In a lot of ways, Serial ATA SSDs have stagnated recently. Most new drives are just slightly different spins on their predecessors. They have similar controllers, lightly massaged firmware, and flash fabbed on finer fabrication processes. And different stickers on the outside. Can’t forget the stickers.
We don’t get big leaps in performance anymore, though. The limited bandwidth of the 6Gbps SATA interface is partly to blame, as are the inefficiencies of the associated AHCI protocol. Even with those handicaps, most decent drives are already fast enough for the vast majority of desktop applications.
None of that makes for a compelling storyline. There’s one more thing, however, and it’s a pretty big deal. SSDs are getting cheaper. Like, a lot cheaper. Just look at the release-day prices for the last four generations of Crucial drives:
Crucial’s first 6Gbps SATA offering was the RealSSD C300, which arrived in 2010 with 34-nm flash. The drive rang in at over $600 for 256GB, making it an expensive luxury even for high-end PCs. Since then, each successive NAND generation has come with a substantial discount, culminating in the 16-nm MX100 that debuts today. Crucial’s latest is priced at just $109.99 for 256GB.
Let me repeat that. The MX100 is priced at just $109.99 for 256GB.
That’s only $0.43 per gig, more than a 5X decrease from the C300—and a 50% drop from the M500’s introductory sticker one year ago. Quite the opposite of stagnation, don’t you think?
Crucial’s parent company, Micron, deserves much of the credit for plummeting prices. SSDs are getting cheaper because memory makers are using smaller process geometries to cram more and more gigabytes onto each silicon wafer. Micron aggressively pursues cutting-edge fabrication technologies, and Crucial enjoys the spoils.
The MX100 is the first SSD to use Micron’s 16-nm MLC NAND. 16GB chips based on that process have been sampling since last year, and Micron claims they have “the greatest number of bits per square millimeter at the lowest cost of any MLC device in existence.” We’re waiting on details about the exact die dimensions and how they compare to the previous generation. For what it’s worth, Micron says its 16-nm process is capable of squeezing “nearly 6TB” onto a single wafer.
Although smaller fabrication techniques are great for increasing bit densities, shrinking the process geometry typically decreases endurance. NAND wears out because writing data erodes the physical structure of the memory cells. That structure becomes more fragile as it shrinks, reducing the volume of writes the cell can tolerate. Packing cells closer together also increases the potential for interference from neighboring cells.
Micron isn’t ready to talk about how many program-erase cycles its 16-nm NAND can endure. However, most desktop users will struggle to exceed the MX100’s endurance specification. The drive is rated for 72TB of total writes, which works out to 40GB per day for five years. That rating matches the endurance spec for Crucial’s M500 and M550 SSDs, both of which are based on 20-nm NAND. The MX100 has the same three-year warranty as those drives, too. Here’s how the three families compare:
|NAND||20nm MLC||16/20nm MLC||20nm MLC|
|Controller||Marvell 88SS9187||Marvell 88SS9189||Marvell 88SS9189|
|Random read||62-80k IOps||80-90k IOps||90-95k IOps|
|Random write||35-80k IOps||40-85k IOps||75-85k IOps|
|Warranty||Three years||Three years||Three years|
The MX100 is essentially a replacement for the M500. It promises to outperform its predecessor at a lower cost, but there are a few caveats, including the fact that the M500 is much cheaper today than it was last year.
While the M500 is available in capacities up to 960GB, the MX100 is capped at 512GB. Folks who want more storage are directed to the higher-end M550, which goes up to 1TB, and to the M500 960GB, which hasn’t been retired yet. It sounds like Crucial plans to keep the big M500 around for a little while longer.
At the other end of the spectrum, we should note that the MX100 128GB actually uses older 20-nm NAND. Only the 256GB and 512GB versions have the latest 16-nm flash.
All three drives are loaded with 16GB dies, which is a liability for the lower-capacity models. Modern controllers typically require at least 32 dies for peak performance. With 16GB per die, all the MX100s south of 512GB lacks sufficient NAND to exploit controller’s internal parallelism. The 128GB and 256GB drives have lower performance ratings as a result.
