From: Philippe Gerum <rpm@xenomai.org>
To: Lowell Gilbert <kludge@be-well.ilk.org>, xenomai@xenomai.org
Subject: Re: [Xenomai] interrupt service
Date: Fri, 27 Feb 2015 00:21:44 +0100 [thread overview]
Message-ID: <54EFAA88.3020303@xenomai.org> (raw)
In-Reply-To: <44wq34cmfh.fsf@lowell-desk.lan>
On 02/26/15 23:55, Lowell Gilbert wrote:
> I really wouldn't mind letting the kernel get time more frequently; I just
> need to be sure that my real time task gets at least 8 microseconds out
> of every fifteen. Would I be able to guarantee that in a polled
> architecture? What would be involved: short sleeps from a high-priority
> realtime task?
>
Yes, I'd think so.
I don't have the context switch time figures in mind on a typical Cortex
A9 (assuming 1Ghz or close to), but the main issue boils down to cache
pollution with a dual kernel system in this case. If the real-time task
sleeps/blocks, then linux may run and cause cache lines used by the rt
code to be evicted, raising the latency.
Now, with such a fast rate (assuming 15 us), there would not be much
time for linux to run and pollute the cache anyway. But this is all so
close to the limit that I can't say that linux could run reliably either.
--
Philippe.
next prev parent reply other threads:[~2015-02-26 23:21 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-18 22:03 [Xenomai] interrupt service Lowell Gilbert
2015-02-18 22:08 ` Gilles Chanteperdrix
2015-02-19 4:44 ` Lowell Gilbert
2015-02-19 21:06 ` Lowell Gilbert
2015-02-20 19:38 ` Lowell Gilbert
2015-02-20 22:57 ` Gilles Chanteperdrix
2015-02-24 23:01 ` Lowell Gilbert
2015-02-24 23:34 ` Gilles Chanteperdrix
2015-02-25 16:22 ` Lowell Gilbert
2015-02-25 17:34 ` Philippe Gerum
2015-02-25 18:35 ` Philippe Gerum
2015-02-25 20:41 ` Lowell Gilbert
2015-02-25 21:02 ` Lowell Gilbert
2015-02-26 11:19 ` Philippe Gerum
2015-02-26 16:38 ` Lowell Gilbert
2015-02-26 17:26 ` Gilles Chanteperdrix
2015-02-26 17:56 ` Philippe Gerum
2015-02-26 19:25 ` Lowell Gilbert
2015-02-26 20:11 ` Gilles Chanteperdrix
2015-02-26 21:58 ` Lowell Gilbert
2015-02-26 22:37 ` Gilles Chanteperdrix
2015-02-26 23:12 ` Lowell Gilbert
2015-02-26 23:09 ` Philippe Gerum
2015-03-06 22:57 ` Lowell Gilbert
2015-03-06 22:58 ` Lowell Gilbert
2015-03-08 15:52 ` Gilles Chanteperdrix
2015-03-09 13:28 ` Lowell Gilbert
2015-02-26 20:24 ` Philippe Gerum
2015-02-26 22:55 ` Lowell Gilbert
2015-02-26 23:17 ` Daniele Nicolodi
2015-02-26 23:21 ` Philippe Gerum [this message]
2015-02-27 7:15 ` Tom Evans
2015-02-25 8:30 ` Philippe Gerum
2015-02-25 9:36 ` Philippe Gerum
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=54EFAA88.3020303@xenomai.org \
--to=rpm@xenomai.org \
--cc=kludge@be-well.ilk.org \
--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.