Intel 510 Series 250GB SSD Review
Five years ago we made some predictions about the future development of SSD technology and how it would revolutionize PC storage. Rather than vague musings, we predicted that 2010 was the year SSDs would gain widespread acceptance in the mainstream markets. It turns out we were very close to the mark and things are lining up nicely for a paradigm shift that could have interesting long-term repercussions for a variety of knock-on technologies. SDDs have come a long way in terms of reliability and now are reckoned to be able to last longer than tradional HDDs thanks to wear-leveling algorithms and use a fraction of the power they did in 2005. Even as recently as January 2009, a technology article on Tom's Hardware concluded that SSD performance was not yet good enough - how far things have come in the last 2 years.
This article is primarily a review of Intel's new 510 Series 250GB SSD but, since few people are really clear about SSDs and even many techies have nagging questions about the technology, we thought we should start off with a technology guide showing how this all came about, the Pros and Cons of SSDs versus traditional HDDs and some Frequently Asked Questions about SSDs. Readers familiar with all this can skip straight to the testing section to see benchmarks but surprisingly, even our hardened techies learnt a thing or two about SSDs while compiling the reference material in the next 3 sections.
What's a disruptive technology?
It's something that has poor performance characteristics at present compared to the incumbent or mainstream current solution but the rate of improvement (the slope of the line or curve with regards to time) is such that at some point in the future it will overtake the current leading solution. The best way to illustrate this is with the following graph:
Using HDDs as our example we can see (looking forward from 2005, say) that disk speeds are steadily increasing as we move from ATA-33 to ATA-66, ATA-100, ATA-133 to SATA-1, SATA-2 and (unknown to us in 2005) SATA-3). Capacity doubles every year while the price remains constant. Speed has gone up by a factor of 5 in 20 years which is nothing to sniff at but look at what those SSDs are doing! In 2005 they cost a fortune and are slower than HDDs (really only being used by the military and some enterprise solutions where HDDs just couldn't stand the heat) but they sure are improving fast and prices are bound to come down as volumes increase.
Today they are much faster (we shall see during testing just how much faster than the latest HDDs) and more importantly we will examine the difference in practical terms (such as Windows boot times and application loading times) rather than just theoretical speeds in benchmarks. First though, let's take a look at the advantages and disadvantages and then (hopefully) all your SSD questions will be answered in the following section.
This FAQ is a compilation of information we have gathered from around the Internet and will hopefully answer most questions about Solid State Disk technology and help explain some of the technical jargon for newcomers to this field and explain from a practical point of view how SSDs work. Many of the questions and answers relate to SSDs in Windows 7 systems and were originally from Microsoft related discussion groups and forums too numerous to reference here but a Google (or Bing) search using the question as the search term should find the sources if more detail is needed.
Random Reads: A very good story for SSDs
SSDs tend to be very fast for random reads. Most SSDs thoroughly trounce traditionally HDDs because the mechanical work required to position a rotating disk head isn’t required. As a result, the better SSDs can perform 4 KB random reads almost 100 times faster than the typical HDD (about 1/10th of a millisecond per read vs. roughly 10 milliseconds).
Sequential Reads and Writes: Also Good
Sequential read and write operations range between quite good to superb. Because flash chips can be configured in parallel and data spread across the chips, today’s better SSDs can read sequentially at rates greater than 200 MB/s, which is close to double the rate many 7200 RPM drives can deliver. For sequential writes, we see some devices greatly exceeding the rates of typical HDDs, and most SSDs doing fairly well in comparison. In today’s market, there are still considerable differences in sequential write rates between SSDs. Some greatly outperform the typical HDD, others lag by a bit, and a few are poor in comparison.
Random Writes & Flushes: Your mileage will vary greatly
The differences in sequential write rates are interesting to note, but for most users they won’t make for as notable a difference in overall performance as random writes.
What’s a long time for a random write? Well, an average HDD can typically move 4 KB random writes to its spinning media in 7 to 15 milliseconds, which has proven to be largely unacceptable. As a result, most HDDs come with 4, 8 or more megabytes of internal memory and attempt to cache small random writes rather than wait the full 7 to 15 milliseconds. When they do cache a write, they return success to the OS even though the bytes haven’t been moved to the spinning media. We typically see these cached writes completing in a few hundred microseconds (so 10X, 20X or faster than actually writing to spinning media). In looking at millions of disk writes from thousands of telemetry traces, we observe 92% of 4 KB or smaller IOs taking less than 1 millisecond, 80% taking less than 600 microseconds, and an impressive 48% taking less than 200 microseconds. Caching works!
