2 .\" Copyright 2006 by Cluster FileSystems. All Rights Reserved.
3 .\" Copyright 2008 by Sun Microsystems. All Rights Reserved.
4 .\" This file may be copied under the terms of the GNU Public License v2.
6 .TH mount.lustre 8 "2008 Mar 15" Lustre "configuration utilities"
8 mount.lustre \- start a Lustre client or target service
11 .BI "mount \-t lustre [\-o " options "] " directory
14 is used to start a Lustre client or target service. This program should not be
15 called directly; rather it is a helper program invoked through
17 as above. Lustre clients and targets are stopped by using the
22 There are two forms for the
24 option, depending on whether a client or a target service is started:
26 .IR <mgsspec> :/ <fsname>
27 mounts the Lustre filesystem named
29 on the client by contacting the Management Service at
31 on the pathname given by
35 is defined below. A mounted client filesystem appears in
37 and is usable like any local filesystem and provides a full
38 POSIX-compilant interface.
41 starts the target service defined by the
43 command on the physical disk
45 A mounted target service filesystem is only useful for
47 operations and appears in
49 to show the device is in use.
52 .BI <mgsspec>:= <mgsnode>[:<mgsnode>]
53 The mgs specification may be a colon-separated list of nodes:
55 .BI <mgsnode>:= <mgsnid>[,<mgsnid>]
56 each node may be specified by a comma-separated list of NIDs.
58 In addition to the standard options listed in
60 Lustre understands the following
65 Enable full flock support, coherent across all client nodes.
68 Enable local flock support, using only client-local flock (faster, for applications that require flock but do not run on multiple nodes).
71 Disable flock support entirely. Applications calling flock will get an error.
74 Enable get/set of extended attributes by regular users. See the
79 Disable use of extended attributes by regular users. Root and system processes can still use extended attributes.
82 Enable POSIX Access Control List support. See the
87 Disable Access Control List support.
89 In addition to the standard mount options and backing disk type
90 (e.g. ext3) options listed in
92 Lustre understands the following
97 Only start the MGC (and MGS, if co-located) for a target service, and not the actual service.
100 Start a MDT with a co-located MGS without starting the MGS.
103 Start a client or MDT with a (colon-separated) list of known inactive OSTs.
106 Abort client recovery and start the target service immediately.
109 .B mount -t lustre cfs21@tcp0:/testfs /mnt/myfilesystem
110 Start a client for the Lustre filesystem 'testfs' at the mount point
111 /mnt/myfilesystem. The Management Service is running on a node reachable
112 from this client via the nid cfs21@tcp0.
114 .B mount -t lustre /dev/sda1 /mnt/test/mdt
115 Start the Lustre metadata target service from /dev/sda1 on mountpoint /mnt/test/mdt.
117 .B mount -t lustre -L testfs-MDT0000 -o abort_recov /mnt/test/mdt
118 Start the testfs-MDT0000 service (by using the disk label), but abort the
121 Not very many mount options can be changed with
123 Please report all bugs to Sun Microsystems using http://bugzilla.lustre.org/
128 filesystem package and is available from Sun Microsystems, Inc.
130 http://downloads.lustre.org
135 .BR tunefs.lustre (8),