Re: [Xen-devel] [PATCH] x86/nmi: lower initial watchdog frequency to avoid boot hangs

[Igor Druzhinin <igor.druzhinin@xxxxxxxxxx>]

On 07/02/18 09:13, Jan Beulich wrote:
>>>> On 06.02.18 at 22:51, <igor.druzhinin@xxxxxxxxxx> wrote:
>> The problem with a quirk/commandline parameter is that the issue is
>> reported for a wide variety of systems and, as it looks like, depends on
>> the default BIOS setup - means it's hard to identify particular
>> machines. We should obviously sort this out with Intel but until then
>> lowering the initial frequency is our only option.
> 
> "Wide variety" is interesting, considering that we've had no earlier
> reports. As the description of the patch talks about "post-Skylake" -
> are these production machines? If not, a command line option
> would quite certainly be sufficient here. If yes, I'd like "wide variety"
> to be further qualified. After all we're talking about a processing
> overhead on the order of 10ms here, which is absurd. There are
> systems anyway where the watchdog doesn't work - we may need
> to consider to suggest to people to simply not enable the watchdog
> on such systems until the firmware issue has been taken care of.
> 
> As mentioned before - if firmware takes on the order of 10ms to
> process the SMI intercept, I can't see why it wouldn't be possible
> for them to screw up further and take 20, 50, or 100ms, at which
> point your seemingly random HZ / 10 would no longer work either.
> The same goes for the case of someone coming along and
> changing HZ to a higher value (with a good reason provided).
> 
> Jan
> 

So far the issue confirmed:
Dell PowerEdge R740, Huawei systems based on Xeon Gold 6152 (the one
that it was tested on), Intel S2600XX, etc.

Also see:
https://bugs.xenserver.org/browse/XSO-774

Well, no-watchdog is what we currently recommend in that case but we
hoped there is a general solution here from Xen side. You have your
point that they should fix this on their side because it's their fault
indeed. But the user experience is also important for us I think.

Igor

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel