Re: [PATCH 2/2] x86/mce: Add mce=panic_on_ce_count to panic on a corrected error flood
From: Luck, Tony
Date: Wed Aug 26 2026 - 13:43:11 EST
On Wed, Aug 26, 2026 at 09:09:34AM -0700, Borislav Petkov wrote:
> On Wed, Aug 26, 2026 at 06:22:27AM -0700, Breno Leitao wrote:
> > In other words, I'm more interested in flagging that a host is a lemon
> > than in keeping it limping along half-alive, thus my approach in this
> > patchset.
>
> This is your use case but I'm sure others would prefer the limping and
> gracefully saving work the system has done until now...
>
> Putting my user hat on:
>
> + Panic once a machine check bank has logged this many corrected
> + errors. 0, the default, disables it.
> +
> + The setting is global rather than per-CPU, and it is compared
> + against a running total kept per CPU and per bank. Lowering it
> + below a total a bank has already reached takes the machine
> + down on that bank's next corrected error.
>
> Ah, so how many CEs is "many"?
>
> I have read that correctable errors do not have any effect on the system and
> they can keep happening and do not influence execution.
The only problem they cause is performance due to the time taken to log them.
>
> So what do I put there? I don't know... hmm.
Absolute numbers are a problem. Maybe you choose 8000 as your threshold.
But then some system ticks along happily logging one error per hour with
virtually no effect on system performance. Then panics when it has been
up for almost a year because it reaches the 8000 threshold.
Perhaps it would be better to adapt the storm code to allow tuning
the criteria for a storm and have a mce=panic_on_storm option?
>
> ... Dropping user hat. Putting devil's advocate hat...
>
> How many CEs do you put in your kernels?
>
> Does the same number fit any machine and platform?
>
> Or you simply say, after X CEs, we simply panic the machine - instead of
> gracefully powering it off after leaving a helpful message in dmesg - and have
> lab technicians inspect it?
>
> Hmmm.
-Tony