From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Martitz Subject: Re: [RFC PATCH 0/2] dirreadahead system call Date: Fri, 1 Aug 2014 09:14:37 +0000 (UTC) Message-ID: References: <1406309851-10628-1-git-send-email-adas@redhat.com> <193414027.14151264.1406551934098.JavaMail.zimbra@redhat.com> <7EBB0CF1-6564-4C63-8006-7DEEE8800A19@dilger.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit To: linux-fsdevel@vger.kernel.org Return-path: Received: from plane.gmane.org ([80.91.229.3]:48296 "EHLO plane.gmane.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754130AbaHAJUJ (ORCPT ); Fri, 1 Aug 2014 05:20:09 -0400 Received: from list by plane.gmane.org with local (Exim 4.69) (envelope-from ) id 1XD90O-0005H1-Lg for linux-fsdevel@vger.kernel.org; Fri, 01 Aug 2014 11:20:04 +0200 Received: from avm-guido.avm.de ([87.234.237.148]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 01 Aug 2014 11:20:04 +0200 Received: from kugel by avm-guido.avm.de with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 01 Aug 2014 11:20:04 +0200 Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Andreas Dilger dilger.ca> writes: > Since this would be an advisory syscall (i.e. it doesn't really > return anything and cannot guarantee that all the inodes will be in > memory), then if the filesystem is having trouble prefetching the > inodes (e.g. invalid inode number(s) or lock ordering or contention > issues) it could always bail out and leave it to stat() to actually > fetch the inodes into memory when accessed. > The first sentence made me think whether the existing fadvice64() syscall can be reused (with the dir fd) in place if the new dirreadahead()? If not, dirreadahead should have a flags param (https://lwn.net/Articles/585415/) Best regards.