From: Karim Yaghmour <karim@opersys.com>
To: paulmck@us.ibm.com
Cc: Kristian Benoit <kbenoit@opersys.com>,
linux-kernel@vger.kernel.org, bhuey@lnxw.com, andrea@suse.de,
tglx@linutronix.de, mingo@elte.hu, pmarques@grupopie.com,
bruce@andrew.cmu.edu, nickpiggin@yahoo.com.au, ak@muc.de,
sdietrich@mvista.com, dwalker@mvista.com, hch@infradead.org,
akpm@osdl.org, rpm@xenomai.org
Subject: Re: PREEMPT_RT vs I-PIPE: the numbers, part 2
Date: Mon, 20 Jun 2005 22:29:32 -0400 [thread overview]
Message-ID: <42B77B8C.6050109@opersys.com> (raw)
In-Reply-To: <20050621015542.GB1298@us.ibm.com>
Paul E. McKenney wrote:
> It looks to me that I-PIPE is an example of a "nested OS", with
> Linux nested within the I-PIPE functionality.
Sorry, the I-pipe is likely in the "none-of-the-above" category. It's
actually not much of a category itself. For one thing, it's clearly
not an RTOS in any sense of the word.
The I-pipe is just a layer that allows multiple pieces of code to
share an interrupt stream in a prioritized fashion. It doesn't
schedule anything or provide any sort of abstraction whatsoever.
Your piece of code just gets a spot in the pipeline and receives
interrupts accordingly. Not much nesting there. It's just a new
feature in Linux.
Have a look at the patches and description posted by Philippe last
Friday for more detail.
> One could take
> the RTAI-Fusion approach, but this measurement is of I-PIPE
> rather than RTAI-Fusion, right? (And use of RTAI-Fusion might
> or might not change these results significantly, just trying to
> make sure I understand what these specific tests apply to.)
That's inconsequential. Whether Fusion is loaded or not doesn't
preclude a loaded driver to have a higher priority than
Fusion itself and therefore continue receiving interrupt even if
Fusion itself has disabled interrupts ...
The loading of Fusion would change nothing to these measurements.
> Also, if I understand correctly, the interrupt latency measured
> is to the Linux kernel running within I-PIPE, rather than to I-PIPE
> itself. Is this the case, or am I confused?
What's being measured here is a loadable module that allocates an
spot in the ipipe that has higher priority than Linux and puts
itself there. Therefore, regardless of what other piece of code
in the kernel disables interrupts, that specific driver still
has its registered ipipe handler called deterministically ...
Don't know, but from the looks of it we're not transmitting on
the same frequency ...
Karim
--
Author, Speaker, Developer, Consultant
Pushing Embedded and Real-Time Linux Systems Beyond the Limits
http://www.opersys.com || karim@opersys.com || 1-866-677-4546
next prev parent reply other threads:[~2005-06-21 3:31 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-06-20 17:13 PREEMPT_RT vs I-PIPE: the numbers, part 2 Kristian Benoit
2005-06-20 18:31 ` Bill Huey
2005-06-22 16:00 ` Karim Yaghmour
2005-06-22 19:29 ` Bill Huey
2005-06-22 20:05 ` Ingo Molnar
2005-06-22 20:39 ` Karim Yaghmour
2005-06-22 22:04 ` Ingo Molnar
2005-06-22 23:03 ` Lee Revell
2005-06-22 23:52 ` Karim Yaghmour
2005-06-22 23:38 ` Karim Yaghmour
2005-06-22 23:57 ` Andrea Arcangeli
2005-06-23 0:05 ` Daniel Walker
2005-06-23 0:48 ` Karim Yaghmour
2005-06-23 0:06 ` Ingo Molnar
2005-06-23 0:47 ` Karim Yaghmour
2005-06-23 0:55 ` Bill Huey
2005-06-23 1:09 ` Karim Yaghmour
2005-06-23 1:15 ` Bill Huey
2005-06-23 1:47 ` Karim Yaghmour
2005-06-23 0:59 ` David Lang
2005-06-23 1:22 ` Karim Yaghmour
2005-06-23 1:42 ` David Lang
2005-06-23 2:09 ` Karim Yaghmour
2005-06-23 2:15 ` David Lang
2005-06-23 1:34 ` Ingo Molnar
2005-06-23 2:02 ` Karim Yaghmour
2005-06-23 3:57 ` Lee Revell
2005-06-23 4:13 ` Karim Yaghmour
2005-06-22 20:10 ` Karim Yaghmour
2005-06-22 20:15 ` Bill Huey
2005-06-21 1:55 ` Paul E. McKenney
2005-06-21 2:29 ` Karim Yaghmour [this message]
2005-06-22 1:19 ` Paul E. McKenney
2005-06-22 15:31 ` Karim Yaghmour
2005-06-22 15:27 ` Kristian Benoit
2005-06-22 16:27 ` Paul E. McKenney
2005-06-22 17:20 ` Kristian Benoit
2005-06-22 17:34 ` Ingo Molnar
2005-06-22 17:40 ` Ingo Molnar
2005-06-22 18:12 ` Karim Yaghmour
2005-06-22 18:14 ` Ingo Molnar
2005-06-22 19:04 ` Karim Yaghmour
2005-06-22 18:50 ` Paul E. McKenney
2005-06-22 19:04 ` Ingo Molnar
2005-06-22 20:17 ` Karim Yaghmour
2005-06-22 20:22 ` Ingo Molnar
2005-06-22 21:03 ` Karim Yaghmour
2005-06-22 21:10 ` Ingo Molnar
2005-06-22 21:32 ` Karim Yaghmour
2005-06-22 22:41 ` Ingo Molnar
2005-06-22 23:02 ` Karim Yaghmour
2005-06-22 21:20 ` Paul E. McKenney
2005-06-22 19:08 ` Karim Yaghmour
2005-06-23 14:48 ` Paulo Marques
2005-06-22 17:58 ` Karim Yaghmour
2005-06-22 18:47 ` Paul E. McKenney
2005-06-22 19:16 ` Karim Yaghmour
2005-06-22 21:23 ` Paul E. McKenney
2005-06-22 17:17 ` Lee Revell
2005-06-22 17:32 ` Karim Yaghmour
2005-06-29 7:43 ` PREEMPT_RT & threading IRQ 0 Ingo Molnar
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=42B77B8C.6050109@opersys.com \
--to=karim@opersys.com \
--cc=ak@muc.de \
--cc=akpm@osdl.org \
--cc=andrea@suse.de \
--cc=bhuey@lnxw.com \
--cc=bruce@andrew.cmu.edu \
--cc=dwalker@mvista.com \
--cc=hch@infradead.org \
--cc=kbenoit@opersys.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=nickpiggin@yahoo.com.au \
--cc=paulmck@us.ibm.com \
--cc=pmarques@grupopie.com \
--cc=rpm@xenomai.org \
--cc=sdietrich@mvista.com \
--cc=tglx@linutronix.de \
/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