by Ilya Gavrichenkov
09/17/2012 | 10:55 AM
Reviewing the SanDisk Extreme SSD, the first of the new breed of SandForce-based solutions featuring 24 nm Toggle NAND flash memory, we didn’t expect to return to this topic so soon. However, the original design suggested by SanDisk has been found viable by other manufacturers. So, today we are going to benchmark yet another SSD with an SF-2281 controller and 24 nm Toggle Mode flash. The product is called Force GS and it makes an addition to Corsair’s existing SandForce-based solutions from the Force 3 and Force GT series.
There are two reasons for us to be interested in this SSD. First of all, we have some questions left about the new SSD design after our SanDisk Extreme tests. The SanDisk didn’t use the newest firmware, so its performance wasn’t always as good as expected. The Force GS is free from this downside as its manufacturer is always careful about firmware updates. Moreover, Corsair is known to be fastidious about its product nomenclature, so if there’s a new SSD series in Corsair’s product line-up, we can expect it to be really different. Considering that the previous design with 32 nm Toggle Mode NAND flash was not adopted by Corsair for some reason, we hope that the Force GS may prove to be one of the best implementations of the SandForce platform in hardware.
As a matter of fact, Corsair positions its Force GS series as a flagship SandForce-based solution. Force GS models are only available in capacities above 180 GB and are somewhat more expensive than their Force GT counterparts, which employ conventional ONFI flash. So, on one hand, the Force GS can help us while away the time waiting for the highly promising Corsair Neutron series with controllers from Link A Media Devices debuting on the mass market, and on the other hand, it can be a good replacement for SandForce-based SSDs with 32 nm Toshiba flash that are leaving the market right now. Well, we’re running too far ahead now. Let’s first take a look at the packaging and design of the 240 GB Corsair Force GS drive we’ve received for our tests.
We’ve seen a lot of Corsair SSDs, so this packaging is quite familiar to us. Besides a colorful picture and promo slogans, you can find the product’s specs and part number on the sides of the small cardboard box.
The SSD is protected by a transparent plastic wrap. It is accompanied by a set of mounting screws and an adapter that helps install this 2.5-inch drive into a computer’s 3.5-inch bay. We guess these accessories are quite sufficient.
As for the exterior design, the Force GS resembles Corsair’s Force GT series. Its case is the same color and shape. The red top of the case has a rough texture. The case is made of aluminum and has a standard height of 9.5 millimeters, which prevents this SSD from being installed into ultrabooks. Of course, color doesn’t affect its consumer properties, yet we can’t but notice that the Force GS (and the Force GT, too) is one of the most beautiful SSDs we’ve seen. The only external difference from the GT series is the label that helps easily identify a GT series product.
It is the interior design that we should examine to find more substantial differences between the new Force GS and the old Force GT series. There’s something interesting waiting for us there.
The PCB is smaller than usual, suggesting that Corsair developed a custom PCB design (and saved some PCB material in the process) instead of using SandForce’s reference one. The 240 GB model is based on the well-known LSI SandForce 2281 Flash Storage Processor connected to 16 memory chips (SanDisk SDZNPQBHER-016GT). It is these chips that make the Corsair Force GS special. The 24 nm Toggle Mode HBL (hierarchical bit-line) NAND flash we’ve only seen so far in the SanDisk Extreme SSD is a competitor to synchronous flash memory from Intel and Micron.
The 240 GB SanDisk Extreme SSD employed 32-gigabit chips but Corsair prefers 16-gigabit ones. This isn’t a serious difference, though. Each of the 16 flash memory chips inside the Force GS 240 GB contains two 64-gigabit NAND devices, so the controller can use 4-way interleaving to access the memory array. This structure makes the Force GS similar to SSDs with synchronous ONFI 2.0 flash whereas SSDs with 32 nm Toggle Mode flash used to have a higher level of the memory access interleave. So, from a theoretical standpoint, the higher interface bandwidth of the SanDisk flash is the only edge the Corsair Force GS has against the popular SSDs with SF-2281 controllers and synchronous flash from Intel or Micron.
