From: Subject: Re: [PATCH] NFS client doesn't flush dirty mmap'd pages during fsync/msync Date: Tue, 20 Jan 2004 14:31:05 +0100 (CET) Sender: nfs-admin@lists.sourceforge.net Message-ID: <35223.68.42.103.198.1074605465.squirrel@webmail.uio.no> References: <20040120120116.GP17993@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Cc: , Return-path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.11] helo=sc8-sf-mx1.sourceforge.net) by sc8-sf-list2.sourceforge.net with esmtp (Exim 4.30) id 1AivyN-0003vh-GG for nfs@lists.sourceforge.net; Tue, 20 Jan 2004 05:31:15 -0800 Received: from pat.uio.no ([129.240.130.16] ident=7411) by sc8-sf-mx1.sourceforge.net with esmtp (Exim 4.30) id 1AivyN-0001Dk-2c for nfs@lists.sourceforge.net; Tue, 20 Jan 2004 05:31:15 -0800 To: In-Reply-To: <20040120120116.GP17993@suse.de> Errors-To: nfs-admin@lists.sourceforge.net List-Unsubscribe: , List-Id: Discussion of NFS under Linux development, interoperability, and testing. List-Post: List-Help: List-Subscribe: , List-Archive: > Given that we have the inode for these dirty pages, couldn't we at least > compare the req->wb_inode to filp->f_dentry->d_inode? I believe that is indeed what Chuck's patch does. Previously we would in addition check that the filp matches. For ordinary files that is fine, but in the special case of msync(MS_SYNC), it was causing the fsync() method to skip precisely those dirty pages that we wanted to sync to disk. Cheers, Trond ------------------------------------------------------- The SF.Net email is sponsored by EclipseCon 2004 Premiere Conference on Open Tools Development and Integration See the breadth of Eclipse activity. February 3-5 in Anaheim, CA. http://www.eclipsecon.org/osdn _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs