From: Andi Kleen <andi@firstfloor.org>
To: Russ Anderson <rja@sgi.com>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>,
"Luck, Tony" <tony.luck@intel.com>,
Mauro Carvalho Chehab <mchehab@redhat.com>,
"Young, Brent" <brent.young@intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
"bluesmoke-devel@lists.sourceforge.net"
<bluesmoke-devel@lists.sourceforge.net>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Doug Thompson <dougthompson@xmission.com>,
Joe Perches <joe@perches.com>,
Thomas Gleixner <tglx@linutronix.de>,
Linux Edac Mailing List <linux-edac@vger.kernel.org>,
Ingo Molnar <mingo@elte.hu>, Matt Domsch <Matt_Domsch@dell.com>
Subject: Re: Hardware Error Kernel Mini-Summit
Date: Mon, 24 May 2010 20:26:03 +0200 [thread overview]
Message-ID: <20100524182603.GA3429@gargoyle.fritz.box> (raw)
In-Reply-To: <20100524162124.GB7145@sgi.com>
> Having the infrastructure to automatically off-line pages
> is a good thing. The details of where to set the predictive
It's already there with a modern mcelog in daemon mode
and a recent kernel that supports soft offlining.
> threshold likely will be hardware specific (different DIMM
> types failing at different rates). It needs to be adjustable.
The current default in mcelog is 10 corrected errors per 24h
per 4k page or 1 uncorrected error on the page (if your CPU
supports recovering from that). It is on by default.
You can configure it to be different if you want.
-Andi
------------------------------------------------------------------------------
WARNING: multiple messages have this Message-ID (diff)
From: Andi Kleen <andi@firstfloor.org>
To: Russ Anderson <rja@sgi.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
"Luck, Tony" <tony.luck@intel.com>,
Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>,
Mauro Carvalho Chehab <mchehab@redhat.com>,
"Young, Brent" <brent.young@intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Matt Domsch <Matt_Domsch@dell.com>,
Doug Thompson <dougthompson@xmission.com>,
Joe Perches <joe@perches.com>, Ingo Molnar <mingo@elte.hu>,
"bluesmoke-devel@lists.sourceforge.net"
<bluesmoke-devel@lists.sourceforge.net>,
Linux Edac Mailing List <linux-edac@vger.kernel.org>
Subject: Re: Hardware Error Kernel Mini-Summit
Date: Mon, 24 May 2010 20:26:03 +0200 [thread overview]
Message-ID: <20100524182603.GA3429@gargoyle.fritz.box> (raw)
In-Reply-To: <20100524162124.GB7145@sgi.com>
> Having the infrastructure to automatically off-line pages
> is a good thing. The details of where to set the predictive
It's already there with a modern mcelog in daemon mode
and a recent kernel that supports soft offlining.
> threshold likely will be hardware specific (different DIMM
> types failing at different rates). It needs to be adjustable.
The current default in mcelog is 10 corrected errors per 24h
per 4k page or 1 uncorrected error on the page (if your CPU
supports recovering from that). It is on by default.
You can configure it to be different if you want.
