Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754430Ab1C2U0b (ORCPT ); Tue, 29 Mar 2011 16:26:31 -0400 Received: from cable-static-216-94.intergga.ch ([87.102.216.94]:51102 "EHLO mail.ffwll.ch" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751836Ab1C2U0a (ORCPT ); Tue, 29 Mar 2011 16:26:30 -0400 X-Spam-ASN: X-Spam-Spammy: 0.966-+--H*r:mail.ffwll.ch, 0.957-+--amazing, 0.875-+--H*F:D*ffwll.ch X-Spam-Hammy: 0.000-+--H*Ad:U*dri-devel, 0.000-+--HCc:D*freedesktop.org, 0.000-+--HCc:D*lists.freedesktop.org Date: Tue, 29 Mar 2011 22:26:08 +0200 From: Daniel Vetter To: Jerome Glisse Cc: Lucas Stach , r6144 , linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org Subject: Re: GEM-related desktop sluggishness due to linear-time arch_get_unmapped_area_topdown() Message-ID: <20110329202608.GA3454@viiv.ffwll.ch> Mail-Followup-To: Jerome Glisse , Lucas Stach , r6144 , linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org References: <1301310995.5615.92.camel@wangqingchuan> <1301336010.2217.20.camel@workstation> <1301409864.5615.98.camel@wangqingchuan> <1301421664.2151.12.camel@Portable-Work> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-Operating-System: Linux viiv 2.6.38-08569-g16c29da User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1287 Lines: 25 On Tue, Mar 29, 2011 at 03:45:34PM -0400, Jerome Glisse wrote: > Short lived & small bo would definitly doesn't work well for this kind > of API, it would all be a function of the ioctl cost. But i am not > sure the drawback would be that big, intel tested with pread/pwrite > and gived up don't remember why. For the vbo case you describe the > scheme i was thinking would be : allocate bo and on buffer data call > upload to the allocated bo using the bind user page feature that would > mean zero extra copy operation. For the fire forget case of vbo, > likely somekind of transient buffer would be more appropriate. Just to clarify: Uploads to linear buffers are all done with pwrite (due to an api foobar, it's not so great for 2d/tiled stuff). It's amazing how much faster that is: Switching vbo's from mmpa to pwrite has given a few percent more fps in openarena in i915g! As long as the chunk you're gonna write fits into L1 cache, it's probably a net win. -Daniel -- Daniel Vetter Mail: daniel@ffwll.ch Mobile: +41 (0)79 365 57 48 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/