From mboxrd@z Thu Jan 1 00:00:00 1970 From: Richard Henderson Subject: Re: [Qemu-devel] [PATCH v2] Register Linux dyntick timer as per-thread signal Date: Fri, 17 Jun 2011 11:06:49 -0700 Message-ID: <4DFB97B9.2030205@twiddle.net> References: <4DF9CD7E.5020509@siemens.com> <4DFB1D9D.7060108@siemens.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Cc: qemu-devel , Anthony Liguori , Paolo Bonzini , Sasha Levin , kvm To: Jan Kiszka Return-path: Received: from mail-vw0-f46.google.com ([209.85.212.46]:40465 "EHLO mail-vw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751090Ab1FQSGz (ORCPT ); Fri, 17 Jun 2011 14:06:55 -0400 Received: by vws1 with SMTP id 1so2139893vws.19 for ; Fri, 17 Jun 2011 11:06:54 -0700 (PDT) In-Reply-To: <4DFB1D9D.7060108@siemens.com> Sender: kvm-owner@vger.kernel.org List-ID: On 06/17/2011 02:25 AM, Jan Kiszka wrote: > Derived from kvm-tool patch > http://thread.gmane.org/gmane.comp.emulators.kvm.devel/74309 > > Ingo Molnar pointed out that sending the timer signal to the whole > process, just blocking it everywhere, is suboptimal with an increasing > number of threads. QEMU is also using this pattern so far. > > Linux provides a (non-portable) way to restrict the signal to a single > thread: We can use SIGEV_THREAD_ID unless we are forced to emulate > signalfd via an additional thread. That case could theoretically be > optimized as well, but it doesn't look worth bothering. > > Signed-off-by: Jan Kiszka Reviewed-by: Richard Henderson r~