public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: emann@mrv.com (Eran Mann)
To: Ingo Molnar <mingo@elte.hu>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm2-V0.7.32-2
Date: Tue, 07 Dec 2004 16:37:44 +0200	[thread overview]
Message-ID: <41B5C038.1090501@mrv.com> (raw)
In-Reply-To: <20041204175636.GA3115@elte.hu>

Ingo Molnar wrote:
...

> i've implemented the 'tracing follows the task' logic in the -32-2
> patch, available from the usual place:
> 
>     http://redhat.com/~mingo/realtime-preempt/
> 
> i've also added a CPU# field and i've reworked latency_trace format, to
> make it more readable. Whenever preempt_wakeup_timing is enabled,
> user-tracing will follow the traced task, if it's disabled then tracing
> will stay on the CPU. No other changes.
...
> 	Ingo

On my machine, disabling CONFIG_LATENCY_TRACE causes the kernel to stop 
reporting preempt latencies. After
# echo 1 > /proc/sys/kernel/preempt_max_latency

/proc/sys/kernel/preempt_max_latency always shows 1 no matter what load 
is on the machine. I´ve seen this behavior since the first time I tried 
to disable CONFIG_LATENCY_TRACE, around V0.7.31.something.

Below is the exact diff between the 2 configs (the one that shows 
latencies and the one that doesn´t). Note that the only intentional 
change is turning off CONFIG_LATENCY_TRACE.
=======================================================
--- /tmp/config-2.6.10-rc2-mm3-V0.7.32-2.lat    2004-12-07 
16:25:03.000000000 +0200
+++ /tmp/config-2.6.10-rc2-mm3-V0.7.32-2.no_lat 2004-12-07 
11:06:19.000000000 +0200
@@ -1,7 +1,7 @@
  #
  # Automatically generated make config: don't edit
  # Linux kernel version: 2.6.10-rc2-mm3-V0.7.32-2
-# Tue Dec  7 11:07:07 2004
+# Mon Dec  6 20:24:09 2004
  #
  CONFIG_X86=y
  CONFIG_MMU=y
@@ -137,6 +137,7 @@
  CONFIG_MTRR=y
  # CONFIG_EFI is not set
  CONFIG_HAVE_DEC_LOCK=y
+# CONFIG_REGPARM is not set

  #
  # Performance-monitoring counters support
@@ -1711,12 +1712,12 @@
  CONFIG_CRITICAL_IRQSOFF_TIMING=y
  CONFIG_CRITICAL_TIMING=y
  CONFIG_LATENCY_TIMING=y
-CONFIG_LATENCY_TRACE=y
-CONFIG_MCOUNT=y
+# CONFIG_LATENCY_TRACE is not set
  # CONFIG_RT_DEADLOCK_DETECT is not set
  # CONFIG_DEBUG_KOBJECT is not set
  CONFIG_DEBUG_BUGVERBOSE=y
  # CONFIG_DEBUG_INFO is not set
+CONFIG_USE_FRAME_POINTER=y
  CONFIG_FRAME_POINTER=y
  CONFIG_EARLY_PRINTK=y
  # CONFIG_DEBUG_STACKOVERFLOW is not set
=======================================================
-- 
Eran Mann


       reply	other threads:[~2004-12-07 14:38 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <OFD07DEEA4.7C243C76-ON86256F5F.007976EC@raytheon.com>
     [not found] ` <20041204175636.GA3115@elte.hu>
2004-12-07 14:37   ` Eran Mann [this message]
2004-12-07 15:37     ` [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm2-V0.7.32-2 Ingo Molnar
2004-12-07 17:51       ` Eran Mann
2004-12-07 18:40       ` Gene Heskett
2004-12-07 21:47         ` Ingo Molnar
2004-12-08  1:05           ` Gene Heskett
2004-12-08 19:48             ` john cooper
2004-12-08 20:38               ` Gene Heskett

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=41B5C038.1090501@mrv.com \
    --to=emann@mrv.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    /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