From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Matt Fleming <matt@console-pimps.org>,
Tejun Heo <htejun@gmail.com>,
linux-kernel@vger.kernel.org, Tony Luck <tony.luck@intel.com>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [RFC][PATCH 0/5] Signal scalability series
Date: Mon, 3 Oct 2011 15:07:01 +0200 [thread overview]
Message-ID: <20111003130701.GB25952@redhat.com> (raw)
In-Reply-To: <1317474209.12973.15.camel@twins>
On 10/01, Peter Zijlstra wrote:
>
> On Sat, 2011-10-01 at 11:16 +0100, Matt Fleming wrote:
> > I also think Thomas/Peter mentioned something about latency in
> > delivering timer signals because of contention on the per-process
> > siglock. They might have some more details on that.
>
> Right, so signal delivery is O(nr_threads),
Yes, a !SIGEV_THREAD_ID timer needs to find a thread which doesn't
block the signal.
But this series can't help afaics. At least in its current state. It
only adds more locking to the sending paths.
And anyway it is wrong (afaics, and I didn't read it yet ;).
> which precludes being able
> to deliver signals from hardirq context, leading to lots of ugly in -rt.
I think, the best solution would be: never send the signal from irq
context, and ->siglock shouldn't disable irqs.
> The hope is that this work is a stepping stone to O(1) signal delivery.
Probably this is possible too. I was thinking anout this when
set_current_blocked() was added. Unfortunately this needs a lot of
complications.
> Breaking up the multitude of uses of siglock certainly seems worthwhile
> esp.
Agreed. But I am not sure how much we should split the locking when
it comes to sending/dequeueing/etc signals. 5 locks seems too much.
> And yes, aside from that the siglock can be quite contended because its
> pretty much the one lock serializing all of the process wide state.
True.
Mostly this is because we moved misc stuff from tasklist to siglock,
previously this was a win. Today this doesn't look good.
Oleg.
next prev parent reply other threads:[~2011-10-03 14:11 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-30 15:12 [RFC][PATCH 0/5] Signal scalability series Matt Fleming
2011-09-30 15:12 ` [RFC][PATCH 1/5] signal: Document signal locking rules Matt Fleming
2011-09-30 15:12 ` [RFC][PATCH 2/5] signal: Add rwlock to protect sighand->action Matt Fleming
2011-09-30 15:25 ` Peter Zijlstra
2011-09-30 15:56 ` Matt Fleming
2011-09-30 15:12 ` [RFC][PATCH 3/5] signal: Reduce sighand->siglock hold time in get_signal_to_deliver() Matt Fleming
2011-09-30 15:12 ` [RFC][PATCH 4/5] signal: Add signal->ctrl_lock for job control Matt Fleming
2011-09-30 15:30 ` Peter Zijlstra
2011-09-30 15:36 ` Matt Fleming
2011-09-30 15:12 ` [RFC][PATCH 5/5] signal: Split siglock into shared_siglock and per-thread siglock Matt Fleming
2011-09-30 16:52 ` [RFC][PATCH 0/5] Signal scalability series Oleg Nesterov
2011-09-30 18:54 ` Oleg Nesterov
2011-09-30 20:00 ` Matt Fleming
2011-09-30 23:56 ` Tejun Heo
2011-10-01 10:16 ` Matt Fleming
2011-10-01 13:03 ` Peter Zijlstra
2011-10-03 1:38 ` Tejun Heo
2011-10-03 13:56 ` Thomas Gleixner
2011-10-04 7:37 ` Tejun Heo
2011-10-03 13:07 ` Oleg Nesterov [this message]
2011-10-03 15:22 ` Peter Zijlstra
2011-10-04 17:14 ` Oleg Nesterov
2011-10-04 17:52 ` Oleg Nesterov
2011-10-04 17:54 ` Linus Torvalds
2011-10-04 18:13 ` Oleg Nesterov
2011-10-03 13:16 ` Oleg Nesterov
2011-10-04 8:56 ` Matt Fleming
2011-10-04 17:29 ` Oleg Nesterov
2011-09-30 22:30 ` Andi Kleen
2011-10-01 9:35 ` Matt Fleming
2011-10-03 15:28 ` Linus Torvalds
2011-10-03 15:43 ` Matt Fleming
2011-10-03 16:35 ` Oleg Nesterov
2011-10-03 20:58 ` Matt Fleming
2011-10-03 21:45 ` Linus Torvalds
2011-10-03 22:13 ` Thomas Gleixner
2011-10-04 8:20 ` Matt Fleming
2011-10-04 17:39 ` Oleg Nesterov
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=20111003130701.GB25952@redhat.com \
--to=oleg@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=htejun@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=matt@console-pimps.org \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.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.