The democratization of SSDs has been an exciting trend to watch. Over the past few years, prices have tumbled dramatically, and performance has improved by leaps and bounds. SSDs have gone from prohibitively expensive luxuries to essential components for all but the most affordable PCs.
More recently, consumer-grade SSDs seem to have plateaued. Prices have stabilized and even crept upward slightly from where they were last year. We haven’t seen much development on the controller front, though NAND makers continue to churn out chips based on ever-smaller lithography. Most new SSDs are little more than tweaked versions of existing models outfitted with the next generation of flash memory. To be honest, that’s made writing about them a little dull.
When SanDisk first introduced us to its Extreme II SSD, I thought we were in for more of the same. My eyes rolled—but only once, because this isn’t another cookie-cutter SSD. Like most solid-state drives, the Extreme II relies on an array of MLC NAND for storage. However, it also has a built-in flash cache based on SLC memory.
SLC NAND has higher write performance and better endurance than MLC flash, making it ideal for caching solutions. It’s also popular in high-end server SSDs. With only one bit per cell, though, SLC NAND costs more per gigabyte than its two-bit MLC counterpart. The Extreme II attempts to blend the best of both worlds by using an SLC cache to improve performance and MLC mass storage to keep the pricing competitive. How’s that for something different?
Introducing the nCache
Solid-state caches are nothing new, of course. They’re employed in hybrids that combine flash memory and mechanical storage in a single drive. SSD caching is also available via dual-drive configurations that use software to marry separate solid-state and mechanical drives. Unlike those implementations, the SanDisk Extreme II doesn’t have a mechanical component; its so-called nCache sits in front of solid-state storage. The cache is used quite differently than what we’ve seen from other solutions, as well.
Only three kinds of data are stored in the nCache. The highest priority is given to the metadata that map logical block addresses to physical NAND locations. These data are replicated from the drive’s DRAM cache memory, and they’re backed up again in main storage for extra redundancy. Flush commands are also stored in the nCache, while the remaining space is dedicated to what SanDisk characterizes as “small” random writes.
The nCache accumulates smaller writes at a higher speed than the rest of the SSD. These writes are bundled into larger blocks, which are then moved to the main flash. This collation is employed to bridge the widening gap between the typical request size and the block sizes used in flash memory. Most system writes are 4KB or less, while the block size of newer NAND has pushed beyond 1MB.
SanDisk says the nCache has a “little less” than 1GB of total storage capacity. Some of that will be consumed by the metadata, leaving even less available as a random write buffer. If the nCache is full, all incoming data are written directly to main storage.
A gigabyte of nCache doesn’t sound like a lot, but keep its mission in mind. SanDisk isn’t speculatively pre-loading OS and application data. The small writes collected by the nCache shouldn’t take up too much space.
Perhaps the most intriguing thing about the nCache is where it lives. Instead of being housed on a separate chip, it’s spread evenly across the onboard NAND chips. This configuration allows the cache to exploit all the memory channels built into the controller.
The Extreme II’s 19-nm Toggle DDR flash is made by SanDisk, and it’s a unique SLC/MLC hybrid. One portion of the flash is configured as SLC NAND with one bit per cell. The remainder crams two bits per cell in an MLC setup. SLC flash boasts higher random write performance than the MLC stuff, which is why it’s reserved for the nCache. MLC NAND offers a higher storage density, making it better suited for mass storage. Combining the two in a single chip is pretty slick.
In addition to relying on hybrid NAND, the nCache requires custom firmware. There’s no need for a specialized controller, though. The Extreme II uses an off-the-shelf Marvell 88SS9187 chip. This controller has eight parallel NAND channels and can address up to four individual dies per channel—typical specifications for modern SSD silicon.
