Samsung’s 850 EVO has reigned supreme in the SATA SSD market for a long time. It earned our recommendation when it launched all the way back in 2014 and has been the 800-pound gorilla of client SSDs ever since. Samsung was the first to produce a non-planar TLC NAND drive, and the 850 EVO’s success has affected the shape of the entire SSD market since. Pick up a random SSD and peer inside, and the odds are high that you’ll find 3D TLC NAND of some kind staring back at you.
Non-planar NAND technologies–whether “3D,” “BiCS,” or “V-NAND”–have become the de facto standard for mainstream solid-state storage. And that’s not likely to change soon, unless more exotic technologies coalesce from the vapor. The only credible threat comes from quad-level-cell NAND. For now, QLC products seem to be targeted towards enterprise-y “write once, read many” workloads, where the technology’s inevitably poorer write performance and endurance can go unnoticed. But perhaps it’s only a matter of time before some plucky manufacturer decides that the cost savings outweigh the potential consumer backlash and forces it into the client space. I expect much wailing and gnashing of teeth in the comments when it happens, so start composing your diatribes today.
Anyway, the name of the game is still non-planar TLC for now, and as we discussed in our 860 Pro review, Samsung has spent the last few years making generational refinements to its V-NAND. Meet the 860 EVO and the 64 layers of TLC V-NAND goodness in each of its flash packages.
|Samsung 860 EVO|
|Capacity||Max sequential (MB/s)||Max random (IOps)|
Now, this drive has been out for most of this year, but the one-two punch of short initial review sample supply and our recently-finished efforts to modernize our test rig knocked this write-up pretty far down the stretch. Our apologies for the delay. Samsung hooked us up with the 1-TB version of the drive, which turns out to be the middle child. The lineup includes the standard 250 GB and 500 GB capacities, and gargantuan 2-TB and 4-TB variants are also available. The 850 EVO series also got 2-TB and 4-TB flavors, but not until well after that drive launched.
The difference between the 860 EVO and Pro, as usual, is TLC V-NAND instead of MLC. Theoretically, that should mean reduced performance, but Samsung’s Intelligent TurboWrite caching scheme will ensure that the EVO operates at near-SATA-6-Gbps limits for most workloads in spite of its extra-bit-per-cell handicap.
Once its shell is shucked, the 860 EVO 1 TB looks almost comically small. Samsung crams all that TLC V-NAND into only two packages: one on either side of the tiny PCB. One of those packages shares elbow room with 1 GB of LPDDR4 RAM and the same MJX controller used in the 860 Pro.
Much like the 860 Pro, the 860 EVO is chock-full of helpful encryption capabilities and comes with a five-year warranty. Unlike the Pro 1 TB, however, the EVO 1 TB gets an endurance rating of 600 TBW, merely half of its higher-end sibling’s 1200-TBW specification. That’s still more than enough headroom to satisfy any ordinary usage.
Samsung’s suggested price at launch was $330 for the 1 TB version, but we’re currently experiencing something of a renaissance for cheap SSDs. The drive is available for $218 at Amazon, marked down a third from Samsung’s projected ask. If the drive’s speeds are anything like the 850 EVO’s, that will make for some incredible performance per dollar. Let’s see how the new guy stands up to our test suite.
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.
All’s well so far. The 860 EVO reads a hair faster than its predecessor. It also writes slightly faster at QD1, but the 850 EVO makes an appreciable gain at QD4 while the 860 EVO gains almost nothing.
Random read response times are close to dead even between the two EVOs. The 860’s random writes, however, are quite a bit snappier at QD4.
It’s more a less a wash between the two generations of EVO series drives so far. But that’s by no means a bad thing–there’s not much ground left to gain for SATA drives. Let’s see how the 860 EVO does in our sustained and scaling tests.
Sustained and scaling I/O rates
Our sustained IOMeter test hammers drives with 4-KB 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.
The two EVOs’ peak and steady-state write rates are very nearly identical, but it looks like the 860 EVO holds onto its maximum for substantially longer. The 850 EVO ramps down sometime after 150 seconds have passed, while the 860 EVO chugs along for an additional 100 seconds before declining.
As suspected, the drives are neck and neck for throughput, but the 860 EVO’s longer high-performance burst is a pleasing upgrade.
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 drive in a simulated used state. Click the buttons below the graph to switch between the different drives. Note that each drive uses a different scale for IOPS to allow us to view the shape of its curves.
The 860 EVO’s performance ramps up quickly, nearing maximum speeds even at QD4. The 850 EVO scaled more slowly, only approaching its maximum at QD16. Let’s look at the drives plotted against each other.
The curves lose some of the their impact when the graph is adjusted to fit the 970 EVO’s NVMe-endowed scaling prowess, but both of the lesser EVOs exhibit noticeable scaling for AHCI drives. The 860 EVO’s throughput more than doubles from QD1 to QD4.
The 860 EVO continues to come out slightly ahead of its forebear, which bodes well for its place in our overall rankings. Now it’s time to put aside IOMeter and transition into real-world testing.
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|
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.
