linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Gene Heskett <gene.heskett@gmail.com>
To: Mike Galbraith <efault@gmx.de>,
	LKML <linux-kernel@vger.kernel.org>,
	emc-users@lists.sourceforge.net
Subject: Re: isolcpus question
Date: Tue, 31 Jan 2012 01:31:19 -0500	[thread overview]
Message-ID: <201201310131.20239.gene.heskett@gmail.com> (raw)
In-Reply-To: <1327985246.6667.8.camel@marge.simson.net>

On Monday, January 30, 2012, Mike Galbraith wrote:
>On Mon, 2012-01-30 at 22:13 -0500, Gene Heskett wrote:
>> Which is, is there a isolcpus troubleshooting tool?
>> 
>> I have an app that is supposed to use the 2nd cpu on a 2 core atom
>> system all by itself, and its insisting on using cpu0 when the boot
>> command line has "isolcpus=1" appended to it, and apparently I am the
>> only one with the problem, its working for about 200-500 others
>> running the same software.
>
>isolcpus=1 isolates CPU1 so no task will automatically end up using it,
>but it's up to your task (or you) to move to the isolated CPU.  Pin your
>task to CPU1 with taskset, and all should work fine.
>
>	-Mike

Cross-posted back to the emc-users list, others might find it useful also.

Mike, you're a genius. The man page for taskset is a bit obtuse but the 
first stab at a '/usr/bin/lcnc' script:
-------------
#!/bin/bash
taskset 0x00000002 emc -l
exit 0
-------------
Seems to launch this application and I believe its now working better than 
ever before.  Now I need to do some experimenting to see just how fast I 
can make linuxcnc's base_thread run without the rest of the box getting 
laggy.  The faster I can make that thread run, the faster and smoother my 
steppers driving my milling machine will run.  I have already cut it down 
to 30 u-secs from 65 u-secs and it is still only using about 26% of the 
target cpu1.  Amazing IMO.

Thank you very much Mike.

Cheers, Gene
-- 
"There are four boxes to be used in defense of liberty:
 soap, ballot, jury, and ammo. Please use in that order."
-Ed Howdershelt (Author)
My web page: <http://coyoteden.dyndns-free.com:85/gene>
When a lion meets another with a louder roar,
the first lion thinks the last a bore.
		-- G.B. Shaw

      reply	other threads:[~2012-01-31  6:31 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-31  3:13 isolcpus question Gene Heskett
2012-01-31  4:47 ` Mike Galbraith
2012-01-31  6:31   ` Gene Heskett [this message]

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=201201310131.20239.gene.heskett@gmail.com \
    --to=gene.heskett@gmail.com \
    --cc=efault@gmx.de \
    --cc=emc-users@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.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).