SanDisk sets aside 7% of the Extreme II’s flash capacity as overprovisioned spare area. Additional capacity is reserved for the nCache, knocking the available models down to 120, 240, and 480GB. Unlike other SSDs with those capacities, the Extreme II doesn’t feature RAID-like die redundancy to guard against physical flash failures. It doesn’t appear to support hardware-accelerated encryption, either.
|Capacity||Die config||Max sequential (MB/s)||4KB random (IOps)||Price||$/GB|
|120GB||16 x 64Gb||550||340||91,000||74,000||$130||$1.08|
|240GB||32 x 64Gb||550||510||95,000||78,000||$230||$0.96|
|480GB||64 x 64Gb||545||500||95,000||75,000||$450||$0.93|
Like most contemporary SSDs, the Extreme II is built with 64Gb (8GB) NAND dies. The controller can address four chips on each of its eight channels, making 32 dies the minimum for optimal performance. The 120GB model doesn’t have enough NAND to deliver peak performance, but the 240 and 480GB variants do. Oddly, though, the larger of the two has slightly lower performance ratings. We’ve asked SanDisk to explain the difference and are awaiting a response.
Regardless of the capacity, the Extreme II SSD is rated for 80TB of total writes. The drive is also covered by a five-year warranty, a perk typically restricted to high-end drives. The Extreme is priced more like a mid-range model, though.
Users can monitor flash wear using the Extreme II’s SMART attributes, which track total host writes in addition to a “life curve” that describes overall drive health. These variables can be monitored with third-party software or checked with SanDisk’s SSD Toolkit. The Toolkit app is considerably more limited than the utilities shipped with Intel and Samsung SSDs, but it does offer a built-in firmware updater.
Our testing methods
If you’re familiar with our testing methods and hardware, the rest of this page is filled with nerdy details you already know; feel free to skip ahead to the benchmark results. For the rest of you, we’ve summarized the essential characteristics of all the drives we’ve tested in the table below. Our collection of SSDs includes the most popular SSD configurations on the market.
|Corsair Force Series 3 240GB||NA||SandForce SF-2281||25nm Micron async MLC|
|Corsair Force Series GT 240GB||NA||SandForce SF-2281||25nm Intel sync MLC|
|Corsair Neutron 240GB||256MB||LAMD LM87800||25nm Micron sync MLC|
|Corsair Neutron GTX 240GB||256MB||LAMD LM87800||26nm Toshiba Toggle MLC|
|Crucial m4 256GB||256MB||Marvell 88SS9174||25nm Micron sync MLC|
|Crucial M500 240GB||256MB||Marvell 88SS9187||20nm 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|
|OCZ Agility 4 256GB||512MB||Indilinx Everest 2||25nm Micron async MLC|
|OCZ Vector 256GB||512MB||Indilinx Barefoot 3||25nm 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 830 Series 256GB||256MB||Samsung MCX||27nm Samsung Toggle MLC|
|Samsung 840 Series 250GB||512MB||Samsung MDX||21nm 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|
|WD Caviar Black 1TB||64MB||NA||NA|
To illustrate how this crop of SSDs stacks up against mechanical storage, we’ve thrown an older Western Digital Caviar Black 1TB into the mix. Don’t expect this 7,200-RPM hard drive to keep up; it’s included for reference only.
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||Corsair Force 3 Series 240GB with 1.3.2 firmware
Corsair Force Series GT 240GB with 1.3.2 firmware
Crucial m4 256GB with 010G firmware
WD Caviar Black 1TB with 05.01D05 firmware
OCZ Agility 4 256GB with 1.5.2 firmware
Samsung 830 Series 256GB with CXM03B1Q firmware
Intel 520 Series 240GB with 400i firmware
OCZ Vertex 4 256GB with 1.5 firmware
Corsair Neutron 240GB with M206 firmware
Corsair Neutron GTX 240GB with M206 firmware
Intel 335 Series 240GB with 335s firmware
Samsung 840 Series 250GB with DXT07B0Q firmware
OCZ Vector 256GB with 10200000 firmware
Samsung 840 Pro Series 256GB with DXM04B0Q firmware
Crucial M500 240GB with MU02 firmware
Seagate 600 SSD 240GB with B660 firmware
OCZ Vertex 450 256GB with 1.0 firmware
SanDisk Extreme II 240GB with R1131
|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.
HD Tune — Transfer rates
HD Tune lets us present transfer rates in a couple of different ways. Using the benchmark’s “full test” setting gives us a good look at performance across the entire drive rather than extrapolating based on a handful of sample points. The full test gives us fodder for line graphs, which we’ve split up by drive maker. You can click the buttons below each line graph to see how the Extreme II compares to its rivals.
