Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754206Ab3EGOcd (ORCPT ); Tue, 7 May 2013 10:32:33 -0400 Received: from mail-ee0-f47.google.com ([74.125.83.47]:37550 "EHLO mail-ee0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753745Ab3EGOcb (ORCPT ); Tue, 7 May 2013 10:32:31 -0400 Message-ID: <51891095.4070008@suse.cz> Date: Tue, 07 May 2013 16:32:53 +0200 From: Jiri Slaby User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:19.0) Gecko/20130124 Thunderbird/19.0 MIME-Version: 1.0 To: "Myklebust, Trond" , Jiri Slaby CC: "linux-kernel@vger.kernel.org" , NeilBrown , "linux-nfs@vger.kernel.org" Subject: Re: [PATCH 09/15] Make selection of 'readdir-plus' adapt to usage patterns. References: <1367936303-13386-1-git-send-email-jslaby@suse.cz> <1367936303-13386-9-git-send-email-jslaby@suse.cz> <1367936852.3580.6.camel@leira.trondhjem.org> In-Reply-To: <1367936852.3580.6.camel@leira.trondhjem.org> X-Enigmail-Version: 1.6a1pre Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2010 Lines: 53 On 05/07/2013 04:27 PM, Myklebust, Trond wrote: > On Tue, 2013-05-07 at 16:18 +0200, Jiri Slaby wrote: >> From: NeilBrown >> >> While the use of READDIRPLUS is significantly more efficient than >> READDIR followed by many GETATTR calls, it is still less efficient >> than just READDIR if the attributes are not required. >> >> We can get a hint as to whether the application requires attr information >> by looking at whether any ->getattr calls are made between >> ->readdir calls. >> If there are any, then getting the attributes seems to be worth while. >> >> This patch tracks whether there have been recent getattr calls on >> children of a directory and uses that information to selectively >> disable READDIRPLUS on that directory. >> >> The first 'readdir' call is always served using READDIRPLUS. >> Subsequent calls only use READDIRPLUS if there was a getattr on a child >> in the mean time. >> >> The locking of ->d_parent access needs to be reviewed. >> As the bit is simply a hint, it isn't critical that it is set >> on the "correct" parent if a rename is happening, but it is >> critical that the 'set' doesn't set a bit in something that >> isn't even an inode any more. >> >> Acked-by: NeilBrown >> Signed-off-by: Neil Brown >> Signed-off-by: Jiri Slaby >> Cc: Trond Myklebust >> Cc: linux-nfs@vger.kernel.org >> --- > > Why am I being Cced on this? Because we have the patch still in _3.9_. Dropped now in favor of the commit below. > You have looked at commit d69ee9b85541a69a1092f5da675bd23256dc62af (NFS: > Adapt readdirplus to application usage patterns) which was upstreamed in > Linux 3.5, right? Thanks for letting me know. -- js suse labs -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/