All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: jdike@addtoit.com, linux-kernel@vger.kernel.org,
	user-mode-linux-devel@lists.sourceforge.net
Subject: Re: [uml-devel] -rt doesn't compile for UML
Date: Wed, 28 Nov 2007 17:05:01 +0100	[thread overview]
Message-ID: <20071128160501.GA7986@elte.hu> (raw)
In-Reply-To: <E1IxPKU-00079S-UH@dorka.pomaz.szeredi.hu>


* Miklos Szeredi <miklos@szeredi.hu> wrote:

> > it doesnt need it - turn IRQOFF_TRACING off.
> 
> # CONFIG_CRITICAL_IRQSOFF_TIMING is not set
> 
> This seems to be off.
> 
> But latency_trace.c uses irqs_disabled_flags(), which is defined in 
> <linux/irqflags.h> only if CONFIG_TRACE_IRQFLAGS_SUPPORT is set.
> 
> So perhaps latency_trace.c should be using raw_irqs_disabled_flags() 
> instead.  But UML doesn't define that either and I have no idea how to 
> do that, so this is still not solved yet.

irqs_disabled_flags() gives us a nonessential bit of the trace output:

                 _------=> CPU#
                / _-----=> irqs-off
               | / _----=> need-resched
               || / _---=> hardirq/softirq
               ||| / _--=> preempt-depth
               |||| /
               |||||     delay
   cmd     pid ||||| time  |   caller
      \   /    |||||   \   |   /
 privoxy-12926 1.Ns1    0us : ktime_get_ts (ktime_get)
 privoxy-12926 1.Ns1    0us : getnstimeofday (ktime_get_ts)
 privoxy-12926 1.Ns1    1us : set_normalized_timespec (ktime_get_ts)
 privoxy-12926 1.Ns1    1us : rb_first (htb_dequeue)

it's the 'irqs-off' flag, which is 'd', 'D' or '.'.

so you can define irqs_off_flags to always-0 and you should be able to 
get pretty good traces still. It should have no functional impact.

	Ingo

-------------------------------------------------------------------------
SF.Net email is sponsored by: The Future of Linux Business White Paper
from Novell.  From the desktop to the data center, Linux is going
mainstream.  Let it simplify your IT future.
http://altfarm.mediaplex.com/ad/ck/8857-50307-18918-4
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo@elte.hu>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: jdike@addtoit.com, user-mode-linux-devel@lists.sourceforge.net,
	linux-kernel@vger.kernel.org
Subject: Re: -rt doesn't compile for UML
Date: Wed, 28 Nov 2007 17:05:01 +0100	[thread overview]
Message-ID: <20071128160501.GA7986@elte.hu> (raw)
In-Reply-To: <E1IxPKU-00079S-UH@dorka.pomaz.szeredi.hu>


* Miklos Szeredi <miklos@szeredi.hu> wrote:

> > it doesnt need it - turn IRQOFF_TRACING off.
> 
> # CONFIG_CRITICAL_IRQSOFF_TIMING is not set
> 
> This seems to be off.
> 
> But latency_trace.c uses irqs_disabled_flags(), which is defined in 
> <linux/irqflags.h> only if CONFIG_TRACE_IRQFLAGS_SUPPORT is set.
> 
> So perhaps latency_trace.c should be using raw_irqs_disabled_flags() 
> instead.  But UML doesn't define that either and I have no idea how to 
> do that, so this is still not solved yet.

irqs_disabled_flags() gives us a nonessential bit of the trace output:

                 _------=> CPU#
                / _-----=> irqs-off
               | / _----=> need-resched
               || / _---=> hardirq/softirq
               ||| / _--=> preempt-depth
               |||| /
               |||||     delay
   cmd     pid ||||| time  |   caller
      \   /    |||||   \   |   /
 privoxy-12926 1.Ns1    0us : ktime_get_ts (ktime_get)
 privoxy-12926 1.Ns1    0us : getnstimeofday (ktime_get_ts)
 privoxy-12926 1.Ns1    1us : set_normalized_timespec (ktime_get_ts)
 privoxy-12926 1.Ns1    1us : rb_first (htb_dequeue)

it's the 'irqs-off' flag, which is 'd', 'D' or '.'.

so you can define irqs_off_flags to always-0 and you should be able to 
get pretty good traces still. It should have no functional impact.

