Re: SSD overheating during scrub in laptop

[Martin Steigerwald <martin@lichtvoll.de>]

Thanks.

Qu Wenruo - 14.09.25, 23:33:01 CEST:
> 在 2025/9/15 06:58, Qu Wenruo 写道:
> > 在 2025/9/14 21:27, Martin Steigerwald 写道:
[…]
> >> Now I had these SSD goodbyes during regular use in times of heavy I/O
> >> and in the end it could not even scrub that /home partition anymore
> >> in one go.
> >> Linux hung and only way to recover was to forcefully power off the
> >> laptop.
> > 
> > Can you setup netconsole and catch the dying message?

I suppose I could do that as I have several laptops at hand. However… 
after cleansing out at least some of the dust it did not happen anymore. 
And I do not quite feel like putting some dust back or otherwise provoke 
the issue. I do not quite feel like trying to overheat the SSD again. :) I 
looked at it more closely, it looks fine enough. Nothing melted 
apparently, but what do I know? And I think it does not add to the 
lifetime of the SSD to overheat it on purpose.

I might have made a photo of some earlier time, but I am not sure. I will 
have a look and see whether I can find any. I remember the kernel wrote a 
lot about NVME opcodes. However I do not recall the details. Unfortunately 
at this recent occasion I did not make a photo.

In case it happens again by itself, I am at going for a netconsole log – 
in case I can reproduce it then. Otherwise I would need to run netconsole 
permanently to be sure to catch it on the first occurrence already. Not 
sure whether that is a good idea.

> > I doubt if it's really the drive dying.

Why? The issue went away after removing at least some of the dust. Of 
course that is a correlation and not necessarily a causation, but what 
makes you think that something different is happening?

I checked the drive smart status. SMART status is passed. So everything 
okay. There is 2% of spare area used, but that is still a very good value.

An indication that there is something to your suspicion is:

Media and Data Integrity Errors:    0
Error Information Log Entries:      0
Warning  Comp. Temperature Time:    0
Critical Comp. Temperature Time:    0

So the drive itself recorded no critical composite temperature times. And 
if it has fields for that, I suppose it could still record it on overheat 
condition.

Oh by the way, it is a Samsung 990 Pro with a firmware version above that 
firmware version that was known to be broken regarding SMART status 
reporting. In the first I bought I made sure of that myself, but this one 
came with a newer firmware version already.

> >> I opened the laptop and removed dust with high pressure air can while
> >> holding the fan still so it would not generate current. And with
> >> disabled laptop battery.
> >> 
> >> This fixed the SSDs goodbye issue and I could even scrub that 2 TiB
> >> filesystem again. However, according to sensors command it still had
> >> about 80,8 °C composite temperature and even 100,8 °C for sensor 2 
> >> for the NVME SSD at "nvme-pci-0300" shortly before the end of the 
> >> scrub, with critical for composite at 84,8 °C, but no critical set 
> >> for sensor 2. That is still quite high. Granted, it took about 7-8
> >> minutes of scrubbing at 3,5 to 4,2 GiB/s in one go for it to heat up
> >> like this. But on the other hand it is not summer anymore and room
> >> is not as hot as in summer.
> > 
> > I have hit similar situation, but the symptom is very different, the
> > death come silently at boot, the drive is no longer recognized by the
> > BIOS thus no longer bootable, and Linux kernel from liveUSB will not
> > recognize it either.

Hmm, did you capture any logs?

> > That's why I'm asking if it's really dying caused by the heat.

Ah okay… You mentioned your physical solution being a thermal pad. So did 
this symptom go away with it? Or was your physical solution a general 
solution to reduce temperature, a solution unrelated to that symptom you 
described?

> >> My solution to this will be to remove the dust inside laptop about
> >> every half year. However… I was a bit surprised that the NVME SSD
> >> would not throttle itself before saying goodbye. Or maybe it tried
> >> and it was not enough or to late? The laptop is a bit less than 15
> >> months old. So I conclude that it takes less than a year for the
> >> cooling system to become quite a bit less effective due to dust.
> >> Good old ThinkPad T520 took way longer for that. But it is way
> >> larger on the other hand with more space to distribute heat.
> > 
> > You can refer to man page of btrfs-scrub, it provides the way to limit
> > the bandwidth of scrub using cgroup or even the btrfs sysfs interface.
> 
> And I forgot my physical solution, with a thick thermal pad, you can
> connect the NVME to the back plate of the laptop to dissipate heat.

Well it has some violet colored pad below the NVME SSD. So a pad that is 
between NVME SSD and motherboard. Not sure whether it is a cooling pad. It 
might be more about isolating the motherboard from the heat of the SSD? It 
has been there for the initial SSD Lenovo put into the laptop that I 
replaced with the larger Samsung 990 Pro one.

But yeah, I may order a cooling plate to connection to the back plate. 
Good idea.
 
> If there is enough space (I doubt for laptop though), you can add some
> thin heatsink for the drive.

Ha ha, no way. I would like to put a 8 TB SSD in there, but it would be 
double layered and I doubt it would be a good idea to put a double layered 
SSD into the laptop.

Best,
-- 
Martin