LU-140 Remove leftovers of iopen

[fs/lustre-release.git] / lustre / doc / tunefs.lustre.8

diff --git a/lustre/doc/tunefs.lustre.8 b/lustre/doc/tunefs.lustre.8
index e99e15a..d7eba1f 100644 (file)
--- a/lustre/doc/tunefs.lustre.8
+++ b/lustre/doc/tunefs.lustre.8
@@ -1,6 +1,5 @@
 .\" -*- nroff -*-
-.\" Copyright 2006 by Cluster File Systems, Inc.  All Rights Reserved.
-.\" Copyright 2008 by Sun Microsystems, Inc.  All Rights Reserved.
+.\" Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
 .\" This file may be copied under the terms of the GNU Public License, v2.
 .\"
 .TH tunefs.lustre 8 "2008 Mar 15" Lustre "configuration utilities"
@@ -44,7 +43,17 @@ The Lustre filesystem this service will be part of.  Default is 'lustre'
 Force a particular OST or MDT index 
 .TP
 .BI \--mountfsoptions= opts
-Set permanent mount options, equivalent to setting in /etc/fstab
+Set  the mount options that will be used when mounting the backing fs.
+WARNING: unlike earlier versions of \fBtunefs.lustre\fR,  this version
+completely replaces the existing mount options with those specified on
+the command line, issuing a warning  on  stderr  if any  of the default
+mount options are omitted.  The defaults for ldiskfs  are
+OST: \fIerrors=remount-ro,mballoc,extents\fR;
+MGS/MDT: \fIerrors=remount-ro,user_xattr\fR.
+\fBDO NOT\fR alter the default mount options unless you know what you are doing.
+.TP
+.BI \--network= net,...
+Network(s) to restrict this ost/mdt to. This option can be repeated as desired.
 .TP
 .BI \--mgs
 Add a configuration management service to this target
@@ -62,13 +71,21 @@ Print less information.
 Print more information.
 .TP
 .BI \--writeconf
-Erase all config logs for the filesystem that this MDT is part of, and
-regenerate them.  This is very dangerous.  All clients and servers should
-be stopped.
-All targets must then be restarted to regenerate the logs.  
+Erase the configuration logs for the filesystem that this server is part of, and regenerate them. This is very dangerous.  All clients must be unmounted and servers for this filesystem should be stopped.  
+All targets (OSTs/MDTs) must then be restarted to regenerate the logs. 
 No clients should be started until all targets have restarted.
-In general this should be executed on the MDT only, not the OSTs.
-
+.br
+Correct order of operations is:
+.br
+* Unmount all clients of this filesystem
+.br
+* Unmount MDT and all OSTs of this filesystem
+.br
+* Run \fBtunefs.lustre --writeconf <device>\fR on every server
+.br
+* Mount MDT and OSTs
+.br
+* Mount clients
 .SH EXAMPLES
 .TP
 .B tunefs.lustre --erase-param --mgsnode=<new_nid> --writeconf /dev/sda