Original Link: https://www.anandtech.com/show/4421/the-2011-midrange-ssd-roundup
The 2011 Mid-Range SSD Roundup: 120GB Agility 3, Intel 510 and More Compared
by Anand Lal Shimpi on June 7, 2011 12:52 PM ESTA year ago whenever I'd request an SSD for review I'd usually get a 128GB drive built using 3x nm 4GB 2-bit MLC NAND die. These days the standard review capacity is twice that as most drives ship with 25nm NAND, using 8GB die. Seeing a bunch of scores for 240GB+ drives however is frustrating to all involved. At these capacities you're almost always looking at two die per NAND device, which has significant performance benefits due to interleaving. Most SSD controllers have eight NAND channels and with sixteen NAND deviecs with two die per device that's four NAND die that the controller can interleave access between for each channel. The 128GB drives by comparison halve the number of NAND, which only allows the controller to interleave requests among two die.
How read interleaving works on a single channel
Not only are these 240GB+ drives the best case performance you'd see from a particular SSD, they are also very expensive. At around $2/GB you're looking at over $500 for a high end 240GB+ SSD. I've spent the past few weeks gathering modern SSDs with 128GB of NAND on-board to provide a look at a more balanced point in the price/capacity spectrum.
Mid-Range 2011 SSD Roundup | ||||||||
Specs (6Gbps) | Corsair P3 128GB | Crucial RealSSD C300 128GB | Intel SSD 320 160GB | Intel SSD 510 120GB | OCZ Agility 3 120GB | OCZ Vertex 3 120GB | ||
Controller | Marvell 6Gbps | Marvell 6Gbps | Intel 3Gbps | Marvell 6Gbps | SF-2281 | SF-2281 | ||
Raw NAND Capacity | 128GB | 128GB | 176GB | 128GB | 128GB | 128GB | ||
Spare Area | ~6.9% | ~6.9% | ~15.3% | ~12.7% | ~12.7% | ~12.7% | ||
User Capacity | 119.2GB | 119.2GB | 149.0GB | 111.8GB | 111.8GB | 111.8GB | ||
Number of NAND Devices | 8 | 16 | 12 | 16 | 16 | 16 | ||
Number of die per Device | 4 | 2 | 1 - 2 | 2 | 1 | 1 | ||
NAND Type | 32nm Toggle | 34nm ONFI 2.0 | 25nm ONFI 2.1 | 34nm ONFI 1.0 | 25nm ONFI 2.1 | 25nm ONFI 2.1 | ||
Street Price | $229.99 | $234.99 | $304.99 | $284.49 | $279.99 | $252.99 | ||
Cost Per GB | $1.797 | $1.836 | $1.906 | $2.222 | $2.187 | $1.976 |
Corsair Performance Series 3
The first drive in the roundup is the one I've had the longest: Corsair's P3.
The P3 is based on the same Marvell controller used by Crucial in the C300 and Intel's SSD 510, however it's using what appears to be Marvell's standard firmware and as of yet Corsair hasn't provided any firmware updates to the drive. Internally the P3 uses 32nm Toshiba NAND on a very small PCB:
There are 8 NAND devices, making this a fully populated controller. Each NAND device has four 32nm die internally:
At $229.99 the P3-128 is the most affordable drive in our roundup, and it's a 6Gbps drive so it should be able to post some pretty high sequential numbers.
Crucial RealSSD C300
The C300 is nothing new, we reviewed this drive last year. I still don't have a 128GB version of the updated m4, however as we discovered in our review of the 256GB m4, performance isn't necessarily better than the C300. In many cases the m4 is actually slower than the C300.
The 128GB drive uses Marvell's 6Gbps controller (with Micron's own firmware) and features 34nm ONFI 2.0 NAND:
With sixteen NAND devices on the PCB, each package has two 4GB die inside it.
The C300 is pretty affordable by today's standards. The 128GB drive we tested here is selling for $234.99.
Intel SSD 320
Based on Intel's X25-M G2 controller but with new firmware the 320 adds features like real time encryption, however 6Gbps isn't in the cards with this drive:
Intel sent along the 160GB version of the 320, which has a pretty unusual NAND configuration. Remember Intel's controller is a 10-channel architecture and on the front of the PCB we have ten 25nm NAND devices:
These are 16GB NAND devices (two 8GB NAND die per package). That alone is good for the 160GB drive capacity, but the 320 needs more spare area than its predecessor so 160GB won't cut it. Flip the PCB over and you see two 8GB NAND devices:
I'm not entirely sure how Intel is striping data across all of the NAND. It's likely that Intel is simply just interleaving more operations on two of the channels. The 160GB 320 is the most expensive drive here at $304.99, but that's mostly because of the drive's capacity. In terms of cost per GB, the 320 is middle of the road here at $1.906 per GB.
