Intel’s X25-E Extreme solid-state drive

Manufacturer Intel
Model X25-E Extreme 32GB
Price (Street)
Availability Now

Intel burst onto the storage scene back in September with its X25-M solid-state drive. This 80GB SSD combined Intel’s formidable chip-making prowess with its years of experience in high-performance storage controller design, and the results were impressive to say the least. Indeed, the X25-M was arguably the fastest solid-state drive we’d ever tested, let down only by the comparatively slow write performance of its multi-level cell (MLC) flash memory chips.

There isn’t much Intel can do about the slow write speeds inherent to MLC memory. However, the company has crafted a new solid-state drive based on single-level cell (SLC) memory chips that aren’t plagued by poor write rates. This latest X25-E Extreme boasts the same 250MB/s sustained read speed as the X25-M, but write speeds have been boosted from a paltry 70MB/s to a much more impressive 170MB/s. Oh my.

Obviously, the X25-E Extreme is going to be faster than the X25-M. Read on to see where the X25-E’s faster write speeds help the most, and in some cases, where they improve performance more than you might expect.

Extreme for enterprise

Solid-state drives use either single-level or multi-level cell flash memory. The former stores one bit per memory cell (a value of 0 or 1) while the latter is capable of storing two bits per cell (with possible values of 00, 01, 10, and 11). Obviously, MLC flash has a significant advantage on the storage density front. However, that advantage comes at the cost of write speeds, which are typically much slower than reads. Intel’s MLC-based X25-M, for example, is capable of reading at up to 250MB/s, but its sustained write speed tops out at only 70MB/s. Single-level cell memory doesn’t suffer such a great disparity between read and write speeds, as evidenced by the X25-E Extreme, which reads at up to 250MB/s and writes at up to 170MB/s.

Of course, the more balanced transfer rates offered by SLC memory don’t come cheap. The X25-M 80GB is currently selling for $621 online, which works out to a seemingly exorbitant $7.76 per gigabyte. But that’s nothing compared to the cost of the X25-E Extreme 32GB, which at $719 online, rings in at an even steeper $22.47 per gigabyte. Solid-state storage isn’t cheap, and single-level cell implementations are about as expensive as SSDs get.

The prospect of shelling out three times as much per gigabyte for the X25-E is certainly daunting, but the drive does offer other perks to justify the premium. For example, its 75-microsecond read latency is 10 microseconds quicker than that of the X25-M. That’s not a huge margin, but within the confines of a modern PC, where bits flip at billions of times per second on multiple processor cores, it’s a notable improvement. To put things in perspective, it’s also worth noting that the access time of a VelociRaptor, which has faster seek times than any other Serial ATA hard drive, is two orders of magnitude slower at 7400 microseconds.

While the X25-E’s faster write speed and quicker access latency are great, it’s on the longevity front that the drive offers the biggest step up over the X25-M. Multi-level memory cells are limited to 10,000 write-erase cycles before they burn out. Single-level memory cells, on the other hand, are good for 100,000 write-erase cycles—a difference of one order of magnitude.

SLC-based flash drives should last much longer than those that use MLC memory chips. Exactly how much longer depends on several factors, including the write-erase content of the workloads involved, the size of the drive, its write amplification factor, and the efficiency of its wear-leveling algorithms. Solid-state drive makers tend not to discuss those last two factors, but according to Intel, they can have a profound impact on a drive’s actual lifespan.

Write amplification refers to the amount of data that must actually be written to a drive to complete a given write request. Say you have a 4KB write request and a drive with a 128KB erase block size. You can’t just erase and re-write 4KB of that 128KB erase block—you have to clear and rewrite the whole thing. The write amplification factor is the actual write size divided by the request size, which in this case is 32. Intel claims that the X25-E Extreme’s write amplification factor is less than 1.1, and that “traditional” SSDs have a write amplification factor of closer to 20.

Wear-leveling is also an important component of flash endurance, as drives spread the love in an attempt to distribute write-erase cycles evenly across available cells. This requires some bit shuffling, and drives must take care to ensure that their wear-leveling algorithms don’t burn through too many write-erase cycles in the process. According to Intel, most SSDs have a wear leveling efficiency factor of three. The X25-E Extreme’s wear leveling efficiency factor is quoted as less than 1.1.

If we combine all the factors that Intel says affect solid-state drive longevity, we come up with the following formula for cycling:

Cycles = (Host writes) * (Write amplification factor) * (Wear leveling factor) / (Drive capacity)

With write amplification and wear leveling efficiency factors of 1.1, and 20GB of write-erase requests per day for five years, we should only burn through 1380 cycles on the X25-E Extreme. The same workload on what Intel defines as a “traditional” SSD, with a write amplification factor of 20 and a wear-leveling efficiency of three, consumes more than 68,000 cycles. We don’t want to rely too much on Intel’s likely pessimistic assessment of the wear leveling efficiency and write amplification factors of other solid-state drives, but other SSD makers haven’t been able to give us equivalent numbers of their own.

The X25-E Extreme’s expected lifespan will, of course, depend on how many gigabytes of write-erase operations are thrown at it. Even with 100GB of write-erase per day, it’ll take more than 72 years to burn through the drive. Couple that with the Extreme’s two-million-hour Mean Time Between Failures (MTBF) rating, and one can probably expect the drive to last.

Like its MLC-based cousin, the X25-E uses a 10-channel storage controller backed by 16MB of cache. Amusingly, the cache is provided by Samsung—one of the biggest players in the SSD market—via a K4S281632I-UC60 SDRAM memory chip. The storage controller is an Intel design that’s particularly crafty, supporting not only SMART monitoring, but also Native Command Queuing (NCQ). NCQ was originally designed to compensate for the rotational latency inherent to mechanical hard drives, but here it’s being used in reverse, because Intel says its SSDs are so fast that they actually encounter latency in the host system. It takes a little time (time is of course relative when you’re talking about an SSD whose access latency is measured in microseconds) between when a system completes a request and the next one is issued. NCQ is used to queue up to 32 requests to keep the X25-E busy during any downtime between requests.

Even with its protective shroud removed, the Extreme looks not unlike the X25-M that preceded it. Both drives use a single circuit board populated with 10 memory chips on each side. Intel makes these chips itself using a 50nm fabrication process. With the X25-E, however, the connection points are covered with what appear to be drippings from World of Goo. No doubt this protective coating has been used to prevent enterprising pirates from, er, installing mod chips, or something.

Thus far, we’ve only touched on the performance benefits that solid-state hard drives can provde, but there are other advantages to moving out of the mechanical world. With no moving parts, SSDs are much more resistant to physical shock. They’re absolutely quiet, too, and typically consume much less power than traditional hard drives. Intel rates the X25-E’s idle power consumption at just 0.06W, and when active, that figure only jumps to 2.4W.

The X25-E’s paltry power consumption will be particularly attractive for the enterprise applications at which the drive is targeted. Indeed, this may be the first enterprise-class product to bring Extreme branding into rack servers. Dude, that’s totally where the X25-E’s power savings will add up, as stacks of drives are combined in RAID arrays where every watt saved will also lower cooling costs for the rack.

Test notes
We’ll be comparing the performance of the X25-E Extreme with that of a slew of competitors, including Samsung’s SLC-based FlashSSD and Intel’s own X25-M. We’ve also thrown in a collection of the latest and greatest Serial ATA drives from Hitachi, Samsung, Seagate, and Western Digital. These drives differ when it comes to external transfer rates, spindle speeds, cache sizes, platter densities, and capacity, all of which can have an impact on performance. Keep in mind the following differences as we move through our benchmarks:


Max external
transfer rate

Spindle speed

Cache size

Platter size

Capacity

Barracuda 7200.11
300MB/s 7,200-RPM 32MB 250GB 1TB

Barracuda 7200.11 1.5TB
300MB/s 7,200-RPM 32MB 375GB 1.5TB

Barracuda ES.2
300MB/s 7,200-RPM 32MB 250GB 1TB

Caviar Black
300MB/s 7,200-RPM 32MB 334GB 1TB


Caviar SE16 (640GB)
300MB/s 7,200-RPM 16MB 320GB 640GB

Deskstar 7K1000
300MB/s 7,200-RPM 32MB 200GB 1TB

FlashSSD
300MB/s NA NA NA 64GB


Raptor WD1500ADFD
150MB/s 10,000-RPM 16MB 75GB 150GB

RE2-GP
300MB/s 5,400-7,200RPM 16MB 250GB 1TB

RE3
300MB/s 7,200-RPM 32MB 334GB 1TB

SpinPoint F1
300MB/s 7,200-RPM 32MB 334GB 1TB

VelociRaptor VR150
300MB/s 10,000-RPM 16MB 150GB 300GB

X25-E Extreme
300MB/s NA 16MB NA 32GB

X25-M
300MB/s NA 16MB NA 80GB

Performance data from such a daunting collection of drives can make our bar graphs a little hard to read, so we’ve colored the bars by manufacturer, with the X25-E appearing in a lighter blue than Intel’s X25-M.

Our testing methods
All tests were run three times, and their results were averaged, using the following test system.

Processor Pentium 4 Extreme Edition 3.4GHz
System bus 800MHz (200MHz quad-pumped)
Motherboard Asus P5WD2 Premium
Bios revision 0422
North bridge Intel 955X MCH
South bridge Intel ICH7R
Chipset drivers Chipset 7.2.1.1003
AHCI/RAID 5.1.0.1022
Memory size 1GB (2 DIMMs)
Memory type Micron DDR2 SDRAM at 533MHz
CAS latency (CL) 3
RAS to CAS delay (tRCD) 3
RAS precharge (tRP) 3
Cycle time (tRAS) 8
Audio codec ALC882D
Graphics Radeon X700 Pro 256MB with CATALYST 5.7 drivers
Hard drives Seagate Barracuda 7200.11 1TB
Seagate Barracuda ES.2 1TB
Samsung SpinPoint F1 1TB
Hitachi Deskstar 7K1000 1TB

Western Digital RE2-GP 1TB


Western Digital VelociRaptor 300GB

Western Digital Raptor WD1500ADFD 150GB


Western Digital Caviar Black 1TB

Western Digital Caviar SE16 640GB

Western Digital RE3 1TB


Seagate Barracuda 7200.11 1.5TB

Western Digital Caviar Green 1TB
Samsung FlashSSD 64GB
Intel X25-M 80GB
Intel X25-E Extreme 32GB
OS Windows XP Professional
OS updates Service Pack 2

Thanks to NCIX for getting us the Deskstar 7K1000 and SpinPoint F1.

Our test system was powered by an OCZ PowerStream power supply unit.

We used the following versions of our test applications:

The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.

All 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.

WorldBench
WorldBench uses scripting to step through a series of tasks in common Windows applications. It then produces an overall score. WorldBench also spits out individual results for its component application tests, allowing us to compare performance in each. We’ll look at the overall score, and then we’ll show individual application results.

The X25-E scores five points higher than its MLC-based cousin in WorldBench. That makes it the fastest drive we’ve ever tested here, and not by an insignificant margin.

Multimedia editing and encoding

MusicMatch Jukebox

Windows Media Encoder

Adobe Premiere

VideoWave Movie Creator

Although it’s not often much faster than the competition, the Extreme still turns in the quickest times through WorldBench’s multimedia editing and encoding tests. Only in the Premiere test does the X25-E put some real distance between itself and the rest of the field, besting the VelociRaptor by 18 seconds.

Image processing

Adobe Photoshop

ACDSee PowerPack

The X25-E takes top honors in WorldBench’s ACDSee test, where it’s 34 seconds faster than the X25-M, likely thanks to the faster write speeds allowed by single-level cell memory.

Multitasking and office applications

Microsoft Office

Mozilla

Mozilla and Windows Media Encoder

Scores are close throughout WorldBench’s office and multitasking tests.

Other applications

WinZip

Nero

The X25-E bounces back strongly in WorldBench’s WinZip and Nero tests, though. In the former, it’s only a little quicker than the X25-M. However, in the Nero test the Extreme really shines, leading the other solid-state drives we tested by more than a minute.

Boot and load times
To test system boot and game level load times, we busted out our trusty stopwatch.

Despite dominating WorldBench, the X25-E is only a middle-of-the-pack performer in our boot time test. It’s essentially tied with the X25-M here, and that puts it more than six seconds slower than Samsung’s FlashSSD.

SSDs dominate our level load tests, with the Extreme curiously turning in a slower Far Cry load time than the X25-M. Even then, it’s still a couple of seconds faster than the VelociRaptor.

