BUG: soft lockup - CPU#0 stuck for 22s! after recent update of Fedora 20

[The Walters]

On 3/15/2014 3:36 PM, poma wrote:
> On 15.03.2014 14:45, The Walters wrote:
> ...
>> I have googled it and have tried the suggestions but none of them have
>> worked. I also searched the list back quite a few months and nothing
>> showed up.
> Search 'linux-kernel':
> http://dir.gmane.org/gmane.linux.kernel
>
> http://marc.info/?l=linux-kernel&m=139215142501687
> This is similar to your case, however the patch is already an integral
> part of the Fedora kernel, so.
>
> Beside filling a bug report:
> https://bugzilla.redhat.com/enter_bug.cgi?product=Fedora&component=kernel
>
> also, don't forget to tell the kernel folks at
> http://vger.kernel.org/vger-lists.html#linux-kernel
>
>
> poma
>
>
The server is a dedicated mail/file server.

I checked the logs but nothing is jumping out that is out of the ordinary.

I can not still boot my fedora 19 installation so that's out of the window.

I do have hyperthreading support enabled and will turn that off and see 
if that does it. but it has been enabled since the get go and I have 
never had any issues with it (the server has been running for a few years).

I also try the stress test with this off and on.

I removed RPCbind and now no longer get the error with kernel 
3.13.4-200.fc20.i686 but it still does it with the latest stable kernel. 
I read in one of my searches that removing that helps because the RPCIOD 
ends up causing issues because it's constantly taking up 50% of the CPU 
or more for some reason. I going to try some of the suggestions and see 
if any of them help with the latest kernel and report back.