[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

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

>>> 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).


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.