File Copy Test
File Copy Test is a pseudo-real-world benchmark that times how long it takes to create, read, and copy files in various test patterns. File copying is tested twice: once with the source and target on the same partition, and once with the target on a separate partition. Scores are presented in MB/s.

To make things easier to read, we’ve separated our FC-Test results into individual graphs for each test pattern. We’ll tackle file creation performance first.

FC-Test’s scripted file creation sequences really stress a drive’s write performance, and it’s here that the benefits of SLC memory become readily apparent. The X25-E is more than three times faster than the X25-M virtually across the board, and it’s much quicker than any of the other drives we’ve assembled, as well.

As one might expect, the Extreme isn’t much quicker than the X25-M when we switch to FC-Test’s read benchmarks. The drives offer roughly equivalent read speeds here, although the X25-E is a little quicker with each workload, perhaps due to its slightly lower read latency.

FC-Test – continued

Next, the true file-copy test combines read and write tasks.

With no write performance weakness to speak of, the X25-E dominates our file copy tests in dramatic fashion.

Copying from one partition to another doesn’t slow down the Extreme, either. It’s still the class of the field, by huge margins with each test pattern.

iPEAK multitasking
We’ve developed a series of disk-intensive multitasking tests to highlight the impact of seek times and command queuing on hard drive performance. You can get the low-down on these iPEAK-based tests here. The mean service time of each drive is reported in milliseconds, with lower values representing better performance.

Our iPEAK workloads were recorded using a 40GB partition, so they’re a little big for the 32GB X25-E. The app had no problems running, but it warned us that I/O requests that referenced areas beyond the drive’s 32GB capacity would be wrapped around to the beginning of the drive. Since there should be no performance difference between the beginning and end of an SSD, the results should be valid.

The X25-E continues to make short work of the competition, slicing through our first wave of multi-tasking workloads with apparent ease. Only the X25-M comes close, and even then, only with the one workload that doesn’t stress write performance.

Our second batch of multitasking workloads proves just as fertile ground for the X25-E, which again mops the floor with its rivals. The X25-M comes close to matching the Extreme’s performance with some workloads, but it’s well behind with those that include a file copy operation as the secondary task.

IOMeter
IOMeter presents a good test case for both seek times and command queuing.

Can you guess which IOMeter test pattern is exclusively made up of read operations? I thought so. Only with the web server test pattern does the X25-M manage to hang with Intel’s latest SSD, as both drives roar out to a huge lead over the competition. The M is quite a bit faster than the rest of the field when faced with IOMeter’s other test patterns, too, but it’s not nearly as quick as the Extreme. Based on these results, it’s easy to see why Intel is targeting the X25-E at enterprise environments. No other drive we’ve tested even comes close to matching its performance, and that includes Samsung’s SLC-based FlashSSD.

The X25-E’s IOMeter CPU utilization is much higher than the rest of the field, but that’s to be expected given the fact that the drive is doing significantly more work.

HD Tach
We tested HD Tach with the benchmark’s full variable zone size setting.

HD Tach’s pedal-to-the-floor sustained throughput drag races nicely put the X25-E’s transfer rates into perspective. The Extreme is shadowed by the X25-M in the read speed test, but it’s all alone in the lead when we look at writes. What’s particularly impressive here is that the X25-E actually exceeds its supposed maximum write speed of 170MB/s by nearly 38MB/s. Perhaps even more striking is the fact that the VelociRaptor is at least 100MB/s behind in both tests.

The Extreme retains the lead through HD Tach’s burst speed test, although it doesn’t have much of an advantage over the competition here.

All three of our solid-state drives share the lead here, flexing their huge access latency advantage over mechanical hard drives. This test only tracks random access times down to a tenth of a millisecond, so it doesn’t expose any differences in performance between the SSDs.

While the Extreme’s CPU utilization is the highest of the lot, keep in mind that HD Tach’s margin of error in this test is +/- 2%.

Noise levels
Noise levels were measured with an Extech 407727 Digital Sound Level meter 1″ from the side of the drives at idle and under an HD Tach seek load. Drives were run with the PCB facing up.

These scores represent the noise generated by our test system as a whole, which is why the SSDs are all pegged at 42 decibels—that’s the ambient noise level of the rest of the system. On their own, flash drives don’t so much as make a sound, regardless of whether they’re idling or under load.

Power consumption
For our power consumption tests, we measured the voltage drop across a 0.1-ohm resistor placed in line with the 5V and 12V lines connected to each drive. Through the magic of Ohm’s Law, we were able to calculate the power draw from each voltage rail and add them together for the total power draw of the drive.

Behold, the power efficiency advantage of SSDs. Mechanical hard drives don’t even come close.

Interestingly, Samsung’s FlashSSD consumes less power than both of Intel’s solid-state drives. We’re only talking about fractions of a watt, though.

Conclusions

I had high expectations for the X25-E Extreme, but even those were exceeded by the drive’s stunning performance. This is without a doubt the fastest solid-state drive we’ve ever tested, and based on just how much quicker it is than Samsung’s FlashSSD, I wonder if it might be the fastest flash drive we see for a while. Intel’s decades of chipset design experience likely deserve much of the credit here, as the X25-E’s storage controller seems to do an excellent job of exploiting all the performance potential available in single-level cell flash memory.

Obviously, the Extreme is at its best when subjected to demanding workloads that combine a highly-randomized mix of read and write requests. The drive’s jaw-dropping IOMeter performance is a testament to just how well it handles heavy multi-user loads, and that’s precisely why the X25-E is perfect for the enterprise environments at which it’s targeted. If all you’re running is a web server that’s going to be slammed with read requests all day, you might want to consider the X25-M. However, that drive is going to run out of write-erase cycles much quicker than the X25-E, which should last ten times longer thanks to the higher endurance of SLC memory.

Lest you think it’s only appropriate for servers, the X25-E’s dominating multitasking performance suggests that it’s a good candidate for workstations, too. Based on the drive’s crushing display in FC-Test, I’d say it’s an attractive option for any system that needs to shuffle files around quickly and often. And let’s not forget that the Extreme operates in absolute silence while barely sipping power.

Of course, the X25-E does have its limitations. For example, the drive won’t dramatically speed up typical desktop applications that aren’t terribly bound by storage subsystem performance. The X25-E’s modest 32GB storage capacity may prove too small for some applications, as well, although Intel is slated to release a 64GB version of the drive next year.

