From: Daniel Vetter Subject: Re: [intel-gfx][PATCH] intel: add a new interface drm_intel_bo_alloc_direct Date: Tue, 1 Jun 2010 20:58:55 +0200 Message-ID: <20100601185854.GA9834@biene.ffwll.ch> References: <1274764010-6660-1-git-send-email-haihao.xiang@intel.com> <20100528140447.GC3612@viiv.ffwll.ch> <1275383865.12142.58.camel@xhh-ctg32> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail.ffwll.ch (cable-static-49-187.intergga.ch [157.161.49.187]) by gabe.freedesktop.org (Postfix) with ESMTP id CE33D9E84F for ; Tue, 1 Jun 2010 11:57:46 -0700 (PDT) Content-Disposition: inline In-Reply-To: <1275383865.12142.58.camel@xhh-ctg32> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org To: "Xiang, Haihao" Cc: "intel-gfx@lists.freedesktop.org" List-Id: intel-gfx@lists.freedesktop.org On Tue, Jun 01, 2010 at 05:17:45PM +0800, Xiang, Haihao wrote: > On Fri, 2010-05-28 at 22:04 +0800, Daniel Vetter wrote: > > On Tue, May 25, 2010 at 01:06:50PM +0800, Xiang, Haihao wrote: > > > This interface is the same as drm_intel_bo_alloc except the allocated > > > size isn't rounded up, so it bypasses the cache bucket. > > > > > > The size of the BO created by drm_intel_bo_alloc for a 1920x800,4:2:0 YUV > > > planar surface is 4M, it is about 2.2M if using drm_intel_bo_alloc_direct. > > > > Have you tried either Chris Wilson's or my fair-lru eviction patches? They > > should help quite a lot, especially for many big objects of exactly the > > same size like libva uses. > Get the following errors when applying your fair-lru eviction patches > > Applying: drm/i915: prepare for fair lru eviction > error: patch failed: drivers/gpu/drm/i915/i915_gem.c:2203 > error: drivers/gpu/drm/i915/i915_gem.c: patch does not apply > > I am using drm-intel-next branch. Kinda expected - the patch series was against drm-intel-next before your bsd ring stuff was merged ;) So either fixup the conflicts yourself (conflicts are probably just due to the bsd merge, so you already know the code) or prod Chris Wilson into implementing his single-scan patch for i915 atop my generic fair-lru drm patches. Or simply wait till I get around to rebase this stuff. But don't hold your breath, that won't happen soon, unfortunately. Too busy atm. Cheers, Daniel -- Daniel Vetter Mail: daniel@ffwll.ch Mobile: +41 (0)79 365 57 48