Slashdot Mirror

← Back to Stories (view on slashdot.org)

Why I'm Usually Unnerved When Modern SSDs Die on Us (utoronto.ca)

Posted by msmash on from the SSDDeathDisturbing dept.

Chris Siebenmann, a Unix Systems Administrator at University of Toronto, writes about the inability to figure out the bottleneck when an SSD dies: What unnerves me about these sorts of abrupt SSD failures is how inscrutable they are and how I can't construct a story in my head of what went wrong. With spinning HDs, drives might die abruptly but you could at least construct narratives about what could have happened to do that; perhaps the spindle motor drive seized or the drive had some other gross mechanical failure that brought everything to a crashing halt (perhaps literally). SSDs are both solid state and opaque, so I'm left with no story for what went wrong, especially when a drive is young and isn't supposed to have come anywhere near wearing out its flash cells (as this SSD was).

(When a HD died early, you could also imagine undetected manufacturing flaws that finally gave way. With SSDs, at least in theory that shouldn't happen, so early death feels especially alarming. Probably there are potential undetected manufacturing flaws in the flash cells and so on, though.) When I have no story, my thoughts turn to unnerving possibilities, like that the drive was lying to us about how healthy it was in SMART data and that it was actually running through spare flash capacity and then just ran out, or that it had a firmware flaw that we triggered that bricked it in some way.

9 of 358 comments (clear)

  1. With spinning disks, you do not know either by gweihir · · Score: 5, Insightful

    Seriously, you do not. You may know the end-result sometimes (head-crash), but the root-cause is usually not clear.

    So get over it. It is a new black-box replacing an older black-box.

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:With spinning disks, you do not know either by 110010001000 · · Score: 5, Insightful

      What is unnerving is that a guy from the Department of Computer Science thinks that SSDs are theoretically immune to manufacturing failures.

    2. Re:With spinning disks, you do not know either by froggyjojodaddy · · Score: 5, Insightful

      From the article:

      "Further, when I have no narrative for what causes SSD failures, it feels like every SSD is an unpredictable time bomb. Are they healthy or are they going to die tomorrow? "

      Emphasis mine. I feel like this guy has opportunities to improve his coping mechanism. For someone in Computer Sciences, it seems like he's way too worried about this. I'm not trying to be mean, but it's like if I got into a car accident and then questioned the entire safety design of all vehicles rather than just taking a few steps back and understanding it's a freak event, but not a totally unexpected one. If you've been driving for 30 years, statistically, you're likely to get into at least one accident, even if it's not your fault

    3. Re:With spinning disks, you do not know either by Anonymous Coward · · Score: 5, Insightful

      All for the SAME reason- the wrong type of cell failed, and the crappy software doesn't know how to recover. The software systems of the SSD and the OS driver side are written by idiots.

      A low level tool that knows your particular SSD driver chipset could trivially access the vast majority of flash cells on your SSD drive. But what good is that FACT if the tools are not readily available.

      And SMART warning do NOT apply to SSD drives. SMART is for electro-mechanical systems with statistical models of gradual failure. SMART is FAKED for SSD.

      A catastrophic SSD failure is when the 'wrong' memory cell dies, and the software locks up. Since all memory cells are equally likely to die at some point, this is a terrible fault of many of these drives.

    4. Re:With spinning disks, you do not know either by viperidaenz · · Score: 5, Insightful

      SMART should be able to provide the number of remapped sectors. There should be manufacturer specific counters for the amount of over provisioning that is left for remapping too. That should tell you precisely when you should plan to replace an SSD due to age.
      How hard would it be to notify something that the drive can't handle any more dead cells, so should not be written to any more? Or that it is down to x% of spare nand?

    5. Re:With spinning disks, you do not know either by dgatwood · · Score: 5, Insightful

      I think you may be missing his point. I've had SSD's die on me as well with absolutely no warning. What's unnerving about it is you have no idea why it failed. Good engineers like failure analysis; it helps determine if you're buying a crappy product, running your product out of spec, or any number of other metrics which can inform future purchases.

      Statistically, without even knowing what the particular product was, I can tell you what caused it: RoHS.

      The change from lead-based solder to lead-free solder is one of the major causes of premature electronics failures — probably more common than all other causes put together. Between tin whiskers, cold solder joints, and stress fractures caused by thermal expansion of component packages, the RoHS lead-free solder rule is a clear example of environmentalism gone amok. Instead of improving our environment by reducing the amount of lead going out into the world, it has, IMO, made our environment worse by dramatically increasing the amount of hardware discarded as junk long before it otherwise would have been.

      --

      Check out my sci-fi/humor trilogy at PatriotsBooks.

  2. Controller failure by macraig · · Score: 5, Insightful

    I've had two SSDs die utterly. It wasn't because there was a failure of any part of the actual storage pathways: it was irreparable failure of the embedded controller circuits. The Flash itself was still fine and safely storing all my data, but there was no means to access it. At least with a platter drive if the PCB fails, you can unscrew and detach it and replace it with a matching PCB from another drive; no way to do that with an SSD. Early on when manufacturers were spending all their time hyping the comparative robustness of the Flash medium, they conveniently forgot to mention how fragile and not-so-robust the embedded third-party controller circuits could be.

  3. The spin is in! by theendlessnow · · Score: 4, Insightful

    One thing I like about spinning disks is that a lot of times the failure is gradual. Bad sectors and such and you have the opportunity to grab data off the drive (noting, you really should have backups).

    With SSD, whatever the issue, it's more like losing a controller board on the drive, everything dies and ceases to operate.

    So... I'll go along and say SSD is "better" and more "reliable", but when it dies, it dies hard. Just the way it is. (not talking about performance degradation... speaking about failure)

  4. Backup your data frequently by Solandri · · Score: 2, Insightful

    Backup your data frequently. Stop worrying. Is that so hard?