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 persistent mount options that will be used when Lustre 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 \--backfs-mount-opts=opts
64 Use these options for mounting backing fs while tune.lustre is working.
66 .BI \--network= net,...
67 Network(s) to restrict this ost/mdt to. This option can be repeated as desired.
70 Add a configuration management service to this target
72 .BI \--mgsnode= nid,...
73 Set the NID(s) of the MGS node, required for all targets other than the MGS.
76 Remove a configuration management service to this target
79 Ignore unset hostid for ZFS import protection. To set hostid either set
80 spl_hostid option for spl.ko or set /etc/hostid, see genhostid(1).
83 Print less information.
86 Print more information.
89 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.
90 All targets (OSTs/MDTs) must then be restarted to regenerate the logs.
91 No clients should be started until all targets have restarted.
93 Correct order of operations is:
95 * Unmount all clients of this filesystem
97 * Unmount MDT and all OSTs of this filesystem
99 * Run \fBtunefs.lustre --writeconf <device>\fR on every server
106 Enable space accounting on old 2.x devices.
110 .B tunefs.lustre --erase-param --mgsnode=<new_nid> --writeconf /dev/sda
111 Change the MGS NID address. (This should be done on every target disk,
112 since they should all be contacting the same MGS.)
114 .B tunefs.lustre --param="failover.node=192.168.0.13@tcp0" /dev/sda
115 Add a failover NID location for this target
117 .B tunefs.lustre --mgs --mdt --fsname=testfs /dev/sda
118 Upgrade an old 1.4.X Lustre MDT to 1.6. The new filesystem name is "testfs".
120 .B tunefs.lustre --writeconf --mgs --mdt --fsname=testfs /dev/sda1
121 Upgrade an old 1.4.X Lustre MDT to 1.6, and start with brand-new 1.6
122 configuration logs. All old servers and clients must be stopped.
132 .BR mount.lustre (8),