Intel X25-E Extreme
November 2008

Perhaps the greatest stumbling block for the X25-E Extreme is one that affects all solid-state drives: price. The Extreme is currently available for as little as $719, which works out to a coronary-inducing $22 per gigabyte. But it would be unwise only to consider the drive in terms of cost per gigabyte. Given its target market, it’s far more appropriate to examine cost as it relates to performance. If we look at the Extreme’s cost per IOMeter transaction, for example, we find that it’s a much better value than any other drive we tested today (with the partial exception of the X25-M, but then only with the web server test pattern).

For those who put a premium on storage subsystem performance, the X25-E actually represents rather good value. And as the fastest drive we’ve ever tested, solid-state or otherwise, bragging rights are guaranteed. Finally, a product deserving of not only its Extreme moniker, but Editor’s Choice distinction, too.

Comments closed
    • SSD Tests
    • 11 years ago

    Ok I have been testing a single Intel X25-E vs a VelociRaptor 74Gb, to find out which is best.

    well looks like im glad i tested it for myself as most if not all reviews and benchmarks on this SSD have been misleading which gave me high hopes. (same thing happened when i checked out a raid card and found out for myslef)

    Simply put the single VelociRaptor 74Gb is as fast at loading photoshop cs3 3dSmax sony vegas etc, i was expecting huge differences, but it was a joke, if the SSD drives were much cheaper and in raid then it should be a clear winner. They even loaded windows the same, not enough diff to make me give a shi

    From now on I will try to Ignore all the crappy benchmarks i see online. anyway the VelociRaptor in HD Tach got a burst of 270.3 mb/s, which would put it in the lead compared to the pics on this site.

    So looks like in a few years+ they will be much better, but as it is they are so similar. A good pro of the SSD was formatting completed fast like within 1-2 minutes, funny thing i found is with the Adaptec 5805 raid card it made a normal 250GBsata format so much quicker too as if it stores info and skips it, but this is after 1 full long time usual format.

    how come no reviews etc of the VelociRaptor 74GB?

    Now im still looking for that amazing difference in loading again!
    and sending back this rip off Intel SSD.
    Go and check them out for yourself and stand up and dont keep it and fool yourself if you dont like it.

      • indeego
      • 11 years ago

      “how come no reviews etc of the VelociRaptor 74GB?”

      probably because it’s not sold by newegg anymore.

      The benches show clear advantages over the Velociraptor.

      If you saved 4 seconds a day using the X25 E or M, that is over 24 minutes a year you would save. Multiply that by hundreds of programs/loading potential, and it adds up quickly.

      “anyway the VelociRaptor in HD Tach got a burst of 270.3 mb/s”
      great, because you will never, ever see sustained speeds of that nature under any raid level with that driveg{<.<}g

    • indeego
    • 11 years ago

    Price has gone up since this reviewg{<.<}g

      • indeego
      • 11 years ago

      Two months later, price is now ~$200 less than the review. Unbelievable g{

    • tremelai
    • 11 years ago

    (Addtional info for posts #79 and #80)
    Here are my thoroughly unscientific bench tests of an SSD vs conventional drive on Linux.

    64GB SSD MCCOE64G5MPP-0VA 2.5in
    vs.
    60GB Hitatchi HTS721060G9S 7200rpm 2.5in

    The system:
    Dell Latitude D620
    2.0Ghz Core 2 T7200
    2GB RAM
    Linux Kernel 2.6.27.6 vanilla
    Ext3 file system (ordered, noatime)

    The test: Best of three; execute OpenOffice 3.0.0 Writer software under the four different I/O schedulers the Linux kernel offers. (reboots in between all tests)

    command line: time oowriter

    (lower is better)

    Hitatchi 60GB 7200 rpm 8mb cache:

    noop (no optimizations, aka FIFO)
    real 0m7.712s
    user 0m0.049s
    sys 0m0.123s

    deadline
    real 0m7.601s
    user 0m0.046s
    sys 0m0.115s

    anticipatory
    real 0m6.725s
    user 0m0.048s
    sys 0m0.146s

    CFQ (Completely Fair Queuing)
    real 0m7.711s
    user 0m0.042s
    sys 0m0.137s

    64GB Samsung SSD:

    noop (no optimizations, aka FIFO)
    real 0m2.369s
    user 0m0.029s
    sys 0m0.111s

    deadline
    real 0m2.380s
    user 0m0.030s
    sys 0m0.128s

    anticapitory
    real 0m2.444s
    user 0m0.036s
    sys 0m0.098s

    CFQ (Completely Fair Queuing)
    real 0m2.668s
    user 0m0.038s
    sys 0m0.112s

    This data shows not only the obvious speed increase the SSD has over a conventional drive but is also shows that the anticipatory/CFQ IO schedulers can help conventional drives and may hurt SSD drives.

    • Bensam123
    • 11 years ago

    I’m not usually a critic of the editor’s choice awards, but how can this even begin to be a candidate when no one will buy one cause they’re so ungodly expensive and even the enterprise sector they’re aimed at would be leery of such costs as well.

      • indeego
      • 11 years ago

      A certain portion of the enterprise market will spend x dollars to reduce the amount of time or increase speed in y product. This has always been the case, and always will be the case.

      The groundbreaking performance enhancements of this product speak for itselfg{<.<}g

    • tremelai
    • 11 years ago

    another quick note. WIndows 7 will detect the hard drive type and if it finds a SSD, it will change its io elevators.

    I/o elevators assume that your hard drive has only one head.
    SSD’s don’t have a head thus these optimizations, designed for mechanical hard drives are obsolete on SSD’s!

    • tremelai
    • 11 years ago

    I would like to see a benchmark using Windows Server 2008 vs Vista or Server 2003 vs XP with user applications.

    Vista and XP both have, what kernel geeks call, disk I/O elevators. Drive elevators are i/o optimization strategies surrounding the physical head position of the drive. A good elevator will re-order I/O requests to transfer blocks near the last head position to the front of the queue, and re-order subsequent i/o’s in close neighborhood chunks. This is much faster than FIFO when you have a multi millisecond head movement cost. On Vista/XP, both OS’s will pause approximately 10ms between major head movements. This wait is designed to anticipate and satisfy an new i/o requests in the heads local neighborhood.