4KB random (IOps)
Dropping to 256GB cuts the MX100’s peak sequential write speed to 330MB/s. The 128GB variant is even slower, and it takes a big hit on random writes. The entry-level unit has higher per-gigabyte pricing than the rest of the lineup, too. No wonder Crucial only sent us the 256GB and 512GB drives. We’ve benched them both, and we’ll see how they stack up in a moment.
The 512GB version is just as competitively-priced as its 256GB sibling, by the way. $224.99 is the lowest list price we’ve ever seen for a 512GB SSD.
Inside and out, the MX100 looks an awful lot like the M550. It has the same eight-channel Marvell controller and nearly identical features. To protect against data loss from physical flash failures, the MX100 employs a RAID-like redundancy scheme called RAIN. Onboard capacitors provide a measure of power-loss protection, enabling the drive to preserve in-flight data if the lights go out. There’s hardware support for 256-bit AES encryption, too, complete with the requisite IEEE and TCG Opal compliance. The MX100 can also dial back its performance if temperatures get too toasty, a valuable capability for notebooks and small-form-factor systems.
The only thing that isn’t on the menu is DevSleep, an extra-low-power mode designed for mobile systems. According to Crucial, the MX100 will respond to the command, and the feature is supported in the firmware. However, because Crucial hasn’t seen a lot of demand for it, DevSleep isn’t part of the drive’s official specification.
DevSleep is geared toward mobile systems, which aren’t really the MX100’s native turf. Sure, the drive will fit into standard 2.5″ notebook bays, but Crucial isn’t making mSATA or M.2 flavors suitable for slimmer ultrabooks, convertibles, and the like. Instead of cranking out mini MX100s, Crucial will continue selling mSATA and M.2 versions of the M500. The M550 is also available in mini formats.
Overall, the MX100 covers all the essentials except utility software. Unlike most SSD vendors, Crucial doesn’t offer an application to monitor health, optimize system settings, and track drive statistics. The firm makes matters worse by giving many of the drive’s SMART attributes vague, vendor-specific titles that can only be deciphered with the aid of a separate decoder ring. The reallocated sector count is clearly marked, at least, but program and erase failures, error correction and RAIN recovery events, and total host writes are not. If Crucial isn’t going to provide its own SSD utility software, it should at least stop making life difficult those monitoring their drives with third-party utilities.
Crucial redeems itself somewhat by shipping the MX100 with a download code for Acronis True Image HD 2014. The imaging software should come in handy for folks upgrading existing systems.
Now, let’s see how the MX100 performs.
CrystalDiskMark — transfer rates
TR regulars will notice that we’ve trimmed a few tests from our usual suite of storage results. The drives were all benchmarked in the same way, but we’ve excluded the results for tests that have grown problematic or less relevant over time. This abbreviated format should be a little easier to digest until our next-gen storage suite is ready.
First, we’ll tackle sequential performance with CrystalDiskMark. This test runs on partitioned drives with the benchmark’s default 1GB transfer size and randomized data. We’ve color-coded the results to make the Crucial drives easier to spot.
Most of the SSDs are closely matched in the sequential read speed test. There, the MX100 keeps up with the M550 and sits roughly in the middle of the pack overall.
The 512GB version hangs with its M550 counterpart in the write speed test, too, but the 256GB drive is 155MB/s slower. Blame the 16GB NAND dies. The M550 256GB uses smaller 8GB dies, giving it twice the parallelism of the equivalent MX100—and none of the performance penalty, at least in this test.
HD Tune — random access times
Next, we’ll turn our attention to random access times. We used HD Tune to measure access times across multiple transfer sizes. SSDs have near-instantaneous seek times, so it’s hard to graph the results on the same scale as mechanical drives. The WD Black and Seagate SSHD will sit out this round to focus our attention on the SSDs.
First, note the scales. The 1MB access times are measured in single-digit milliseconds, while the 4KB results are in the tens of microseconds. SSDs are really, really good at this sort of thing.
The MX100 doesn’t exhibit any signs of weakness in the random read tests. However, the 256GB version struggles with 1MB random writes. It’s notably slower than the 512GB variant, though it’s still quicker than the equivalent M500.
