linux-mips
[Top] [All Lists]

Re: CONFIG_PRINTK_TIME and initial value for jiffies?

To: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Subject: Re: CONFIG_PRINTK_TIME and initial value for jiffies?
From: Tim Bird <tim.bird@am.sony.com>
Date: Mon, 22 May 2006 09:27:30 -0700
Cc: Herbert Valerio Riedel <hvr@gnu.org>, Clem Taylor <clem.taylor@gmail.com>, Linux-MIPS <linux-mips@linux-mips.org>
In-reply-to: <4469C71F.9060004@ru.mvista.com>
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <ecb4efd10605151341l33f491f1ueca8a0ce609c989d@mail.gmail.com> <4468EE9B.4000009@ru.mvista.com> <4468F40F.80902@ru.mvista.com> <1147759399.11301.15.camel@localhost.localdomain> <4469C71F.9060004@ru.mvista.com>
Sender: linux-mips-bounce@linux-mips.org
User-agent: Thunderbird 1.5 (X11/20051201)
Sergei Shtylyov wrote:
>    sched_clock() defined in arch/i386/kernel/timers/timer_tsc.c can
> hardly provide 0-based time if it's using TSC (at least I can't see
> where the TSC is cleared). Even if it's not using TSC, jiffies_64 is not
> 0-based as we saw, and neither it's set to -300 secs because of the
> double cast to ulong and then to u64 which should clear the high word.
> Probably something somewhere clears TSC but I can see the related code
> only in arch/i386/kernel/smpboot.c...

I've worked a lot with the printk_times feature, and it's not unusual
on many systems to see weird values before time_init().  On x86 with a
TSC-based sched_clock() you may see values based on whatever
the TSC happens to be after firmware initialization up until time_init().

Note that you can re-base the timings to an arbitrary printk line
using scripts/show_delta.  See
http://tree.celinuxforum.org/CelfPubWiki/PrintkTimesSample2

=============================
Tim Bird
Architecture Group Chair, CE Linux Forum
Senior Staff Engineer, Sony Electronics
=============================

<Prev in Thread] Current Thread [Next in Thread>