Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 22 Feb 2006 12:05:37 -0500
From:      John Baldwin <jhb@freebsd.org>
To:        Andrey Chernov <ache@freebsd.org>
Cc:        current@freebsd.org, Kris Kennaway <kris@obsecurity.org>
Subject:   Re: [PATCH] possible fix for the runtime going backwards warnings
Message-ID:  <200602221205.40160.jhb@freebsd.org>
In-Reply-To: <20060222162046.GA16663@nagual.pp.ru>
References:  <200602211047.06599.jhb@freebsd.org> <200602221101.41027.jhb@freebsd.org> <20060222162046.GA16663@nagual.pp.ru>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wednesday 22 February 2006 11:20, Andrey Chernov wrote:
> On Wed, Feb 22, 2006 at 11:01:39AM -0500, John Baldwin wrote:
> > Is it more or less than before the patch?  Also, what happens if you just back 
> 
> Less than (for me).

So the patch was a net improvement?

> > The pagezero ones are truly odd.  calcru() shouldn't be called for kthreads 
> > very often (if at all).  I wonder if your tickrate is changing out from under 
> > you.  Try editing sys/i386/i386/tsc.c and where it does 'set_cputicker(rdtsc, 
> > tsc_freq, 1)' change the last parameter to '0' and see if they go away.
> 
> May it interfere with ntpd activity? I have those log lines in one chunk:
> Feb 22 03:36:43 pobrecita ntpd[422]: time reset +0.622691 s
> Feb 22 03:36:43 pobrecita ntpd[422]: kernel time sync disabled 2041
> Feb 22 03:37:45 pobrecita kernel: calcru: runtime went backwards from 292542 usec to 292537 usec for pid 29 (pagezero)
> Feb 22 03:37:45 pobrecita kernel: u 0:0/0 s 38:292542/292537 i 0:0/0

It should not affect ntp.  It is just about the usage calculations for
processes, not related to timekeeping or wall time.

-- 
John Baldwin <jhb@FreeBSD.org>  <><  http://www.FreeBSD.org/~jhb/
"Power Users Use the Power to Serve"  =  http://www.FreeBSD.org



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200602221205.40160.jhb>