TR FileBench — Real-world copy speeds
FileBench, which was concocted by TR’s resident developer Bruno “morphine” Ferreira, runs through a series of file copy operations using Windows 7’s xcopy command. Using xcopy produces nearly identical copy speeds to dragging and dropping files using the Windows GUI, so our results should be representative of typical real-world performance. We tested using the following five file sets—note the differences in average file sizes and their compressibility. We evaluated the compressibility of each file set by comparing its size before and after being run through 7-Zip’s “ultra” compression scheme.
|Number of files||Average file size||Total size||Compressibility|
The names of most of the file sets are self-explanatory. The Mozilla set is made up of all the files necessary to compile the browser, while the TR set includes years worth of the images, HTML files, and spreadsheets behind my reviews. Those two sets contain much larger numbers of smaller files than the other three. They’re also the most amenable to compression.
To get a sense of how aggressively each SSD reclaims flash pages tagged by the TRIM command, the SSDs are tested in a simulated used state after crunching IOMeter’s workstation access pattern for 30 minutes. The drives are also tested in a factory fresh state, right after a secure erase, to see if there is any discrepancy between the two states. There wasn’t much of one with the MX100, so we’re only presenting the used-state scores.
Noticing a pattern yet? The MX100 512GB shadows its M550 competition once again. The 256GB version is slower, but it still beats the M500 240GB handily.
Interestingly, the lower-capacity drives don’t suffer as much in the TR and Mozilla tests, which are loaded with smaller files and have comparatively sluggish copy speeds. The differences between them and the larger SSDs are more pronounced in the other tests, in which larger movie, image, and music files are copied at much faster rates.
TR DriveBench 2.0 — Disk-intensive multitasking
DriveBench 2.0 is a trace-based test comprised of nearly two weeks of typical desktop activity peppered with intense multitasking loads. More details on are available on this page of our last major SSD round-up.
We measure DriveBench performance by analyzing service times—the amount of time it takes drives to complete I/O requests. Those results are split into reads and writes.
The MX100 512GB continues to upstage the pricier M550. Both sit just adrift of the front of the pack, well ahead of their 256GB counterparts.
Even the MX100 256GB is competitive with the equivalent M550, and it actually comes out ahead with reads. These lower-capacity units still have slower mean service times than the 512GB drives, though. They’re particularly far behind with writes, and they’re also not alone. The budget-priced Samsung 840 EVO 250GB and Crucial M500 240GB have even slower mean write service times.
All the SSDs execute the vast majority of DriveBench requests in one millisecond or less—too little time for end users to perceive. We can also sort out the number of service times longer than 100 milliseconds, which is far more interesting data. These extremely long service times make up only a fraction of the overall total, but they’re much more likely to be noticeable.
Crucial SSDs typically log more extremely long write service times than their peers in this test. The MX100 is a big improvement over the M500, but it still suffers way more sluggish write service times than SSDs from other vendors. (The Adata SP920 is just an M550 with a different sticker on the outside.)
At 512GB, the MX100 comes out ahead of the M550 with both reads and writes. The 256GB results are mixed; the MX100 exhibits fewer extremely long service times with reads, but it suffers more of them with writes.
DriveBench 2.0 comprises tens of millions of I/O requests, so don’t read too much into the totals in the graphs. For the MX100 256GB, the number of service times over 100 milliseconds amounts to only 0.037% of read requests and 0.32% of writes.
Our IOMeter workload features a ramping number of concurrent I/O requests. Most desktop systems will only have a few requests in flight at any given time (87% of DriveBench 2.0 requests have a queue depth of four or less). We’ve extended our scaling up to 32 concurrent requests to reach the depth of the Native Command Queuing pipeline associated with the Serial ATA specification. Ramping up the number of requests also gives us a sense of how the drives might perform in more demanding enterprise environments.
We run our IOMeter test using the fully randomized data pattern, which presents a particular challenge for SandForce’s write compression scheme. We’d rather measure SSD performance in this worst-case scenario than using easily compressible data.
There’s too much data to show clearly on a single graph, so we’ve split the results. You can compare the performance of the Crucial MX100 to that of the competition by clicking the buttons below each graph.