    These optimization are a boon in performance for 5400 and 7200 rpm hard drives but they will hold down the performance of RAID arrays with battery backed-up cache, SAN’s with large NVRAM cache and SSDs.

    Windows Server 2003/2008 are optimized for SAN’s and RAID arrays large nvram caches. These two OS’s use i/o elevators that expect mulit-head arrays and are tilted toward FIFO scheduling with deadline, out of order algorithms.

    Linux gives you four io elevators. CFQ or completely fair queuing, Anticipatory (most analogous to XP/vista’s), Deadline and FIFO.

    My tests have shown deadline and FIFO fly with SAN’s and SSD’s.

      • sdack
      • 11 years ago

      Thanks for the info.

    • Krogoth
    • 11 years ago

    This drive is the holy-grail for workstation and server crowd.

    For everybody else, just stick with a mainstream 7200RPM HDDs. They are much cheaper and deliver almost the same performance at non-workstation/server workloads.

    • deruberhanyok
    • 11 years ago

    Maybe I’m missing something here. It’s fast and efficient. And 32GB. So how is it $750?

    I get that there’s a lot of great technology in it… but really, is there so much fancy silicon on there that it is justifiably priced at more than ten times the cost of a 32GB USB flash drive?

      • sdack
      • 11 years ago

      /[

      • indeego
      • 11 years ago

      Yes. If you know of a mass manufacturing process that can supply the parts in bins of hundreds of thousands at that price level or below, you should _[

        • Krogoth
        • 11 years ago

        No, 2011 at earliest will be the year of SSD.

        The technology still needs to prove itself to the conservative IT crowd. The mainstream does not need the benefits of SSDs, especially when it commands a 15x price premium per GB over a HDD.

      • jwb
      • 11 years ago

      These are priced comparably to enterprise disks. A small form factor 36GB 15krpm SAS disk from the channel (meaning it actually has a warranty) is $400. $750 isn’t bad for the same storage and 50 times the IOPS.

    • d0g_p00p
    • 11 years ago

    Man I cannot wait until these become affordable. I currently have a OCZ 60GB SSD as my OS and apps drive and it’s pretty awesome but the write speeds are nothing to write home about. I would like to see these in a RAID array pitted against the Fusion-IO drive.

    Too bad about the storage size and associated price tag.

    • kilkennycat
    • 11 years ago

    Apologies for raining on the party. Using any SSD as the ONLY drive in a PC without an accompanying hard-disk is potentially courting a disaster consisting of flaky operation and lost files. Exactly when that disaster happens is a time-event that is strongly specific-usage-dependent. The fuller the SSD becomes with static program and static data, the faster the disaster will happen. Consider a laptop PC with a single 80Gbyte SSD and with, say, 75Gbytes full of OS, applications and static data. Still perfectly usable. However the remaining 5 Gbytes will be occupied by dynamic data, especially the Windows virtual memory. So now the wear leveling life-time has to be computed for just this 5Gbytes, instead of the original 80Gbytes !!! And the fuller the disk with static data, the faster the remaining “freely-accessible” data-cells will wear out….Any volunteers to compute the number of cycles of Windows virtual memory in a typical day in a laptop with the minimum RAM recommended for the chosen operating system….???

    And please find me the published read-lifetime of a high-density SLC flash-cell after 100,000 cycles. I doubt it is 10 years…. more likely a few weeks, or less. The Tech Report would do us all a great favor if they could extract from Intel’s Reliabity Test department the graphical profile of write-cycles vs guaranteed data-retention time for the SLC flash-cells in the latest generation of the Intel SSDs. That graph seems to be a closely guarded secret…. or maybe I have been looking in the wrong places for it…. Intel’s website, Google etc… Such information has been openly published in the past as reliability information on conventional flash memory — 2-4 weeks of data-retention after 100,000 cycles comes from reliability data on conventional flash-memory of much bigger storage cell-size than current SSDs.

    A SSD is an exceptionally valuable device for rapidly storing and retrieving data on a NON-CYCLIC basis…such as booting-in the OS
    and storing/loading applications and their stored data. Anything involving short-term rapidly-cycled data (e.g: Windows virtual memory) must use a conventional hard-disk for storing/retrieving such data, if a SSD cell-wear catastrophe is to be averted as long as possible.. It is instructive to note that one of the latest Toshiba lap-tops that includes a SSD also mandatorily includes a hard-disk… I wonder why??

    Some other differences with hard-disks:-

    SSD cells will leak data while just sitting there with power applied.

    Data-failure on a hard-disk is generally a one-way event with the failure easily verified by a hard-disk test-program. A marginal SSD cell can remain in a flaky data-state for a long period of time. The flaky nature can result in system-failures with symptoms that are very similar to failing RAM, motherboard or CPU. It may be difficult to pin-point the problem to the SSD… unless the wear-leveling algorithms in the SSD are supplemented by physical hardware-sensing of each cell’s voltage margin above threshold and which can flag the user before the cell-data fails.

      • jwb
      • 11 years ago

      You are a moron. Somebody had to say it. I wonder what is wrong with you people. Do you really think that there are engineers at Intel right now slapping their foreheads because they didn’t realize this problem until some random dingbat on a random internet forum pointed it out?

      The controller on an SSD moves “static data” around as a matter of course. And since the SSD’s erase block (128KiB) is much larger than a filesystem block (4KiB) it can be much smarter about data placement than the operating system is. Also an SSD is typically 10-20% larger than its claimed capacity, and each chip has an additional 5% over its claimed capacity. An 80GB SSD may have as much as 100GB of flash memory on it, so it’s never more than 80% full anyway.

    • indeego
    • 11 years ago

    I just showed my SQL servers the benches and white stuff started oozing out of the drive baysg{<.<}g icky.

      • 5150
      • 11 years ago

      For God sakes man, clean it up before they fertilize!

      • shalmon
      • 11 years ago

      hahaha….wicked…dirty servers

    • TheEmrys
    • 11 years ago

    Indeed, this may be the first enterprise-class product to bring Extreme branding into rack servers. *[

      • jensend
      • 11 years ago

      They’re just mocking the annoyingness of the EXTREME!!!11 branding.

      • btb
      • 11 years ago

      Dude, whats wrong with that? 😉

    • Steel
    • 11 years ago

    A request: since these drives will fit quite nicely in a notebook, it might be a good idea to include at least one standard notebook drive in future comparisons.

