All about Internal Storage
 Latest Internal Storage articles
All Internal Storage articles

Newsletters


  • Ask your question about IT issues
  • Post

Partners

The Games selection

crazy : Interactive Boogy Pick one of the 3 songs, hit on the correct keys matching this boy's dance moves.
crazy : Xiao Xiao 7 A great fight scene from the animation movies Xiao Xiao.
Ads

Sponsored links

Digging Deeper...

Previous Next
2:00 AM - 04/27/2009 by Patrick Schmid and Achim Roos

We took two Intel flash SSDs—the X25-M at 80 GB for enthusiasts and the X25-E 32 GB professional series—as well as Samsung’s latest PB22-J 256 GB drive, to check how performance changes as we bombard the drives with changing workloads.

We decided not to do tests with most of the drives full, as enthusiasts will try to avoid using more capacity than necessary on their fast system SSD, putting most data on complementary hard drives. Instead, we focused on alternating I/O and sequential throughput tests on the SSDs, which turned out to be a good way to push existing performance limits.

We were among the first to notice varying SSD performance when we reviewed Intel’s flash SSD, the 80-GB X25-M in September 2008. While the X25-M would typically provide an average of 70+ MB/s in sequential write throughput, changing between heavy I/O operations and our sequential benchmark resulted in drastically reduced write performance. In fact, write throughput dropped to 10-30 MB/s, and it took a while until the drive “recovered,” meaning that the flash controller was able to finally adjust to the new workload conditions.

We first focused on the issue of performance drops with changing workloads in September 2008.

We discovered that these observations are also valid for all other high performance MLC flash SSDs, and many SLC SSDs as well. The X25-E SLC SSD was included in an effort to look at how performance varies on this particular model, as it is based on the same design as the X25-M.

What Intel Did

Knowing about the circumstances we first covered in September 2008, and under which PC Perspective analyzed in great detail in February, Intel has released a firmware update for its X18-M (1.8”) and X25-M drives. You can download it on the support section of the Intel Web site.

Of course we ran the X25-M tests both with the old firmware 8160 and the new version 8820. Needless to say the new firmware made a huge difference in performance variance with heavily-changing workloads. You can flash the firmware yourself, but it is recommended that you back up your data before doing so.

Talkback
mrubermonkey 04/27/2009 9:16 AM
Hide
-1+

Props to you guys for this review.

Tindytim 04/27/2009 9:47 AM
Hide
-3+

I really wish we were able to Thumb up or Thumb down articles. This one would get a large thumbs up from me.

chookman 04/27/2009 9:58 AM
Hide
-1+

Thumbs up on this one too from me. Although if anyone desires more in depth understanding of the problem i found the PC Perspective articles better in that aspect.

Intel Firmware change
http://www.pcper.com/article.php?aid=691

OCZ Indilinx Chip
http://www.pcper.com/article.php?aid=670

chookman 04/27/2009 9:58 AM
Show
chookman 04/27/2009 9:59 AM
Show
empstar 04/27/2009 10:55 AM
Hide
-5+

why don't show the HDD read / write data here together with SDD?

lire210 04/27/2009 12:56 PM
Show
snotling 04/27/2009 1:29 PM
Hide
-4+

lire210 :
this will not matter at all to servers until the price gooes down. the speed does not make sence in the 4+ bucks a gig. normal hd are safer just in the fact that you can put 7 hd and put it in a raid one fails o well. plus 800 bucks for 64gb o my god


Servers are actually where these drives makes the most sense, and you can RAID SSDs just like you RAID HDs... and about being "safe" well I would put my money on the technology with no moving parts!

xsamitt 04/27/2009 2:27 PM
Hide
-6+

I keep waiting for a reviews of new monitors.it seems we keep getting almost the same kind of topic every week lately.

rubix_1011 04/27/2009 3:37 PM
Hide
-0+

I have to agree with most people on this one...a flashback to the really good reviews Tom's did in the past. A very relevant review for most people with some good data and testing steps.