In other words, the Force GS is quite a typical SandForce-based drive, as is also indicated by the 14% reduction in its user-accessible capacity. The 14% reserve pool is required by the RAISE technology (Redundant Array of Independent Silicon Elements) to improve the drive’s reliability. The user can only access 223 gibibytes out of the drive’s total 256 gibibytes.
Here are the official Force GS 240GB specifications:
It’s hard to analyze specifications of any SSD with the SF-2281 controller. The specified parameters depend on the type of processed data, so it’s up to the manufacturer’s marketing department to choose what exactly numbers to write in the specs. However, we can note that Corsair specifies almost the same speed for the Force GS series as for the Force GT, and that’s higher than the specified speed of the SanDisk Extreme which has the same hardware as the Force GS. This doesn’t seem logical to us, but perhaps we are just not aware of some nuances.
The firmware can make a difference, for example. The Force GS’s current firmware is based on the latest reference firmware (version 5.03) which has been adopted by all Corsair products already.
Like the majority of other SSDs with SF-2281 controller, the Corsair Force GS is shipped with a 3-year warranty.
For our today’s SSD test session we put together a special system on an Intel H67 based mainboard. This chipset provides support for two SATA 6 Gbit/s ports, which we use to connect the tested SSDs.
Since Corsair Force GS 240 GB is a second SSD on SF-2281 controller with 24 nm SanDisk flash memory, which we got our hands on, we decided to compare it not only with solid state drives featuring different hardware configurations, but also against its earlier prototype – SanDisk Extreme SSD 240 GB. As for the other competitors, they were a pretty common crowd and included three different modifications of the SandForce platform: Intel SSD 520 with its exclusive firmware; Corsair Force Series GT with synchronous ONFI memory; Mushkin Chronos deluxe with previous generation 32 nm Toggle Mode NAND. Besides, we also included into the diagrams the results of a few popular high-performance SSDs based on other controllers, such as Crucial m4 and Plextor M3 on Marvell 88SS9174, Samsung SSD 830 using Samsung’s own controller and flash-memory, and OCZ Vertex 4 on Indilinx Everest 2.
Overall our testbed was configured as follows:
We use CrystalDiskMark 3.0.1 benchmark to test the random- and sequential read and write speed. This benchmark is convenient to work with as it can measure the speed of an SSD with both incompressible random and fully compressible recurring data. This feature is important for testing SSDs based on SF-2281/2282 controller, which tries to compress the data before writing it into memory. So, there are two numbers in the diagrams below that reflect the maximum and minimum SSD speed. The real-life performance of an SSD is going to be in-between those two numbers depending on how effective the controller data compression is.
Note that the performance tests in this section refer to SSDs in their “Fresh Out-of-Box” state (FOB). No degradation could have taken place yet.
We’ve studied the behavior of SSDs with second-generation SandForce controllers and fast flash memory quite extensively, so the Force GS can’t really add anything to our knowledge base. Its 24nm flash memory with Toggle Mode interface is close to the popular ONFI 2.0 flash in its characteristics. So, Corsair’s Force GS and Force GT series turn out to be similar not only in their exterior design but also in performance. We can notice a few discrepancies, though. The newer SSD is faster at random reading, which may make it preferable for real-life usage scenarios.
The Force GS series drive is also different from the SanDisk Extreme which has the same hardware design. Oddly enough, the SanDisk is a little faster. We can only explain it by some firmware optimizations.
Overall, the Corsair Force GS seems to be quite a typical SandForce-based SSD with synchronous flash memory. SandForce-based SSDs with 25 nm ONFI flash or 32/24 nm Toggle NAND flash differ in synthetic benchmarks by just a few percent, actually. It’s hard to feel this difference in practical applications, so price becomes the most important factor if we are to choose between the Force GS and other SF-2281 based products. The Force GS is currently somewhat more expensive than SSDs with synchronous flash manufactured by IMFT, but this situation can easily change into the opposite.
There’s still one outstanding product in the SandForce generation. Thanks to its custom firmware, the Intel 520 SSD is completely different from any other SandForce-based product.