On occasion, we’ll see HDDs struggle with bursts of random writes and flushes. Drives that cache too much for too long and then get caught with too much of a backlog of work to complete when a flush comes along, have proven to be problematic. These flushes and surrounding IOs can have considerably lengthened response times. We’ve seen some devices take a half second to a full second to complete individual IOs and take 10’s of seconds to return to a more consistently responsive state. For the user, this can be awful to endure as responsiveness drops to painful levels. Think of it, the response time for a single I/O can range from 200 microseconds up to a whopping 1,000,000 microseconds (1 second).
When presented with realistic workloads, we see the worst of the SSDs producing very long IO times as well, as much as one half to one full second to complete individual random write and flush requests. This is abysmal for many workloads and can make the entire system feel choppy, unresponsive and sluggish.
Random Writes & Flushes: Why is this so hard?
For many, the notion that a purely electronic SSD can have more trouble with random writes than a traditional HDD seems hard to comprehend at first. After all, SSDs don’t need to seek and position a disk head above a track on a rotating disk, so why would random writes present such a daunting a challenge?
The answer to this takes quite a bit of explaining, Anand’s article admirably covers many of the details. We highly encourage motivated folks to take the time to read it as well as this fine USENIX paper. In an attempt to avoid covering too much of the same material, we’ll just make a handful of points.
Performance Degradation Over Time, Wear, and Trim
As mentioned above, flash blocks and cells need to be erased before new bytes can be written to them. As a result, newly purchased devices (with all flash blocks pre-erased) can perform notably better at purchase time than after considerable use. While we’ve observed this performance degradation ourselves, we do not consider this to be a show stopper. In fact, except via benchmarking measurements, we don’t expect users to notice the drop during normal use.
Of course, device manufactures and Microsoft want to maintain superior performance characteristics as best we can. One can easily imagine the better SSD manufacturers attempting to overcome the aging issues by pre-erasing blocks so the performance penalty is largely unrealized during normal use, or by maintaining a large enough spare area to store short bursts of writes. SSD drives designed for the enterprise may have as high as 50% of their space reserved in order to provide lengthy periods of high sustained write performance.
In addition to the above, Microsoft and SSD manufacturers are adopting the Trim operation. In Windows 7, if an SSD reports it supports the Trim attribute of the ATA protocol’s Data Set Management command, the NTFS file system will request the ATA driver to issue the new operation to the device when files are deleted and it is safe to erase the SSD pages backing the files. With this information, an SSD can plan to erase the relevant blocks opportunistically (and lazily) in the hope that subsequent writes will not require a blocking erase operation since erased pages are available for reuse.
As an added benefit, the Trim operation can help SSDs reduce wear by eliminating the need for many merge operations to occur. As an example, consider a single 128 KB SSD block that contained a 128 KB file. If the file is deleted and a Trim operation is requested, then the SSD can avoid having to mix bytes from the SSD block with any other bytes that are subsequently written to that block. This reduces wear.
Windows 7 requests the Trim operation for more than just file delete operations. The Trim operation is fully integrated with partition- and volume-level commands like Format and Delete, with file system commands relating to truncate and compression, and with the System Restore (aka Volume Snapshot) feature.
Windows 7 Optimizations and Default Behavior Summary
As noted above, all of today’s SSDs have considerable work to do when presented with disk writes and disk flushes. Windows 7 tends to perform well on today’s SSDs, in part, because they made many engineering changes to reduce the frequency of writes and flushes. This benefits traditional HDDs as well, but is particularly helpful on today’s SSDs.
Windows 7 will disable disk defragmentation on SSD system drives. Because SSDs perform extremely well on random read operations, defragmenting files isn’t helpful enough to warrant the added disk writing defragmentation produces. The FAQ section below has some additional details.
Be default, Windows 7 will disable Superfetch, ReadyBoost, as well as boot and application launch prefetching on SSDs with good random read, random write and flush performance. These technologies were all designed to improve performance on traditional HDDs, where random read performance could easily be a major bottleneck. See the FAQ section below for more details.
Since SSDs tend to perform at their best when the operating system’s partitions are created with the SSD’s alignment needs in mind, all of the partition-creating tools in Windows 7 place newly created partitions with the appropriate alignment.
Frequently Asked Questions
Before addressing some frequently asked questions, we’d like to remind everyone that we believe the future of SSDs in mobile and desktop PCs (as well as enterprise servers) looks very bright to us. SSDs can deliver on the promise of improved performance, more consistent responsiveness, increased battery life, superior ruggedness, quicker startup times, and noise and vibration reductions. With prices steadily dropping and quality on the rise, we expect more and more PCs to be sold with SSDs in place of traditional rotating HDDs. With that in mind, they focused an appropriate amount of their engineering efforts towards insuring Windows 7 users have great experiences on SSDs.
