From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35897) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1VTutf-0002B4-6u for qemu-devel@nongnu.org; Wed, 09 Oct 2013 10:38:03 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1VTutW-0000as-Pg for qemu-devel@nongnu.org; Wed, 09 Oct 2013 10:37:55 -0400 Received: from mail-vc0-x22f.google.com ([2607:f8b0:400c:c03::22f]:47223) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1VTutW-0000ab-H0 for qemu-devel@nongnu.org; Wed, 09 Oct 2013 10:37:46 -0400 Received: by mail-vc0-f175.google.com with SMTP id ia10so559375vcb.6 for ; Wed, 09 Oct 2013 07:37:46 -0700 (PDT) Sender: Paolo Bonzini Message-ID: <52556A35.7060300@redhat.com> Date: Wed, 09 Oct 2013 16:37:41 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <1381259403-7386-1-git-send-email-hdegoede@redhat.com> <52545950.5070403@redhat.com> <52545B44.70005@redhat.com> <28EE4224-856B-4DC1-8159-A0C274BD269E@alex.org.uk> <52546000.6070308@redhat.com> <6CD4D4EE-341E-48D0-98F4-D55C0D3922D4@alex.org.uk> <52546832.9040900@redhat.com> <5254701B.5070804@redhat.com> <525552D9.90407@redhat.com> In-Reply-To: <525552D9.90407@redhat.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH] main-loop: Don't lock starve io-threads when main_loop_tlg has pending events List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Hans de Goede Cc: qemu-devel@nongnu.org, Alex Bligh Il 09/10/2013 14:58, Hans de Goede ha scritto: > > > I still think we should add my patch in some form, since the lock > starvation > caused by timers set to expire in the past could still happen in other > cases, > esp for timer users who take a time stamp once and then add incremental > values to trigger the next run, these can get behind quite a bit if there > are latency spikes, and we don't wont to run without ever releasing the > lock while these are catching up. I agree. Do you also agree that the equivalent workaround, before Alex's patch, was MIN_REARM_TIMER_NS (and thus 250 microseconds)? Paolo