From: Jan Kara <jack@suse.cz>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jan Kara <jack@suse.cz>,
pmladek@suse.cz, Steven Rostedt <rostedt@goodmis.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 9/9] printk: Hand over printing to console if printing too long
Date: Mon, 6 Jan 2014 10:46:08 +0100 [thread overview]
Message-ID: <20140106094608.GA3312@quack.suse.cz> (raw)
In-Reply-To: <20140104235743.e6714e29.akpm@linux-foundation.org>
On Sat 04-01-14 23:57:43, Andrew Morton wrote:
> On Mon, 23 Dec 2013 21:39:30 +0100 Jan Kara <jack@suse.cz> wrote:
>
> > Currently, console_unlock() prints messages from kernel printk buffer to
> > console while the buffer is non-empty. When serial console is attached,
> > printing is slow and thus other CPUs in the system have plenty of time
> > to append new messages to the buffer while one CPU is printing. Thus the
> > CPU can spend unbounded amount of time doing printing in console_unlock().
> > This is especially serious problem if the printk() calling
> > console_unlock() was called with interrupts disabled.
> >
> > In practice users have observed a CPU can spend tens of seconds printing
> > in console_unlock() (usually during boot when hundreds of SCSI devices
> > are discovered) resulting in RCU stalls (CPU doing printing doesn't
> > reach quiescent state for a long time), softlockup reports (IPIs for the
> > printing CPU don't get served and thus other CPUs are spinning waiting
> > for the printing CPU to process IPIs), and eventually a machine death
> > (as messages from stalls and lockups append to printk buffer faster than
> > we are able to print). So these machines are unable to boot with serial
> > console attached. Also during artificial stress testing SATA disk
> > disappears from the system because its interrupts aren't served for too
> > long.
> >
> > This patch implements a mechanism where after printing specified number
> > of characters (tunable as a kernel parameter printk.offload_chars), CPU
> > doing printing asks for help by setting a 'hand over' state. The CPU
> > still keeps printing until another CPU running printk() or a CPU being
> > pinged by an IPI comes and takes over printing. This way no CPU should
> > spend printing too long if there is heavy printk traffic.
>
> It all seems to rely on luck? If there are 100k characters queued and
> all the other CPUs stop calling printk(), the CPU which is left in
> printk is screwed, isn't it? If so, perhaps it can send an async IPI
> to ask for help?
Let me cite a sentence from the changelog:
"... until another CPU running printk() or a CPU being pinged by an IPI
comes and takes over printing."
So sending IPI (async one) to another CPU to come and take over printing
is already implemented :). Do you have a better suggestion how to make that
more obvious in the changelog?
Honza
--
Jan Kara <jack@suse.cz>
SUSE Labs, CR
next prev parent reply other threads:[~2014-01-06 9:46 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-23 20:39 [PATCH 0/9] printk: Cleanups and softlockup avoidance Jan Kara
2013-12-23 20:39 ` [PATCH 1/9] block: Stop abusing csd.list for fifo_time Jan Kara
2014-02-01 16:48 ` Frederic Weisbecker
2014-02-03 14:48 ` Jan Kara
2014-02-03 17:02 ` Frederic Weisbecker
2013-12-23 20:39 ` [PATCH 2/9] block: Stop abusing rq->csd.list in blk-softirq Jan Kara
2014-01-30 12:39 ` Frederic Weisbecker
2014-01-30 15:45 ` Jan Kara
2014-01-30 17:01 ` Frederic Weisbecker
2014-01-30 22:12 ` Jan Kara
2014-01-31 15:08 ` Frederic Weisbecker
2013-12-23 20:39 ` [PATCH 3/9] kernel: use lockless list for smp_call_function_single() Jan Kara
2014-01-07 16:21 ` Frederic Weisbecker
2013-12-23 20:39 ` [PATCH 4/9] smp: Teach __smp_call_function_single() to check for offline cpus Jan Kara
2014-01-03 0:47 ` Steven Rostedt
2013-12-23 20:39 ` [PATCH 5/9] smp: Provide __smp_call_function_any() Jan Kara
2014-01-03 0:51 ` Steven Rostedt
2013-12-23 20:39 ` [PATCH 6/9] printk: Release lockbuf_lock before calling console_trylock_for_printk() Jan Kara
2014-01-03 1:53 ` Steven Rostedt
2014-01-03 7:49 ` Jan Kara
2013-12-23 20:39 ` [PATCH 7/9] printk: Enable interrupts " Jan Kara
2013-12-23 20:39 ` [PATCH 8/9] printk: Remove separate printk_sched buffers and use printk buf instead Jan Kara
2013-12-23 20:39 ` [PATCH 9/9] printk: Hand over printing to console if printing too long Jan Kara
2014-01-05 7:57 ` Andrew Morton
2014-01-06 9:46 ` Jan Kara [this message]
2014-01-13 7:28 ` Jan Kara
2014-01-15 22:23 ` Andrew Morton
2014-01-16 15:52 ` Jan Kara
2013-12-23 20:39 ` [PATCH 10/10] printk: debug: Slow down printing to 9600 bauds Jan Kara
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=20140106094608.GA3312@quack.suse.cz \
--to=jack@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pmladek@suse.cz \
--cc=rostedt@goodmis.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).