From: Rusty Russell <rusty@rustcorp.com.au>
To: Tim Hockin <thockin@hockin.org>
Cc: vatsa@in.ibm.com, lhcs-devel@lists.sourceforge.net,
linux-kernel@vger.kernel.org, torvalds@osdl.org, akpm@osdl.org,
rml@tech9.net
Subject: Re: CPU Hotplug: Hotplug Script And SIGPWR
Date: Wed, 21 Jan 2004 11:12:46 +1100 [thread overview]
Message-ID: <20040121043608.740302C10D@lists.samba.org> (raw)
In-Reply-To: Your message of "Tue, 20 Jan 2004 00:37:01 -0800." <20040120083700.GB15733@hockin.org>
In message <20040120083700.GB15733@hockin.org> you write:
> > off). There are no correctness concerns AFAICT with userspace not
> > being on a particular CPU, just performance.
>
> Correctness does matter if an affined task violates that affinity. If we
> are going to provide explicit affinity, we need to honor it under all
> conditions, or at least provide an option to honor it.
WHY? Think of an example where this is actually a problem.
"Under all conditions" is not something we can ever implement for
anything.
> I agree about invasiveness. Maybe a combo? Send SIGPWR iff a task is
> actually handling it, otherwise mark it TASK_UNRUNNABLE and let hotplug
> handle it?
Well, I think that violating affinity given that (1) affinity in
userspace is only a performance issue, and (2) we've been explicitly
told to take the CPU down, is a valid solution.
OTOH making tasks unrunnable until hotplug gets around to servicing
them could equally be a disaster. Given that this requires
infrastructure not in Linus' tree and the "simply unbind" solution
doesn't, I'm leaning towards unbinding everything which would become
unrunnable, SIGPWR if they handle it, and hotplug at the end.
Thanks,
Rusty.
--
Anyone who quotes me in their sig is an idiot. -- Rusty Russell.
next prev parent reply other threads:[~2004-01-21 4:38 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20040116174446.A2820@in.ibm.com>
2004-01-20 5:44 ` CPU Hotplug: Hotplug Script And SIGPWR Rusty Russell
2004-01-20 6:33 ` Tim Hockin
2004-01-20 6:43 ` Nick Piggin
2004-01-20 6:52 ` Tim Hockin
2004-01-20 7:11 ` Nick Piggin
2004-01-20 7:30 ` Tim Hockin
2004-01-20 7:45 ` Nick Piggin
2004-01-20 7:54 ` Tim Hockin
2004-01-20 8:14 ` Nick Piggin
2004-01-20 8:29 ` Tim Hockin
2004-01-20 8:37 ` Nick Piggin
2004-01-20 8:43 ` Tim Hockin
2004-01-21 4:06 ` Srivatsa Vaddagiri
2004-01-21 4:14 ` Nick Piggin
2004-01-21 5:09 ` Srivatsa Vaddagiri
2004-01-21 7:08 ` Tim Hockin
2004-01-21 15:07 ` Matthias Urlichs
2004-01-22 5:29 ` Rusty Russell
2004-01-21 7:09 ` Tim Hockin
2004-01-21 7:31 ` Nick Piggin
2004-01-21 7:42 ` Tim Hockin
2004-01-21 8:11 ` Rusty Russell
2004-01-21 5:07 ` Rusty Russell
2004-01-20 8:41 ` Stefan Smietanowski
2004-01-20 8:49 ` Nick Piggin
2004-01-20 9:12 ` Tim Hockin
2004-01-21 0:00 ` Rusty Russell
2004-01-20 23:51 ` Rusty Russell
2004-01-20 7:45 ` Rusty Russell
2004-01-20 8:37 ` Tim Hockin
2004-01-20 9:29 ` Srivatsa Vaddagiri
2004-01-21 0:12 ` Rusty Russell [this message]
[not found] <fa.f37o48p.1io5q5@ifi.uio.no>
[not found] ` <fa.frjqvfo.170g8hq@ifi.uio.no>
2004-01-20 17:49 ` Andy Lutomirski
2004-01-21 4:33 ` Rusty Russell
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=20040121043608.740302C10D@lists.samba.org \
--to=rusty@rustcorp.com.au \
--cc=akpm@osdl.org \
--cc=lhcs-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=rml@tech9.net \
--cc=thockin@hockin.org \
--cc=torvalds@osdl.org \
--cc=vatsa@in.ibm.com \
/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