2 .\" Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
4 .\" Copyright (c) 2011, 2012, Intel Corporation.
6 .\" This file may be copied under the terms of the GNU Public License, v2.
8 .TH tunefs.lustre 8 "2008 Mar 15" Lustre "configuration utilities"
10 tunefs.lustre \- modify the Lustre configuration information on a disk
19 is used to modify the configuration information on a Lustre target
20 disk. This includes upgrading old (pre-Lustre 1.6) disks. This does not
21 reformat the disk or erase the target information, but modifying the
22 configuration information can result in an unusable filesystem. You have
25 Changes made here will affect a filesystem only when the target is next
30 .BI \--comment= comment
31 Set user comment about this disk, ignored by Lustre.
34 Only print what would be done; does not affect the disk
37 Remove all previous parameter info
39 .BI \--failnode= nid,...
40 Set the NID(s) of a failover partner. This option can be repeated as desired.
41 Cannot be used with --servicenode.
43 .BI \--servicenode= nid,....
44 Set the NID(s) of all service partner. This option treats all nodes as equal
45 service nodes. Cannot be used with --failnode.
47 .BI \--fsname= filesystem_name
48 The Lustre filesystem this service will be part of. Default is 'lustre'
51 Force a particular OST or MDT index
53 .BI \--mountfsoptions= opts
54 Set the mount options that will be used when mounting the backing fs.
55 WARNING: unlike earlier versions of \fBtunefs.lustre\fR, this version
56 completely replaces the existing mount options with those specified on
57 the command line, issuing a warning on stderr if any of the default
58 mount options are omitted. The defaults for ldiskfs are
59 OST: \fIerrors=remount-ro,mballoc,extents\fR;
60 MGS/MDT: \fIerrors=remount-ro,user_xattr\fR.
61 \fBDO NOT\fR alter the default mount options unless you know what you are doing.
63 .BI \--network= net,...
64 Network(s) to restrict this ost/mdt to. This option can be repeated as desired.
67 Add a configuration management service to this target
69 .BI \--mgsnode= nid,...
70 Set the NID(s) of the MGS node, required for all targets other than the MGS.
73 Remove a configuration management service to this target
76 Print less information.
79 Print more information.
82 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.
83 All targets (OSTs/MDTs) must then be restarted to regenerate the logs.
84 No clients should be started until all targets have restarted.
86 Correct order of operations is:
88 * Unmount all clients of this filesystem
90 * Unmount MDT and all OSTs of this filesystem
92 * Run \fBtunefs.lustre --writeconf <device>\fR on every server
99 Enable space accounting on old 2.x devices.
103 .B tunefs.lustre --erase-param --mgsnode=<new_nid> --writeconf /dev/sda
104 Change the MGS NID address. (This should be done on every target disk,
105 since they should all be contacting the same MGS.)
107 .B tunefs.lustre --param="failover.node=192.168.0.13@tcp0" /dev/sda
108 Add a failover NID location for this target
110 .B tunefs.lustre --mgs --mdt --fsname=testfs /dev/sda
111 Upgrade an old 1.4.X Lustre MDT to 1.6. The new filesystem name is "testfs".
113 .B tunefs.lustre --writeconf --mgs --mdt --fsname=testfs /dev/sda1
114 Upgrade an old 1.4.X Lustre MDT to 1.6, and start with brand-new 1.6
115 configuration logs. All old servers and clients must be stopped.
125 .BR mount.lustre (8),