From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 1/3] Use signalfd() in io-thread Date: Mon, 05 May 2008 10:23:22 +0300 Message-ID: <481EB5EA.9060605@qumranet.com> References: <1209932438-6957-1-git-send-email-aliguori@us.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: kvm-devel@lists.sourceforge.net, Marcelo Tosatti To: Anthony Liguori Return-path: In-Reply-To: <1209932438-6957-1-git-send-email-aliguori@us.ibm.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces@lists.sourceforge.net Errors-To: kvm-devel-bounces@lists.sourceforge.net List-Id: kvm.vger.kernel.org Anthony Liguori wrote: > This patch reworks the IO thread to use signalfd() instead of sigtimedwait(). > This will eliminate the need to use SIGIO everywhere. In this version of the > patch, we use signalfd() when it's available. When it isn't available, we > create a separate thread and use sigwaitinfo() to simulate signalfd(). > > We cannot handle thread-specific signals with signalfd() emulation so also > replace SIGUSR1 notifications to the io-thread with an eventfd. Since eventfd > isn't always available, use pipe() to emulate eventfd. > Please break the SIGUSR1 changes into a separate patch. Ditto with *fd syscall compat. -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone