time to recover.

The media set is made up of large movie files, high-bitrate MP3s, and 18-megapixel RAW and JPG images. There are only a few hundred files in total, and the data set isn’t amenable to compression. The work set comprises loads of TR files, including documents, spreadsheets, and web-optimized images. It also includes a stack of programming-related files associated with our old Mozilla compiling test and the Visual Studio test on the next page. The average file size is measured in kilobytes rather than megabytes, and the files are mostly compressible.

Let’s take a look at the media set first. The buttons switch between read, write, and copy results.



The WD Black NVMe’s performance in the media set is nothing short of spectacular, a far cry from the doldrums of IOMeter. The Black claims a record speeds in the 1T write test as well as both copy tests. In fact, its copy results were so good I was forced to change the axis scale from previous reviews.

Next, the work set.



Our work set is typically a great equalizer. The WD Black still puts up great numbers, but it’s not so dominant as it is in the media set. Nonetheless, it snags new records in the 8T write and copy tests.

In the span of a single page of tests, the WD Black NVMe went from unremarkable to record-setting. This is why we can’t rely purely on synthetics. Our last page of tests will see how the Black fares with boot duties.

 

Boot times

Until now, all of our tests have been conducted with the SSDs connected as secondary storage. This next batch uses them as system drives.

We’ll start with boot times measured two ways. The bare test depicts the time between hitting the power button and reaching the Windows desktop, while the loaded test adds the time needed to load four applications—Avidemux, LibreOffice, GIMP, and Visual Studio Express—automatically from the startup folder. Our old boot tests focused on the time required to load the OS, but these new ones cover the entire process, including drive initialization.

The Black’s boot times land very near the top of the charts. No complaints.

Load times

Next, we’ll tackle load times with two sets of tests. The first group focuses on the time required to load larger files in a collection of desktop applications. We open a 790-MB 4K video in Avidemux, a 30-MB spreadsheet in LibreOffice, and a 523-MB image file in the GIMP. In the Visual Studio Express test, we open a 159-MB project containing source code for the LLVM toolchain. Thanks to Rui Figueira for providing the project code.

Nothing out of the ordinary. The WD Black’s application load times are typical.

Games also load up as snappily as can be expected. 

Like every other SSD in our test set, the WD Black NVMe blends into the crowd when it comes to boot and load times. Now we’re out of tests, so read on for test methods or skip a page to go straight to the conclusion.

 

Test notes and methods

Here are the essential details for all the drives we tested:

