Al Hopper
2008-Jun-11 08:16 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
I''ve been reading, with great (personal/professional) interest about Sun getting very serious about SSD-equipping servers as a standard feature in the 2nd half of this year. Yeah! Excellent news - and it''s nice to see Sun lead, rather than trail the market! Those of us, who are ZFS zealots, know the value of a ZFS log, and/or ZFS cache device and how these devices can (very positively) impact the performance of a ZFS raid configuration built on cost effective SATA disk drives. But - based on personal observation - there is a lot of hype surrounding SSD reliability. Obviously the *promise* of this technology is higher performance and *reliability* with lower power requirements due to no (mechanical) moving parts. But... if you look broadly at the current SSD product offerings, you see: a) lower than expected performance - particularly in regard to write IOPS (I/O Ops per Second) and b) warranty periods that are typically 1 year - with the (currently rare) exception of products that are offered with a 5 year warranty. Obviously, for SSD products to live up to the current marketing hype, they need to deliver superior performance and *reliability*. Everyone I know *wants* one or more SSD devices - but they also have the expectation that those devices will come with a warranty at least equivalent to current hard disk drives (3 or 5 years). So ... I''m interested in learning from anyone on this list, and, in particular, from Team ZFS, what the reality is regarding SSD reliability. Obviously Sun employees are not going to compromise their employment and divulge upcoming product specific data - but there must be *some* data (white papers etc) in the public domain that would provide some relevant technical data?? Regards, -- Al Hopper Logical Approach Inc,Plano,TX al at logical-approach.com Voice: 972.379.2133 Timezone: US CDT OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007 http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
Tobias Exner
2008-Jun-11 08:59 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
Hi Al, Sorry, but "leading the market" is not right at this point. www.superssd.com has the answer to all those questions about SSD and reliability/speed for many years.. But I''m with you. I''m looking forward the coming products of SUN concerning SSD.. btw: it''s seems to me that this thread is a little bit OT. regards, Tobias Exner Al Hopper schrieb:> I''ve been reading, with great (personal/professional) interest about > Sun getting very serious about SSD-equipping servers as a standard > feature in the 2nd half of this year. Yeah! Excellent news - and > it''s nice to see Sun lead, rather than trail the market! Those of us, > who are ZFS zealots, know the value of a ZFS log, and/or ZFS cache > device and how these devices can (very positively) impact the > performance of a ZFS raid configuration built on cost effective SATA > disk drives. But - based on personal observation - there is a lot of > hype surrounding SSD reliability. Obviously the *promise* of this > technology is higher performance and *reliability* with lower power > requirements due to no (mechanical) moving parts. But... if you look > broadly at the current SSD product offerings, you see: a) lower than > expected performance - particularly in regard to write IOPS (I/O Ops > per Second) and b) warranty periods that are typically 1 year - with > the (currently rare) exception of products that are offered with a 5 > year warranty. > > Obviously, for SSD products to live up to the current marketing hype, > they need to deliver superior performance and *reliability*. > Everyone I know *wants* one or more SSD devices - but they also have > the expectation that those devices will come with a warranty at least > equivalent to current hard disk drives (3 or 5 years). > > So ... I''m interested in learning from anyone on this list, and, in > particular, from Team ZFS, what the reality is regarding SSD > reliability. Obviously Sun employees are not going to compromise > their employment and divulge upcoming product specific data - but > there must be *some* data (white papers etc) in the public domain that > would provide some relevant technical data?? > > Regards, > >
Al Hopper
2008-Jun-11 09:07 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Wed, Jun 11, 2008 at 3:59 AM, Tobias Exner <texner at eoipso.com> wrote:> Hi Al, > > Sorry, but "leading the market" is not right at this point. > > www.superssd.com has the answer to all those questions about SSD and > reliability/speed for many years.. > > But I''m with you. I''m looking forward the coming products of SUN concerning > SSD.. > > > btw: it''s seems to me that this thread is a little bit OT.I don''t think its OT - because SSDs make perfect sense as ZFS log and/or cache devices. If I did not make that clear in my OP then I failed to communicate clearly. In both these roles (log/cache) reliability is of the utmost importance. Thanks for the link - I''ll take a look/see.