From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:48918) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1R5cQ5-0005ga-4w for qemu-devel@nongnu.org; Mon, 19 Sep 2011 07:53:54 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1R5cQ4-0007Fo-8p for qemu-devel@nongnu.org; Mon, 19 Sep 2011 07:53:53 -0400 Received: from mail-iy0-f173.google.com ([209.85.210.173]:37326) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1R5cQ4-0007Fh-4v for qemu-devel@nongnu.org; Mon, 19 Sep 2011 07:53:52 -0400 Received: by iagf6 with SMTP id f6so6566572iag.4 for ; Mon, 19 Sep 2011 04:53:51 -0700 (PDT) From: Frediano Ziglio Date: Mon, 19 Sep 2011 13:54:15 +0200 Message-Id: <1316433257-4863-1-git-send-email-freddy77@gmail.com> Subject: [Qemu-devel] [PATCH 0/2][RFC?] Remove SIGUSR2 from posix-aio List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: aliguori@us.ibm.com, kwolf@redhat.com Cc: qemu-devel@nongnu.org, Frediano Ziglio Now that iothread is always compiled sending a signal seems only an additional step. This patch also avoid writing to two pipe (one from signal and one in qemu_service_io). Tested and works correctly with KVM enabled. Performances are only sligthly better (as I expected). strace output is more readable. Doubts: - any sense having two patches and not only last one? - comment is perhaps wrong as is also affect main core - is ok if KVM is disabled? more testing required Frediano Ziglio (2): block: avoid storing a constant in qemu_paiocb structure block: avoid SIGUSR2 cpus.c | 5 ----- posix-aio-compat.c | 17 ++++------------- 2 files changed, 4 insertions(+), 18 deletions(-)