All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Kiszka <jan.kiszka@domain.hid>
To: "M. Koehrer" <mathias_koehrer@domain.hid>
Cc: xenomai@xenomai.org
Subject: Re: [Xenomai-help] Xenomai User Space: Using 100% CPU power
Date: Mon, 13 Nov 2006 16:57:48 +0100	[thread overview]
Message-ID: <455895FC.7060203@domain.hid> (raw)
In-Reply-To: <29293133.1163432148953.JavaMail.ngmail@domain.hid>

[-- Attachment #1: Type: text/plain, Size: 1305 bytes --]

M. Koehrer wrote:
> Hi everybody,
> 
> I have an application where I need extreme precise timing (about 1µs) for a couple of seconds
> using a standard PC (to access a I/O PCI board).
> For this, I want to write an application that initializes normally and 
> whenever the software is in a certain state, I want to enter a  "high-precision-timing mode".
> In this high-precision-timing mode, I want to disable all interrupts and poll permanently on a PCI I/O board.
> The timing itself can be directly taken from the CPU's TSC using rdtsc.
> Within this mode, the time measurement of register changes on the PCI I/O board is very important.
> After a couple of seconds, when all relevant data is taken, I want to leave this
> "high-precision-mode" and come back to the normal mode.
> Then the measurement results are interpreted in detail.
> All this should happen in user mode, not in kernel mode.
> 
> My questions are now: 
> Is this possible using Xenomai?
> How can I enter a mode that disables all interrupts (including timer) for a while?

We had this discussion recently here, see

https://mail.gna.org/public/xenomai-help/2006-10/msg00172.html

And be aware that you are about to toast Linux's time keeping (but I
guess that of lower priority in this scenario).

Jan


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 250 bytes --]

      reply	other threads:[~2006-11-13 15:57 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-13 15:35 [Xenomai-help] Xenomai User Space: Using 100% CPU power M. Koehrer
2006-11-13 15:57 ` Jan Kiszka [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=455895FC.7060203@domain.hid \
    --to=jan.kiszka@domain.hid \
    --cc=mathias_koehrer@domain.hid \
    --cc=xenomai@xenomai.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 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.