> regards, > > Tobias Exner > > > > Al Hopper schrieb: >> >> I''ve been reading, with great (personal/professional) interest about >> Sun getting very serious about SSD-equipping servers as a standard >> feature in the 2nd half of this year. Yeah! Excellent news - and >> it''s nice to see Sun lead, rather than trail the market! Those of us, >> who are ZFS zealots, know the value of a ZFS log, and/or ZFS cache >> device and how these devices can (very positively) impact the >> performance of a ZFS raid configuration built on cost effective SATA >> disk drives. But - based on personal observation - there is a lot of >> hype surrounding SSD reliability. Obviously the *promise* of this >> technology is higher performance and *reliability* with lower power >> requirements due to no (mechanical) moving parts. But... if you look >> broadly at the current SSD product offerings, you see: a) lower than >> expected performance - particularly in regard to write IOPS (I/O Ops >> per Second) and b) warranty periods that are typically 1 year - with >> the (currently rare) exception of products that are offered with a 5 >> year warranty. >> >> Obviously, for SSD products to live up to the current marketing hype, >> they need to deliver superior performance and *reliability*. >> Everyone I know *wants* one or more SSD devices - but they also have >> the expectation that those devices will come with a warranty at least >> equivalent to current hard disk drives (3 or 5 years). >> >> So ... I''m interested in learning from anyone on this list, and, in >> particular, from Team ZFS, what the reality is regarding SSD >> reliability. Obviously Sun employees are not going to compromise >> their employment and divulge upcoming product specific data - but >> there must be *some* data (white papers etc) in the public domain that >> would provide some relevant technical data?? >> >> Regards, >> >> >Regards, -- Al Hopper Logical Approach Inc,Plano,TX al at logical-approach.com Voice: 972.379.2133 Timezone: US CDT OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007 http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
Adam Leventhal
2008-Jun-11 09:31 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Jun 11, 2008, at 1:16 AM, Al Hopper wrote:> But... if you look > broadly at the current SSD product offerings, you see: a) lower than > expected performance - particularly in regard to write IOPS (I/O Ops > per Second)True. Flash is quite asymmetric in its performance characteristics. That said, the L2ARC has been specially designed to play well with the natural strengths and weaknesses of flash.> and b) warranty periods that are typically 1 year - with > the (currently rare) exception of products that are offered with a 5 > year warranty.You''ll see a new class of SSDs -- eSSDs -- designed for the enterprise with longer warranties and more write/erase cycles. Further, ZFS will do its part by not killing the write/erase cycles of the L2ARC by constantly streaming as fast as possible. You should see lifetimes in the 3-5 year range on typical flash.> Obviously, for SSD products to live up to the current marketing hype, > they need to deliver superior performance and *reliability*. > Everyone I know *wants* one or more SSD devices - but they also have > the expectation that those devices will come with a warranty at least > equivalent to current hard disk drives (3 or 5 years).I don''t disagree entirely, but as a cache device flash actually can be fairly unreliable and we''ll pick it up in ZFS.> So ... I''m interested in learning from anyone on this list, and, in > particular, from Team ZFS, what the reality is regarding SSD > reliability. Obviously Sun employees are not going to compromise > their employment and divulge upcoming product specific data - but > there must be *some* data (white papers etc) in the public domain that > would provide some relevant technical data??A typical high-end SSD can sustain 100k write/erase cycles so you can do some simple math to see that a 128GB device written to at a rate of 150M/s will last nearly 3 years. Again, note that unreliable devices will result in a performance degradation when you fail a checksum in the L2ARC, but the data will still be valid out of the main storage pool. You''re going to see much more on this in the next few months. I made a post to my blog that probably won''t answer your questions directly, but may help inform you about what we have in mind. http://blogs.sun.com/ahl/entry/flash_hybrid_pools_and_future Adam -- Adam Leventhal, Fishworks http://blogs.sun.com/ahl