The Extreme II tops the field in HD Tune’s sequential write speed test. It’s only a few MB/s faster than the contenders nipping at its heels, though.
The same is true in the write speed test, although the field is more spread out. Some of the slowdown in the middle of the pack can be blamed on the peculiar transfer rate profiles illustrated by the line graphs. The write rates of the SandForce- and LAMD-based SSDs oscillate dramatically, lowering their respective averages. There are no such issues with the Extreme II, which maintains a consistent write rate from start to finish.
HD Tune runs on unpartitioned drives, with no file system in place, which might explain the spikes on some of the SSDs. For another take on sequential speed, we’ll turn to CrystalDiskMark, which runs on partitioned drives. We used the benchmark’s sequential test with the default 1GB transfer size and randomized data.
CrystalDiskMark doesn’t change the equation much for the Extreme II. The SanDisk SSD remains the fastest of the bunch in the read speed test. It slips into fourth place in the write speed test but doesn’t stray too far from the leaders.
HD Tune — Random access times
In addition to letting us test transfer rates, HD Tune can measure random access times. We’ve tested with four transfer sizes and presented all the results in a couple of line graphs. We’ve also busted out the 4KB and 1MB transfers sizes into bar graphs that should be easier to read without the presence of the mechanical drive.
Don’t try to differentiate between the SSDs in the line graphs. Those graphs are meant to illustrate the massive gap in access times between solid-state and mechanical storage.
Most of the SSDs have similar random read access times. Although the SanDisk Extreme II is technically the quickest in the 4KB test, its slim margin of victory carries little weight. You’re not going to notice differences of a few microseconds.
Of course, you will notice the difference between solid-state and mechanical storage. Our old hard drive is thoroughly outclassed here, with access times at least an order of magnitude slower than those of the SSDs.
The Extreme II’s nCache appears to be of little assistance in HD Tune’s random write speed test. It doesn’t give the drive an edge in the 4KB test, and the results for the 512-byte test are similar. Those writes should be small enough to put into the nCache. Perhaps the caching scheme only works when there’s a file system in place. Remember that HD Tune runs on unpartitioned drives.
We wouldn’t expect the larger writes of the 1MB test to be candidates for caching. The Extreme II sits in the middle of the pack in that test, but it’s still only fractions of a millisecond behind the quickest SSDs.
TR FileBench — Real-world copy speeds
Concocted by resident developer Bruno “morphine” Ferreira, FileBench 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, we run FileBench with the solid-state drives in two states. We first test the SSDs in a fresh state after a secure erase. They’re then subjected to a 30-minute IOMeter workload, generating a tortured used state ahead of another batch of copy tests. We haven’t found a substantial difference in the performance of mechanical drives between these two states. Let’s start with the fresh-state results.
The Extreme II shows signs of weakness in our first batch of file copy tests. Although it fares well when copying the larger files in the movie test, the drive falls down the standings as we move to smaller files. With the exception of the movie test, the Extreme II sticks close to the Crucial M500, which is based on the same Marvell controller chip.
Putting the Extreme II into a simulated used state doesn’t change its FileBench performance. The drive’s fresh- and used-state copy speeds are within a few percentage points of each other. Most modern SSDs maintain consistent copy speeds between our two batches of FileBench tests.
TR DriveBench 1.0 — Disk-intensive multitasking
TR DriveBench allows us to record the individual IO requests associated with a Windows session and then play those results back as fast as possible on different drives. We’ve used this app to create a set of multitasking workloads that combine common desktop tasks with disk-intensive background operations like compiling code, copying files, downloading via BitTorrent, transcoding video, and scanning for viruses. The individual workloads are explained in more detail here.
Below, you’ll find an overall average followed by scores for each of our individual workloads. The overall score is an average of the mean performance score for each multitasking workload.
The Extreme II’s nCache is supposed to improve multitasking performance. However, it doesn’t appear to help in our disk-intensive multitasking tests. The SanDisk SSD languishes near the back of the pack and is even beaten by the old Crucial m4. Let’s see what the individual test results tell us.
