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 77BCD6B0088 for ; Tue, 23 Nov 2010 03:02:21 -0500 (EST) Received: by iwn10 with SMTP id 10so1041639iwn.14 for ; Tue, 23 Nov 2010 00:02:20 -0800 (PST) MIME-Version: 1.0 In-Reply-To: <20101122235331.23552604.akpm@linux-foundation.org> References: <20101122141449.9de58a2c.akpm@linux-foundation.org> <20101122210132.be9962c7.akpm@linux-foundation.org> <20101122212220.ae26d9a5.akpm@linux-foundation.org> <20101122214814.36c209a6.akpm@linux-foundation.org> <20101122231558.57b6e04c.akpm@linux-foundation.org> <20101122235331.23552604.akpm@linux-foundation.org> Date: Tue, 23 Nov 2010 17:02:19 +0900 Message-ID: Subject: Re: [RFC 1/2] deactive invalidated pages From: Minchan Kim Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: Andrew Morton Cc: linux-mm , LKML , Peter Zijlstra , Rik van Riel , KOSAKI Motohiro , Johannes Weiner , Nick Piggin , Mel Gorman List-ID: On Tue, Nov 23, 2010 at 4:53 PM, Andrew Morton wrote: > On Tue, 23 Nov 2010 16:44:50 +0900 Minchan Kim wr= ote: > >> On Tue, Nov 23, 2010 at 4:15 PM, Andrew Morton >> wrote: >> > On Tue, 23 Nov 2010 15:05:39 +0900 Minchan Kim = wrote: >> > >> >> On Tue, Nov 23, 2010 at 2:48 PM, Andrew Morton >> >> >> > move it to the head of the LRU anyway. __But given that the user= has >> >> >> >> >> >> Why does it move into head of LRU? >> >> >> If the page which isn't mapped doesn't have PG_referenced, it woul= d be >> >> >> reclaimed. >> >> > >> >> > If it's dirty or under writeback it can't be reclaimed! >> >> >> >> I see your point. And it's why I add it to head of inactive list. >> > >> > But that *guarantees* that the page will get a full trip around the >> > inactive list. __And this will guarantee that potentially useful pages >> > are reclaimed before the pages which we *know* the user doesn't want! >> > Bad! >> > >> > Whereas if we queue it to the tail, it will only get that full trip if >> > reclaim happens to run before the page is cleaned. __And we just agree= d >> > that reclaim isn't likely to run immediately, because pages are being >> > freed. >> > >> > So we face a choice between guaranteed eviction of potentially-useful >> > pages (which are very expensive to reestablish) versus a *possible* >> > need to move an unreclaimable page to the head of the LRU, which is >> > cheap. >> >> How about flagging SetPageReclaim when we add it to head of inactive? >> If page write is complete, end_page_writeback would move it to tail of >> inactive. > > ooh, that sounds clever. =A0We'd want to do that for both PageDirty() and > for PageWriteback() pages. > > But if we do it for PageDirty() pages, we'd need to clear PageReclaim() > if someone reuses the page for some reason. =A0We'll end up with pages > all over the place which have PageReclaim set. =A0I guess we could clear > PageReclaim() in mark_page_accessed(), but that's hardly going to give > us full coverage. > > hmm. =A0Maybe just do it for PageWriteback pages. =A0Then userspace can d= o > > =A0 =A0 =A0 =A0sync_file_range(SYNC_FILE_RANGE_WRITE); > =A0 =A0 =A0 =A0fadvise(DONTNEED); > > and all those pages which now have PageWriteback set will also get > PageReclaim set. > > But we'd need to avoid races against end_io when setting PageReclaim > against the PageWriteback pages - if the interrupt happens while we're > setting PageReclaim, it will end up being incorrectly set. > Okay. I will see it and resend new version. Thanks for good comment, Andrew. --=20 Kind regards, Minchan Kim -- 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/ . Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/ Don't email: email@kvack.org