Samsung starts mass production of 5th gen V-NAND
Quote:
This 96-layer V-NAND uses a Toggle DDR 4.0 interface running at 1.4Gbps.
Read more.
Re: Samsung starts mass production of 5th gen V-NAND
SSD tech is confusing nowadays: V-NAND versus 3D X-point which rules?
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
lumireleon
SSD tech is confusing nowadays: V-NAND versus 3D X-point which rules?
In what terms and use case? I think that 3D x-point wins in performance but V-NAND in price and price/performance.
One step closer to reach SSD price/performance of HDD. Good :)
Re: Samsung starts mass production of 5th gen V-NAND
HDDs only have price, they have no performance.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
Glyce
HDDs only have price, they have no performance.
Not a very true statement. However indeed I made mistake there - I meant price/size.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
Glyce
HDDs only have price, they have no performance.
They also have wear resistance. If you have a write heavy application, that fills and overwrites your storage many times a day. (Think security cameras, or a DVR), then almost any type of SSD will wear out and fail within months. The magnetic domains in an HDDs will cope fine with getting re-written millions of times, but the cells in an SSD will stop working after about 10k writes.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
chrestomanci
the cells in an SSD will stop working after about 10k writes.
It can be a lot less than that; the latest QLC NAND is only good for about 1K program / erase cycles. Obviously wear-leveling & over provisioning can extend the life of a drive for quite some time, but as data densities increase, NAND cell lifetime tends to decrease...
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
MrJim
It can be a lot less than that; the latest QLC NAND is only good for about 1K program / erase cycles. Obviously wear-leveling & over provisioning can extend the life of a drive for quite some time, but as data densities increase, NAND cell lifetime tends to decrease...
Is there any software out there that's free and can look at how much of the overprovisioned space has been used and therefore give you an idea of how long your drive has left? I have an old 80GB Intel SSD that I may want to consider removing from service (although there's nothing essential on it now and it's backed up).
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
DevDrake
Not a very true statement. However indeed I made mistake there - I meant price/size.
Size? If your pockets are deep enough you can get pretty big SSDs, and in a tiny 2.5in form factor to boot.
Quote:
Originally Posted by
chrestomanci
They also have wear resistance. If you have a write heavy application, that fills and overwrites your storage many times a day. (Think security cameras, or a DVR), then almost any type of SSD will wear out and fail within months. The magnetic domains in an HDDs will cope fine with getting re-written millions of times, but the cells in an SSD will stop working after about 10k writes.
And yet things like dashcams continuously write to a Micro-SD card which generally have pitiful endurance compared to SSD. Recording a lot of security cameras onto a single hard drive, yeah that requires spinning rust to work at reasonable cost (which again is price/performance).
Note also that the next HAMR generation of HDD will require a laser to write data, and semiconductor lasers have a life expectancy before they fail which doesn't look that much better than SSD write endurance.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
philehidiot
Is there any software out there that's free and can look at how much of the overprovisioned space has been used and therefore give you an idea of how long your drive has left? I have an old 80GB Intel SSD that I may want to consider removing from service (although there's nothing essential on it now and it's backed up).
It isn't like the spare sectors on a HDD mapping out failed sectors, it seems to be more down to providing plenty of slack space to make it easier for the flash controller to maintain wear levelling.
Standard SMART tools should tell you how much data has been written. smartctl on Linux says my Samsung drive is 98% good:
177 Wear_Leveling_Count 0x0013 098 098 000 Pre-fail Always - 25
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
DanceswithUnix
It isn't like the spare sectors on a HDD mapping out failed sectors, it seems to be more down to providing plenty of slack space to make it easier for the flash controller to maintain wear levelling.
Standard SMART tools should tell you how much data has been written. smartctl on Linux says my Samsung drive is 98% good:
177 Wear_Leveling_Count 0x0013 098 098 000 Pre-fail Always - 25
Ah, I dunno why but I can't get my brain to switch from the old HDD sector to SSD pages. That makes sense. I was wondering if the SMART stuff in the BIOS would warn you when a failure is imminent.
Mine was an early consumer SSD and it's getting on a bit now (I'm sure well past the MTBF but by WD Raptor HDD is also....) so I think it's prudent to poke at it and see how decrepit it really is.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
MrJim
It can be a lot less than that; the latest QLC NAND is only good for about 1K program / erase cycles. Obviously wear-leveling & over provisioning can extend the life of a drive for quite some time, but as data densities increase, NAND cell lifetime tends to decrease...
On the flip side, as SSDs approach hard drive volumes, you need to do far less write per cell.
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
philehidiot
Ah, I dunno why but I can't get my brain to switch from the old HDD sector to SSD pages. That makes sense. I was wondering if the SMART stuff in the BIOS would warn you when a failure is imminent.
No reason why not, but in practice SSDs seem to just fall off a cliff with no warning.
Re: Samsung starts mass production of 5th gen V-NAND
Actually don't Intel Ssd's simply go into read only mode ... and that is done regardless of true ability to go on, just as soon as the allowed 1000 drive writes are done, or service life is over.
Media wear out indicator .... (intel kiss of death)
Re: Samsung starts mass production of 5th gen V-NAND
Quote:
Originally Posted by
persimmon
Actually don't Intel Ssd's simply go into read only mode ... and that is done regardless of true ability to go on, just as soon as the allowed 1000 drive writes are done, or service life is over.
*SOME* Intel SSDs go into read only mode when they wear out, other Intel SSDs, and most other brands just stop working and take your data with them. TheTech Report did a wear out until they are dead test a few years ago.
More recently there was this rant on the Debian-ARM mailing list, from a Linux dev who's options I trust.
Quote:
Originally Posted by lkcl@lkcl.net
firmware on low-cost (and newly-designed unusual) SSDs is extremely
dodgy. one of the drives that i tested literally crawled to an
absolute stand-still after a certain sustained amount of parallel
writing (from different processes). the article went out on slashdot
and i was given some advice about it: stop the parallel write
queueing. there's a linux kernel parameter somewhere for it... i
didn't get to try it out unfortunately.
this was after OCZ had been caught switching on a firmware #define
which they had been TOLD under no circumstances to enable as it causes
data corruption (they wanted to be "faster" than the competition).
the data corruption was so bad it actually in some cases overwrote the
actual firmware *on the drive*, meaning that the SSD was no longer...
an SSD.
the only reasonably-priced SSDs i trust now are the intel s35xx
series. other drives such as the toshibas which are also supposed to
have supercapacitors for "enhanced power loss protection", the
supercapacitors simply aren't large enough, so a sustained series of
writes above a certain threshold speed, pull the power and there's not
enough in the supercapacitors to cover the time it takes to save the
cached data.
only the intel s35xx series has had the work put into it,
technically, to do the job *at a reasonable price*. i ran a 4-day
test writing several terabytes of data, the power was randomly pulled
at between 7 and 25 second intervals, for a total of six and a half
THOUSAND times, and *not a single byte* was lost. which is deeply
impressive.
the s37xx series is by a different team and they use the rubbishrubbishrubbishrubbishwit
marvel "consumer" chipset that's so troublesome in kingston, crucial
and other SSDs.
really not being funny or anything: if you care about your data
(*and* your wallet) just don't buy anything other than intel s35xx
series SSDs. of course if you have over $10k to spend there are
plenty of data-centre quality SSDs.