	Ingo

  reply	other threads:[~2007-11-28 16:05 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-28 12:47 [uml-devel] -rt doesn't compile for UML Miklos Szeredi
2007-11-28 12:47 ` Miklos Szeredi
2007-11-28 12:50 ` [uml-devel] " Ingo Molnar
2007-11-28 12:50   ` Ingo Molnar
2007-11-28 13:09   ` [uml-devel] " Miklos Szeredi
2007-11-28 13:09     ` Miklos Szeredi
2007-11-28 13:15     ` [uml-devel] " Ingo Molnar
2007-11-28 13:15       ` Ingo Molnar
2007-11-28 13:15       ` [uml-devel] " Ingo Molnar
2007-11-28 13:15         ` Ingo Molnar
2007-11-28 13:24         ` [uml-devel] " Miklos Szeredi
2007-11-28 13:24           ` Miklos Szeredi
2007-11-28 15:08     ` [uml-devel] " Jeff Dike
2007-11-28 15:08       ` Jeff Dike
2007-11-28 15:38       ` [uml-devel] " Miklos Szeredi
2007-11-28 15:38         ` Miklos Szeredi
2007-11-28 15:41         ` [uml-devel] " Ingo Molnar
2007-11-28 15:41           ` Ingo Molnar
2007-11-28 16:00           ` [uml-devel] " Miklos Szeredi
2007-11-28 16:00             ` Miklos Szeredi
2007-11-28 16:05             ` Ingo Molnar [this message]
2007-11-28 16:05               ` Ingo Molnar
2007-11-28 16:57               ` [uml-devel] " Miklos Szeredi
2007-11-28 16:57                 ` Miklos Szeredi
2007-11-28 17:02                 ` [uml-devel] " Ingo Molnar
2007-11-28 17:02                   ` Ingo Molnar
2007-11-28 17:02                 ` [uml-devel] " Miklos Szeredi
2007-11-28 17:02                   ` Miklos Szeredi
2007-11-28 17:24                   ` [uml-devel] " Ingo Molnar
2007-11-28 17:24                     ` Ingo Molnar
2007-11-28 17:25                   ` [uml-devel] " Miklos Szeredi
2007-11-28 17:25                     ` Miklos Szeredi
2007-11-28 17:38         ` [uml-devel] " Jeff Dike
2007-11-28 17:38           ` Jeff Dike
2007-11-28 15:06 ` [uml-devel] " Jeff Dike
2007-11-28 15:06   ` Jeff Dike
2007-11-28 15:35   ` [uml-devel] " Miklos Szeredi
2007-11-28 15:35     ` Miklos Szeredi
2007-11-28 18:29     ` [uml-devel] " Jeff Dike
2007-11-28 18:29       ` Jeff Dike
2007-11-28 18:37       ` [uml-devel] " Ingo Molnar
2007-11-28 18:37         ` Ingo Molnar
2007-11-28 18:46       ` [uml-devel] " Miklos Szeredi
2007-11-28 18:46         ` Miklos Szeredi
2007-11-29 10:19         ` [uml-devel] scheduling anomaly on uml (was: -rt doesn't compile for UML) Miklos Szeredi
2007-11-29 10:19           ` Miklos Szeredi
2007-11-29 10:57           ` [uml-devel] " Ingo Molnar
2007-11-29 10:57             ` Ingo Molnar
2007-11-29 11:36             ` [uml-devel] " Miklos Szeredi
2007-11-29 11:36               ` Miklos Szeredi
2007-11-29 11:50               ` [uml-devel] " Ingo Molnar
2007-11-29 11:50                 ` Ingo Molnar
2007-11-29 16:07             ` [uml-devel] " Miklos Szeredi
2007-11-29 16:07               ` Miklos Szeredi
2007-11-29 16:25               ` [uml-devel] " Ingo Molnar
2007-11-29 16:25                 ` Ingo Molnar
2007-11-29 18:05                 ` [uml-devel] " Miklos Szeredi
2007-11-29 18:05                   ` Miklos Szeredi
2007-11-29 19:26                   ` [uml-devel] " Ingo Molnar
2007-11-29 19:26                     ` Ingo Molnar
2007-11-29 17:02           ` [uml-devel] " Jeff Dike
2007-11-29 17:02             ` Jeff Dike
2007-11-29 17:16             ` [uml-devel] " Ingo Molnar
2007-11-29 17:16               ` Ingo Molnar
2007-11-29 17:58               ` [uml-devel] " Miklos Szeredi
2007-11-29 17:58                 ` Miklos Szeredi
2007-11-30 19:44             ` [uml-devel] " Miklos Szeredi
2007-11-30 19:44               ` Miklos Szeredi

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=20071128160501.GA7986@elte.hu \
    --to=mingo@elte.hu \
    --cc=jdike@addtoit.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=user-mode-linux-devel@lists.sourceforge.net \
    /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.