The reliability of flash increasing alot if "wear leveling" is implemented and there''s the capability to build a raid over a couple of flash-modules ( maybe automatically by the controller ). And if there are RAM-modules as a cache infront of the flash the most problems will be solved regarding fast read- and write-access. I''m very interested what kind of data security will be implemented by SUN in future. I was not able to find any technical information until now. @ Adam I never heared about "eSSD". Do you have more information about this? google and me cannot find anything. regards, Tobias Adam Leventhal schrieb: On Jun 11, 2008, at 1:16 AM, Al Hopper wrote: But... if you look broadly at the current SSD product offerings, you see: a) lower than expected performance - particularly in regard to write IOPS (I/O Ops per Second) True. Flash is quite asymmetric in its performance characteristics. That said, the L2ARC has been specially designed to play well with the natural strengths and weaknesses of flash. and b) warranty periods that are typically 1 year - with the (currently rare) exception of products that are offered with a 5 year warranty. You''ll see a new class of SSDs -- eSSDs -- designed for the enterprise with longer warranties and more write/erase cycles. Further, ZFS will do its part by not killing the write/erase cycles of the L2ARC by constantly streaming as fast as possible. You should see lifetimes in the 3-5 year range on typical flash. Obviously, for SSD products to live up to the current marketing hype, they need to deliver superior performance and *reliability*. Everyone I know *wants* one or more SSD devices - but they also have the expectation that those devices will come with a warranty at least equivalent to current hard disk drives (3 or 5 years). I don''t disagree entirely, but as a cache device flash actually can be fairly unreliable and we''ll pick it up in ZFS. So ... I''m interested in learning from anyone on this list, and, in particular, from Team ZFS, what the reality is regarding SSD reliability. Obviously Sun employees are not going to compromise their employment and divulge upcoming product specific data - but there must be *some* data (white papers etc) in the public domain that would provide some relevant technical data?? A typical high-end SSD can sustain 100k write/erase cycles so you can do some simple math to see that a 128GB device written to at a rate of 150M/s will last nearly 3 years. Again, note that unreliable devices will result in a performance degradation when you fail a checksum in the L2ARC, but the data will still be valid out of the main storage pool. You''re going to see much more on this in the next few months. I made a post to my blog that probably won''t answer your questions directly, but may help inform you about what we have in mind. http://blogs.sun.com/ahl/entry/flash_hybrid_pools_and_future Adam -- Adam Leventhal, Fishworks http://blogs.sun.com/ahl _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Darren J Moffat
2008-Jun-11 11:20 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
Tobias Exner wrote:> The reliability of flash increasing alot if "wear leveling" is > implemented and there''s the capability to build a raid over a couple of > flash-modules ( maybe automatically by the controller ). > And if there are RAM-modules as a cache infront of the flash the most > problems will be solved regarding fast read- and write-access. > > I''m very interested what kind of data security will be implemented by > SUN in future. I was not able to find any technical information until now.If by data security you mean encrypting the data then see this project: http://opensolaris.org/os/project/zfs-crypto/ If you don''t mean encrypting the data in the filesystem then what do you mean by that term ? Note that Sun also has tape encryption products as well. -- Darren J Moffat
Richard L. Hamilton
2008-Jun-11 11:58 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
> > btw: it''s seems to me that this thread is a little > bit OT. > > I don''t think its OT - because SSDs make perfect > sense as ZFS log > and/or cache devices. If I did not make that clear > in my OP then I > failed to communicate clearly. In both these roles > (log/cache) > reliability is of the utmost importance.Older SSDs (before cheap and relatively high-cycle-limit flash) were RAM cache+battery+hard disk. Surely RAM+battery+flash is also possible; the battery only needs to keep the RAM alive long enough to stage to the flash. That keeps the write count on the flash down, and the speed up (RAM being faster than flash). Such a device would of course cost more, and be less dense (given having to have battery+charging circuits and RAM as well as flash), than a pure flash device. But with more limited write rates needed, and no moving parts, _provided_ it has full ECC and maybe radiation-hardened flash (if that exists), I can''t imagine why such a device couldn''t be exceedingly reliable and have quite a long lifetime (with the battery, hopefully replaceable, being more of a limitation than the flash). It could be a matter of paying for how much quality you want... As for reliability, from zpool(1m):>log > > A separate intent log device. If more than one log device is specified, then > writes are load-balanced between devices. Log devices can be mirrored. > However, raidz and raidz2 are not supported for the intent log. For more > information, see the ?Intent Log? section. > > cache > > A device used to cache storage pool data. A cache device cannot be mirrored > or part of a raidz or raidz2 configuration. For more information, see the > ?Cache Devices? section.