It’s close to even between the 850 EVO and 860 EVO in the media set. The write tests offer the most differentiation, but unfortunately it’s in favor of the older drive. We’re talking a 5-8% difference though, so it’s not a big deal. Maybe the work set will change the outlook.
This time we can call it a tie. The two drives trade blows across read, write, and copy tests.
Overall, the 850 EVO and 860 EVO behave largely the same in RoboBench, as they did with IOMeter. But if it ain’t broke, don’t fix it. Our last page of tests will see how it fares when it’s expected to load up an operating system.
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—automatically from the startup folder. These tests cover the entire boot process, including drive initialization.
The 860 EVO will have you booted up before you’ve finished putting your face on for Windows Hello. Of course, so will the 850 EVO.
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 Microsoft’s PowerShell.
Load times for the first three programs are recorded using PassMark AppTimer. AppTimer’s load completion detection doesn’t play nice with Visual Studio, so we’re still using a stopwatch for that one.
Yet again, the two EVO drives yield remarkably similar results. Visual Studio is more than half a second kinder to the newer drive, though.
If you can’t spare the 0.3-or-less extra seconds it takes the 860 EVO to load games, you better stick with the 850 EVO. Either drive will serve your Steam library well.
That’s all of our tests. The 860 EVO gave us no surprises while serving as a boot drive. Our test methods are on the next page, and our conclusions on the following.
Test notes and methods
Here are the essential details for all the drives we tested:
|Adata XPG SX8200 480GB||PCIe Gen3 x4||Silicon Motion SM2262||64-layer Micron 3D TLC|
|Crucial MX500 500GB||SATA 6Gbps||Silicon Motion SM2258||64-layer Micron 3D TLC|
|Intel X25-M G2 160GB||SATA 3Gbps||Intel PC29AS21BA0||34-nm Intel MLC|
|Samsung 850 EVO 1TB||SATA 6Gbps||Samsung MEX||32-layer Samsung TLC|
|Samsung 860 EVO 1TB||SATA 6Gbps||Samsung MJX||64-layer Samsung TLC|
|Samsung 970 EVO 1TB||PCIe Gen3 x4||Samsung Phoenix||64-layer Samsung TLC|
|Toshiba RC100||PCIe Gen3 x2||Toshiba||64-layer Toshiba BiCS TLC|
The SATA SSDs were connected to the motherboard’s Z270 chipset. The PCIe drives were connected via one of the motherboard’s M.2 slots, which also draw their lanes from the Z270 chipset.
We used the following system for testing:
|Processor||Intel Core i7-6700K|
|Motherboard||Gigabyte Aorus Z270X-Gaming 5|
|Memory size||16 GB (2 DIMMs)|
|Memory type||Corsair Vengeance LPX DDR4 at 2133 MT/s|
|System drive||Corsair Force LS 240GB with S8FM07.9 firmware|
|Power supply||Rosewill Fortress 550 W|
|Operating system||Windows 10 x64 1803|
Thanks to Gigabyte for providing the system’s motherboard, to Intel for the CPU, to Corsair for the memory and system drive, and to Rosewill for the PSU. And thanks to the drive makers for supplying the rest of the SSDs.
We used the following versions of our test applications:
- IOMeter 1.1.0 x64
- TR RoboBench 0.2a
- Passmark AppTimer 1.0
- Avidemux 2.7.1 x64
- GIMP 2.10.0
- LibreOffice 188.8.131.52
- Visual Studio Community 2017 15.7.4
- Batman: Arkham Origins
- Tomb Raider
- Middle Earth: Shadow of Mordor
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 4.0 GHz. 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 1920×1200 at 60 Hz. 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.
The 860 EVO 1 TB gave us the solid mainstream performance we’ve come to expect out of Samsung’s EVO line. 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.
The 860 EVO 1 TB is the fastest SATA drive thus far in our burgeoning new test set. As with the 860 Pro, Samsung’s goal for the 860 EVO was to transition its mainstream products onto its latest mass-produced NAND technologies without introducing performance regressions. Clearly, the firm has done so with resounding success.
The intro had some spoilers for this next part, so you may already suspect how the 860 EVO 1 TB will fall on our value scatter plot. In the graph below, the most compelling position is toward the upper left corner, where the price per gigabyte is low and performance is high.
A terabyte of solid-state storage just doesn’t yield a retailer as many dollars as it used to. It’s a great time to buy an SSD in any market segment. Amazon’s $218 price tag for the 860 EVO translates to a tempting 22 cents per gigabyte. I remember buying an 850 EVO 500 GB for $150 some years ago (or 30 cents per gig) and thinking it was a steal. $0.22 per gig is a price that until recently was reserved for truly bargain-basement drives with shorter warranties, lower performance, and no encryption features.
The 860 EVO would likely have gotten our recommendation even without today’s pricing moves in play, but right now it’s really a no-brainer. Though the novelty has faded from the technologies the drive is built on, the 860 EVO still offers a winning blend of strong performance, high endurance, and quality-of-life features like 256-bit hardware encryption acceleration in its controller. The only thing that might hold a prospective buyer back is the call of cheaper NVMe drives like Adata’s SX8200. But if you’ve been on the prowl for a meaty chunk of SATA space, the time is ripe. You can’t go wrong with an 860 EVO 1 TB.