Unpowered SSDs slowly lose data • Hacker News Board

Re: Unpowered SSDs slowly lose data

#81

Post by whitepoplar » Tue, Nov 25, 2025, 1:43 AM UTC

fairfeather wrote: post #54

dale_glass wrote: post #46

So on the off-chance that there's a firmware engineer in here, how does this actually work? Like does a SSD do some sort of refresh on power-on, or every N hours, or you have to access the specific block, or...? What if you interrupt the process, eg, having a NVMe in an external case that you just plug once a month for a few minutes to just use it as a huge flash drive, is that a problem? What about the unused space,…

SSD firmware engineer here. I work on enterprise stuff, so ymmv on consumer grade internals. Generally, the data refresh will all happen in the background when the system is powered (depending on the power state). Performance is probably throttled during those operations, so you just see a slightly slower copy while this is happening behind the scenes. The unused space decaying is probably not an issue, since the int…

How long does the data refresh take, approx? Let's say I have an external portable SSD that I keep stored data on. Would plugging the drive into my computer and running

  dd if=/dev/sdX of=/dev/null bs=1M status=progress

work to refresh any bad blocks internally?

Re: Unpowered SSDs slowly lose data

#82

Post by bigstrat2003 » Tue, Nov 25, 2025, 1:46 AM UTC

867-5309 wrote: post #34

ggm wrote: post #22

Earlier quoted context omitted.

tell me about this $2/week filestore option. I'm interested.

continuing the bizarre trend, I'm here for the $2/day deal

That would be Tarsnap. Cool product and the owner is a good dude, but good Lord is it expensive. I would love to support him but just can't afford it.

Re: Unpowered SSDs slowly lose data

#83

Post by RachelF » Tue, Nov 25, 2025, 1:52 AM UTC

userbinator wrote: post #77

One key point about retention which is not often mentioned, and indeed neither does this article, is that retention is inversely proportional to program/erase cycles and decreases exponentially with increasing temperature. Hence why retention specs are usually X amount of time after Y cycles at Z temperature. Even a QLC SSD that has only been written to once, and kept in a freezer at -40, may hold data for several de…

Endurance going down is hardly a surprise given that the feature size has gone down too. The same goes for logic and DRAM memory.

I suspect that 2035 years time, hardware from 2010 will work, while that from 2020 will be less reliable.

Re: Unpowered SSDs slowly lose data

#84

Post by markhahn » Tue, Nov 25, 2025, 1:54 AM UTC

PunchyHamster wrote: post #32

loloquwowndueo wrote: post #19

Earlier quoted context omitted.

Who do you pay for this? (To rephrase : which cloud storage vendors do you use?) interested in the $2/month price point :)

Backblaze B2 is $6TB/mo, so if you have around 300GB... stuff like restic or kopia backups nicely to it

$72/yr is somewhere around 3x purchase price (per year). BB seems to be pretty smart about managing their exposure, infrastructure overhead, etc.

Re: Unpowered SSDs slowly lose data

#85

Post by djtango » Tue, Nov 25, 2025, 1:59 AM UTC

bossyTeacher wrote: post #9

This is why I would rather pay someone a couple of dollars per year to handle all this for me. If need be pay two providers to have a backup.

Do we actually know the clouds will do this? S3 is just about coming to its 20th anniversary.

Long enough to experience data rot to a small degree but realistically what proportion of users have archived things away for 10+ years then audited the fidelity of their data on retrieval after fetching it from Glacier

Re: Unpowered SSDs slowly lose data

#86

Post by Dylan16807 » Tue, Nov 25, 2025, 2:00 AM UTC

RachelF wrote: post #83

userbinator wrote: post #77

One key point about retention which is not often mentioned, and indeed neither does this article, is that retention is inversely proportional to program/erase cycles and decreases exponentially with increasing temperature. Hence why retention specs are usually X amount of time after Y cycles at Z temperature. Even a QLC SSD that has only been written to once, and kept in a freezer at -40, may hold data for several de…

Endurance going down is hardly a surprise given that the feature size has gone down too. The same goes for logic and DRAM memory. I suspect that 2035 years time, hardware from 2010 will work, while that from 2020 will be less reliable.

As far as I'm aware flash got a bit of a size boost when it went 3D and hasn't shrunk much since then. If you use the same number of bits per cell, I don't know if I would expect 2010 and 2020 or 2025 flash to vary much in endurance.

For logic and DRAM the biggest factors are how far they're being pushed with voltage and heat, which is a thing that trends back and forth over the years. So I could see that go either way.

Re: Unpowered SSDs slowly lose data

#87

Post by nrhrjrjrjtntbt » Tue, Nov 25, 2025, 2:04 AM UTC

topato wrote: post #65

seg_lol wrote: post #60

Earlier quoted context omitted.

You should absolutely be doing a full block read of your disk, dd if=/dev/disk of=/dev/null every couple weeks

pretty accurate username

Amusing profile too. For some reason he calls us here on HN a "congress".

Re: Unpowered SSDs slowly lose data

#88

Post by nrhrjrjrjtntbt » Tue, Nov 25, 2025, 2:05 AM UTC

testartr wrote: post #25

what is the exact protocol to "recharge" an ssd which was offline for months? do I just plug it in and let the computer on for a few minutes? does it needs to stay on for hours? do I need to run a special command or TRIM it?

Back it up. 1 2 3.

Re: Unpowered SSDs slowly lose data

#89

Post by cosmic_cheese » Tue, Nov 25, 2025, 2:15 AM UTC

Is there any type of flash-based storage (preferably accessible to end users) that focuses on long term data retention?

If not, that feels like a substantial hole in the market. Non-flash durable storage tend to be annoying or impractical for day to day use. I want to be able to find a 25 year old SD card hiding in some crevice and unearth an unintentional time capsule, much like how one can pick up 20+ year old MiniDiscs and be able to play the last thing their former owners recorded to them perfectly.

Re: Unpowered SSDs slowly lose data

#90

Post by coppsilgold » Tue, Nov 25, 2025, 2:25 AM UTC

My scrub script:

    dd if=$1 of=/dev/null iflag=direct bs=16M status="progress"
    smartctl -a $1

If someone wants to properly study SSD data-retention they could encrypt the drive using plain dm-crypt and fill the encrypted volume with zeroes and check at some time point afterwards to see if there are any non-zero blocks. This is an accessible way (no programming involved) to let you write random data to the SSD and save it without actually saving the entire thing - just the key. It will also ensure maximum variance in charge levels of all the cells. Will also prevent the SSD from potentially playing tricks such as compression.