Will Windows 7 support Trim?
Yes. See the above section for details.
Will disk defragmentation be disabled by default on SSDs?
Yes. The automatic scheduling of defragmentation will exclude partitions on devices that declare themselves as SSDs. Additionally, if the system disk has random read performance characteristics above the threshold of 8 MB/sec, then it too will be excluded. The threshold was determined by internal analysis.
The random read threshold test was added to the final product to address the fact that few SSDs on the market today properly identify themselves as SSDs. 8 MB/sec is a relatively conservative rate. While none of their tested HDDs could approach 8 MB/sec, all of their tested SSDs exceeded that threshold. SSD performance ranged between 11 MB/sec and 130 MB/sec. Of the 182 HDDs tested, only 6 configurations managed to exceed 2 MB/sec on our random read test. The other 176 ranged between 0.8 MB/sec and 1.6 MB/sec.
Will Superfetch be disabled on SSDs?
Yes, for most systems with SSDs.
If the system disk is an SSD, and the SSD performs adequately on random reads and doesn’t have glaring performance issues with random writes or flushes, then Superfetch, boot prefetching, application launch prefetching, ReadyBoost and ReadDrive will all be disabled.
Initially, we had configured all of these features to be off on all SSDs, but we encountered sizable performance regressions on some systems. In root causing those regressions, we found that some first generation SSDs had severe enough random write and flush problems that ultimately lead to disk reads being blocked for long periods of time. With Superfetch and other prefetching re-enabled, performance on key scenarios was markedly improved.
Is NTFS Compression of Files and Directories recommended on SSDs?
Compressing files help save space, but the effort of compressing and decompressing requires extra CPU cycles and therefore power on mobile systems. That said, for infrequently modified directories and files, compression is a fine way to conserve valuable SSD space and can be a good tradeoff if space is truly a premium.
We do not, however, recommend compressing files or directories that will be written to with great frequency. Your Documents directory and files are likely to be fine, but temporary internet directories or mail folder directories aren’t such a good idea because they get large number of file writes in bursts.
Does the Windows Search Indexer operate differently on SSDs?
Is Bitlocker’s encryption process optimized to work on SSDs?
Yes, on NTFS. When Bitlocker is first configured on a partition, the entire partition is read, encrypted and written back out. As this is done, the NTFS file system will issue Trim commands to help the SSD optimize its behavior.
We do encourage users concerned about their data privacy and protection to enable Bitlocker on their drives, including SSDs.
Does Media Center do anything special when configured on SSDs?
No. While SSDs do have advantages over traditional HDDs, SSDs are more costly per GB than their HDD counterparts. For most users, a HDD optimized for media recording is a better choice, as media recording and playback workloads are largely sequential in nature.
Does Write Caching make sense on SSDs and does Windows 7 do anything special if an SSD supports write caching?
Some SSD manufacturers including RAM in their devices for more than just their control logic; they are mimicking the behavior of traditional disks by caching writes, and possibly reads. For devices that do cache writes in volatile memory, Windows 7 expects flush commands and write-ordering to be preserved to at least the same degree as traditional rotating disks. Additionally, Windows 7 expects user settings that disable write caching to be honored by write caching SSDs just as they are on traditional disks.
Do RAID configurations make sense with SSDs?
Yes. The reliability and performance benefits one can obtain via HDD RAID configurations can be had with SSD RAID configurations. (Please note - SSD RAID Arrays cannot user TRIM at present even if each drive alone can)
Should the pagefile be placed on SSDs?
Yes. Most pagefile operations are small random reads or larger sequential writes, both of which are types of operations that SSDs handle well.
In looking at telemetry data from thousands of traces and focusing on pagefile reads and writes, we find that
In fact, given typical pagefile reference patterns and the favorable performance characteristics SSDs have on those patterns, there are few files better than the pagefile to place on an SSD.
Are there any concerns regarding the Hibernate file and SSDs?
No, hiberfile.sys is written to and read from sequentially and in large chunks, and thus can be placed on either HDDs or SSDs.
What Windows Experience Index changes were made to address SSD performance characteristics?
In Windows 7, there are new random read, random write and flush assessments. Better SSDs can score above 6.5 all the way to 7.9. To be included in that range, an SSD has to have outstanding random read rates and be resilient to flush and random write workloads.
