From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1NF9PZ-00086S-Pq for qemu-devel@nongnu.org; Mon, 30 Nov 2009 11:47:43 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1NF9PU-000844-3B for qemu-devel@nongnu.org; Mon, 30 Nov 2009 11:47:40 -0500 Received: from [199.232.76.173] (port=58705 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1NF9PR-00083Z-HK for qemu-devel@nongnu.org; Mon, 30 Nov 2009 11:47:34 -0500 Received: from mail-iw0-f197.google.com ([209.85.223.197]:37923) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1NF9PQ-0007Ph-G1 for qemu-devel@nongnu.org; Mon, 30 Nov 2009 11:47:32 -0500 Received: by iwn35 with SMTP id 35so2215486iwn.4 for ; Mon, 30 Nov 2009 08:47:31 -0800 (PST) MIME-Version: 1.0 In-Reply-To: <4B13F570.4030605@redhat.com> References: <1259256300-23937-1-git-send-email-glommer@redhat.com> <4B12B042.9020409@web.de> <5d6222a80911300342x4d29653as6c23acac598dec64@mail.gmail.com> <5d6222a80911300755o4fed5447w9ddae1abaccf7100@mail.gmail.com> <4B13F570.4030605@redhat.com> Date: Mon, 30 Nov 2009 14:47:31 -0200 Message-ID: <5d6222a80911300847w2faa9d39nb2fc6ee3ccb9ccfd@mail.gmail.com> Subject: Re: [Qemu-devel] Re: [PATCH 0/7] KVM SMP support, early version From: Glauber Costa Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: Glauber Costa , Jan Kiszka , aliguori@us.ibm.com, qemu-devel@nongnu.org On Mon, Nov 30, 2009 at 2:40 PM, Avi Kivity wrote: > On 11/30/2009 05:55 PM, Glauber Costa wrote: >> >> reset code is responsible for most remote calls in qemu. One of the >> only ones we still >> have left is the gdb stuff. Do you have any suggestion to do that >> without the current >> on_vcpu mechanism? >> > > No. =C2=A0But what's wrong with on_vcpu? intrinsically racy. signal passing slow down things, etc. That said, as I've stated many times: I don't believe there's anything fundamentally wrong with on_vcpu. But we might get benefits from a re-desig= n of things to avoid it whenever possible. (just like the vcpu_reset() I've just posted) --=20 Glauber Costa. "Free as in Freedom" http://glommer.net "The less confident you are, the more serious you have to act."