Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 11 Mar 2010 11:09:43 -0800
From:      Mark Atkinson <atkin901@gmail.com>
To:        freebsd-fs@freebsd.org
Cc:        freebsd-stable@freebsd.org
Subject:   Re: proliant server lockups with freebsd-amd64-stable (2010-03-10)
Message-ID:  <hnbf5n$eod$1@dough.gmane.org>
In-Reply-To: <4B993D19.60504@icyb.net.ua>
References:  <20100311133916.42ba69b0@orwell.free.de>	<hnbcid$339$1@dough.gmane.org> <4B993D19.60504@icyb.net.ua>

next in thread | previous in thread | raw e-mail | index | archive | help
On 03/11/10 10:57, Andriy Gapon wrote:
> on 11/03/2010 20:25 Mark Atkinson said the following:
>> On 03/11/10 04:39, Kai Gallasch wrote:
>>> Hi.
>>>
>>> I have some trouble with an opteron server locking up spontaneously. It looses
>>> all networks connectivity and even through console I can get no shell.
>>>
>>> Lockups occur mostly under disk load (periodic daily, bacula backup
>>> running, make buildworld/buildkernel) and I can provoke them easily.
>>
>> try adding:
>>
>> vm.pmap.pg_ps_enabled="0"
> 
> The lockups happen with this setting too.
> This is likely a red herring, because Kai already has Alan's workaround from head.

I'm not sure that the workaround covered the processor listed here

> CPU: Quad-Core AMD Opteron(tm) Processor 2352 (2100.08-MHz K8-class CPU)
>  Origin = "AuthenticAMD"  Id = 0x100f23  Stepping = 3


(mine is the same number and wasn't covered by the coded workaround
commited to Linux, or IIRC Freebsd -- I'll have to look again).

Turning off superpages totally solves the problem for me.  But for Kai's
problem, as Andriy points out, turning it off may not solve it.

If I turn off superpages and enable MCE's I'll get the MCE when hitting
the condition, so I just leave the MCE code off.

>> to /boot/loader.conf and reboot.
>>
>> Long thread reference:
>>
>> http://thread.gmane.org/gmane.os.freebsd.current/121035/focus=121457
>>
>> possible AMD "errata 147"
> 
> 147?
> 

I thought this problem was speculated to be from the bug:

http://bugzilla.kernel.org/show_bug.cgi?id=11305

Which references an AMD "errata 147" from "Revision Guide for AMD
Athlon™ 64 and AMD Opteron™ Processors."

http://support.amd.com/us/Processor_TechDocs/25759.pdf




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?hnbf5n$eod$1>