[...]> Cache Devices > > Devices can be added to a storage pool as ?cache devices.? These devices > provide an additional layer of caching between main memory and disk. For > read-heavy workloads, where the working set size is much larger than what can > be cached in main memory, using cache devices allow much more of this > working set to be served from low latency media. Using cache devices provides > the greatest performance improvement for random read-workloads of mostly > static content. > > To create a pool with cache devices, specify a ?cache? vdev with any number > of devices. For example: > > # zpool create pool c0d0 c1d0 cache c2d0 c3d0 > > Cache devices cannot be mirrored or part of a raidz configuration. If a read > error is encountered on a cache device, that read I/O is reissued to the > original storage pool device, which might be part of a mirrored or raidz > configuration. > > The content of the cache devices is considered volatile, as is the case with > other system caches.That tells me that the zil can be mirrored and zfs can recover from cache errors. I think that means that these devices don''t need to be any more reliable than regular disks, just much faster. So...expensive ultra-reliability SSD, or much less expensive SSD plus mirrored zil? Given what zfs can do with cheap SATA, my bet is on the latter... This message posted from opensolaris.org
Richard Elling
2008-Jun-11 14:15 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
Richard L. Hamilton wrote:> > Older SSDs (before cheap and relatively high-cycle-limit flash) > were RAM cache+battery+hard disk. Surely RAM+battery+flash > is also possible; the battery only needs to keep the RAM alive long > enough to stage to the flash. That keeps the write count on the flash > down, and the speed up (RAM being faster than flash). Such a device > would of course cost more, and be less dense (given having to have > battery+charging circuits and RAM as well as flash), than a pure flash device. > But with more limited write rates needed, and no moving parts, _provided_ > it has full ECC and maybe radiation-hardened flash (if that exists), I can''t > imagine why such a device couldn''t be exceedingly reliable and have quite > a long lifetime (with the battery, hopefully replaceable, being more of > a limitation than the flash). >NB. Flash is inherently radiation hard (rad-hard). There are some other, interesting SSD technologies that are also inherently rad-hard: mram, feram, pvram, etc. If you want to be a billionaire, invent the perfect SSD :-) -- richard
Bob Friesenhahn
2008-Jun-11 15:35 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Wed, 11 Jun 2008, Al Hopper wrote:> disk drives. But - based on personal observation - there is a lot of > hype surrounding SSD reliability. Obviously the *promise* of this > technology is higher performance and *reliability* with lower power > requirements due to no (mechanical) moving parts. But... if you look > broadly at the current SSD product offerings, you see: a) lower than > expected performance - particularly in regard to write IOPS (I/O Ops > per Second) and b) warranty periods that are typically 1 year - with > the (currently rare) exception of products that are offered with a 5 > year warranty.Other than the fact that SSDs eventually wear out from use, SSDs are no different from any other electronic device in that the number of individual parts, and the individual reliability of those parts, results in an overall reliability factor for the subsystem comprised of those parts. SSDs are jam-packed with parts. In fact, if you were to look inside an SSD and then look at how typical computers are implemented these days, you will see that one SSD has a whole lot more complex parts than the rest of the computer. SSDs will naturally become more reliable as their parts count is reduced due to higher integration and product maturity. Large SSD storage capacity requires more parts so large storage devices have less relability than smaller devices comprised of similar parts. SSDs are good for laptop reliability since hard drives tend to fail with high shock levels and laptops are often severely abused. Bob =====================================Bob Friesenhahn bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/
Andy Lubel