    • da sponge
    • 11 years ago

    I’d REALLY like to see this in comparison with 3.5″ & 2.5″ 15K RPM SAS drives. Especially given that it’s as expensive, if not more expensive than SAS. SATA comparisons are neat and all, but there nowhere in the same class. Why not make a more useful comparison?

    • flip-mode
    • 11 years ago

    Obligatory:

    But, can it play /[

      • eitje
      • 11 years ago

      and can it fold?

    • clone
    • 11 years ago

    I’d love to buy one of these or even 2 but Intel will have to cut the price in half for it to happen.

    80gb’s for $800 is just too much….. I’m sure their is a market but I wouldn’t ignore the enthusiast segment at the same time and with that price Intel is totally ignoring it.

    in reality I’d buy 2 of these at 1 / 4 the current price if they offered 100mb/s read and 80mb/s write because the latency times are gone in going with one…. or two which is more than enough reason to buy.

    but again Intel apparently has no interest in the enthusiast atm in this market.

      • Meadows
      • 11 years ago

      Strange suggestion, I’d have thought there’s no demand for this whatsoever other than news flashing and marketing buzz.

        • titan
        • 11 years ago

        There certainly is a demand. I’d be very interested in getting an SSD if it were more affordable. Page file and swap access are little files and are hindered more by the time it takes to get to the data than the actual transfer. Also, games are bound to see a bigger benefit throughout the play because it isn’t just sequential transfers.

          • Meadows
          • 11 years ago

          “There certainly is a demand. I’d be very interested in getting an SSD if it were more affordable.”

          Which means there’s no demand.
          I’m talking about this drive in particular. It’s too expensive for a home consumer, and too low on capacity to be of any use at a corporation. It’s basically useless.

            • titan
            • 11 years ago

            Then you clearly haven’t thought about its use use in a Web server. I’m pretty sure places like Google, NewEgg, Amazon and Slashdot have either considered or have already put SSD’s into play. Being able to serve a significant amount more per machine is extremely tantalizing when one considers the additional costs over conventional HDD’s.

      • sdack
      • 11 years ago

      This was a high-end SSD and will likely set the limits of what we will see arriving at the markets for a while. I am pretty sure TR will do more test reports on SSDs in the future. You are not the only one with a demand for cheaper SSDs.

      • d0g_p00p
      • 11 years ago

      Get the OCZ Core Series V2. I have this as my OS/Apps disk and it has the specs you are looking for. I picked mine up for around $140 for the 60GB model and I am sure it’s cheaper now.

    • eitje
    • 11 years ago

    I’m curious about the idle & load ratings from Intel, and why they’re so wildly different from TR’s results. After all, the idle rating was off by an order of magnitude… what tests did they run to get that 0.06W number?

    And not to sound like a total bumpkin, I know that company ratings are normally the very top and bottom they expect from the drive, with actual operating values somewhere in between. I just expected them to be somewhat closer.

      • sdack
      • 11 years ago

      It could have to do with sleep modes and the drive’s power management. At 0.06W I could imagine that it is in a deep sleep mode and TR may have only measured the power usage while the drives were idle for only a few minutes.

    • Neutronbeam
    • 11 years ago

    Picked this up somewhere, maybe DailyTech — it’s part of notes I’m keeping for my new build next year–

    “The street price for the 2.5″ 80GB X25-M will drop from $600 to $525 on November 30.

    Moving over to the single-level cell (SLC) parts, Intel will introduce its high performance 32GB X25-E and the price will drop to $575 on December 28. A 64GB part will be introduced in the first half of 2009 for $990.”

    • S_D
    • 11 years ago

    My only surprise is that it didn’t win in absolutely all the test (apart from CPU usage). Why didn’t it boot the quickest for example? What could be the reason for this?

      • sdack
      • 11 years ago

      It is a tough question … Is Windows not running some sort of disk benchmark while it boots? I think it is called “diskperf” and it does some initial measurements the OS then uses AFAIK. If it probes disk speed on boot-up it could backfire, i.e. rerun itself with different parameters when it thinks the first run was too fast to be accurate. …

      It is worth investigating.

    • Fighterpilot
    • 11 years ago

    I expect if you bought one of those SSDs today and a bunch of hard drives of various sizes and ran them in a machine,the hard drives would be cold, dead mechanical door stoppers before the SSD would fail.

      • sdack
      • 11 years ago

      And: It is sometimes not the MTBF that cripples a device – most people will have bought a new disk before then – but rather the bugs in a drive’s BIOS.

      • Nitrodist
      • 11 years ago

      MTBF is not really an accurate measure of when a unit will fail.

        • sdack
        • 11 years ago

        What is an accurate measure of when a unit will fail?

        If you are referring to crystal balls and tea leaves for an accurate prediction of the future then I suppose you are right. But if not, then the MTBF is an accurate measure for the life-time of a device (and under its given terms and conditions).

    • axeman
    • 11 years ago

    Kudos on using the 1 ohm resistor, it’s a pretty easy method to measure current draw, not to mention more accurate and useful than measuring system power consumption as a whole. Was this a first in TR reviews? I can’t remember. On a side note, look at that power consumption of the Hitachi drive under load… 15 watts is lot for a 7K drive!

      • eitje
      • 11 years ago

      They’ve been doing it on HDD reviews for quite a while.

    • Pax-UX
    • 11 years ago

    r[

      • Firestarter
      • 11 years ago

      I’d like to hear from anyone who can legitimately claim that he/she destroyed a SSD through normal use.

        • Meadows
        • 11 years ago

        Given the recent appearance of these devices, you may have to wait a bit.

        • axeman
        • 11 years ago

        I agree, there’s no empirical data to suggest they will die, but the expected life, at least on the MLC flash drives, makes me suspicious.

    • Meadows
    • 11 years ago

    This was the thing they should’ve come up with originally for the X25-M, then I probably would’ve dissed it less.

    Tests show it’s not bad, but it’s not revolutionary yet. I guess Windows 7 will help these spread (first through geeks), but it won’t exactly make them faster, just give them a longer overall life for the most part (the majority of which you can already do by turning off automatic defragmentation in Vista – Windows 7 turns that off for you for an SSD, among other things).

      • Fighterpilot
      • 11 years ago

      very nice …but $3000?….yikes!

