From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:44719) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1S8X2L-0006ix-LV for qemu-devel@nongnu.org; Fri, 16 Mar 2012 09:17:46 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1S8X1w-0004oB-Ra for qemu-devel@nongnu.org; Fri, 16 Mar 2012 09:17:41 -0400 Received: from e6.ny.us.ibm.com ([32.97.182.146]:37129) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1S8X1w-0004k9-Mb for qemu-devel@nongnu.org; Fri, 16 Mar 2012 09:17:16 -0400 Received: from /spool/local by e6.ny.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 16 Mar 2012 09:17:07 -0400 Received: from d01relay07.pok.ibm.com (d01relay07.pok.ibm.com [9.56.227.147]) by d01dlp01.pok.ibm.com (Postfix) with ESMTP id B3B7538C805A for ; Fri, 16 Mar 2012 09:16:47 -0400 (EDT) Received: from d03av06.boulder.ibm.com (d03av06.boulder.ibm.com [9.17.195.245]) by d01relay07.pok.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id q2GDGjUb3129524 for ; Fri, 16 Mar 2012 09:16:45 -0400 Received: from d03av06.boulder.ibm.com (loopback [127.0.0.1]) by d03av06.boulder.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id q2GDH0LW006666 for ; Fri, 16 Mar 2012 07:17:00 -0600 Message-ID: <4F633D37.60806@us.ibm.com> Date: Fri, 16 Mar 2012 08:16:39 -0500 From: Anthony Liguori MIME-Version: 1.0 References: <4F633153.9030004@siemens.com> In-Reply-To: <4F633153.9030004@siemens.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH] Kick io-thread on qemu_chr_accept_input List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Jan Kiszka Cc: Marek Vasut , qemu-devel , Paolo Bonzini On 03/16/2012 07:25 AM, Jan Kiszka wrote: > Once a chr frontend is able to receive input again, we need to inform > the io-thread about this fact. Otherwise, main_loop_wait may continue to > select without the related backend file descriptor in its set. This can > cause high input latencies if only low-rate events arrive otherwise. > > Signed-off-by: Jan Kiszka I'm not nacking this patch, but please note that this is a band-aid as not all char devices actually use qemu_chr_accept_input(). Regards, Anthony Liguori > --- > > /me wonders if a similar issue explains the slirp slowness under KVM > with in-kernel irqchip enabled. Need to check... > > qemu-char.c | 1 + > 1 files changed, 1 insertions(+), 0 deletions(-) > > diff --git a/qemu-char.c b/qemu-char.c > index 9a5be75..a589a84 100644 > --- a/qemu-char.c > +++ b/qemu-char.c > @@ -177,6 +177,7 @@ void qemu_chr_accept_input(CharDriverState *s) > { > if (s->chr_accept_input) > s->chr_accept_input(s); > + qemu_notify_event(); > } > > void qemu_chr_fe_printf(CharDriverState *s, const char *fmt, ...)