  Interface Flash controller NAND
Adata Premier SP550 480GB SATA 6Gbps Silicon Motion SM2256 16-nm SK Hynix TLC
Adata Ultimate SU800 512GB SATA 6Gbps Silicon Motion SM2258 32-layer Micron 3D TLC
Adata Ultimate SU900 256GB SATA 6Gbps Silicon Motion SM2258 Micron 3D MLC
Adata XPG SX8200 480GB PCIe Gen3 x4 Silicon Motion SM2262 64-layer Micron 3D TLC
Adata XPG SX930 240GB SATA 6Gbps JMicron JMF670H 16-nm Micron MLC
Corsair MP500 240GB PCIe Gen3 x4 Phison 5007-E7 15-nm Toshiba MLC
Crucial BX100 500GB SATA 6Gbps Silicon Motion SM2246EN 16-nm Micron MLC
Crucial BX200 480GB SATA 6Gbps Silicon Motion SM2256 16-nm Micron TLC
Crucial MX200 500GB SATA 6Gbps Marvell 88SS9189 16-nm Micron MLC
Crucial MX300 750GB SATA 6Gbps Marvell 88SS1074 32-layer Micron 3D TLC
Crucial MX500 500GB SATA 6Gbps Silicon Motion SM2258 64-layer Micron 3D TLC
Crucial MX500 1TB SATA 6Gbps Silicon Motion SM2258 64-layer Micron 3D TLC
Intel X25-M G2 160GB SATA 3Gbps Intel PC29AS21BA0 34-nm Intel MLC
Intel 335 Series 240GB SATA 6Gbps SandForce SF-2281 20-nm Intel MLC
Intel 730 Series 480GB SATA 6Gbps Intel PC29AS21CA0 20-nm Intel MLC
Intel 750 Series 1.2TB PCIe Gen3 x4 Intel CH29AE41AB0 20-nm Intel MLC
Intel DC P3700 800GB PCIe Gen3 x4 Intel CH29AE41AB0 20-nm Intel MLC
Mushkin Reactor 1TB SATA 6Gbps Silicon Motion SM2246EN 16-nm Micron MLC
OCZ Arc 100 240GB SATA 6Gbps Indilinx Barefoot 3 M10 A19-nm Toshiba MLC
OCZ Trion 100 480GB SATA 6Gbps Toshiba TC58 A19-nm Toshiba TLC
OCZ Trion 150 480GB SATA 6Gbps Toshiba TC58 15-nm Toshiba TLC
OCZ Vector 180 240GB SATA 6Gbps Indilinx Barefoot 3 M10 A19-nm Toshiba MLC
OCZ Vector 180 960GB SATA 6Gbps Indilinx Barefoot 3 M10 A19-nm Toshiba MLC
Patriot Hellfire 480GB PCIe Gen3 x4 Phison 5007-E7 15-nm Toshiba MLC
Plextor M6e 256GB PCIe Gen2 x2 Marvell 88SS9183 19-nm Toshiba MLC
Samsung 850 EV0 250GB SATA 6Gbps Samsung MGX 32-layer Samsung TLC
Samsung 850 EV0 1TB SATA 6Gbps Samsung MEX 32-layer Samsung TLC
Samsung 850 Pro 512GB SATA 6Gbps Samsung MEX 32-layer Samsung MLC
Samsung 860 Pro 1TB SATA 6Gbps Samsung MJX 64-layer Samsung MLC
Samsung 950 Pro 512GB PCIe Gen3 x4 Samsung UBX 32-layer Samsung MLC
Samsung 960 EVO 250GB PCIe Gen3 x4 Samsung Polaris 32-layer Samsung TLC
Samsung 960 EVO 1TB PCIe Gen3 x4 Samsung Polaris 48-layer Samsung TLC
Samsung 960 Pro 2TB PCIe Gen3 x4 Samsung Polaris 48-layer Samsung MLC
Samsung 970 EVO 1TB PCIe Gen3 x4 Samsung Phoenix 64-layer Samsung TLC
Samsung SM951 512GB PCIe Gen3 x4 Samsung S4LN058A01X01 16-nm Samsung MLC
Samsung XP941 256GB PCIe Gen2 x4 Samsung S4LN053X01 19-nm Samsung MLC
Toshiba OCZ RD400 512GB PCIe Gen3 x4 Toshiba TC58 15-nm Toshiba MLC
Toshiba OCZ VX500 512GB SATA 6Gbps Toshiba TC358790XBG 15-nm Toshiba MLC
Toshiba TR200 480GB SATA 6Gbps Toshiba TC58 64-layer Toshiba BiCS TLC
Toshiba XG5 1TB PCIe Gen3 x4 Toshiba TC58 64-layer Toshiba BiCS TLC
Transcend SSD370 256GB SATA 6Gbps Transcend TS6500 Micron or SanDisk MLC
Transcend SSD370 1TB SATA 6Gbps Transcend TS6500 Micron or SanDisk MLC
Western Digital Black NVMe 1TB PCIe Gen3 x4   64-layer SanDisk BiCS TLC

 

All the SATA SSDs were connected to the motherboard’s Z97 chipset. The M6e was connected to the Z97 via the motherboard’s M.2 slot, which is how we’d expect most folks to run that drive. Since the XP941, 950 Pro, RD400, and 960 Pro require more lanes, they were connected to the CPU via a PCIe adapter card. The 750 Series and DC P3700 were hooked up to the CPU via the same full-sized PCIe slot.