      • jwb
      • 11 years ago

      Yes, but it’s also a desperately inconvenient form factor, and it only has drivers for Linux or Win64, and those drivers are terrible. With a SATA disk you don’t worry about the drivers, because there aren’t any.

    • Convert
    • 11 years ago

    Sooo Dissonance, the burning question is, what was the personal experience like?

    I know it’s subjective but I am curious.

      • Tairc
      • 11 years ago

      Agreed –
      Can we get some interpretive comments from the reviewer regarding ‘teh snappy’, boot times, app start times, and other things? I’d love to know if apps will start faster, for example – as a hotkey junkie, every 0.1 seconds matters where my fingers are idle, waiting to give the next command.

      • sdack
      • 11 years ago

      They gave it the Editor’s Choice Award and ponder over its future. Looks like they found something satisfying, saying it deserves its title of being extreme.

      Filling up the cold facts with colorful language only blurs the information. I think it was a very interesting, informative and insightful read and I do not see a need for entertainment here. (I watch TV for my dosage of entertainment.)

        • Convert
        • 11 years ago

        No offense to you or TR but the awards they hand out are 100% useless to me.

        The exceptional review content is what matters and is what I use to buy or recommend products.

        Also a lot of the comments made are just reflection on the results. Which is fine. Though it doesn’t really tell me what I asked.

        q[< Filling up the cold facts with colorful language only blurs the information. I think it was a very interesting, informative and insightful read and I do not see a need for entertainment here. (I watch TV for my dosage of entertainment.) <]q I will PM you some day if I start caring and need insight into other things, but that will probably never happen as I am not prone to head injuries. Graphs are great, benchmarks are great and the review itself is great. I never expected him to say "OMG wow this drive is the tits" but when you see something obliterate the competition on almost every single benchmark the burning question is "Does it really feel any different". IIRC I think I remember reading a similar comment when the x2 came out or the a64, I can't remember, but it was basically "I feel a difference using windows" type of comment. So it's not like TR is beyond describing such things.

          • sdack
          • 11 years ago

          I will ignore the snappish remarks as long as you do not start caring for me.

          If it helps, every change above 10%-15% can be felt. Meaning you do not need to run repeated tests and to measure the times to notice a difference, but instead will you notice a difference based on your long term memory.

          Take a look at the graphs and see where the difference is more than 10%-15% and you can see if it will be snappy.

            • Convert
            • 11 years ago

            Problem is some of the graphs don’t correlate with what you see in the real world perception wise. As in yeah great it can do x task 20% faster but it doesn’t actually translate into tangible gains.

            Transfer speeds, compile times and all that good stuff would obviously have a direct and tangible difference.

            I am simply curious about how it was actually using the system, something the benchmarks don’t cover.

            • sdack
            • 11 years ago

            /[

            • indeego
            • 11 years ago

            /[

            • Krogoth
            • 11 years ago

            There is not much of a point to upgrade the test rig.

            This benchmark is meant to test I/O performance. I doubt aging ICH7 southbridge is any bottleneck nor are any of the other key system components.

            Changing OSs only tests the file system not the HDD/SSDs per say.

            • indeego
            • 11 years ago

            There certainly are bottlenecks in benchmarks like worldbench, due to bus/I/O and CPU differences. There may be less or more of a *[

            • Convert
            • 11 years ago

            He is talking about the specifications of the drive and or the benchmarks.

            Why the heck is this so hard for you to understand, it’s like you are simply interested in reading your own posts or something.

            All I am curious about is if the system felt any different while using the drive. The benchmarks told me everything else I wanted to know.

            • sdack
            • 11 years ago

            For Christ’s Sake, have a guess.

            What you want is a kids version of the TR test and I hope you will never get to see one! If the maturity level of the writer is over your head then it is not writer’s fault, really, you know?

            Or try Tom’s Hardware for your dosage of cheesy test reports.

            • eitje
            • 11 years ago

            you’re being exceptionally rude, sdack.

            what he’s asking for is reasonable. your responses are not. please chill.

            • sdack
            • 11 years ago

            What he wants is a report where someone sticks an enterprise class SSD into a standard PC and then says “it feels faster”. Do you have any idea how stupid this will come across? I guess not. Journalists work hard and for many years to get to the point where they can write accurate reports about a product with a little amount of lines, filled with only relevant details, still produce two pages of text, and _[

            • eitje
            • 11 years ago

            I can see you’ll be nothing but problems.

            Take a look at some of the articles in the “Mobile” section of TR for descriptions of the subjective feel of a system that Convert is asking to see.

            • sdack
            • 11 years ago

            So you cannot tell a good article from a bad one. For someone who thinks telling the truth is rude does this not come as a surprise.

            Anything else on your mind?

            • Convert
            • 11 years ago

            Nice complex you have there, did it develop early in life?

            I like how the “truth” is a personal opinion in your world, a completely subjective view on how things /[

            • sdack
            • 11 years ago

            You sound a little dissonant. Read what you just wrote to reflect on your initial comment and see if it helps.

            • Convert
            • 11 years ago

            Point out the error, because I don’t see it.

            • sdack
            • 11 years ago

            You are giving advise to others without knowing if it is any good or when you know it is not good.

            • Convert
            • 11 years ago

            Err what? What advice was I giving?

            • sdack
            • 11 years ago

            When you ask for a subjective view in a comment then that is an advise for TR on how to write a better article as it would obviously help you in reading it. Yet you knew it was subjective.

            I then gave you some pointers on how to interpret the article (i.e. the award) to which you responded with criticism, a snappish remark and continued in pointing out the importance of a subjective view. You continued to point out the importance several times.

            If this was not an attempt in giving advice then what was it and why did you write it?

            • Convert
            • 11 years ago

            Are you for real?

            There wasn’t an ounce of suggestion or advice in my post. The only possible advice any sane person could glean from my posts was the suggestion for you to get a voice recorder to save us from your babbling.

            Why did I make the post? Hmm gee, maybe I had a ******* question? Would that be possible? What the heck kind of world do you live in, are you off on another site reading a post from someone else that has a similar name to mine?

            Sooo Dissonance, the burning *[

            • sdack
            • 11 years ago

            I am for real. Now you can stop lying. I will not take interest in you any longer as I do not think you have anything of value to contribute. You are probably just some kid who did not get enough of the report, has no real interest in SSDs and likes make voice devices. Or perhaps you use the comment section as your make voice device, who knows?