2008-Jun-11 15:53 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Jun 11, 2008, at 11:35 AM, Bob Friesenhahn wrote:> On Wed, 11 Jun 2008, Al Hopper wrote: >> disk drives. But - based on personal observation - there is a lot of >> hype surrounding SSD reliability. Obviously the *promise* of this >> technology is higher performance and *reliability* with lower power >> requirements due to no (mechanical) moving parts. But... if you look >> broadly at the current SSD product offerings, you see: a) lower than >> expected performance - particularly in regard to write IOPS (I/O Ops >> per Second) and b) warranty periods that are typically 1 year - with >> the (currently rare) exception of products that are offered with a 5 >> year warranty. > > Other than the fact that SSDs eventually wear out from use, SSDs are > no different from any other electronic device in that the number of > individual parts, and the individual reliability of those parts, > results in an overall reliability factor for the subsystem comprised > of those parts. SSDs are jam-packed with parts. In fact, if you were > to look inside an SSD and then look at how typical computers are > implemented these days, you will see that one SSD has a whole lot more > complex parts than the rest of the computer. > > SSDs will naturally become more reliable as their parts count is > reduced due to higher integration and product maturity. Large SSD > storage capacity requires more parts so large storage devices have > less relability than smaller devices comprised of similar parts. > > SSDs are good for laptop reliability since hard drives tend to fail > with high shock levels and laptops are often severely abused.Yeah I was going to add the fact that they dont spin at 7k+ rpm and have no ''moving'' parts. I do agree that there is a lot of circuitry involved and eventually they will reduce that just like they did with mainboards. Remember how packed they used to be? Either way, I''m really interested in the vendor and technology Sun will choose for providing these SSD''s in systems or as an add on card/ drive. -Andy> > > Bob > =====================================> Bob Friesenhahn > bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ > GraphicsMagick Maintainer, http://www.GraphicsMagick.org/ > > _______________________________________________ > zfs-discuss mailing list > zfs-discuss at opensolaris.org > http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Mertol Ozyoney
2008-Jun-11 17:29 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
Hi All ; Every NAND based SSD HDD have some ram. Consumer grade products will have smaller not battery protected ram with a smaller number of prallel working nand chips and a slower cpu to distribute the load. Also consumer product will have less number of spare cells. Enterprise SSD''s are genrally compose of several nand devices and a lot of spare cells controlled by a fast micro computer which also have some cache and a super capacitor to protect the cache. Regardless of NAND write cycle capability, vendors can design a reliable SSD with incorprating more spare cells in to the desing. Mertol Mertol Ozyoney Storage Practice - Sales Manager Sun Microsystems, TR Istanbul TR Phone +902123352200 Mobile +905339310752 Fax +902123352222 Email mertol.ozyoney at Sun.COM -----Original Message----- From: zfs-discuss-bounces at opensolaris.org [mailto:zfs-discuss-bounces at opensolaris.org] On Behalf Of Richard L. Hamilton Sent: Wednesday, June 11, 2008 2:58 PM To: zfs-discuss at opensolaris.org Subject: Re: [zfs-discuss] SSD reliability, wear levelling, warranty period> > btw: it''s seems to me that this thread is a little > bit OT. > > I don''t think its OT - because SSDs make perfect > sense as ZFS log > and/or cache devices. If I did not make that clear > in my OP then I > failed to communicate clearly. In both these roles > (log/cache) > reliability is of the utmost importance.Older SSDs (before cheap and relatively high-cycle-limit flash) were RAM cache+battery+hard disk. Surely RAM+battery+flash is also possible; the battery only needs to keep the RAM alive long enough to stage to the flash. That keeps the write count on the flash down, and the speed up (RAM being faster than flash). Such a device would of course cost more, and be less dense (given having to have battery+charging circuits and RAM as well as flash), than a pure flash device. But with more limited write rates needed, and no moving parts, _provided_ it has full ECC and maybe radiation-hardened flash (if that exists), I can''t imagine why such a device couldn''t be exceedingly reliable and have quite a long lifetime (with the battery, hopefully replaceable, being more of a limitation than the flash). It could be a matter of paying for how much quality you want... As for reliability, from zpool(1m):>log > > A separate intent log device. If more than one log device is specified, then > writes are load-balanced between devices. Log devices can be mirrored. > However, raidz and raidz2 are not supported for the intent log. For more > information, see the ?Intent Log? section. > > cache > > A device used to cache storage pool data. A cache device cannot be mirrored > or part of a raidz or raidz2 configuration. For more information, see the > ?Cache Devices? section.[...]