All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tim Hockin <thockin@hockin.org>
To: Nick Piggin <piggin@cyberone.com.au>
Cc: Rusty Russell <rusty@au1.ibm.com>,
	vatsa@in.ibm.com, linux-kernel@vger.kernel.org,
	torvalds@osdl.org, akpm@osdl.org, rml@tech9.net
Subject: Re: CPU Hotplug: Hotplug Script And SIGPWR
Date: Mon, 19 Jan 2004 23:54:09 -0800	[thread overview]
Message-ID: <20040120075409.GA13897@hockin.org> (raw)
In-Reply-To: <400CDCA1.5070200@cyberone.com.au>

On Tue, Jan 20, 2004 at 06:45:37PM +1100, Nick Piggin wrote:
> >I guess a hotplug script MAY fail.  I don't think it's a good idea to make
> >your CPU hotplug script fail.  May and Misght are different.  It's up to 
> >the
> >implementor whether the script can get into a failure condition.
> >
> 
> Sorry bad wording. The script may fail to be executed.

Under what conditions?  Not arbitrary entropy, surely.  If a hotplug script
is present and does not blow up, it should be safe to assume it will be run
upon an event being delivered.  If not, we have a WAY bigger problem :)

> >What if <which> process needs guaranteed scheduling latency?  Do we really
> >_guarantee_ scheduling latency *anywhere*?
> 
> We do guarantee that a realtime task won't be blocked waiting for
> a hotplug script to fault in and start it up again (which may not
> happen). Not sure how important this issue is.

We have a conflict of priority here.  If an RT task is affined to CPU A and
CPU A gets yanked out, what do we do?

Obviously the RT task can't keep running as it was.  It was affined to A.
Maybe for a good reason.  I see we have a few choices here:

* re-affine it automatically, thereby silently undoing the explicit
  affinity.
* violate it's RT scheduling by not running it until it has been re-affined
  or CPU A returns to the pool/

Sending it a SIGPWR means you have to run it on a different CPU that it was
affined to, which is already a violation.

Basically, RT tasks + CPU affinity + hotplug CPUs do not play nicely
together.  I don't see much that can be done to solve that.  With the
procstate stuff I did, and with planned CPU unplugs we *do* have time before
the CPU really goes offline in which to act.  With unplanned CPU offlining,
we don't.


  reply	other threads:[~2004-01-20  7:54 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 [this message]
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
     [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=20040120075409.GA13897@hockin.org \
    --to=thockin@hockin.org \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=piggin@cyberone.com.au \
    --cc=rml@tech9.net \
    --cc=rusty@au1.ibm.com \
    --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 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.