I have seen a lot of discussion on how fragile SSDs are and that you should not do this or that because that will put wear and tear on the SSD.
However, I have not yet seen a single thread about a failing SSD - in contrast, there are a lot of threads about failing HDDs.
Are those SSDs maybe sturfier than we are made to believe ??
The only seemingly reliable information I've seen on ssd failure rates puts it at around 3 to 4 percent. There really hasn't been enough time of them being out there to really get solid numbers though. I seriously doubt there's a huge chunk of the population out there with them in the first place right now, and those that are out there are only a couple of years old or less. I wouldn't expect to see a large number of hdd's dead in that period of time either. Barring doa's which happen with basically all tech items.
Basically my stance is it's too early to really say, or provide reliable numbers on this, there just aren't enough of them out there being heavily used. For us, the tech guys and geeks, it may seem otherwise, but they are hardly making up a significant portion of what's out there right now.
More time and larger portion of the market are required to make a honest statistical analysis of this.
Some time ago I had come across this podcast with Steve Gibson, heres the relevant part where he's speaking about SSDs.
Source: Security Now! Transcript of Episode #122But the other thing that happens is, if you write to them over and over and over, they die. So they don't die fast. It's like on the order of 10 to the 5 write cycles, so like 100,000 write cycles. But not infinite. Hard drives are infinite. That is, it doesn't hurt them in any way to change the data on them. It actually hurts non-volatile memory to change its data. So in order to mitigate the damage, non-volatile RAM has a technology that spreads the actual writing around the surface of the RAM. So that even if you are reading and writing the same area, that is, the same address of the RAM over and over and over, it's actually occurring in a distributed fashion across different physical areas of the RAM. They do that in order to spread out the damage caused by writing to it.
And this is waht Michael Yang of Samsung had to say.
Source: Samsung defends flash reliability in solid-state drives | Nanotech - The Circuits Blog - CNET NewsA flash device that is rated at 100,000 write cycles, for example, can write 100,000 times "to every single (memory) cell within the device," Yang said. In other words, the device doesn't write to the same cell over and over again but spreads out the writes over many different cells. This is achieved through "wear leveling," which is carried out by the SSD's controller, he said.
This would make it virtually impossible to wear out a flash chip. Yang said a pattern could be perpetually repeated in which a 64GB SSD is completely filled with data, erased, filled again, then erased again every hour of every day for years, and the user still wouldn't reach the theoretical write limit. He added that if a failure ever does occur, it will not occur in the flash chip itself but in the controller.
Hello Wolfgang,
I agree with David above that it's still early to have any long term "field use" reliablity information yet.
Personally, I have had a 1st genaration Patriot SSD drive and 1 OCZ Vertex 2 50GB SSD drive fail on me. They must have been defective since the free replacements thet sent have been rock soild.
Currently, I'm using 2 OCZ 2 Vertex 50GB SSD drives in RAID 0 in a laptop, and a Revodrive X2 160GB on the desktop. They have been rock solid so far.
Overall, I would say that the newer generation of SSD drives should be more sturdy and reliable (time will tell) than a HDD since a SSD does not have any moving mechanical parts prone to eventual failure.
Short of SIDS or a firmware problem, I've never heard of one just "wearing out". I'll be very curious to see if there are lots of problems a few years from now.
I have heard that the newer drives coming out with smaller lithography reach their wear limit faster than older drives. But then again wear on an SSD will result in lowered performance versus an all out failure.
Yes, that is the 'discussion' that went on in the OCZ forums when OCZ went from 34mm to the new 22mm. It was said that the 22mm had a shorter life expectancy and lower performance.
FWIW, I bought an OCZ vertex2 several months ago and had to RMA it. It was a sort of DOA but not really. It worked well for the first 3 days but then started giving me overheat warnings. The replacement was a 22mm drive but so far has worked well.
Maybe some of you experts can explain exactly what happened here. I also had an intel X25. A few days ago I had a ram failure and BSOD. After replacing the ram, the X25 was DOA to the point that if I hooked it up to the computer the computer would freeze. So, IMO that was not an SSD failure but I didn't realize ram failure could do that.
One thing I'm curious about concerning the "maximum write" concept, and SSDs and thumb drives in general:
There seems to be no limit to writing to common RAM, so what makes flash memory different in that respect?
It's probably going to take 5+ years, but heavy heavy writes and I/O users might start to notice problems with their first generation SSD's wearing out. I expect my SSD to last at least 10 years, and I don't think 10 years down the road I'm going to want my 80GB SSD. It would be like using my 20GB IDE drive today...I just don't.
out of the 60-70 SSD drives Ive fitted (differing makes) I have had one with a dodgy controller at install point and it had to be RMA'd
has anyone been using them long enough to know the true lifespan ?
Quote