We used the following system for testing:

Processor Intel Core i5-4690K 3.5GHz
Motherboard Asus Z97-Pro
Firmware 2601
Platform hub Intel Z97
Platform drivers Chipset: 10.0.0.13

RST: 13.2.4.1000

Memory size 16GB (2 DIMMs)
Memory type Adata XPG V3 DDR3 at 1600 MT/s
Memory timings 11-11-11-28-1T
Audio Realtek ALC1150 with 6.0.1.7344 drivers
System drive Corsair Force LS 240GB with S8FM07.9 firmware
Storage Crucial BX100 500GB with MU01 firmware

Crucial BX200 480GB with MU01.4 firmware

Crucial MX200 500GB with MU01 firmware

Intel 335 Series 240GB with 335u firmware

Intel 730 Series 480GB with L2010400 firmware

Intel 750 Series 1.2GB with 8EV10171 firmware

Intel DC P3700 800GB with 8DV10043 firmware

Intel X25-M G2 160GB with 8820 firmware

Plextor M6e 256GB with 1.04 firmware

OCZ Trion 100 480GB with 11.2 firmware

OCZ Trion 150 480GB with 12.2 firmware

OCZ Vector 180 240GB with 1.0 firmware

OCZ Vector 180 960GB with 1.0 firmware

Samsung 850 EVO 250GB with EMT01B6Q firmware

Samsung 850 EVO 1TB with EMT01B6Q firmware

Samsung 850 Pro 500GB with EMXM01B6Q firmware

Samsung 950 Pro 512GB with 1B0QBXX7 firmware

Samsung XP941 256GB with UXM6501Q firmware

Transcend SSD370 256GB with O0918B firmware

Transcend SSD370 1TB with O0919A firmware

Power supply Corsair AX650 650W
Case Fractal Design Define R5
Operating system Windows 8.1 Pro x64

Thanks to Asus for providing the systems’ motherboards, to Intel for the CPUs, to Adata for the memory, to Fractal Design for the cases, and to Corsair for the system drives and PSUs. And thanks to the drive makers for supplying the rest of the SSDs.

We used the following versions of our test applications:

Some further notes on our test methods:

  • To ensure consistent and repeatable results, the SSDs were secure-erased before every component of our test suite. For the IOMeter database, RoboBench write, and RoboBench copy tests, the drives were put in a simulated used state that better exposes long-term performance characteristics. Those tests are all scripted, ensuring an even playing field that gives the drives the same amount of time to recover from the initial used state.

  • We run virtually all our tests three times and report the median of the results. Our sustained IOMeter test is run a second time to verify the results of the first test and additional times only if necessary. The sustained test runs for 30 minutes continuously, so it already samples performance over a long period.

  • Steps have been taken to ensure the CPU’s power-saving features don’t taint any of our results. All of the CPU’s low-power states have been disabled, effectively pegging the frequency at 3.5GHz. Transitioning between power states can affect the performance of storage benchmarks, especially when dealing with short burst transfers.

The test systems’ Windows desktop was set at 1920×1080 at 60Hz. Most of the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

 

Conclusions

The WD Black NVMe suffered an asthmatic performance in IOMeter, but its RoboBench performance was phenomenal. Western Digital had its sights set on the 970 EVO, and we expect that the Black’s overall performance will fall fairly close to its rival. We distill the overall performance rating using an older SATA SSD as a baseline. To compare each drive, we then take the geometric mean of a basket of results from our test suite. Only drives which have been through the entire current test suite on our current rig are represented.

Close, but a little short. The 970 EVO suffered its own share of setbacks in IOMeter versus its faultless predecessor, but the WD Black’s shortcomings weighed it down a bit more heavily in the overall rankings. Nonetheless, this is an impressive showing from Western Digital. Samsung is the top dog in this market, and WD has wasted no time in wielding its newly-acquired solid-state prowess to build a platform that can challenge the 800-lb gorilla’s traditional technology advantage.

But does this have any meaning for us small-time hobbyist builders? We have to examine the value proposition first. In the plots below, the most compelling position is toward the upper left corner, where the price per gigabyte is low and performance is high. Use the buttons to switch between views of all drives, only SATA drives, or only PCIe drives.


Despite being announced at $450, the Black NVMe 1 TB is going for $400 at both Newegg and Western Digital’s own website. If Samsung and WD want to play a game of chicken with their prices, all the better for you and me. The $0.40 per gigabyte that the $400 tag represents exactly matches the cost of the 970 EVO 1 TB. That’s a fine price for the sort of performance that these drives deliver. That’s especially true since there’s a dearth of cheaper options in NVMe storage right now. Intel’s 760p 512 GB has a suggested price of $200 even, but street prices are currently hovering around $220. The only NVMe drive in our set currently cheaper than the WD Black or 970 EVO is the Adata SX8200 we just reviewed.

