From: Peter Zijlstra <peterz@infradead.org>
To: "Metzger, Markus T" <markus.t.metzger@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"hpa@zytor.com" <hpa@zytor.com>,
"markus.t.metzger@gmail.com" <markus.t.metzger@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Paul Mackerras <paulus@samba.org>
Subject: RE: [PATCH] perf_counter: Fix a race on perf_counter_ctx
Date: Tue, 18 Aug 2009 16:01:31 +0200 [thread overview]
Message-ID: <1250604091.7583.296.camel@twins> (raw)
In-Reply-To: <928CFBE8E7CB0040959E56B4EA41A77EC1CB77C8@irsmsx504.ger.corp.intel.com>
On Tue, 2009-08-18 at 14:54 +0100, Metzger, Markus T wrote:
> Well, that would push out the limit a bit, but it would still be quite fragile.
>
> Currently, I'm not sure that this (i.e. that the interrupt handling takes too long)
> is the underlying problem of the hangs that I'm seeing.
>
> If it truly is, then I would go with the two-buffer approach. This would make the
> ISR itself predictably and reliably fast - at the expense of additional locked memory.
comment out that perf_counter_output() call and see what happens ;-)
> Do you think that this truly is the problem?
> How would the kernel react if interrupts were disabled for too long? I would definitely
> expect bad responsiveness, but can the kernel kill itself?
If we're branch tracing while processing the interrupt (not sure here),
then we might well generate enough output to generate a new interrupt,
causing back-to-back interrupts, basically DoSing the machine.
next prev parent reply other threads:[~2009-08-18 14:01 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-21 13:56 [patch] x86, perf_counter, bts: add bts to perf_counter Markus Metzger
2009-08-04 10:24 ` Peter Zijlstra
2009-08-04 11:14 ` Ingo Molnar
2009-08-04 11:35 ` Ingo Molnar
2009-08-05 11:10 ` Metzger, Markus T
2009-08-07 7:29 ` Metzger, Markus T
2009-08-07 8:21 ` Peter Zijlstra
2009-08-07 10:18 ` Metzger, Markus T
2009-08-07 10:29 ` Peter Zijlstra
2009-08-07 12:18 ` Metzger, Markus T
2009-08-07 13:05 ` Peter Zijlstra
2009-08-07 10:31 ` Ingo Molnar
2009-08-07 10:36 ` Ingo Molnar
2009-08-07 10:57 ` Metzger, Markus T
2009-08-07 11:17 ` Metzger, Markus T
2009-08-07 11:24 ` Ingo Molnar
2009-08-07 11:33 ` Ingo Molnar
2009-08-07 17:49 ` [PATCH] perf_counter: Fix a race on perf_counter_ctx Peter Zijlstra
2009-08-08 11:52 ` [tip:perfcounters/core] " tip-bot for Peter Zijlstra
2009-08-08 12:03 ` [PATCH] " Ingo Molnar
2009-08-10 12:33 ` Metzger, Markus T
2009-08-10 12:59 ` Peter Zijlstra
2009-08-10 13:46 ` Ingo Molnar
2009-08-11 6:33 ` Metzger, Markus T
2009-08-11 8:59 ` Metzger, Markus T
2009-08-18 12:49 ` Metzger, Markus T
2009-08-18 12:59 ` Peter Zijlstra
2009-08-18 12:59 ` Peter Zijlstra
2009-08-18 13:20 ` Metzger, Markus T
2009-08-18 13:37 ` Peter Zijlstra
2009-08-18 13:54 ` Metzger, Markus T
2009-08-18 14:00 ` Ingo Molnar
2009-08-18 14:15 ` Metzger, Markus T
2009-08-28 9:56 ` Metzger, Markus T
2009-09-01 11:17 ` [discuss] BTS overflow handling, was: " Metzger, Markus T
2009-09-01 13:00 ` Peter Zijlstra
2009-09-01 13:09 ` Ingo Molnar
2009-09-01 13:32 ` Metzger, Markus T
2009-09-01 13:53 ` Peter Zijlstra
2009-09-01 14:27 ` Metzger, Markus T
2009-09-01 14:35 ` Peter Zijlstra
2009-09-03 14:25 ` Metzger, Markus T
2009-08-18 14:01 ` Peter Zijlstra [this message]
2009-08-18 14:19 ` Metzger, Markus T
2009-08-09 11:10 ` [tip:perfcounters/core] " tip-bot for Peter Zijlstra
2009-08-07 11:26 ` [patch] x86, perf_counter, bts: add bts to perf_counter Ingo Molnar
2009-08-07 11:29 ` Ingo Molnar
2009-08-07 12:14 ` Metzger, Markus T
2009-08-07 11:19 ` Ingo Molnar
2009-08-07 11:34 ` Metzger, Markus T
2009-08-07 11:37 ` Metzger, Markus T
2009-08-04 11:37 ` [tip:perfcounters/urgent] x86, perf_counter, bts: Add BTS support to perfcounters tip-bot for Markus Metzger
2009-08-07 10:10 ` [tip:perfcounters/core] " tip-bot for Markus Metzger
2009-08-08 11:43 ` tip-bot for Markus Metzger
2009-08-08 11:53 ` tip-bot for Markus Metzger
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=1250604091.7583.296.camel@twins \
--to=peterz@infradead.org \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=markus.t.metzger@gmail.com \
--cc=markus.t.metzger@intel.com \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=tglx@linutronix.de \
/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.