6 Replies Latest reply on Jul 3, 2011 10:50 AM by

    Intel SSD Media Wearout

    blanket

      Dear users,

       

      I would like to know what the lowest media wear out level anyone has experienced using his / her Intel SSD (please also state the lifetime of your drive; this will give me a good indication). Furthermore I would like to use the drive for some research which involves large data sets (usage of max. 10TB a day). Would it be advisable to buy a SSD?

       

      In this video (http://communities.intel.com/community/tech/solidstate), someone from Intel stated: "That if the number is approaching zero, you should be really careful". What does approaching zero means in this context? Should like 20 be stated as approaching zero or should it really be like <10?

       

      Thank you for your answers.

        • 2. Re: Intel SSD Media Wearout
          NandFlashGuy

          Hello Blanket,

           

          There are leaked Intel SSD roadmaps on the web that talk about "Lyndonville".  According to this website, this may use enterprise-MLC Nand to dramatically increase the Nand flash lifetime.  This may be ideal for your usage model:

          http://www.xbitlabs.com/news/storage/display/20100615213913_Intel_to_Use_Enterprise_MLC_in_Next_Gen_Enterprise_Solid_State_Drives.html

          • 3. Re: Intel SSD Media Wearout

            Does TRIM work correctly on an OS software raid
            whose members are set to AHCI mode e.g. for dedicated data partition(s)?


            As a general rule, should MLC SSDs be assembled in RAID 0 arrays,
            in order to spread the wear?


            In other words, is this theoretically correct and can this be confirmed experimentally ...


            50% reduction per drive w/ 2 x SSDs in RAID 0? (half as much per drive)
            67% reduction per drive w/ 3 x SSDs in RAID 0? (one-third as much per drive)
            75% reduction per drive w/ 4 x SSDs in RAID 0? (one-fourth as much per drive)


            Lastly, has Intel done any research using SSDs with Windows NTFS compression enabled?

            (in drive letter Properties, see:  "Compress drive to save disk space" and a check box)



            Thanks!



            MRFS

            • 4. Re: Intel SSD Media Wearout
              DuckieHo

              The more data written to a SSD, the more wear occurs regardless of RAID or not.  So yes, there is an about 50% reduction in writes on a single member of a 2xRAID0.

               

               

              As for NTFS Compression: http://blogs.msdn.com/b/e7/archive/2009/05/05/support-and-q-a-for-solid-state-drives-and.aspx

               

              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.

              1 of 1 people found this helpful
              • 5. Re: Intel SSD Media Wearout
                blanket

                Thanks! Based on those graph in the frist post link, I would conclude that it is still not suitable yet for my research data to be stored there. However maybe instead of tackling the problem from the SSD side, I can tackle the problem from writing less.

                 

                Thanks all for your answers, you've all been very helpful to me!

                • 6. Re: Intel SSD Media Wearout

                  Blanket,

                   

                  My office is also responsible for maintaining a research database.

                   

                  Here's what we have found:

                   

                  (1)  a 2xRAID0 of rotating platters is generally faster, and

                  contrary to widespread public opinion, the load on each is

                  roughly 50% over time;

                   

                  (2)  if one member fails, the practical effect is the same

                  as a single drive failing:  the failed drive must be replaced and

                  the data restored -->  "same difference" practically speaking

                   

                  (3)  quality input power is a must, e.g. good UPS;

                   

                  (4)  proper environmental control is also a must:

                  keeping dust filters clean, keeping ambient temps

                  under control and within range, etc.

                   

                  (5)  all high-performance HDDs must be installed

                  in drive cages with active cooling;

                   

                  (6)  the HDDs with 5-year warranties are more reliable,

                  and the cost per warranty year is usually preferred

                  as compared to 3-year warranties; e.g. Western Digital

                  RAID Edition HDDs ("RE");

                   

                  (7)  a key management policy is to EXPECT a failure,

                  and to have enough backups to recover gracefully;

                   

                  (8)  application of rigorous probability and statistics

                  urges this conclusion:  the conditional probability

                  that both drives fail, given that one drive of a 2xRAID0 fails,

                  is extremely small;  and, 50% less WRITEs are a major

                  factor increasing longevity;

                   

                  (9)  data rate is directly proportional to track circumference

                  on all rotating HDDs, because they maintain the same or

                  similar recording density on all tracks;  thus, more frequently

                  accessed files should be allocated to "short-stroked" regions

                  on all HDDs, if possible;

                   

                  (10)  short-stroked drives move the READ/WRITE armature less,

                  which in turn reduces wear on the armature bearing and

                  servo-mechanism;  and, in combination with RAID-0 arrays,

                  short-stroking is enhanced in proportion to the number of

                  RAID-0 members (a 100GB RAID0 partition uses only

                  the first 25GB worth of tracks on a 4x RAID0);

                   

                  (11)  for temporary files like browser caches and OS swap files,

                  consider a generous ramdisk:  this offloads rotating platters,

                  further reducing wear on the latter;  and, properly configured,

                  ramdisks can increase real-time performance 15- to 20- TIMES

                  over rotating platters;  cf. my review of RamDisk Plus here:

                   

                  http://www.supremelaw.org/systems/superspeed/RamDiskPlus.Review.htm

                  (DDR3 has become even faster, since that review was written:

                  and, quad-channel memory access is expected for LGA2011 sockets)

                   

                  (12)  we're still waiting for an answer to our question about TRIM

                  on OS software RAIDs when members are configured in AHCI mode;

                   

                  (13)  all of the above strongly suggests that the Media Wearout Indicator ("MWI")

                  on modern Nand Flash SSDS will decline half as fast with a 2xRAID0,

                  one third as fast with a 3xRAID0, and one-fourth as fast with a 4xRAID0,

                  simply because of the way "striping" happens on all RAID 0 arrays;

                   

                  (14)  an experiment that Intel should consider doing, and publishing,

                  is to formulate a proper experimental matrix, and test the real effects

                  that result from enabling NTFS compression on Nand Flash SSDs,

                  with and without RAID configurations;  SandForce controllers do

                  real-time compression, reportedly to reduce WRITEs as much as possible;

                  why not make this the DEFAULT that is performed by the OS, regardless

                  of the SSD's make or model?

                   

                  (15)  the results of proper experimentation at (14) above should

                  produce data that will suggest an optimal policy:  for example,

                  perhaps a 3xRAID0 does more to reduce WRITEs to each SSD member

                  than default NTFS compression, due to the type of compression that

                  is done in real-time by Windows operating systems (LZ77?):

                   

                  http://oldwww.rasip.fer.hr/research/compress/algorithms/fund/lz/lz77.html

                   

                  (16)  and, given the proliferation of multi-core CPUs, in addition to those

                  that also support Hyper-Threading, there should be otherwise unused

                  CPU core resources to perform decompression rapidly in real-time, without

                  adding too much overhead or causing excessive additional latency

                  when accessing compressed files;  SpeedStep and Turbo Boost

                  will only help mitigate this overhead, if they are activated to help

                  accelerate real-time decompression.

                   

                   

                  Those are just some lessons we've learned here, after many years

                  at Hard Knocks University.

                   

                   

                  Hope this helps.

                   

                   

                  Sincerely yours,
                  /s/ Paul A. Mitchell, Instructor,
                  Inventor and Systems Development Consultant

                   

                  All Rights Reserved without Prejudice