At the end of the day, the WD Black NVMe 1 TB and 970 EVO 1 TB both boast more than enough oomph for the typical enthusiast’s needs. Builders who need better encryption features will gravitate towards the Samsung, while others may value the WD’s absurd file transfer speeds. More than likely, it will come down which drive your favorite retailer is currently running a sale on. Western Digital has built a fine home for 64-layer BiCS 3D flash in its Black NVMe drive, and the  company can proudly call the Black NVMe 1TB TR Recommended.

Comments closed
    • Unknown-Error
    • 1 year ago

    Thank you for the article Mr. Tony Thomas .

    • ptsant
    • 1 year ago

    I remember having asked previously whether anyone noticed a difference going SATA -> NVMe. Until I’m convinced, and since I have a roomy case, I’ll probably stick to SATA to save money.

    Reliability/stress tests would be nice at some point. Maybe a reboot of the torture write test that had taken place a few years ago on NVMe drives…

      • Chrispy_
      • 1 year ago

      As someone who has moved from a very old, early SATA drive to a current-gen NVMe drive – I can confirm that the difference is trivial.

      Reviews all show very little change between low-end TLC-NAND SATA drives and the latest NVMe drives, but I was hoping I’d at least notice [i<]some[/i<] difference coming from such an old drive. As I mentioned below, the difference was nothing. Not only did I not notice the difference upgrading, I also didn't notice any worse performance when I moved back to it a few months later so that I could use the NVMe drive in another machine for VMWare. Consumer workloads are not bottlenecked by storage any more. I think SATA3 is enough for 95% of the permance advantages SSDs can provide, everything else is just willy-waving and marketing hype.

        • Waco
        • 1 year ago

        Yep. Until the desktop IO model changes (to increase queue depth or at least optimize the IO paths) we won’t see many changes in load times or better usability.

        Even running straight off of RAM doesn’t do a whole lot for performance for desktop workloads – the limitation just isn’t in the storage hardware itself.

      • deruberhanyok
      • 1 year ago

      The only time I’ve noticed a difference has been with much older drives that are starting to run down.

      For instance, I’ve got an old Kingston V300 120GB SSD that’s showing about 80% health on it now. I occasionally get the general UI lag when using it that I consider “normal” for a spinning disk. It’s not constant, but it’s there and obvious when it happens.

      Anyways, dying disks aside, I couldn’t tell if an SSD was a SATA type or NVMe type for day to day use. I’ve swapped some around from one system to another while doing the “hardware shuffle” and the difference IMO is immaterial.

      Maybe – and this is a very big maybe – in load times in some games, but we’re talking about a few seconds, nothing like going from several minutes of a spinner to an SSD.

    • Beahmont
    • 1 year ago

    Why Windows 8.1? To be able to use numbers from a greater stable of drives and older tests?

      • Jeff Kampman
      • 1 year ago

      Yes. That said, this is the last review we’ll be running with that setup.

        • Chrispy_
        • 1 year ago

        I hope you have time to run several popular drives on the new test platform just so that TR’s showing plenty of references points.

        I know it’s a lot of work but I also know Tony loves his storage <3

        xx

    • elites2012
    • 1 year ago

    not at that price for me. i could run a 8 drive raid with the 1tb hdd’s for $50 a piece. to each their own!

      • kuraegomon
      • 1 year ago

      And one NVMe SSD would be _significantly_ more responsive than that honking RAID array for things like web browsing or code compilation. Hell, a SATA SSD would likely be more responsive. I’m willing to pay a (small) boatload for responsiveness. To each their own indeed! 😉

      • Waco
      • 1 year ago

      You could run an 8 drive RAID 0 with 128 GB SSDs for the less money. :shrug:

      //totally doesn’t have that in his desktop

      • Spunjji
      • 1 year ago

      Plus the cost of hardware to support that. Say, a much, much larger case and a dedicated RAID card so you’ll actually see a performance benefit without thrashing your CPU.

      In summary, that’s a silly comparison.

