From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f178.google.com (mail-wi0-f178.google.com [209.85.212.178]) by kanga.kvack.org (Postfix) with ESMTP id A7DAB6B0255 for ; Thu, 6 Aug 2015 04:55:42 -0400 (EDT) Received: by wicne3 with SMTP id ne3so13636544wic.1 for ; Thu, 06 Aug 2015 01:55:42 -0700 (PDT) Received: from mail-wi0-x22b.google.com (mail-wi0-x22b.google.com. [2a00:1450:400c:c05::22b]) by mx.google.com with ESMTPS id jy3si11449624wjb.152.2015.08.06.01.55.40 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 06 Aug 2015 01:55:41 -0700 (PDT) Received: by wicne3 with SMTP id ne3so13635657wic.1 for ; Thu, 06 Aug 2015 01:55:40 -0700 (PDT) Message-ID: <1438851337.4626.72.camel@gmail.com> Subject: Re: [PATCH] mm: add resched points to remap_pmd_range/ioremap_pmd_range From: Mike Galbraith Date: Thu, 06 Aug 2015 10:55:37 +0200 In-Reply-To: <20150730165803.GA17882@Sligo.logfs.org> References: <1437688476-3399-3-git-send-email-sbaugh@catern.com> <20150724070420.GF4103@dhcp22.suse.cz> <20150724165627.GA3458@Sligo.logfs.org> <20150727070840.GB11317@dhcp22.suse.cz> <20150727151814.GR9641@Sligo.logfs.org> <20150728133254.GI24972@dhcp22.suse.cz> <20150728170844.GY9641@Sligo.logfs.org> <20150729095439.GD15801@dhcp22.suse.cz> <1438269775.23663.58.camel@gmail.com> <20150730165803.GA17882@Sligo.logfs.org> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: owner-linux-mm@kvack.org List-ID: To: =?ISO-8859-1?Q?J=F6rn?= Engel Cc: Michal Hocko , Spencer Baugh , Toshi Kani , Andrew Morton , Fengguang Wu , Joern Engel , "Kirill A. Shutemov" , Mel Gorman , Johannes Weiner , Shachar Raindel , Boaz Harrosh , Andy Lutomirski , Joonsoo Kim , Andrey Ryabinin , Roman Pen , Andrey Konovalov , Eric Dumazet , Dmitry Vyukov , Rob Jones , WANG Chao , open list , "open list:MEMORY MANAGEMENT" , Spencer Baugh On Thu, 2015-07-30 at 09:58 -0700, JA?rn Engel wrote: > On Thu, Jul 30, 2015 at 05:22:55PM +0200, Mike Galbraith wrote: > > > > I piddled about with the thought that it might be nice to be able to > > sprinkle cond_resched() about to cut rt latencies without wrecking > > normal load throughput, cobbled together a cond_resched_rt(). > > > > On my little box that was a waste of time, as the biggest hits are block > > softirq and free_hot_cold_page_list(). > > Block softirq is one of our problems as well. It is a bit of a joke > that __do_softirq() moves work to ksoftirqd after 2ms, but block softirq > can take several 100ms in bad cases. On my little desktop box, one blk_done_softirq() loop iteration can take up to a few milliseconds, leaving me wondering if breaking that loop will help a studly box much. iow, I'd like to know how bad it gets, if one iteration can be huge, loop breaking there is fairly pointless, and I can stop fiddling. Do you happen to know iteration time during a size huge block softirq hit? On my little box, loop break/re-raise and whatnot improves the general case substantially, but doesn't do much at all for worst case.. or rather the next worst case in a list of unknown length ;-) -Mike -- 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