Instead of presenting the results of multiple access patterns, we’re concentrating on IOMeter’s database test. This access pattern has a mix of read and write requests, and it’s similar to the file server and workstation tests. The results for these three access patterns are usually pretty similar. We also run IOMeter’s web server access pattern as part of our standard suite of tests, but it’s made up exclusively of read requests, so the results aren’t as applicable to real-world scenarios. Our own web servers log a fair amount of writes, for example.
A few of the SSDs ramp up their I/O rates aggressively as the load increases. The MX100 scales at a more leisurely pace, and it starts to plateau after eight concurrent requests. Still, the drive manages higher throughput than most of its peers, including the Samsung SSDs. It effectively ties the M550, too.
Before timing a couple of real-world applications, we first have to load the OS. We can measure how long that takes by checking the Windows 7 boot duration using the operating system’s performance-monitoring tools. This is actually the first test in which we’re booting Windows off each drive; up until this point, our testing has been hosted by an OS housed on a separate system drive.
Level load times
Modern games lack built-in timing tests to measure level loads, so we busted out a stopwatch with a couple of titles.
The key takeaway here is that all the SSDs are pretty close to each other. The gaps between the solid-state and mechanical drives are much larger than the deltas between the SSDs.
In a bit of a surprise, the MX100 256GB loads Windows about a second faster than the 512GB. The difference between eight and nine seconds is difficult to discern, though, especially for a task typically performed no more than once per day.
We’re working on an updated batch of load-time tests for our next-gen storage suite. Shoot me an email if you have any suggestions.
We tested power consumption under load with IOMeter’s workstation access pattern chewing through 32 concurrent I/O requests. Idle power consumption was probed one minute after processing Windows 7’s idle tasks on an empty desktop.
The MX100’s power consumption is pretty average overall. Nothing to see here, folks.
That’s it for performance testing. The next page is filled with nerdy details about our test systems and methods. It contains loads of information for folks who are curious about how we do things here at TR, but it doesn’t make for particularly engaging reading. We won’t be offended if you skip ahead to the conclusion.
Test notes and methods
Here’s a full rundown of the SSDs we tested, along with their essential characteristics.
|Adata SP920 512GB||512MB||Marvell 88SS9189||20nm Micron sync MLC|
|Corsair Force Series GT
|NA||SandForce SF-2281||25nm Intel sync MLC|
|Corsair Neutron 240GB||256MB||LAMD LM87800||25nm Micron sync MLC|
|Corsair Neutron GTX
|256MB||LAMD LM87800||26nm Toshiba Toggle MLC|
|Crucial M500 240GB||256MB||Marvell 88SS9187||20nm Micron sync MLC|
|Crucial M500 480GB||512MB||Marvell 88SS9187||20nm Micron sync MLC|
|Crucial M500 960GB||1GB||Marvell 88SS9187||20nm Micron sync MLC|
|Crucial M550 256GB||256MB||Marvell 88SS9189||20nm Micron sync MLC|
|Crucial M550 512GB||512MB||Marvell 88SS9189||20nm Micron sync MLC|
|Crucial M550 1TB||1GB||Marvell 88SS9189||20nm Micron sync MLC|
|Crucial MX100 256GB||256MB||Marvell 88SS9189||16nm Micron sync MLC|
|Crucial MX100 512GB||512MB||Marvell 88SS9189||16nm Micron sync MLC|
|Intel 335 Series 240GB||NA||SandForce SF-2281||20nm Intel sync MLC|
|Intel 520 Series 240GB||NA||SandForce SF-2281||25nm Intel sync MLC|
|Intel 730 Series 480GB||1GB||Intel PC29AS21CA0||20nm Intel sync MLC|
|OCZ Vertex 4 256GB||512MB||Indilinx Everest 2||25nm Micron sync MLC|
|OCZ Vertex 450 256GB||512MB||Indilinx Barefoot 3 M10||20nm Intel sync MLC|
|SanDisk Extreme II 240GB||256MB||Marvell 88SS9187||19nm SanDisk Toggle SLC/MLC|
|Samsung 840 Series 250GB||512MB||Samsung MDX||21nm Samsung Toggle TLC|
|Samsung 840 EVO 250GB||256MB||Samsung MEX||19nm Samsung Toggle TLC|
|Samsung 840 EVO 500GB||512MB||Samsung MEX||19nm Samsung Toggle TLC|
|Samsung 840 EVO 1TB||1GB||Samsung MEX||19nm Samsung Toggle TLC|
|Samsung 840 Pro 256GB||512MB||Samsung MDX||21nm Samsung Toggle MLC|
|Seagate 600 SSD 240GB||256MB||LAMD LM87800||19nm Toshiba Toggle MLC|
|Seagate Desktop SSHD 2TB||64MB||NA||24nm Toshiba Toggle SLC/MLC|
|WD Caviar Black 1TB||64MB||NA||NA|
Our main body of results contains some of the most popular SSDs around. The bulk of the field is in the 240-256GB range, and most of those drives have 32-die configurations with no performance handicaps. For the Crucial M500, M550, MX100, and Samsung 840 EVO, whose lower-capacity flavors are tagged with slower specs, we have results for multiple capacities, including the fastest models. You can find full reviews of most of the drives in our storage section.