Intel SSD 510
While the 320 is Intel's mainstream drive, the 510 is the high performance 6Gbps offering for enthusiasts. Intel is using Marvell's 6Gbps controller, again with its own custom firmware. The drive uses Intel's 34nm NAND and doesn't support the encryption features of the 320.
Since it uses 34nm NAND, Intel has 16 NAND devices internally each with two 4GB die:
The 510 is our second most expensive drive here at $284.49 and the most expensive on a cost-per-GB basis as well ($2.222):
OCZ's Agility 3 & Vertex 3
OCZ was the first to ship a SF-2281 based drive and now there are multiple offerings in the OCZ lineup. The Vertex 3 uses 25nm IMFT synchronous NAND, while the Agility 3 uses 25nm IMFT asynchronous NAND. As I hinted at in our review of the 240GB Agility 3, I fully expect a lot of pricing fluctuation between these two lines depending on availability of NAND. As a result, today you can buy a Vertex 3 from Newegg for less than you can an Agility 3. Obviously at the same price the Vertex 3 is the recommended drive but I expect to see these two flip flop more in the future.
Internally the Agility 3 (and Vertex 3) use 16 NAND devices with one die per device:
OCZ is very aggressive on Vertex 3 pricing, you can get the 120GB version today for $252.99.
The Test
CPU |
Intel Core i7 965 running at 3.2GHz (Turbo & EIST Disabled) Intel Core i7 2600K running at 3.4GHz (Turbo & EIST Disabled) - for AT SB 2011, AS SSD & ATTO |
Motherboard: |
Intel DX58SO (Intel X58) Intel H67 Motherboard |
Chipset: |
Intel X58 + Marvell SATA 6Gbps PCIe Intel H67 |
Chipset Drivers: |
Intel 9.1.1.1015 + Intel IMSM 8.9 Intel 9.1.1.1015 + Intel RST 10.2 |
Memory: | Qimonda DDR3-1333 4 x 1GB (7-7-7-20) |
Video Card: | eVGA GeForce GTX 285 |
Video Drivers: | NVIDIA ForceWare 190.38 64-bit |
Desktop Resolution: | 1920 x 1200 |
OS: | Windows 7 x64 |
Random Read/Write Speed
The four corners of SSD performance are as follows: random read, random write, sequential read and sequential write speed. Random accesses are generally small in size, while sequential accesses tend to be larger and thus we have the four Iometer tests we use in all of our reviews.
Our first test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random access that you'd see on an OS drive (even this is more stressful than a normal desktop user would see). I perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time. We use both standard pseudo randomly generated data for each write as well as fully random data to show you both the maximum and minimum performance offered by SandForce based drives in these tests. The average performance of SF drives will likely be somewhere in between the two values for each drive you see in the graphs. For an understanding of why this matters, read our original SandForce article.
At worst, SandForce's small file random write performance is equal to its closest competitors, but at best it is significantly greater. Both the Vertex 3 and Agility 3 take the cake here. The Marvell based solutions are significantly slower, however we'll see if that matters in the real world tests.
Many of you have asked for random write performance at higher queue depths. What I have below is our 4KB random write test performed at a queue depth of 32 instead of 3. While the vast majority of desktop usage models experience queue depths of 0 - 5, higher depths are possible in heavy I/O (and multi-user) workloads:
At higher queue depths the advantage just grows for the SF-2281 drives.
Crucial optimized very heavily for random read performance, and to this day nothing (even the replacement m4/C400) can outperform the C300 in our small file random read test. Intel's SSD 510 is the next fastest 6Gbps drive we've got here, followed by the P3 and eventually the Vertex 3/Agility 3.
Sequential Read/Write Speed
To measure sequential performance I ran a 1 minute long 128KB sequential test over the entire span of the drive at a queue depth of 1. The results reported are in average MB/s over the entire test length.
To post high sequential read speeds you need to have a 6Gbps interface these days. Armed with one the Intel SSD 510 and Corsair P3 both post the highest scores here. Even the Vertex 3/Agility 3 are a bit behind the two Marvell drives.