For the most part, the Extreme II sticks to the tail end of the middle of the pack. The drive is more competitive when the multitasking workload includes a background file copy. Even then, though, the SanDisk SSD’s actual I/O rate is well below that of its fastest rivals.
TR DriveBench 2.0 — More disk-intensive multitasking
As much as we like DriveBench 1.0’s individual workloads, the traces cover only slices of disk activity. Because we fire the recorded I/Os at the disks as fast as possible, solid-state drives also have no downtime during which to engage background garbage collection or other optimization algorithms. DriveBench 2.0 addresses both of those issues with a much larger trace that spans two weeks of typical desktop activity peppered with multitasking loads similar to those in DriveBench 1.0. We’ve also adjusted our testing methods to give solid-state drives enough idle time to tidy up after themselves. More details on DriveBench 2.0 are available on this page of our last major SSD round-up.
Instead of looking at a raw IOps rate, we’re going to switch gears and explore service times—the amount of time it takes drives to complete an I/O request. We’ll start with an overall mean service time before slicing and dicing the results.
Maybe there’s something to the Extreme II’s nCache after all. The SanDisk SSD has the lowest overall mean service time we’ve measured in DriveBench 2.0. Sure, its advantage over the next-closest competitor is only 0.02 milliseconds—not enough to get excited about. But there is evidence that clever caching deserves some of the credit for the low overall average. Look at what happens when we consider reads and writes separately.
The Extreme II is only good enough for fourth place with reads, but it’s the quickest of the bunch with writes. About half of DriveBench 2.0 write requests are 4KB or smaller, so there’s plenty of fodder for the nCache. That said, the performance deltas between the top contenders remain quite slim.
There are millions of I/O requests in this trace, so we can’t easily graph service times to look at the variance. However, our analysis tools do report the standard deviation, which can give us a sense of how much service times vary from the mean.
There’s less variability in the Extreme II’s write service times than for any of its peers. The SanDisk SSD’s read service times aren’t as consistent, but the standard deviation isn’t much higher than it is for the leaders.
We can’t easily graph all the service times recorded by DriveBench 2.0, but we can sort them. The graphs below plot the percentage of service times that fall below various thresholds. You can click the buttons below the graphs to see how the M500s compare to the other drives.
The write distributions are very close overall, and there’s plenty of overlap between the various SSDs. However, the Extreme II has slightly more service times under each threshold than most of the competition.
There are greater differences between the read distributions of the various SSDs. The Extreme II looks strong overall, but some of its rivals have an edge at specific thresholds. Those advantages are larger than the ones the Extreme II enjoys in the write distributions.
Overall, the SSDs complete the vast majority of their read and write requests in one millisecond or less. Hardly any requests take longer than 100 milliseconds, but those are the ones that are problematic. Extremely long service times have the potential to cause the sort of hitching that users might notice, so we’ve graphed the individual percentages for each drive. The actual percentages may be low, but keep in mind that DriveBench 2.0 comprises tens of millions of I/O requests.
Only a few of the SSDs have notably high percentages of extremely long read service times. The Extreme II isn’t among them. In fact, it scores an order of magnitude better than the worst solid-state offender. That performance is only good enough to put the SanDisk drive in the middle of the pack, though.
There are even fewer outliers in the write results. There, the Extreme II essentially ties the front half of the SSD field.
Our IOMeter workloads feature 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 tests 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 for each access pattern, so we’ve once again split the results by drive maker. You can compare the performance of the Extreme II to that of the competition by clicking the buttons below each graph.
The web server test is made up entirely of read requests, so we’ll deal with it separately. This workload isn’t ideal for the Extreme II, which has lower throughput than SSDs from Samsung, Corsair, and OCZ. The nCache can’t do anything to accelerate this test’s read requests, though. What happens when our other workloads mix read and write requests?
The Extreme II’s relative standing improves. In addition to beating the Samsung trio almost across the board, the SanDisk SSD widens its lead over the SandForce-based drives. However, it goes back and forth with the OCZ Vector and Vertex SSDs, and it can’t catch the LAMD-based drives from Corsair and Seagate.
