• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

SSD Endurance at 1 PB

I'm frankly quite surprised the Intel bowed out that early. The 840 and Kingston didn't surprise me, other then the fact that the Sammy just up and quit, no warning.

I disagree on the neutron being around for a lot longer. I think that read speed reduction is indicative of ECC kicking in. I have a feeling most of its NAND is ash, and its using ECC to pick up the pieces.
 
The Samsung did die suddenly but hardly without warning if you read it. "The Samsung 840 Series died suddenly, but the writing had been on the wall for a while in the form of mounting block failures."
 
Mad[H]atter;1040901470 said:
The Samsung did die suddenly but hardly without warning if you read it. "The Samsung 840 Series died suddenly, but the writing had been on the wall for a while in the form of mounting block failures."
Click to expand...

Fair enough, but that's not quite what I meant. I meant an OS flag, or actual SMART event. The Sammy just gave up, no chance to recover data, no chance to backup before it goes, no nothing. Just flat dead. The Intel and the Kingston both threw up surrender flags and requested that you save its data to another drive before its commander died.
 
Based on that test, in my particular usage, my 250GB Samsung 840 would last 75 years before the wear leveling count hit zero and 225 years before it died. (My laptop's 250GB 840 is 16 months old and had 5.2TB total written to it.) Too bad the test didn't have multiple drives of each model. One data point doesn't really say much overall.

Samsung should throw up a warning when things are going bad and it looks like there is a long period between the wear leveling count hitting zero and the block reserve decreasing by 1/2 (wlc = 0 @ 300TB and block reserve ~50% @ 900TB). If anything, this shows you probably don't want a TLC 840 in any kind of critical/heavy use scenario.
 
pxc hits exactly my thought process when I read this article and then the posts. These are desktop-grade SSD's that according to the single-trial tests show ridiculous resiliency compared to expectations. At Enterprise-level gear it's a different story, but even as an enthusiast, you're most likely never going to hit the expected brick wall with these drives before obsolescence. Yes there will be the odd failure due to manufacturing defect. But assuming these tests show what the average life span is, there's not much to worry about.

Regarding the failure of the Sammy. Being in the more cutthroat market of desktop hardware as these drives are, I can't imagine that Samsung thought there'd be a reason to add that kind of code into the controller. With the extreme nature of this test compared to average usage. I don't have much of an issue with the results. You can have it Fast, Cheap or Reliable, pick two.
 
You must log in or register to reply here.
Back
Top