In the Beta timeframe of Windows 7, there was a capping of scores at 1.9, 2.9 or the like if a disk (SSD or HDD) didn’t perform adequately when confronted with their random write and flush assessments. Feedback on this was fairly consistent, with most feeling the level of capping to be excessive. As a result, they now simply restrict SSDs with performance issues from joining the newly added 6.0+ and 7.0+ ranges. SSDs that are not solid performers across all assessments effectively get scored in a manner similar to what they would have been in Windows Vista, gaining no Win7 boost for great random read performance.
Finally we can move on to the main focus of this review which is Intel's 510 Series 250GB SATA-3 Solid State Disk.
The Intel G25-M was the first SSD to make people sit up and take notice. It was followed by a G-2 refresh that used 34nm memory and was cheaper. A year ago Intel was the brand to beat in terms of performance and reliability. Since then SandForce has come along with a controller that can be paired with cheap flash memory to give remarkable performance. This posed a thorn in the side on Intel who have now responded with their SATA-3 capable drive boasting claimed speeds of up to 500MB/s. Crucial have had a drive able to (barely) make use of SATA-3 for many months but the write performance was quite poor by comparison. The 510 SSD is the first drive to offer write speeds exceeding the SATA-2 specifications. The drive comes in a retail box that includes a mounting kit
The packaging clearly shows all aspects of the drive's features and will be useful for those who like to shop in big stores rather than over the Internet (such people will have made a purchase decision already and will not be concerned about packaging).
The kit includes a tray for placing the SSD in a 3.5" bay, a molex to SATA power lead and a SATA data lead as well as the usual screws. We advise using this lead for SATA-3 operation as the quality seems a lot better than that supplied with most motherboards we have come across and may translate into increased performance due to fewer data transmission errors at high speeds.
The drive itself is made from strong plastic with a sandstone texture. SSDs have been quite tough recently (see the video below for what they can withstand). We didn't hesitate to remove the cover with a fine screwdriver to reveal the insides.
Gone is the Intel controller and is replaced with a Marvel 9174 controller and 128MB Hynix DDR3-1333 SDRAM. This does not necessarily mean that Intel could not produce a newer controller as one of the factors in the price of Intel drives was cost which was attributed to in a substantial way by the controller cost. Without producing controllers in bulk for many varied manufacturers (as SandForce have done), Intel is forced to adopt a low cost alternative and Marvel have made big strides in the performance of their controllers in recent months. Switching to a Marvel controller actually seems like a sound business decision from Intel's point fo view.
This is an amusing video showing just how tough Solid State Disks are. Just don't try this at home - it's not covered by the 3 year warranty. No traditional hard drive could take even a fraction of this punishment.
note: Some of the listed capacity is used for formatting and other functions and
thus is not available for data storage.
We will be testing using the Intel 510, Kingston V+, a high performance HDD (Samsung's 7200rpm 1TB SATA-2 drive), a high performance replacement SSD aimed at the NetBook market and a low end SSD that comes as standard with NetBooks. We'll also show the results for using Windows file compression with the most basic SSD to simulate users who just can't afford to upgrade and would like to know what effect compression has on performance. Because this is the first drive we are testing to break the 300MBps SATA-2 barrier, we will be running each test twice for the Intel SSD, once on a SATA-2 port and again on a SATA-3 port to see how important having the correct controller is.
HD Tune Pro 3.5 is our standard benchmark for storage devices and has served us well since we moved from HD-Tach. It allows comprehensive read and write tests that stress both SSD and HDDs as well as optical and flash drives.
The Intel 510 does slightly better than the V+ on a SATA-2 port and leaves the NetBook SSDs for dust. Connect to a SATA-3 port and it shoots ahead. It's worth noting also that while the minimum and maximum performance of the HDD varies considerably, that of the SSDs is much more consistent. The SaberTooth does well at the same price point as the Samsung HDD but is restricted to 32GB of capacity compared to the whopping 1000GB of the HDD.
Looking at write speeds shows how the 510 has triple the average and quadruple the minimum speed of the conventional HDD. The traditional weakness of SSDs has been slow write speeds and it's a testament to the quality of modern controllers are that write speeds are so high (still short of read speeds - dramatically so in the case of some entry level models). Burst rates are really only theoretical and depend more on cache than any sustainable performance so the first three indicators are key here.
Now time to hang on to your hats as we demonstrate the real reason why we have been champions of SSDs for years. HDDs are limited by having to physically move heads over spinning magnetic media whereas SSDs have no such limits on the number of operations they can complete in one second. For small block sizes the HDD heads have to move back and forth furiously clicking away and spend far more time traveling than they do reading and/or writing data. This allows modern SSDs to be over 100 times faster than the Samsung HDD for such operations and even the ultra cheap SSDs that come with NetBooks as standard can easily beat the high end HDD.