> Cache Devices > > Devices can be added to a storage pool as ?cache devices.? These devices > provide an additional layer of caching between main memory and disk. For > read-heavy workloads, where the working set size is much larger than what can > be cached in main memory, using cache devices allow much more of this > working set to be served from low latency media. Using cache devices provides > the greatest performance improvement for random read-workloads of mostly > static content. > > To create a pool with cache devices, specify a ?cache? vdev with any number > of devices. For example: > > # zpool create pool c0d0 c1d0 cache c2d0 c3d0 > > Cache devices cannot be mirrored or part of a raidz configuration. If a read > error is encountered on a cache device, that read I/O is reissued to the > original storage pool device, which might be part of a mirrored or raidz > configuration. > > The content of the cache devices is considered volatile, as is the case with > other system caches.That tells me that the zil can be mirrored and zfs can recover from cache errors. I think that means that these devices don''t need to be any more reliable than regular disks, just much faster. So...expensive ultra-reliability SSD, or much less expensive SSD plus mirrored zil? Given what zfs can do with cheap SATA, my bet is on the latter... This message posted from opensolaris.org _______________________________________________ zfs-discuss mailing list zfs-discuss at opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Al Hopper
2008-Jun-11 18:40 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Wed, Jun 11, 2008 at 10:35 AM, Bob Friesenhahn <bfriesen at simple.dallas.tx.us> wrote:> On Wed, 11 Jun 2008, Al Hopper wrote: >> >> disk drives. But - based on personal observation - there is a lot of >> hype surrounding SSD reliability. Obviously the *promise* of this >> technology is higher performance and *reliability* with lower power >> requirements due to no (mechanical) moving parts. But... if you look >> broadly at the current SSD product offerings, you see: a) lower than >> expected performance - particularly in regard to write IOPS (I/O Ops >> per Second) and b) warranty periods that are typically 1 year - with >> the (currently rare) exception of products that are offered with a 5 >> year warranty. > > Other than the fact that SSDs eventually wear out from use, SSDs are no > different from any other electronic device in that the number of individual > parts, and the individual reliability of those parts, results in an overall > reliability factor for the subsystem comprised of those parts. SSDs are > jam-packed with parts. In fact, if you were to look inside an SSD and then > look at how typical computers are implemented these days, you will see that > one SSD has a whole lot more complex parts than the rest of the computer.Agreed - but the effect on overall system reliability is dominated by the required number of interconnections (soldered joints etc), rather than the total number of parts. But we''re drifting OT here...> SSDs will naturally become more reliable as their parts count is reduced due > to higher integration and product maturity. Large SSD storage capacity > requires more parts so large storage devices have less relability than > smaller devices comprised of similar parts.Again - agreed - but the root "problem" being addressed is the reduction in the number of *interconnections* - which is directly related to the number of parts.> SSDs are good for laptop reliability since hard drives tend to fail with > high shock levels and laptops are often severely abused.My personal experience, echoed by numereous others I''ve talked with, is that a typical laptop drive dies in 18 months - whether the laptop travels or stays fixed on a desktop with occasional travel, for example, in the office all week and brought home for the weekend. For most laptops, the real enemy of laptop disk drive reliability is the operation of the drive at elevated temperatures common inside a laptop - rather than vibration/shock. I don''t remember the number - but a vast number of laptops spend the vast majority of their time "glued" to a desk. Regards, -- Al Hopper Logical Approach Inc,Plano,TX al at logical-approach.com Voice: 972.379.2133 Timezone: US CDT OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007 http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
Al Hopper
2008-Jun-11 18:51 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Wed, Jun 11, 2008 at 4:31 AM, Adam Leventhal <ahl at eng.sun.com> wrote:> On Jun 11, 2008, at 1:16 AM, Al Hopper wrote: >> >> But... if you look >> broadly at the current SSD product offerings, you see: a) lower than >> expected performance - particularly in regard to write IOPS (I/O Ops >> per Second) > > True. Flash is quite asymmetric in its performance characteristics. > That said, the L2ARC has been specially designed to play well with the > natural strengths and weaknesses of flash. > >> and b) warranty periods that are typically 1 year - with >> the (currently rare) exception of products that are offered with a 5 >> year warranty. > > You''ll see a new class of SSDs -- eSSDs -- designed for the enterprise > with longer warranties and more write/erase cycles. Further, ZFS will > do its part by not killing the write/erase cycles of the L2ARC by > constantly streaming as fast as possible. You should see lifetimes in > the 3-5 year range on typical flash. > >> Obviously, for SSD products to live