            • Convert
            • 11 years ago

            That’s called a troll apology. I guess it’s better than nothing.

            Next time don’t assume you know what you are talking about and then dig a hole so deep you can’t climb out of it.

            At any point in time you could have said “Ooops I thought you meant you wanted TR to change the review to reflect your viewpoint, I see now you just had a innocent question” and things would have been easier for everyone.

            • sdack
            • 11 years ago

            You think I am apologizing to you?

            What did I do to you?

            • Convert
            • 11 years ago

            Attacking my post based on your incorrect assumption I wanted them to edit the review. Being a troll. Being a nuisance. Being delusional. Continuation of assey behavior whilst foot was firmly in mouth. Did I mention being a troll already?

            Take your pick, doesn’t matter which one. I think the most important one is attacking a innocent question, which is something that should not take place in a discussion where people are genuinely interested in learning something. Do that and you make it a inhospitable environment to participate in. Which is probably why the mods were firm with your forum behavior.

            Why would anyone participate when some jack hole is more interested in a pissing contest.

            • sdack
            • 11 years ago

            You have a funny way of coming around 😉

            I think what is missing and what would have helped you is a “TR Ranking” of all the HDDs and SSDs. The final part, the conclusions, should present a graph where all devices get an overall score based on the individual benchmarks. This would be like a subjective view.

            • Convert
            • 11 years ago

            q[

            • eitje
            • 11 years ago

            your content isn’t rude, it’s your delivery of that content which is rude.

            q[

            • sdack
            • 11 years ago

            I am so sorry! I hope I am not creeping out anyone?!?

            • Convert
            • 11 years ago

            Hey I was enjoying watching how far he could get his foot down his throat, why did you have to go and spoil it with proof TR does what he is railing against 😉

            • Convert
            • 11 years ago

            You know they make voice recorders, that would definitely be a more effective means at stroking your ego and it might even get you away from your keyboard.

            As for writing like a clown, that’s what makes TR special. They aren’t afraid to get a little goofy while writing their reviews. Though you wouldn’t know that would you, only being here for a few months and all.

            Which makes sense because you obviously haven’t learned how to follow a conversation online. It’s like you think I ignored the review and only wanted to know if the cards in solitaire bounced faster or something. Meanwhile I am discussing the use of these drives in a customer’s server, so yeah, keep living in your delusional world where you are clearly more interested in talking over people than listening to what they are actually asking.

            Not that I asked for your input, oddly enough I only remember asking Diss, the author of this great article, for something obviously subjective and for something I never expected to be in the article in first place given the target audience for the drive. I am so glad you thought your personal views were wanted or that they actually had any bearing on the question, sadly they weren’t and didn’t.

            Your post is incredibly ridiculous, child’s level, seriously? Do you realize they tested game load times? Did you even read this review?

            You know you are right, silly me, reading the post I wrote I see now that I advocated they scrap the review and all of their work and instead replace it with a few sentences describing how fast the thumbnail generation was on the collection of midget porn.

            • Usacomp2k3
            • 11 years ago

            Sadly Vista did away with the bouncing. Sadness. That was the exciting part about winning. Then again, once monitor got bigger than 1024×768, it was very hard to fill up the screen.

      • Freon
      • 11 years ago

      It is baffling that you would prefer the very flawed methodology of subjective experience over objective tests. I think you’ve missed what TR is good at, which is providing objective, metric-based benchmarks.

      It’s one thing to point out that benchmarks don’t exactly match the real world. But it is another to actually claim subjective experience is a better gauge than objective tests. There is so much room for BS.

      If you want subjective bullcrap, there are plenty of poorly written, BS-infused enthusiast websites out there looking to spam you with ads without providing any truly useful information. Heck, I can make stuff up, too, using emotion based words like “awesome” and “speedy” or “bitchin’ fast.” Can I get some ad checks? Pretty easy when you don’t actually have to do any real work to write a review…

    • Loie
    • 11 years ago

    The goo is there to secure and protect the BGA underneath the chips from oxidation, thermal expansion, and the microfractures that would result.

    Lead free solder is a PITA for the entire industry.

      • Forge
      • 11 years ago

      Yes, but World of Goo linkage FTW.

      The resemblance is also strong.

      • Turd-Monkey
      • 11 years ago

      q[http://www.techreport.com/articles.x/15433<]§ My *[

        • mako
        • 11 years ago

        Epoxy can be used for mechanical purposes. Or it’s for retarding eventual tin whisker growth, though that’s just speculation on my part.

        • ludi
        • 11 years ago

        Look again — that X25-M is only using one BGA chip (the controller). The FLASH array is a flat-pack design.

        Given that this design is intended for enterprise (where a certain amount of mechanical abuse is to be expected) AND is using an entire board filled with BGA chips, Intel probably decided the added manufacturing cost of adding oobleck was justified by reliability concerns.

      • ssidbroadcast
      • 11 years ago

      Oh ummk I thought Venom’s Symbiote was makin’ it more powerful/angsty.

    • Jasked1
    • 11 years ago

    I suggest that you consider reporting “CPU utilization/throughput” when reporting CPU utilization. This would provide much more meaningful information.

    • Voldenuit
    • 11 years ago

    ICH7? Does this present any potential bottlenecks that we should be aware of?

      • Forge
      • 11 years ago

      No.r[< <]rl[< <]l

      • DrDillyBar
      • 11 years ago

      Sustained > Peak

      • jwb
      • 11 years ago

      Actually yes, it does. In my SSD tests nvidia SATA ports are rather faster than Intel SATA ports. You’d never notice on a regular disk.

    • Usacomp2k3
    • 11 years ago

    Holy price batman!

    Holy performance batman! Too bad it’s not in anything I’d have a use for.

      • Skrying
      • 11 years ago

      Yes, it’s hard to tell what is more impressive. The price or performance.

    • StashTheVampede
    • 11 years ago

    SSD for most apps, HDs for backup and storage.

      • shalmon
      • 11 years ago

      yeah, that’s what i could see myself doing myself once the price gets lower…run one for a system partition with hd in tandem for backup & storage.

      hopefully my current rig lasts me the next couple years until that happens….it’s already 4 years old

    • Bruce
    • 11 years ago

    Ignore me, my maths was wrong 🙁

Pin It on Pinterest