      • derFunkenstein
      • 1 year ago

      Perhaps you don’t understand the point of solid-state storage. 8-drive RAID has its place for enormous file storage. Backup to a network appliance, storing files you’ll read sequentially, etc. 1TB SSD is for random access. Boot drives, game libraries, and the like.

    • emorgoch
    • 1 year ago

    Personally, this one ranks above Samsung if only for the fact that Samsung’s warranty support in Canada for SSD’s is spotty at best right now.

    • Chrispy_
    • 1 year ago

    Sorry, I skipped straight to [url=https://techreport.com/review/33707/western-digital-black-1-tb-nvme-ssd-reviewed/5<]this page[/url<], and then didn't bother reading anything else. Consumer storage is so dull these days.

      • cmrcmk
      • 1 year ago

      You’re right, it’s bizarre that key performance metrics can be so hugely different when real world performance is indistinguishable. Is it just that software isn’t making the most of these resources or is there another bottleneck we’re not testing?

        • Stochastic
        • 1 year ago

        I would love it if TR did an in-depth investigation on what affects boot and load times in modern software. What’s the bottleneck for game load times? CPU? GPU? RAM? Something else?

          • Chrispy_
          • 1 year ago

          I suspect it’s CPU/software decompression bottlenecks for most things, and potentially a case of wait timers for things like application startup and OS boot time.

          I would love a definitive answer but in the grand scheme of things all SSDs are equal for consumer workloads. Using an NVMe drive might be worth the spend if you’re looking for a scratch disk to use with raw 4K or 8K video footage, but that’s well outside the realm of normal consumer use, other than just doing it for the heck of it – and already into expensive production software that puts it into professional territory.

      • Goty
      • 1 year ago

      The issue with focusing on load times is that you miss where all of the improvements have been happening, which is in random read/write operations, which I would argue probably affect your day to day experience more than sequential throughput.

      The most important thing I think people should look for is read/write performance (especially mixed I/O) at low queue depth, which is one of the things that I think it most representative of the sort of workload a drive will encounter in the typical users’s PC.

        • Chrispy_
        • 1 year ago

        I’m not expecting you to stalk my posts, but I’ve been campaigning for improved 4K QD1 performance for years.

        It’s a metaphorical drum I’ve stopped banging recently though – because even when 4K QD1 performance increases by several orders of magnitude (Optane), nothing really changes, and that was borne out when I stumbled across an opportunity to replace an old Sandforce drive with an Enterprise NVMe Samsung (Samsung 960 Pro equivalent). Zero real-world improvement :\

          • albundy
          • 1 year ago

          I’ve also been searching for the best 4KQD1 nvme drives at the best possible price, but I am glad I read your post. It seems the only real performance gains are transferring from one nvme to another nvme, or extracting a 10GB WinRAR file, or installing a 100GB game stored on another nvme drive, which generally take from 30 min to an hour if the game is stored on an HDD.
          I received a 1TB HP EX920 last week that I picked up for $250. Hopefully it will do for a number of years. It has excellent 4KQD1 performance that was compared to the EVO, but I just don’t notice it.

      • Takeshi7
      • 1 year ago

      I’ve been saying this ever since it became clear that the old VX500 SATA SSD was spanking the Intel 750 beast at load times. They need to move the loading time tests from SSD reviews into CPU reviews.

        • Chrispy_
        • 1 year ago

        That’s actually a pretty good suggestion, though I wouldn’t be surprised if that just told us that neither storage [i<]nor CPU[/i<] performance was the limiting factor, and it's just dumb code that's holding everything up. Still, +1 for scientific method.

    • dragontamer5788
    • 1 year ago

    [quote<]The naming scheme may not be crystal clear, so let's break it down. The older Black is 2017's "Black PCIe SSD." It came in 256-GB and 512-GB capacities and was intended to be a low-cost entry point into NVMe PCIe drives. This year's Black drive is the "Black NVMe SSD."[/quote<] I hate WD so much right now, but thanks for the clarification.

      • Goty
      • 1 year ago

      The clarification is that this drive is not actually called the “Western Digital Black”, it’s called the “Western Digital [b<]WD[/b<] Black." Says it right on the sticker.

        • albundy
        • 1 year ago

        i thought the first one with the blue pcb also said WD Black?

Pin It on Pinterest

Share This