up to the current marketing hype, >> they need to deliver superior performance and *reliability*. >> Everyone I know *wants* one or more SSD devices - but they also have >> the expectation that those devices will come with a warranty at least >> equivalent to current hard disk drives (3 or 5 years). > > I don''t disagree entirely, but as a cache device flash actually can be > fairly unreliable and we''ll pick it up in ZFS. > >> So ... I''m interested in learning from anyone on this list, and, in >> particular, from Team ZFS, what the reality is regarding SSD >> reliability. Obviously Sun employees are not going to compromise >> their employment and divulge upcoming product specific data - but >> there must be *some* data (white papers etc) in the public domain that >> would provide some relevant technical data?? > > > A typical high-end SSD can sustain 100k write/erase cycles so you can > do some simple math to see that a 128GB device written to at a rate of > 150M/s will last nearly 3 years. Again, note that unreliable devices > will result in a performance degradation when you fail a checksum in > the L2ARC, but the data will still be valid out of the main storage > pool. > > You''re going to see much more on this in the next few months. I made a > post to my blog that probably won''t answer your questions directly, but > may help inform you about what we have in mind. > > http://blogs.sun.com/ahl/entry/flash_hybrid_pools_and_future > > Adam > > -- > Adam Leventhal, Fishworks http://blogs.sun.com/ahl > >Ahh Haa! So this is the "secret" project (probably one of many) that you guys have been working on! :) Great post and I really appreciate how this thread has provided lots of interesting stuff to think about. I think that I''ll (personally) avoid the initial rush-to-market comsumer level products by vendors with no track record of high tech software development - let alone those who probably can''t afford the PhD level talent it takes to get the "wear leveling" algorithms correct - and then to implement them correctly. Instead I''ll wait for a Sun product - from a company with a track record of proven design and *implementation* for enterprise level products (software and hardware). Otherwise, I think that I would be really upset with an SSD device that died every 2+ years - even if it has a 5 year warranty. No one I know would tolerate that kind of system disruption from todays hard disk drives - despite anticipated failures. Its more aggravation that most production oriented systems can simply live without! Again - thanks to all contributors for this interesting thread. Regards, -- Al Hopper Logical Approach Inc,Plano,TX al at logical-approach.com Voice: 972.379.2133 Timezone: US CDT OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007 http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
Vincent Fox
2008-Jun-11 20:25 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
Your key problem is going to be: Will Sun use SLC or MLC?>From what I have read the trend now is towards MLC chips which have much lower number of write cycles but are cheaper and more storage. So then they end up layering ECC and wear-levelling on to address this shortened life-span. A lot of the large USB thumb-drives now are MLC and the appallingly slow write speeds and shortened lifespan are a problem. Older 4-gig and 8-gig SLC versions of the same device are superior. Hard to find this info though.I would use any SSD in a mirror assuming there WILL be cells going out over time. This would be true for me with both boot drives and slog devices. You can mirror the log device also for ZFS. I''m not really clear though if the log device is a huge enough win on SSD to warrant all this trouble. Depends on your application. I think if performance were my god I would chase after something like a RAMSAN device instead for logging. RAM-based performance with disk as backing-store. YMMV. This message posted from opensolaris.org
Adam Leventhal
2008-Jun-11 21:56 UTC
[zfs-discuss] SSD reliability, wear levelling, warranty period
On Wed, Jun 11, 2008 at 01:51:17PM -0500, Al Hopper wrote:> I think that I''ll (personally) avoid the initial rush-to-market > comsumer level products by vendors with no track record of high tech > software development - let alone those who probably can''t afford the > PhD level talent it takes to get the "wear leveling" algorithms > correct - and then to implement them correctly. Instead I''ll wait for > a Sun product - from a company with a track record of proven design > and *implementation* for enterprise level products (software and > hardware).Wear leveling is actually a fairly mature technology. I''m more concerned with what will happen as people continue pushing these devices out of the consumer space and into the enterprise where stuff like failure modes and reliability matters in a completely different way. If my iPod sucks that''s a hassle, but it''s a different matter if an SSD hangs an I/O request on my enterprise system. Adam -- Adam Leventhal, Fishworks http://blogs.sun.com/ahl