mikeprice Posted November 29, 2016 Posted November 29, 2016 Hi all I was at an ANME thingy a while ago and there was a presentation from Fujitsu about this topic. They seemed to be saying that SSDs have a large amount of memory but that when it was written to it couldn't be unwritten - when you changed it the internal disk system flagged that part as unusuable and activated another unused part Hence consumer SSDs have far less 'memory' than server SSDs - and hence fail sooner Which seems strange - surely memory can be changed?? - or was I just totally confused from drinking too much coffee?? anyway - I was wondering if anyone knows about this - and maybe has a link to an knowledgable source TIA Mike
jbunoomally Posted November 29, 2016 Posted November 29, 2016 This ACM article is from 2012, but gives a good technical introduction. JB.
jinnantonnixx Posted November 29, 2016 Posted November 29, 2016 (edited) Hi all I was at an ANME thingy a while ago and there was a presentation from Fujitsu about this topic. They seemed to be saying that SSDs have a large amount of memory but that when it was written to it couldn't be unwritten - when you changed it the internal disk system flagged that part as unusuable and activated another unused part Hence consumer SSDs have far less 'memory' than server SSDs - and hence fail sooner Which seems strange - surely memory can be changed?? - or was I just totally confused from drinking too much coffee?? anyway - I was wondering if anyone knows about this - and maybe has a link to an knowledgable source TIA Mike It was probably a mix-up over wear levelling, whereby deleted data is flagged as available for overwriting, but not immediately overwritten. https://en.wikipedia.org/wiki/Wear_leveling A flash memory storage system with no wear leveling will not last very long if data is written to the flash. Without wear leveling, the underlying flash controller must permanently assign the logical addresses from the operating system (OS) to the physical addresses of the flash memory. This means that every write to a previously written block must first be read, erased, modified, and re-written to the same location. This approach is very time-consuming and frequently written locations will wear out quickly, while other locations will not be used at all. Once a few blocks reach their end of life, such a device becomes inoperable.[2] Edited November 29, 2016 by jinnantonnixx
robyholmes Posted November 29, 2016 Posted November 29, 2016 My understanding is consumer SSD have a max number of writes, server SSD's will be higher. Some SSD's state this number on the product page. For most modern SSD's with a client OS it would take 5 years or more to reach the max. It used to be a problem on older drives.
speckytecky Posted November 29, 2016 Posted November 29, 2016 I understand that a plus side of SSDs is that they are not wiped out by EMP (Electromagnetic Pulse) were one of the vast arsenal on nuclear devices proliferating the Earth at present.
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now