From mboxrd@z Thu Jan 1 00:00:00 1970 From: KOSAKI Motohiro Subject: Re: [PATCH v6] add MAP_UNLOCKED mmap flag Date: Wed, 20 Jan 2010 09:24:06 +0900 (JST) Message-ID: <20100120091051.405D.A69D9226@jp.fujitsu.com> References: <20100119082638.GK14345@redhat.com> <84144f021001190044s397c6665qb00af48235d2d818@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <84144f021001190044s397c6665qb00af48235d2d818@mail.gmail.com> Sender: owner-linux-mm@kvack.org To: Pekka Enberg Cc: kosaki.motohiro@jp.fujitsu.com, Gleb Natapov , Alan Cox , linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-api@vger.kernel.org, akpm@linux-foundation.org, andrew.c.morrow@gmail.com, "Paul E. McKenney" , Rik van Riel , Johannes Weiner , minchan.kim@gmail.com List-Id: linux-api@vger.kernel.org > Hi Gleb, > > On Tue, Jan 19, 2010 at 10:26 AM, Gleb Natapov wrote: > >> design would still be broken, no? Did you try using (or extending) > >> posix_madvise(MADV_DONTNEED) for the guest address space? It seems to > > After mlockall() I can't even allocate guest address space. Or do you mean > > instead of mlockall()? Then how MADV_DONTNEED will help? It just drops > > page table for the address range (which is not what I need) and does not > > have any long time effect. > > Oh right, MADV_DONTNEED is no good. Off topic: posix_madvise(MADV_DONTNEED) is nop. glibc's posix_madvise(MADV_DONTNEED) don't call linux's madvise(MADV_DONTNEED). It's because madvise(MADV_DONTNEED) is not POSIX compliant. The behavior of linux madvise(MADV_DONTNEED) is similar to Solaris (or *BSD) madvise(MADV_FREE). -- 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