HDDs are limited in their seek times by moving heads as per the previous benchmark and here we can see typical access times. Without any moving parts the Intel SSD is up to 100 times faster at accessing data. This is not the case with all SSDs though as we can see the budget ones that use low quality memory and cheap controllers are actually worse than the Samsung HDD.
At the end of the day speed is king and when accessing lots of little files there is a big slowdown for every drive but the HDD is affected so badly that it is beaten by all the contenders. On the more representative Random access scale, the Intel 510 SSD is over 10 times faster than the HDD. This is also the closest indicator of how fast windows will boot with a particular drive as the types of files loaded during booting are of this mixture. It does not mean that windows will boot up 10 times faster since other bottlenecks such as the CPU will affect load times and the time spent POSTing by the BIOS varies from one motherboard to the next.
This graph can be a little misleading as the SaberTooth and Phison SSDs were tested on an ASUS Eee PC 901 and in fact, when we compensate for the fact we are using an i7-2600K system and not an Intel Atom one, the CPU utilization for all the drives is around the 1-2% mark showing a level of efficiency that is very close to optimal for all test participants.
AS SSD is a benchmark designed exclusively for SSDs but handles HDDs just as well. It also gives a nice graphical summary of results so readers don't have to look at boring derived Excel charts. We looked at comparative performance in the previous section and the Intel 510 Series SSD is a clear winner. Now we'll look at the difference between using a SATA-2 port and a SATA-3 port. In practice readers with a SATA-3 port will use that and never look back but for those with motherboards only supporting SATA-2 it is very useful to know what sort of performance boost (if any) they will gain upon upgrading.
On the left is the SATA-2 test and on the right we used a SATA-3 port. You can click on either one to launch a higher resolution picture in another window if you're having trouble making out the detail in these shots. The scoring system may seem a little arbitrary but supports the test results we have seen so far. There is a phenominal 81% increase in sequential read speeds and a 26% increase in sequential writes. Less of a difference in random read/write speeds but for everyday use most people will notice a profound improvement.
CrystalDiskMark is a disk benchmark software that measures performance for sequential reads/writes and random 4KB/512KB reads/writes for any storage device. It does not require the target device to be formatted.
Here we see a similar improvement in sequential read and write speeds. It's clear that the bottleneck is the SATA bandwidth holding back the true capabilities of the Intel SSD.
We knew that the Intel 250GB SSD was going to beat the Samsung 1TB HDD but would it be enough to justify ten times the price and almost 80 times the cost per Gigabyte? In our opinion, the answer is most definitely yes, not because of the benchmarks but rather the experience of using an SSD instead of HDD and having Windows 7 boot up in less than half the time and even more, seeing games and applications load in the blink of an eye because SSDs can be a hundred times faster than HDDs when loading numerous small files. We are not comparing like for like in this instance as the markets are very different and anyone purchasing the Intel 510 SSD will not doubt have sufficient funds to also purchase a large HDD for storage of less critical data (DVD/BD images, music achives etc.).
The real test is between the Intel 510 and the Kingston V+. They are similarly priced per GB so its all down to performance. The Intel 510 wipes the floor with all contendors but only when paired with a SATA-3 port. Its not so long ago people were complaining about HDD and SSD speeds not being enough to justify a SATA-3 port. Clearly, things have changed a lot. Until the arrival of the new SandForce drives based on their 2K series controller Intel has the fastest SSD available. If you have have a SATA-3 port on your motherboard then the Intel 510 SSD will get you the best performance available. If you only have a SATA-2 port then you will get the best performance that your system can manage but with the re-assurance that as soon as you upgrade to SATA-3, the SSD performance will jump massively to take advantage of it.
SSDs have a long way to go before being cheaper than HDDs in terms of cost per GB but this should not put people off purchasing as the best combination today is an SSD as the boot drive containing the Operating System and a conventional HDD of whatever size is needed for storage/archiving data that is less frequently accessed. An interesting technology is coming soon with the release of Intel's Z68 chipset called SSD Caching which will allow a small SSD or part of a larger SSD to be used as a cache for a conventional hard drive (a bit like Windows Virtual Memory). This addresses the performance/cost issues raised above allowing 1TB and larger HDDs with performance which can potentially rival that of SSDs at a fraction of the cost of a 1TB SSD. How this works in practice will have to wait until we test such a system when it becomes available and we will be making use of Intel's speedy 510 series SSD when that time comes.
The Intel 510 Series SSD is an excellent choice in terms of performance and future longevity and we heartilly recommend it.
All trademarks are the property of their respective owners.