NAND endurance is something that always raises questions among those considering a move to solid state storage. Even though we have showed more than once that the endurance of today's MLC NAND based SSDs is more than enough for even enterprise workloads, the misconception of SSDs having a short lifespan still lives. Back in the day when we had 3Xnm MLC NAND with 5,000 P/E cycles, people were worried about wearing our their SSDs, although there was absolutely nothing to worry about. The move to ~20nm MLC NAND has reduced the available P/E cycles to 3,000, but that's still plenty.

We have tested MLC NAND endurance before but with the release of Samsung SSD 840, we had something new to test: TLC NAND. We have explained the architectural differences between SLC, MLC and TLC NAND several times by now, but I'll do a brief recap here (I strongly recommend reading the detailed explanation if you want to truly understand how TLC NAND works):

  SLC MLC TLC
Bits per Cell 1 2 3
P/E Cycles (2Xnm) 100,000 3,000 1,000
Read Time 25us 50us ~75us
Program Time 200-300us 600-900us ~900-1350us
Erase Time 1.5-2ms 3ms ~4.5ms

The main difference is that MLC stores two bits per cell, whereas TLC stores three. This results in eight voltage states instead of four (also means that one TLC cell has eight possible data values). Voltages used to program the cell are usually between 15V and 18V, so there isn't exactly a lot room to play with when you need to fit twice as many voltage states within the same space. The problem is that when the cell gets cycled (i.e. programmed and erased), the room taken by one voltage state increases due to electron trapping and current leakage. TLC can't tolerate as much change in the voltage states as MLC can because there is less voltage headroom and you can't end up in a situation where two voltage states become one (the cell wouldn't give valid values because it doesn't know if it's programmed as "110" or "111" for example). Hence the endurance of TLC NAND is lower; it simply cannot be programmed and erased as many times as MLC NAND and thus you can't write as much to a TLC NAND based SSD.

No manufacturer has openly wanted to discuss the endurance of TLC, so the numbers we have seen before have been educated guesses. 1,000 - 1,500 P/E cycles is what I've heard for TLC NAND. The reality can also be different from what manufacturers claim as we discovered in the Intel SSD 335 (though there is a high probability that it's just a firmware bug), so actually testing the endruance is vital. 

There was one obstacle, though. Samsung does not report NAND writes like Intel does and without NAND writes we can't know for sure how much data is written to the NAND because of write amplification. Fortunately, there is a a workaround: I wrote incompressible 128KB sequential data (QD=1) to the drive and took down the duration of each run and the Wear Leveling Count (similar to Media Wear Indicator). If I know the average write speed and the duration, I can figure out how much I wrote to the drive. Sequential large block-size data should also result in write amplification near 1x because the data is sequential and thus doesn't fragment the drive. I then compared the amount of data I wrote to the WLC values I had recorded:

Samsung SSD 840 (250GB) Endurance Testing
Total Amount of Data Written 92,623 GiB
Total Amount of WLC Exhausted 34
Estimated Total Amount of P/E Cycles 1,064
Estimated Total Write Endurance 272,420 GiB

It seems that 1,000 P/E cycles is indeed accurate. The raw Wear Leveling Count seems to indicate the amount of exhausted P/E cycles as it's inversely proportional to the normalized WLC value and once it hits 1,000, the WLC will hit zero. 

Note that if Samsung's WLC is anything like Intel's Media Wear Indicator, when the normalized counter value drops to 0 there's still a good amount of endurance actually left on the NAND (it could be as high as another 20 - 30%). At least with Intel drives, the MWI hitting 0 is a suggestion that you may want to think about replacing the drive and not a warning of imminent failure.

Conclusions

1,000 P/E cycles may not sound much but when it's put into perspective, it's still plenty. Client workloads rarely exceed 10GiB of writes per day on average and write amplification should stay within reasonable magnitudes as well:

SSD Lifetime Estimation
NAND MLC—3K P/E Cycles TLC—1K P/E Cycles
NAND Capacity 128GiB 256GiB 128GiB 256GiB
Writes per Day 10GiB 10GiB 10GiB 10GiB
Write Amplification 3x 3x 3x 3x
Total Estimated Lifespan 35.0 years 70.1 years 11.7 years 23.4 years

Of course, if you write 20GiB a day, the estimated lifespan will be halved, although we are still looking at several years. Even with 30GiB of writes a day the 256GiB TLC drive should be sufficient in terms of endurance. Write amplification can also go over 10x if your workload is heavily random write centric, but that is more common in the enterprise side - client workloads are usually much lighter. 