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 reasonably recent titles.
All the SSDs stop the clock within about a second of each other in our load time tests. I’m not sure you’d be able to tell the drives apart in the real world. The difference between solid-state and mechanical storage is much starker—and easily discernible for even casual users.
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 Extreme II is one of the most power-efficient SSDs we’ve tested. It draws less power than all but a few of rivals at idle and under load.
The value perspective
Welcome to our famous value analysis, which adds capacity and pricing to the performance data we’ve explored over the preceding pages. We used Newegg prices for most of the SSDs, and we didn’t take mail-in rebates into account when performing our calculations.
First, we’ll look at the all-important cost per gigabyte, which we’ve obtained using the amount of storage capacity accessible to users in Windows.
With a $230 asking price and 240GB of storage, the SanDisk Extreme II just slips under the dollar-per-gig threshold. The Extreme II’s lower capacity puts it at a disadvantage versus 256GB drives like the Samsung 840 Pro, though. Despite costing 10 bucks more than the SanDisk SSD, the 840 Pro delivers more storage per dollar.
Our remaining value calculation uses a single performance score that we’ve derived by comparing how each drive stacks up against a common baseline provided by the Momentus 5400.4, a 2.5″ notebook drive with a painfully slow 5,400-RPM spindle speed. This index uses a subset of our performance data described on this page of our last SSD round-up.
The top three SSDs separate themselves from the second tier by notable margins. The next nine drives are tightly packed, and the Extreme II is the fastest among them.
Now for the real magic. We can plot this overall score on one axis and each drive’s cost per gigabyte on the other to create a scatter plot of performance per dollar per gigabyte. The best place on the plot is the upper-left corner, which combines high performance with a low price.
We’ve truncated the axes to focus on the SSDs. The scatter clearly shows that second tier of drives between 850 and 900%. The Extreme II has the highest performance in that group, but it’s also one of the pricier options.
SanDisk faces potentially stiffer competition from a couple of top-tier contenders. The Samsung 840 Pro is faster overall and slightly cheaper per gigabyte. So is the OCZ Vertex 450, although the 256GB version of that drive remains out of stock at Newegg.
I wouldn’t get too hung up on what are ultimately modest differences in price and performance. Looking at the broader price/performance picture puts things into perspective.
The gulf between solid-state and mechanical storage is huge. In comparison, the price and performance differences between the various SSDs are relatively minor. This is especially true for the mid-range and high-end drives, which crowd the upper right corner of the plot.
On the surface, the Extreme II appears to be Yet Another SSD. But it’s not, because unlike most solid-state drives, the Extreme II offers something original. In addition to MLC main storage, it has an SLC write cache—and both are derived from the same 19-nm flash chips. That’s not something you see every day.
Using hybrid NAND to fuel an SLC write cache is a neat idea, and there’s wisdom in focusing on small random writes. However, it’s hard to say whether the nCache has a substantial impact on real-world performance. The Extreme II certainly exhibited impressive write performance in a number of tests. In our real-world DriveBench 2.0 simulation, it had the quickest and the most consistent response times. However, the SanDisk SSD’s margins of victory were slim, and the drive struggled to keep up with the leaders in a handful of other tests.
That said, the Extreme II still offers great all-around performance. Though its pokey copy speeds with smaller files may keep the drive out of the top tier overall, the Extreme II is right on the doorstep. More importantly, there are no red flags in our results that would keep me from recommending the Extreme II for desktop or notebook use.
Even today’s mid-range SSDs are plenty quick for typical user workloads. There are other factors to consider, such as the Extreme II’s notebook-friendly power consumption and slender 7-mm case. The five-year warranty is a nice bonus, too, and so is the generous 80TB write limit. That’s a pretty good deal considering the $230 price tag attached to the 240GB model. The only thing missing is hardware-accelerated encryption support, a feature few consumers use.
When all those elements are taken into account, the Extreme II SSD looks like a strong contender. This isn’t the fastest SSD we’ve tested. It’s not the best value, either. But the Extreme II comes close enough on both counts to be worth considering, and its nCache is the most interesting SSD feature we’ve seen in a while. We can’t wait to see what SanDisk comes up with next.