From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail191.messagelabs.com (mail191.messagelabs.com [216.82.242.19]) by kanga.kvack.org (Postfix) with SMTP id 715E66B01F1 for ; Sat, 10 Apr 2010 16:49:33 -0400 (EDT) Received: by pvg11 with SMTP id 11so2627022pvg.14 for ; Sat, 10 Apr 2010 13:49:32 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <4BC0E2C4.8090101@redhat.com> References: <20100406090813.GA14098@elte.hu> <20100410184750.GJ5708@random.random> <20100410190233.GA30882@elte.hu> <4BC0CFF4.5000207@redhat.com> <20100410194751.GA23751@elte.hu> <4BC0DE84.3090305@redhat.com> <4BC0E2C4.8090101@redhat.com> From: Jason Garrett-Glaser Date: Sat, 10 Apr 2010 13:49:12 -0700 Message-ID: Subject: Re: [PATCH 00 of 41] Transparent Hugepage Support #17 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: Avi Kivity Cc: Ingo Molnar , Mike Galbraith , Andrea Arcangeli , Linus Torvalds , Pekka Enberg , Andrew Morton , linux-mm@kvack.org, Marcelo Tosatti , Adam Litke , Izik Eidus , Hugh Dickins , Nick Piggin , Rik van Riel , Mel Gorman , Dave Hansen , Benjamin Herrenschmidt , Mike Travis , KAMEZAWA Hiroyuki , Christoph Lameter , Chris Wright , bpicco@redhat.com, KOSAKI Motohiro , Balbir Singh , Arnd Bergmann , "Michael S. Tsirkin" , Peter Zijlstra , Johannes Weiner , Daisuke Nishimura List-ID: On Sat, Apr 10, 2010 at 1:42 PM, Avi Kivity wrote: > On 04/10/2010 11:24 PM, Avi Kivity wrote: >>> >>> Oh, this tickled some memories: x264 compressed encoding can be very >>> cache and >>> TLB intense. Something like the encoding of a 350 MB video file: >>> >>> =A0 wget http://media.xiph.org/video/derf/y4m/soccer_4cif.y4m =A0 =A0 = =A0 # NOTE: >>> 350 MB! >>> =A0 x264 --crf 20 --quiet soccer_4cif.y4m -o /dev/null --threads 4 >>> >>> would be another thing worth trying with transparent-hugetlb enabled. >>> >> >> I'll try it out. >> > > 3-5% improvement. =A0I had to tune khugepaged to scan more aggressively s= ince > the run is so short. =A0The working set is only ~100MB here though. I'd try some longer runs with larger datasets to do more testing. Some things to try: 1) Pick a 1080p or even 2160p sequence from http://media.xiph.org/video/der= f/ 2) Use --preset ultrafast or similar to do a ridiculously memory-bandwidth-limited runthrough. 3) Use --preset veryslow or similar to do a very not-memory-limited runthro= ugh. Jason -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org