Sequential write performance is another story entirely. With highly compressible data the Vertex 3 is untouched and even in the worst case it's still among the fastest drives. I'll chalk this one up as a win for OCZ, however the rest of the competitors do well here.
AnandTech Storage Bench 2011
I didn't expect to have to debut this so soon, but I've been working on updated benchmarks for 2011. Last year we introduced our AnandTech Storage Bench, a suite of benchmarks that took traces of real OS/application usage and played them back in a repeatable manner. I assembled the traces myself out of frustration with the majority of what we have today in terms of SSD benchmarks.
Although the AnandTech Storage Bench tests did a good job of characterizing SSD performance, they weren't stressful enough. All of the tests performed less than 10GB of reads/writes and typically involved only 4GB of writes specifically. That's not even enough exceed the spare area on most SSDs. Most canned SSD benchmarks don't even come close to writing a single gigabyte of data, but that doesn't mean that simply writing 4GB is acceptable.
Originally I kept the benchmarks short enough that they wouldn't be a burden to run (~30 minutes) but long enough that they were representative of what a power user might do with their system.
Not too long ago I tweeted that I had created what I referred to as the Mother of All SSD Benchmarks (MOASB). Rather than only writing 4GB of data to the drive, this benchmark writes 106.32GB. It's the load you'd put on a drive after nearly two weeks of constant usage. And it takes a *long* time to run.
I'll be sharing the full details of the benchmark in some upcoming SSD articles but here are some details:
1) The MOASB, officially called AnandTech Storage Bench 2011 - Heavy Workload, mainly focuses on the times when your I/O activity is the highest. There is a lot of downloading and application installing that happens during the course of this test. My thinking was that it's during application installs, file copies, downloading and multitasking with all of this that you can really notice performance differences between drives.
2) I tried to cover as many bases as possible with the software I incorporated into this test. There's a lot of photo editing in Photoshop, HTML editing in Dreamweaver, web browsing, game playing/level loading (Starcraft II & WoW are both a part of the test) as well as general use stuff (application installing, virus scanning). I included a large amount of email downloading, document creation and editing as well. To top it all off I even use Visual Studio 2008 to build Chromium during the test.
Update: As promised, some more details about our Heavy Workload for 2011.
The test has 2,168,893 read operations and 1,783,447 write operations. The IO breakdown is as follows:
AnandTech Storage Bench 2011 - Heavy Workload IO Breakdown | ||||
IO Size | % of Total | |||
4KB | 28% | |||
16KB | 10% | |||
32KB | 10% | |||
64KB | 4% |
Only 42% of all operations are sequential, the rest range from pseudo to fully random (with most falling in the pseudo-random category). Average queue depth is 4.625 IOs, with 59% of operations taking place in an IO queue of 1.
Many of you have asked for a better way to really characterize performance. Simply looking at IOPS doesn't really say much. As a result I'm going to be presenting Storage Bench 2011 data in a slightly different way. We'll have performance represented as Average MB/s, with higher numbers being better. At the same time I'll be reporting how long the SSD was busy while running this test. These disk busy graphs will show you exactly how much time was shaved off by using a faster drive vs. a slower one during the course of this test. Finally, I will also break out performance into reads, writes and combined. The reason I do this is to help balance out the fact that this test is unusually write intensive, which can often hide the benefits of a drive with good read performance.
There's also a new light workload for 2011. This is a far more reasonable, typical every day use case benchmark. Lots of web browsing, photo editing (but with a greater focus on photo consumption), video playback as well as some application installs and gaming. This test isn't nearly as write intensive as the MOASB but it's still multiple times more write intensive than what we were running last year.
As always I don't believe that these two benchmarks alone are enough to characterize the performance of a drive, but hopefully along with the rest of our tests they will help provide a better idea.
The testbed for Storage Bench 2011 has changed as well. We're now using a Sandy Bridge platform with full 6Gbps support for these tests. All of the older tests are still run on our X58 platform.
AnandTech Storage Bench 2011 - Heavy Workload
We'll start out by looking at average data rate throughout our new heavy workload test:
What SandForce has done with the SF-2281 controller is very impressive when you look at these results. Keep in mind that our Heavy Workload is the most write-heavy of our new benchmarks and it uses a lot of data that's already compressed (images, videos, file archives). Despite the makeup of the workload, the SF-2281 based Vertex 3 is nearly the fastest drive here - outpacing both the P3 and C300. The Agility 3, with its asynchronous NAND isn't quite as strong and is actually outpaced by Corsair's P3.
