From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751722Ab0CVEU3 (ORCPT ); Mon, 22 Mar 2010 00:20:29 -0400 Received: from gabe.freedesktop.org ([131.252.210.177]:38190 "EHLO gabe.freedesktop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751188Ab0CVEU2 (ORCPT ); Mon, 22 Mar 2010 00:20:28 -0400 From: Eric Anholt To: Karl Vogel , linux-kernel@vger.kernel.org Subject: Re: i915 lockup / extreme delay In-Reply-To: References: Date: Sun, 21 Mar 2010 21:20:24 -0700 Message-ID: <87wrx5m1h3.fsf@pollan.anholt.net> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="=-=-="; micalg=pgp-sha1; protocol="application/pgp-signature" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-=-= Content-Transfer-Encoding: quoted-printable On Sat, 20 Mar 2010 14:41:41 +0100, Karl Vogel wrote: > I have been experiencing a very sluggish X server right after starting=20 > my laptop. The effect goes away after a few minutes, so it was rather=20 > hard to track down. >=20 > Recently after updating WINE to a newer release, I've been able to=20 > trigger the effect by running a certain game under wine on a remote=20 > computer and using VirtualGL to transport the GL display to my laptop.=20 > As I first thought the issue was somewhere with wine/virtualgl, I posted= =20 > the question to the virtualgl mailing list. The thread is here: >=20 > http://thread.gmane.org/gmane.comp.video.opengl.virtualgl.user/170 >=20 > But after some further investigation, it seems the issue is with the=20 > i915 driver. >=20 > The 'effect' is that only the mouse pointer works in the X server. The=20 > cpu usage on the laptop during the sluggishness is minimal. When I=20 > suspend the game with winedbg, the X server slowly becomes responsive aga= in. >=20 > The output from latencytop seems to point to i915 being the culprit: If there's some code doing glFlush()es, it's probably that code at fault. You don't need to do that unless you're doing frontbuffer rendering, and if you're doing frontbuffer rendering you should really be doing backbuffer rendering. I don't see a kernel issue here. --=-=-= Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iEYEARECAAYFAkum8AgACgkQHUdvYGzw6vf7/wCdEmZL7zfFR8ttwi7w4hhsG3DT 8W8An2fksvrjugbkvf8KzY9iqRnw04WX =lUCx -----END PGP SIGNATURE----- --=-=-=--