8 comments

[ 2.6 ms ] story [ 46.8 ms ] thread
The obvious question is what are the failures? While it may not matter to BB in this case, a drive going read-only is far less of an issue than losing data.
For what it's worth the only SSD I've had that failed into a readonly state was (IIRC) an Intel one. Had others fail in worse ways (and some Pacer drives that just silently corrupted your data - proved this out with a test program I wrote that filled the disk with pseudorandom bits and read them back).
I always do this with new USB sticks. Write one random file, fill the drive with copies and then test for the checksum, for example for a 16 gig thumbdrive:

    $ cd /path/to/thumbdrive
    $ dd if=/dev/urandom of=test.bin bs=1000000 count=100
    $ for i in $(seq 1 160); do echo "Writing file $i"; cp test.bin test$i.bin; done
    $ md5 test.bin
    MD5 (test.bin) = 0d3c4fe338109b09b61fcea3e11b0e4b 
    $ ls *.bin | xargs md5 | grep -v 0d3c4fe338109b09b61fcea3e11b0e4b
I'd be happy to hear if there's a oneliner for this, though.
flash uses over-provisioning, I'm not sure this script would have the desired effect.
Related: proving that your fake $50 16TB USB drive really is fake. Really clever malicious firmware would notice your script is writing the same 100MB over and over (or the same 25K block checksums over and over), and would successfully trick your script.

Different threat model, though.

The most important part, which I missed at first because I rushed to the graphs:

>> We started using SSDs as boot drives beginning in Q4 of 2018. Since that time, all new storage servers and any with failed HDD boot drives have had SSDs installed. Boot drives in our environment do much more than boot the storage servers. Each day they also read, write, and delete log files and temporary files produced by the storage server itself

IMO it's very light load which usually doesn't wear the drive much. [0]

It would be more interesting if they provided wear (as reported by the drive) and TBW values.

[0] Anecdata: a pair of Samsung 860 Pro 512Gb SSDs, apparently running LUKS, still had 45% endurance after 4 years (of unknown load though).

Wow they’re keeping their drives quite cool. Everything I’ve got at home is much toastier