arkadi 04/27/2009 3:39 PM
Hide
-0+

Well it like it was written specially for me. Grate job! One of the best articles i encounter in long time.
I posted a question on storage configuration just few day ago, with no reply btw, with exactly the same thing on my mind. Hope we can go deeper with that, and talk how we can take an advantage of what we learned here in different situations with diffident storage/system configuration's, combining SSD with regular drives, raid configurations, moving tmp/swap some programs etc.. to different drives etc...

arkadi 04/27/2009 3:40 PM
Show
tipoo 04/27/2009 3:45 PM
Hide
-1+

Nice review. So will you guys be reviewing the 1TB PCI-Express OCZ SSD? :-)

Anonymous 04/27/2009 4:50 PM
Hide
-0+

So if your SSD starts to slow down, does a reformat get rid of that issue?

yourhighness 04/27/2009 6:22 PM
Hide
-0+

You guys had any problems with that Power Supply?

I bought an OCZ Elite Extreme 800W PSU last year an dhad 3 of them die in 6 months....The RMA process was long and slow, but they eventually made it right by upgrading me to a PC Power and cooling PSU.

Area51 04/27/2009 6:49 PM
Hide
-2+

lire210 :
this will not matter at all to servers until the price gooes down. the speed does not make sence in the 4+ bucks a gig. normal hd are safer just in the fact that you can put 7 hd and put it in a raid one fails o well. plus 800 bucks for 64gb o my god


You need to have a better understanding of the problem before you make statements like this...

1. The number of HD required to get the same IOPS will put the total price to be higher than SSD's
2. The power requirement is much higher for the number of HD that you need to get the same performance as a single Intel SLC SSD. This can drop the power consumption of a server significantly down from regular HD, and increase it’s performance.
3. Remember that in many servers it’s not the capacity that matters, It’s the performance that is more important.
4. Since SSD's can do a very nice job of simultaneous read, and write running multiple jobs is not derogated by the SSD's as it is with regular HD's.
5. SMART command in SSD’s can give you a predictive failure analysis, something that you cannot do with HD’s, HD’s can only show you if the Drive is good or bad. This is very important since data can be copied before the drive goes bad.
6. MTBF of SSD’s (at lease Intel’s) are much higher than HD’s. 2M hrs. vs 1.2M hrs on HD’s


krazyderek 04/28/2009 1:06 AM
Hide
-2+

wheres the OCZ vertex ?????

krazyderek 04/28/2009 1:08 AM
Hide
-0+

lire210 :
this will not matter at all to servers until the price gooes down. the speed does not make sence in the 4+ bucks a gig. normal hd are safer just in the fact that you can put 7 hd and put it in a raid one fails o well. plus 800 bucks for 64gb o my god


have you seen how much SAS drives are??

hustler539 04/28/2009 1:07 PM
Hide
-0+

Good to see more review sites doing articles on these performance degradations, helps us make a better informed decision when purchasing new hardware.

Here's another great article which gives you a good in depth look at it
http://www.anandtech.com/storage/s [...] i=3531&p=4
a must read if you are thinking of upgrading to some of those new shiny ssds

hustler539 04/28/2009 1:08 PM
Hide
--1+

krazyderek :
wheres the OCZ vertex ?????




^ a review of that is in the article as well


Comments are closed on this page.

Sponsored links

Related articles

  • Does Power-Saving Technology Kill SSD Performance?

    Processor speed matters. We found that a fast solid state disk drive, such as Intel’s X25-E, can be greatly impaired by a system running with all of its CPU’s power saving features turned on. Surprised? Read our full analysis for the specifics.

  • The SSD Workload Performance Analysis

    Today we're running a series of benchmarks on the latest SSD offering from Intel and Samsung to see how performance changes over time. We discovered that there are some severe performance issues, but also solutions you should know about.

  • The SSD Power Consumption Hoax

    Manufacturers tout the power savings of flash-based solid state drives compared to conventional hard drives. True? Check out our notebook battery tests.