From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Kirill A. Shutemov" Subject: Re: [PATCH V4 5/6] mm: mmap: Add mmap flag to request VM_LOCKONFAULT Date: Wed, 22 Jul 2015 14:25:58 +0300 Message-ID: <20150722112558.GC8630@node.dhcp.inet.fi> References: <1437508781-28655-1-git-send-email-emunson@akamai.com> <1437508781-28655-6-git-send-email-emunson@akamai.com> Mime-Version: 1.0 Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=shutemov.name; s=default; t=1437564358; bh=T01qSVqpqXH9K8iB4w6nJOLmDAKq/BEJkuftpJ4INJ0=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=UGjqvocf9GiUgC1QHGl6V4T5QTAopnJCNNE+gKqXAvFYyodOlo4b1WF4j2rYrAGzw FLVVNH3vJv2T1yAe7yhQMJpLTE8kccP6LOUdH5QP5vhR8ApZdGPNJiuKswEDAF/0lr G6G8ax8lz13vPnT/KUEixvFTlj6O4sWqVsCsp9qw= Content-Disposition: inline In-Reply-To: <1437508781-28655-6-git-send-email-emunson@akamai.com> Sender: sparclinux-owner@vger.kernel.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Eric B Munson Cc: Andrew Morton , Michal Hocko , Vlastimil Babka , Paul Gortmaker , Chris Metcalf , Guenter Roeck , linux-alpha@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mips@linux-mips.org, linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, sparclinux@vger.kernel.org, linux-xtensa@linux-xtensa.org, linux-mm@kvack.org, linux-arch@vger.kernel.org, linux-api@vger.kernel.org On Tue, Jul 21, 2015 at 03:59:40PM -0400, Eric B Munson wrote: > The cost of faulting in all memory to be locked can be very high when > working with large mappings. If only portions of the mapping will be > used this can incur a high penalty for locking. > > Now that we have the new VMA flag for the locked but not present state, > expose it as an mmap option like MAP_LOCKED -> VM_LOCKED. What is advantage over mmap() + mlock(MLOCK_ONFAULT)? -- Kirill A. Shutemov From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Kirill A. Shutemov" Date: Wed, 22 Jul 2015 11:25:58 +0000 Subject: Re: [PATCH V4 5/6] mm: mmap: Add mmap flag to request VM_LOCKONFAULT Message-Id: <20150722112558.GC8630@node.dhcp.inet.fi> List-Id: References: <1437508781-28655-1-git-send-email-emunson@akamai.com> <1437508781-28655-6-git-send-email-emunson@akamai.com> In-Reply-To: <1437508781-28655-6-git-send-email-emunson@akamai.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Eric B Munson Cc: Andrew Morton , Michal Hocko , Vlastimil Babka , Paul Gortmaker , Chris Metcalf , Guenter Roeck , linux-alpha@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mips@linux-mips.org, linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, sparclinux@vger.kernel.org, linux-xtensa@linux-xtensa.org, linux-mm@kvack.org, linux-arch@vger.kernel.org, linux-api@vger.kernel.org On Tue, Jul 21, 2015 at 03:59:40PM -0400, Eric B Munson wrote: > The cost of faulting in all memory to be locked can be very high when > working with large mappings. If only portions of the mapping will be > used this can incur a high penalty for locking. > > Now that we have the new VMA flag for the locked but not present state, > expose it as an mmap option like MAP_LOCKED -> VM_LOCKED. What is advantage over mmap() + mlock(MLOCK_ONFAULT)? -- Kirill A. Shutemov From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f176.google.com (mail-wi0-f176.google.com [209.85.212.176]) by kanga.kvack.org (Postfix) with ESMTP id 8675A9003C7 for ; Wed, 22 Jul 2015 07:26:04 -0400 (EDT) Received: by wibud3 with SMTP id ud3so167466654wib.0 for ; Wed, 22 Jul 2015 04:26:04 -0700 (PDT) Received: from mail-wi0-x229.google.com (mail-wi0-x229.google.com. [2a00:1450:400c:c05::229]) by mx.google.com with ESMTPS id i7si24184169wiz.121.2015.07.22.04.26.01 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 22 Jul 2015 04:26:02 -0700 (PDT) Received: by wibud3 with SMTP id ud3so149647046wib.1 for ; Wed, 22 Jul 2015 04:26:01 -0700 (PDT) Date: Wed, 22 Jul 2015 14:25:58 +0300 From: "Kirill A. Shutemov" Subject: Re: [PATCH V4 5/6] mm: mmap: Add mmap flag to request VM_LOCKONFAULT Message-ID: <20150722112558.GC8630@node.dhcp.inet.fi> References: <1437508781-28655-1-git-send-email-emunson@akamai.com> <1437508781-28655-6-git-send-email-emunson@akamai.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1437508781-28655-6-git-send-email-emunson@akamai.com> Sender: owner-linux-mm@kvack.org List-ID: To: Eric B Munson Cc: Andrew Morton , Michal Hocko , Vlastimil Babka , Paul Gortmaker , Chris Metcalf , Guenter Roeck , linux-alpha@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mips@linux-mips.org, linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, sparclinux@vger.kernel.org, linux-xtensa@linux-xtensa.org, linux-mm@kvack.org, linux-arch@vger.kernel.org, linux-api@vger.kernel.org On Tue, Jul 21, 2015 at 03:59:40PM -0400, Eric B Munson wrote: > The cost of faulting in all memory to be locked can be very high when > working with large mappings. If only portions of the mapping will be > used this can incur a high penalty for locking. > > Now that we have the new VMA flag for the locked but not present state, > expose it as an mmap option like MAP_LOCKED -> VM_LOCKED. What is advantage over mmap() + mlock(MLOCK_ONFAULT)? -- Kirill A. Shutemov -- 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