The solid-state crowd is augmented by a couple of mechanical drives. WD’s Caviar Black 1TB represents the old-school hard drive camp. Seagate’s Desktop SSHD 2TB is along for the ride, as well. The SSHD combines mechanical platters with 8GB of flash cache, but like the Caviar Black, it’s really not a direct competitor to the SSDs. The mechanical and hybrid drives are meant to provide additional context for our SSD results.
We used the following system configuration for testing:
|Processor||Intel Core i5-2500K 3.3GHz|
|CPU cooler||Thermaltake Frio|
|Motherboard||Asus P8P67 Deluxe|
|Platform hub||Intel P67 Express|
|Platform drivers||INF update 184.108.40.2060
|Memory size||8GB (2 DIMMs)|
|Memory type||Corsair Vengeance DDR3 SDRAM at 1333MHz|
|Audio||Realtek ALC892 with 2.62 drivers|
|Graphics||Asus EAH6670/DIS/1GD5 1GB with Catalyst 11.7 drivers|
|Hard drives||Seagate Desktop SSHD 2TB with CC43 firmware
WD Caviar Black 1TB with 05.01D05 firmware
Corsair Force Series GT 240GB with 1.3.2 firmware
Corsair Neutron 240GB with M206 firmware
Corsair Neutron GTX 240GB with M206 firmware
Crucial MX100 256GB with MU01 firmware
Crucial MX100 512GB with MU01 firmware
Crucial M500 240GB with MU03 firmware
Crucial M500 480GB with MU03 firmware
Crucial M500 960GB with MU03 firmware
Crucial M550 256GB with MU01 firmware
Crucial M550 1TB with MU01 firmware
Intel 335 Series 240GB with 335s firmware
Intel 520 Series 240GB with 400i firmware
Intel 730 Series 480GB with XXX firmware
OCZ Vector 150 256GB with 1.1 firmware
OCZ Vertex 450 256GB with 1.0 firmware
SanDisk Extreme II 240GB with R1131
Samsung 830 Series 256GB with CXM03B1Q firmware
Samsung 840 Series 250GB with DXT07B0Q firmware
Samsung 840 EVO 250GB with EXT0AB0Q firmware
Samsung 840 EVO 500GB with EXT0AB0Q firmware
Samsung 840 EVO 1TB with EXT0AB0Q firmware
Samsung 840 Pro Series 256GB with DXM04B0Q firmware
Seagate 600 SSD 240GB with B660 firmware
|Power supply||Corsair Professional Series Gold AX650W|
|OS||Windows 7 Ultimate x64|
Thanks to Asus for providing the systems’ motherboards and graphics cards, Intel for the CPUs, Corsair for the memory and PSUs, Thermaltake for the CPU coolers, and Western Digital for the Caviar Black 1TB system drives.