Intel's 160GB SSD 320 is a 3Gbps SATA drive and thus it can't compete with the 6Gbps offerings near the top. If we only look at 3Gbps results however, the standings aren't all that impressive. The 320, P3 and Agility 3 all fall within the same performance group, with the Vertex 3 clearly pulling ahead.
There's another drive from Intel however that does manage to impress: the Intel SSD 510. At 250GB, the 510 isn't competitive with OCZ's 240GB Vertex 3 however at 120GB the tests tell a different story. OCZ loses the ability to interleave reads/writes on a per device basis and thus takes a pretty significant performance hit. It's likely all of the incompressible data in this workload that really forces a difference between the 240GB and 120GB Vertex 3s. The 510 however doesn't have that problem, and the 120GB drive actually outperforms the Vertex 3 here. Not to mention that it should be more reliable if history is any indication.
The breakdown of reads vs. writes tells us more of what's going on:
Read performance is where the Vertex 3 really makes up most of its advantage. At 114.7MB/s the Vertex 3 is nearly 30% faster than the Agility 3 here. Write speed however is a closer race between all of the drives:
The next three charts just represent the same data, but in a different manner. Instead of looking at average data rate, we're looking at how long the disk was busy for during this entire test. Note that disk busy time excludes any and all idles, this is just how long the SSD was busy doing something:
AnandTech Storage Bench 2011 - Light Workload
Our new light workload actually has more write operations than read operations. The split is as follows: 372,630 reads and 459,709 writes. The relatively close read/write ratio does better mimic a typical light workload (although even lighter workloads would be far more read centric).
The I/O breakdown is similar to the heavy workload at small IOs, however you'll notice that there are far fewer large IO transfers:
AnandTech Storage Bench 2011 - Light Workload IO Breakdown | ||||
IO Size | % of Total | |||
4KB | 27% | |||
16KB | 8% | |||
32KB | 6% | |||
64KB | 5% |
Despite the reduction in large IOs, over 60% of all operations are perfectly sequential. Average queue depth is a lighter 2.2029 IOs.
Under more typical desktop usage models the Vertex 3 is the fastest, but not by a huge margin. The Agility 3 and Intel SSD 510 are both within 10%. The major advantage for OCZ here is in read performance, which is what you do most of the time with a desktop (non-file archival) workload:
Write performance is clearly not one of the Vertex 3's strong points, at least compared to the 510 and Corsair P3 - both of which deliver top notch performance here. Despite using identical controllers, there is a tangible performance difference between these two drives.
AS-SSD Incompressible Sequential Performance
The AS-SSD sequential benchmark uses incompressible data for all of its transfers. The result is a pretty big reduction in sequential write speed on SandForce based controllers.
Peak read speed is obviously something the Vertex 3 does very well, while the P3 and 510 fall in second and third places, OCZ has a substantial lead. Now look at what happens when AS-SSD runs a pass of incompressible writes:
Corsair's P3 is now our leader. What's important to notice here is that Corsair's firmware allows for much higher sequential performance than what Intel outfitted the 510 with, however Intel's drive generally delivers better real world performance as we've seen from our 2011 Storage Bench tests.
Overall System Performance using PCMark Vantage
Next up is PCMark Vantage, another system-wide performance suite. For those of you who aren’t familiar with PCMark Vantage, it ends up being the most real-world-like hard drive test I can come up with. It runs things like application launches, file searches, web browsing, contacts searching, video playback, photo editing and other completely mundane but real-world tasks. I’ve described the benchmark in great detail before but if you’d like to read up on what it does in particular, take a look at Futuremark’s whitepaper on the benchmark; it’s not perfect, but it’s good enough to be a member of a comprehensive storage benchmark suite. Any performance impacts here would most likely be reflected in the real world.
The SandForce drives hold a 10% advantage over the Intel SSD 510 in this test. For truly light desktop workloads it's near impossible to offer better performance than SandForce as most of the data written never actually hits NAND.
AnandTech Storage Bench 2010
To keep things consistent we've also included our older Storage Bench. Note that the old storage test system doesn't have a SATA 6Gbps controller, so we only have one result for the 6Gbps drives.
