1. 19

  2. 6

    Very interesting read. In my opinion, it was a bit too Windows / NTFS centric, I would have loved to read more about how TRIM is handled on other operating systems or on embedded platforms.

    I also think that he could have worded the section on SSD lifetime better. He makes it sound like you buy an SSD and it keeps working for many decades:

    has an estimated life of 1 million+ hours and a write limit if 40 terabytes. One million hours is 114 years, so we can forget that. As for writes, at 1 gb a day - far more than my current rate of data use - it would take the same 114 years to reach 40 tb. Even with massive write overhead this SSD is not going to wear out in the forseeable future.

    Yes, you’re not gonna write your SSD to death. But let’s keep in mind that an SSD has a useful life span of 5-10 years, maybe up to 15 if you’re pushing it. The electronics will fail. And they will fail instantly and with no warning. It’s not like with HDDs where it starts making weird noises, gets slower and has some bad blocks. It just goes dark instantly. Backups are more important than ever.

    1. 1

      Yes and no.

      SSDs have ‘bad blocks’ and internally the ‘machine’ will transparently remap this for you similarly to how some USB sticks do. This information is meant to be exposed via SMART but of course this is vendor dependent.

      The spinning blades of rust, to the user, expose the same transparent remapping/etc.

    2. 5

      Things I’ve learned from using SSDs at prgmr:

      Since the firmware is more complicated than hard drives, they are way more likely to brick themselves completely instead of a graceful degradation. Manufacturers can also have nasty firmware bugs . I’d recommend using a mix of SSDs at different lifetimes, and/or different manufacturers, in a RAID configuration.

      How different manufacturers deal with running SMART tests under load drastically varies. Samsung tests always take the same amount of time. The length of Intel tests vary depending on load. Micron SMART tests get stuck if they are under constant load. Seagate SMART tests appear to report being at 90% done or complete, but the tests do actually run.

      Different SSDs also are more or less tolerant to power changes. Micron SSDs are prone to resetting when a hard disk is inserted in the same backplane power domain, and we have to isolate them accordingly.

      Manual overprovisioning is helpful when you aren’t able to use TRIM.

      What a drive does with secure-erase-enhanced can be different too. Some drives only change the encryption key and then return garbage on read. Some additionally wipe the block mappings so that reads return 0.

      1. 3

        “Website is sleeping” what the heck

        1. 3