-Andi
next prev parent reply other threads:[~2010-05-24 18:26 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-17 18:23 Hardware Error Kernel Mini-Summit Mauro Carvalho Chehab
2010-05-17 22:41 ` Andi Kleen
2010-05-18 16:50 ` Mauro Carvalho Chehab
2010-05-18 18:10 ` Andi Kleen
2010-05-18 18:10 ` Andi Kleen
2010-05-18 6:52 ` Hidetoshi Seto
2010-05-18 6:52 ` Hidetoshi Seto
2010-05-18 16:44 ` Mauro Carvalho Chehab
2010-05-18 16:44 ` Mauro Carvalho Chehab
2010-05-18 17:42 ` Joe Perches
2010-05-18 17:59 ` Mauro Carvalho Chehab
2010-05-18 18:45 ` Andi Kleen
2010-05-18 18:57 ` Joe Perches
2010-05-18 18:53 ` Ingo Molnar
2010-05-18 19:08 ` Luck, Tony
2010-05-18 19:18 ` Borislav Petkov
2010-05-18 19:34 ` Ingo Molnar
2010-05-18 22:14 ` Eric W. Biederman
2010-05-18 22:14 ` Eric W. Biederman
2010-05-18 22:28 ` Andi Kleen
2010-05-19 1:14 ` Eric W. Biederman
2010-05-19 1:14 ` Eric W. Biederman
2010-05-19 6:46 ` Borislav Petkov
2010-05-19 7:09 ` Ingo Molnar
2010-05-19 11:54 ` Mauro Carvalho Chehab
2010-05-19 11:54 ` Mauro Carvalho Chehab
2010-05-20 12:37 ` Ingo Molnar
2010-06-14 10:03 ` Nils Carlson
2010-06-14 10:03 ` Nils Carlson
2010-06-14 11:49 ` Andi Kleen
2010-06-14 19:47 ` Nils Carlson
2010-06-14 19:47 ` Nils Carlson
2010-06-14 20:21 ` Andi Kleen
2010-06-14 21:02 ` Nils Carlson
2010-06-14 20:06 ` Eric W. Biederman
2010-06-14 20:06 ` Eric W. Biederman
2010-06-14 20:21 ` Luck, Tony
2010-06-14 20:36 ` Andi Kleen
2010-06-14 20:36 ` Andi Kleen
2010-06-14 21:34 ` Tony Luck
2010-06-14 21:34 ` Tony Luck
2010-06-14 23:46 ` Doug Thompson
2010-06-15 6:56 ` Andi Kleen
2010-06-15 8:06 ` Nils Carlson
2010-06-15 8:06 ` Nils Carlson
2010-06-15 10:01 ` Borislav Petkov
2010-06-15 11:41 ` Andi Kleen
2010-06-15 11:41 ` Andi Kleen
2010-06-15 12:21 ` Nils Carlson
2010-06-15 18:15 ` Luck, Tony
2010-06-15 18:38 ` Nils Carlson
2010-06-15 18:38 ` Nils Carlson
2010-06-15 19:37 ` Andi Kleen
2010-06-15 19:37 ` Andi Kleen
2010-06-15 19:35 ` Andi Kleen
2010-06-15 20:48 ` Nils Carlson
2010-06-15 20:48 ` Nils Carlson
2010-06-16 9:40 ` Andi Kleen
2010-06-16 9:40 ` Andi Kleen
2010-06-15 22:33 ` Tony Luck
2010-06-15 6:44 ` Andi Kleen
2010-06-15 6:44 ` Andi Kleen
2010-05-19 9:03 ` Andi Kleen
2010-05-24 16:21 ` Russ Anderson
2010-05-24 18:26 ` Andi Kleen [this message]
2010-05-24 18:26 ` Andi Kleen
2010-05-19 17:30 ` Tony Luck
2010-05-24 15:55 ` Russ Anderson
2010-05-24 17:35 ` Tony Luck
2010-05-24 18:31 ` Andi Kleen
2010-05-18 22:29 ` Ingo Molnar
2010-05-18 19:30 ` Ingo Molnar
2010-05-18 20:42 ` Ingo Molnar
2010-05-18 21:37 ` Tony Luck
2010-05-18 22:00 ` Ingo Molnar
2010-05-24 17:13 ` Russ Anderson
2010-05-19 6:39 ` Ingo Molnar
2010-05-18 13:06 ` Borislav Petkov
2010-05-18 16:52 ` Mauro Carvalho Chehab
2010-05-18 16:52 ` Mauro Carvalho Chehab
2010-05-18 17:06 ` Mauro Carvalho Chehab
2010-05-18 17:06 ` Mauro Carvalho Chehab
-- strict thread matches above, loose matches on Subject: below --
2010-06-16 8:57 George Spelvin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20100524182603.GA3429@gargoyle.fritz.box \
--to=andi@firstfloor.org \
--cc=Matt_Domsch@dell.com \
--cc=bluesmoke-devel@lists.sourceforge.net \
--cc=brent.young@intel.com \
--cc=dougthompson@xmission.com \
--cc=ebiederm@xmission.com \
--cc=joe@perches.com \
--cc=linux-edac@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mchehab@redhat.com \
--cc=mingo@elte.hu \
--cc=rja@sgi.com \
--cc=seto.hidetoshi@jp.fujitsu.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.