We used the following versions of our test applications:
- Intel IOMeter 1.1.0 RC1
- HD Tune 4.61
- TR DriveBench 1.0
- TR DriveBench 2.0
- TR FileBench 0.2
- Qt SDK 2010.05
- MinGW GCC 4.4.0
- Duke Nukem Forever
- Portal 2
Some further notes on our test methods:
- To ensure consistent and repeatable results, the SSDs were secure-erased before almost every component of our test suite. Some of our tests then put the SSDs into a used state before the workload begins, which better exposes each drive’s long-term performance characteristics. In other tests, like DriveBench and FileBench, we induce a used state before testing. In all cases, the SSDs were in the same state before each test, ensuring an even playing field. The performance of mechanical hard drives is much more consistent between factory fresh and used states, so we skipped wiping the HDDs before each test—mechanical drives take forever to secure erase.
- We run all our tests at least three times and report the median of the results. We’ve found IOMeter performance can fall off with SSDs after the first couple of runs, so we use five runs for solid-state drives and throw out the first two.
- Steps have been taken to ensure that Sandy Bridge’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 2500K at 3.3GHz. Transitioning in and out of different power states can affect the performance of storage benchmarks, especially when dealing with short burst transfers.
The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at a 75Hz screen refresh rate. 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.
Before we weigh in with our final verdict, we’ll bust out a few of our famous value scatter plots. These plots use an overall performance score derived by comparing how each drive stacks up against a common baseline. This score is based on a subset of the performance data from our full suite, but with CrystalDiskMark’s sequential transfer rates substituted for older HD Tune scores. (More details about how we calculate overall performance are available here.)
We’ve mashed up the overall scores with per-gigabyte prices from Newegg. (Crucial’s suggested retail prices were used for the MX100, since it’s not selling online as I write this.) The best solutions will gravitate toward the upper left corner of the plot, which signifies high performance and low prices.
Solid-state and mechanical storage have vastly different performance and prices, and those disparities make the main plot a little busy. Click the buttons below the plot to switch between all the drives and a cropped look at just the SSDs—and keep in mind that we’ve trimmed the axes for the SSD-only plot.
The MX100s have lower per-gigabyte prices than all the other SSDs. The 256GB version doesn’t score especially well in our overall performance metric, but it’s definitely faster than the equivalent M500, and it’s a fair bit cheaper than the M550. Samsung’s 840 EVO 250GB is perhaps the most appropriate competition outside Crucial’s stable. That drive is faster overall, but it’s pricier, too.
Most of the top SSDs are clustered in a relatively narrow performance band. The MX100 512GB is fast enough to keep up with that group, and its low cost per gig lands the drive in a particularly enviable position on our plots. The budget-oriented drive nearly matches the overall performance of its pricier M550 counterpart, which will probably make for some uncomfortable family gatherings. We’re not complaining, though. Agressive pricing is a big part of the MX100’s appeal.
Now, the MX100 still has some issues. The lack of utility software is disappointing, especially for a product that targets upgraders and everyday consumers. Even seasoned enthusiasts are likely to be frustrated by Crucial’s propensity to obscure vital SSD statistics.
Also, the use of 16GB NAND dies compromises performance on the 256GB model. Even the 512GB struggles in some scenarios, so power users running storage-intensive applications should probably give the MX100 a pass. That said, the drive is speedy enough for typical desktop work, and even the 256GB version is a huge improvement over old-school hard drives.
In fact, the MX100 256GB might be the most compelling SSD for those seeking to free themselves from the shackles of mechanical storage. At $109.99 online, it’s easily affordable even for budget-minded builds. And, with 256GB of storage, there’s plenty of room for an operating system, applications, and a decent number of games. Throw in power-loss protection, AES encryption, and Crucial’s strong reliability reputation, and the MX100 looks like the budget SSD to beat.
While the 256GB version is good enough for our TR Recommended award, its 512GB sibling deserves Editor’s Choice distinction. That drive avoids some of the performance pitfalls associated with the smaller version, but it’s just as cheap per gig. The $224.99 asking price is about what SSD vendors were charging for 256GB drives last year, which is a pretty sweet deal.
For a while, we’ve been recommending that folks purchase the biggest SSD they can afford from a reputable vendor. It’s better to have more solid-state storage than a slightly faster SSD, we think, and the MX100 fits that focus perfectly.