Unfortunately, SSDs are not always as fast as in their “fresh” state. In most cases their performance goes down after some time and in real life we deal with completely different write speeds than what we see on the diagrams in the previous chapter of our review. The reason for this phenomenon is the following: as the SSD runs out of free pages in the flash memory, its controller has to clear memory page blocks before saving data into them, which causes substantial delays. Although, modern SSD controllers can alleviate the performance drop by erasing unused flash memory pages ahead of time, when idle. They use two techniques for that: idle-time garbage collection and TRIM.
Of course, users are more interested in the consistent performance of their SSDs over a long period of time rather than the peak speed they are going to see only during the initial short-term usage period, while the drive is still “fresh”. The SSD makers, however, declare the speed characteristics of “fresh” SSDs for marketing reasons. That’s why we decided to test the performance hit that occurs when a “fresh” SSD becomes a “steady” one.
To get a complete picture of SSD performance degradation we ran special tests based on the SNIA SSSI TWG PTS (Solid State Storage Performance Test Specification) methodology. The main idea of this approach is to measure write speed consecutively in four different cases. First we measure the “fresh” SSD speed. Then we measure the speed after the SSD has been fully filled with data twice. The third test occurs after a 30-minute break during which the controller can partially restore performance by running the idle-time garbage collection. And finally, we measure the speed after issuing a TRIM command.
We ran the tests in synthetic IOMeter 1.1.0 RC1 benchmark, where we measured random write speed when working with 4 KB data blocks aligned to flash memory pages at 32 requests queue depth. The test data were pseudo-random.
The type of controller says it all. Every drive based on the SF-2281 chip is far from efficient when it comes to garbage collection and the TRIM command. Once such an SSD is filled with data, its write performance drops and cannot be restored even by the OS’s cleanup. It is only with the Secure Erase procedure, which is rather difficult for an inexperienced user and destructive in itself, that the SSD can be restored to its original speed. The performance hit at writing usually amounts to 10-20% and the Corsair Force GS fits into that range, too.
This is a good result, however. Using the same hardware design, the SanDisk Extreme SSD suffers a heavier performance hit. That’s because the Force GS’s newer firmware is optimized in terms of garbage collection.
Since the characteristics of most SSDs do change once they transition from fresh out-of-the-box state into steady state, we measure their performance once again using CrystalDiskMark 3.0.1 benchmark. The diagrams below show the obtained results. We use random data writing and measure only performance during writes, because read speed remains constant.
The steady-state writing performance of SandForce-based SSDs is lower compared to their competitors. The Force GS cannot do anything about it. It is a typical SandForce-based drive, even though with a rarely used type of flash memory. On the other hand, writing is not as important for real-life application as reading, so the low performance of the Corsair Force GS shown in the three previous diagrams is not a catastrophe.
The popular PCMark 7 contains an individual disk subsystem benchmark. It is not a synthetic test, but is based on real-life applications. This benchmark reproduces typical disk usage scenarios and measures how fast they are completed in popular applications. Moreover, the disk access commands are not executed as a steady uninterrupted flow, but in a more realistic manner – with certain pauses caused by the need to process the data. The benchmark generates an overall disk subsystem performance rating as well as speed readings in MB/s in individual usage scenarios. Note that the absolute speed in these scenarios is not too high because of the above mentioned pauses between individual input/output operations. In other words, PCMark 7 shows you the speed of the disk subsystem from the application’s point of view. Numbers like that show us not only the pure performance of an SSD, but mostly how big of a performance gain a certain SSD can guarantee in real life.
We ran PCMark 7 on “steady” SSDs, which is what they are going to be in actual computer systems most of the time. Their performance in this case is affected not only by their controller or flash memory speed but also by the efficiency of their internal algorithms that fight performance degradation.
Futuremark PCMark 7 suggests that the Force GS is quite a good SSD, placing it third in the SandForce hierarchy behind the exceptional Intel SSD 520 and the Mushkin Chronos Deluxe which employs the SF-2281 controller together with older 32 nm Toggle NAND flash.