Furthermore, it should be kept in mind that all SMART values that predict lifespan are conservative; it's highly unlikely that your drive will drop dead once the WLC or MWI hits zero. There is a great example at XtremeSystems where a 256GB Samsung SSD 830 is currently at nearly 6,000TiB of writes. Its WLC hit zero at 828TiB of writes, which means its endurance is over seven times higher than what the SMART values predicted. That doesn't mean all drives are as durable but especially SSDs from NAND manufacturers (e.g. Intel, Crucial/Micron, Samsung etc.) seem to be more durable than what the SMART values and datasheets indicate, which isn't a surprise given that they can cherry-pick the highest quality NAND chips.

POST A COMMENT

46 Comments

View All Comments

  • twotwotwo - Friday, November 16, 2012 - link

    Yes, they reshuffle the content. The crazy thing about SSDs is that they look like hard drives do your OS, but they're doing totally different stuff underneath. Look up 'wear leveling'; here are a couple links:

    http://en.wikipedia.org/wiki/Wear_leveling
    http://www.anandtech.com/show/2829/6
    Reply
  • UpSpin - Friday, November 16, 2012 - link

    Thanks, didn't knew about the 'static wear leveling' which, just as you said, also reshuffles the static content, thus makes my concerns invalid and TLC NAND a usable less expensive alternative to MLC. Reply
  • Impulses - Friday, November 16, 2012 - link

    This is why Anand talks about write amplification... Because of all the wear Keeling"leveling algorithms, and those do indeed cause more wear, it's a balancing act. Reply
  • Visual - Tuesday, November 20, 2012 - link

    No, write amplification has little to do with wear leveling. The most major cause is the fact that flash is organized in blocks that must always be written to entirely. You may want to write just a single byte, but the drive would internally have to read the whole block (say 4KB) and then erase and white the whole block with that one byte changed. Reply
  • bwat47 - Saturday, August 03, 2013 - link

    The SSD's firmware actually does "Reshuffle" the content, so you don't need to worry about the SSD trying to just wear-level the same 20gb, they are much more intelligent than that. Reply
  • David.Sucesso - Monday, August 19, 2013 - link

    UpSpin what you are talking is so true that really scares me...

    i have registered just to confirm that i only have an ssd drive 120gb ( and the space that is normally free is as 35GB to write every day. the other are files that doesnt get moved on

    now this is serious for the consumer
    Reply
  • gevorg - Friday, November 16, 2012 - link

    looks like I have to find a sweet deal for Samsung 830 while its still available Reply
  • alextall - Friday, November 16, 2012 - link

    For anyone concerned about a short lifespan, I have put an SSD in all three of my machines now. My daily use can generate 10-50GiB of data. While that means I may have considerably shortened life on these drives (which is still 7-10 years according to the MLC data above), the increased productivity more than makes up for the difference. I don't even plan on keeping these computers half that long.

    Besides, with the current prices for SSDs are, and where they are (very quickly) moving, it really isn't a difficult value proposition to switch.
    Reply
  • name99 - Friday, November 16, 2012 - link

    Don't waste your breath.

    The psychology here is not that of "let's have an honest discussion about usage patterns, cost, and change". The psychology is "I want to be a contrarian to show the world that I'm a deep thinker who doesn't follow the crowd".
    It's the same psychology that drives the non-ideological pundits (the one's who say stupid things attacking both parties) and, as you may have noticed, those people have not altered their shtick one bit, even after fifteen years of the internet shaming them with their atrocious record of insight.

    It's the same thing here. These people, if they were old enough, were very concerned that we were replacing floppy disks too soon. They felt that maybe we shouldn't be so quick to ditch VGA. They felt that sealed batteries were definitely going to cause trouble.
    If they knew anything about the technology, they'd be bleating that "sure, Haswell's lock elision looks good, but how can we be SURE that it won't occasionally miss a memory collision?"
    Whatever it is, they are sure that gut instinct trumps engineering skill and actual knowledge of the relevant statistics every time.

    The only way to deal with them is to avoid them (and on sites like Ars Technica) filter them out of the comment stream.
    Reply
  • bebimbap - Friday, November 16, 2012 - link

    If you think about it, even if it were to last 5 years, it's quite long enough.
    in 2007 SSDs were $7.5/GB for the cheapest drives or about $1000 for 128gb worth of drive.
    in 2010 128gb drives were about $400?
    Today 5 years later 128GB 830s drives are as cheap as $70 on sale. that's $0.55/GB
    so 5 years from now you'll probably be going to buy a 2TB drive will cost you <$100
    As drive capacities increase so will their longevity due to wear leveling.
    When 2TB SSDs come out even 250-500 P/E cycles might be more than enough
    Reply

Log in

Don't have an account? Sign up now