The first in our benchmark suite is a light/typical usage case. The Windows 7 system is loaded with Firefox, Office 2007 and Adobe Reader among other applications. With Firefox we browse web pages like Facebook, AnandTech, Digg and other sites. Outlook is also running and we use it to check emails, create and send a message with a PDF attachment. Adobe Reader is used to view some PDFs. Excel 2007 is used to create a spreadsheet, graphs and save the document. The same goes for Word 2007. We open and step through a presentation in PowerPoint 2007 received as an email attachment before saving it to the desktop. Finally we watch a bit of a Firefly episode in Windows Media Player 11.
There’s some level of multitasking going on here but it’s not unreasonable by any means. Generally the application tasks proceed linearly, with the exception of things like web browsing which may happen in between one of the other tasks.
The recording is played back on all of our drives here today. Remember that we’re isolating disk performance, all we’re doing is playing back every single disk access that happened in that ~5 minute period of usage. The light workload is composed of 37,501 reads and 20,268 writes. Over 30% of the IOs are 4KB, 11% are 16KB, 22% are 32KB and approximately 13% are 64KB in size. Less than 30% of the operations are absolutely sequential in nature. Average queue depth is 6.09 IOs.
The performance results are reported in average I/O Operations per Second (IOPS):
Our old light workload from 2010 highlights an important point about all of these SSDs. For light usage, in a completely IO bound workload, there's only a 13% difference in performance between the fastest 6Gbps drive and last year's C300. If there's only a 13% difference in this completely IO bound test, the real world difference will surely be nonexistent.
If there’s a light usage case there’s bound to be a heavy one. In this test we have Microsoft Security Essentials running in the background with real time virus scanning enabled. We also perform a quick scan in the middle of the test. Firefox, Outlook, Excel, Word and Powerpoint are all used the same as they were in the light test. We add Photoshop CS4 to the mix, opening a bunch of 12MP images, editing them, then saving them as highly compressed JPGs for web publishing. Windows 7’s picture viewer is used to view a bunch of pictures on the hard drive. We use 7-zip to create and extract .7z archives. Downloading is also prominently featured in our heavy test; we download large files from the Internet during portions of the benchmark, as well as use uTorrent to grab a couple of torrents. Some of the applications in use are installed during the benchmark, Windows updates are also installed. Towards the end of the test we launch World of Warcraft, play for a few minutes, then delete the folder. This test also takes into account all of the disk accesses that happen while the OS is booting.
The benchmark is 22 minutes long and it consists of 128,895 read operations and 72,411 write operations. Roughly 44% of all IOs were sequential. Approximately 30% of all accesses were 4KB in size, 12% were 16KB in size, 14% were 32KB and 20% were 64KB. Average queue depth was 3.59.
Our heavy workload is really no different in terms of the performance spread. All of the newer drives show very similar performance.
The gaming workload is made up of 75,206 read operations and only 4,592 write operations. Only 20% of the accesses are 4KB in size, nearly 40% are 64KB and 20% are 32KB. A whopping 69% of the IOs are sequential, meaning this is predominantly a sequential read benchmark. The average queue depth is 7.76 IOs.
Power Consumption
The lowest idle power consumption belongs to Intel, however under load Intel and the SF drives are comparable (assuming you toss incompressible data at the SF drives). If SandForce is given a more dedupe friendly workload however, the Vertex 3/Agility 3 become the more power efficient drives.
Final Words
When I reviewed the 240GB Vertex 3, it looked like game over for all of the other new 6Gbps drives. Intel's SSD 510 was competitive but clearly in second place. Moving to 120GB, the Vertex 3 lost a lot of steam thanks to a reduction in the total number of NAND die. The Intel SSD 510 however still uses 34nm NAND and manages to either outperform or remain competitive with the Vertex 3 in all key areas. Combine that with Intel's track record for reliability and compatibility and I think we have a winner here.
OCZ does have a MAX IOPS version of the Vertex 3 which uses 32nm Toggle NAND. I'm still waiting on my review sample but it's quite possible that the 120GB MAX IOPS drive will be enough to restore OCZ's performance advantage. There are still firmware concerns of course, which SandForce appears to be actively working on. I'm guessing when the smoke clears the best balance of reliability and performance will still be the 510, at least until the current crop of SF-2200 firmware issues get worked out.
In terms of value, Corsair's P3 is actually pretty impressive. My only concern there is the lack of a public firmware strategy at this point, but based on everything we've seen here today it offers the best performance per dollar out of the group.
It's funny how little the recommendations have changed over the years. Intel still offers a good balance of performance and reliability, however if you're willing to take a risk on the reliability front you can get better value elsewhere.