Now let’s check out the individual tests to get a more detailed picture of what our SSDs are capable of under various types of operational load:
SandForce-based SSDs have always performed well in PCMark 7, and the Corsair Force GS carries this tradition on. Judging by its high place in the standings, it seems to be among the best midrange offers available. By the way, it differs from the SanDisk Extreme SSD which is slow due to its suboptimal TRIM implementation.
Intel NASPT is another disk sub-system test that uses real-life usage scenarios. Like PCMark 7, Intel NASPT reproduces predefined disk activity traces and measures how fast they are executed. However, the default traces are designed for network attached storage devices rather than for SSDs. Therefore during our test session we replace them with the specially developed SSD Benchmarking Suite which offers more relevant usage scenarios such as compressing and decompressing files, compiling large projects, copying files and folders, loading 3D game levels, installing software, batch-processing photos, searching a digital library for data, mass-launching applications, and transcoding video.
Like PCMark 7, this benchmark gives us a true-to-life illustration of disk subsystem performance. Here the SSDs are again tested in their “steady” state.
The SSDs with SF-2281 controller are all very close to each other in the diagram with the exception of the Intel 520, confirming our point that it’s hard to see a practical difference between SandForce SSDs with synchronous flash. Intel NASPT thinks that such products are faster than the Crucial m4 but worse than the Samsung 830, Plextor M3 and Intel 520. It is in the individual benchmarking traces that we can see the SandForce-based SSDs differ more or less conspicuously.
Note that the data-transfer rate is higher than the SATA III interface bandwidth in some subtests. That’s because INASPT is a high-level test that uses standard Windows functions to access the disk subsystem. As a result, the OS caching mechanisms also affect the results.
There are only a few scenarios where the Force GS differs noticeably from the Force GT, the latter being a typical representative of SSDs with second-generation SandForce controller and synchronous flash memory. The examples are the test of copying a folder with lots of files to the SSD and the software installation test. The Force GT is faster in them. The Force GS is ahead in the gaming test (a popular 3D shooter loading save files and new levels).
We use AS SSD version 1.6.4237.30508 test to benchmark the speed of copying files within a single partition the size of the whole SSD. The SSDs are tested in their steady state.
The Force GS is unexpectedly slow in the file copying tests, especially as the SanDisk Extreme, with the same hardware design, does much better here. The difference must be due to some firmware optimizations, so we can expect the Force GS to improve with firmware updates.
The Corsair Force GS is a second product representing a new modification of the second-generation SandForce platform. The SF-2281 controller can be combined with synchronous or asynchronous flash memory manufactured by Intel and Micron or with 32 nm flash from Toshiba, but the Force GS has a new design: 24 nm synchronous flash with Toggle Mode interface. The first SSD designed like that was the SanDisk Extreme but it had some firmware issues and we decided to wait for more products like that before we could form our opinion about them. Now that we’ve got two SSDs of this kind, their features have become more obvious.
First of all, we have to note that, despite the newer version of the reference firmware, the Force GS isn’t much different from the SanDisk Extreme in performance. The identical hardware design shows up in their test results.
Second, the use of 24 nm Toggle NAND flash on the SandForce platform doesn’t endow the resulting SSD with any new properties. The Force GS is actually very similar to conventional SSDs with ONFI memory such as Corsair Force GT, OCZ Vertex 3, Kingston HyperX 3K, etc. There are, of course, certain differences in certain scenarios, but the Force GS is indeed similar to the Force GT in performance, not only in the series name. Yes, the newer series is somewhat faster, but by a very narrow margin.
So, if you’re shopping for an SSD with SF-2281 controller and synchronous flash, you can base your choice on the price factor. Corsair’s Force GS products are somewhat more expensive than SSDs with flash memory from IMFT, but the pricing may change eventually, making the Force GS series a more attractive option.
Some time ago we started to fill in a summary table with test results of various SandForce-based SSDs. Now that there are other controllers available, we add them into that table as well. So, the updated table contains the basic hardware information about the tested SSDs and allows to quickly determine the general position of a particular model among its competitors in terms of relative performance.