2 .\" Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
4 .\" Copyright (c) 2012, 2016, Intel Corporation.
6 .\" This file may be copied under the terms of the GNU Public License v2.
8 .TH mount.lustre 8 "2008 Mar 15" Lustre "configuration utilities"
10 mount.lustre \- start a Lustre client or target service
13 .BI "mount \-t lustre [\-o " options "] " directory
16 is used to start a Lustre client or target service. This program should not be
17 called directly; rather it is a helper program invoked through
19 as above. Lustre clients and targets are stopped by using the
24 There are two forms for the
26 option, depending on whether a client or a target service is started:
28 .IR <mgsspec> :/ <fsname>[/<subdir>]
29 mounts the Lustre filesystem named
33 if specified) on the client by contacting the Management Service at
35 on the pathname given by
39 is defined below. A mounted client filesystem appears in
41 and is usable like any local filesystem and provides a full
42 POSIX-compilant interface.
45 starts the target service defined by the
47 command on the physical disk
49 A mounted target service filesystem is only useful for
51 operations and appears in
53 to show the device is in use.
56 .BI <mgsspec>:= <mgsnode>[:<mgsnode>]
57 The mgs specification may be a colon-separated list of nodes:
59 .BI <mgsnode>:= <mgsnid>[,<mgsnid>]
60 each node may be specified by a comma-separated list of NIDs.
62 In addition to the standard options listed in
64 Lustre understands the following
69 Enable full flock support, coherent across all client nodes.
72 Enable local flock support, using only client-local flock (faster, for applications that require flock but do not run on multiple nodes).
75 Disable flock support entirely. Applications calling flock will get an error.
78 Enable get/set of extended attributes by regular users. See the
83 Disable use of extended attributes by regular users. Root and system processes can still use extended attributes.
86 Enable POSIX Access Control List support. See the
91 Disable Access Control List support.
94 Force a client to keep pinging even if servers have enabled suppress_pings.
97 Enable mount/umount console messages.
100 Disable mount/umount console messages.
103 Enable FID to path translation by regular users.
106 Disable FID to path translation by regular users. Root and process with
107 CAP_DAC_READ_SEARCH can still perform FID to path translation.
109 .BI skpath= file|directory
110 Path to a file or directory with the keyfile(s) to load for this mount command.
111 Keys are inserted into the KEY_SPEC_SESSION_KEYRING keyring with a description
112 containing "lustre:" and a suffix which depends on whether the context of the
113 mount command is for an MGS, MDT/OST, or client.
114 This option is only available when built with --enable-gss.
117 Limit connections from the client to be on the network NID specified by 'net'.
118 'net' designates a single network NID, like 'o2ib2' or 'tcp1'.
119 This option can be useful in case of several Lustre client mount
120 points on the same node, with each mount point using a different
121 network. It is also interesting when running Lustre clients from
122 containers, by restricting each container to a specific network.
124 In addition to the standard mount options and backing disk type
125 (e.g. ext3) options listed in
127 Lustre understands the following
132 Only start the MGC (and MGS, if co-located) for a target service, and not the actual service.
135 Start a MDT with a co-located MGS without starting the MGS.
138 Not trigger OI scrub automatically when detect some inconsistency, unless it is started explicitly.
141 Not resume the former paused/crashed LFSCK automatically when mount.
144 Start a client or MDT with a (colon-separated) list of known inactive OSTs.
147 Abort client recovery and start the target service immediately.
149 .BI md_stripe_cache_size
150 Sets the stripe cache size for server side disk with a striped raid
154 Automatically Sets the block device parameter of 'max_sectors_kb' for the
155 MDT or OST target. When max_sectors_kb isn't specified, that parameter for
156 block device will be set to same as it's own 'max_hw_sectors_kb' (up to a
157 maximum of 16M), this is default behavior suited for most users. When
158 max_sectors_kb is specified as zero, the old parameter value will be kept.
159 When max_sectors_kb is specified as a positive number, the parameter will
160 be set to this number arbitrarily.
162 .BI recovery_time_soft= timeout
163 Allow 'timeout' seconds for clients to reconnect for recovery after a server
164 crash. This timeout will be incrementally extended if it is about to expire
165 and the server is still handling new connections from recoverable clients.
166 The default soft recovery timeout is set to 300 seconds (5 minutes).
168 .BI recovery_time_hard= timeout
169 The server will be allowed to incrementally extend its timeout up to a hard
170 maximum of 'timeout' seconds. The default hard recovery timeout is set to
171 900 seconds (15 minutes).
174 .B mount -t lustre cfs21@tcp0:/testfs /mnt/myfilesystem
175 Start a client for the Lustre filesystem 'testfs' at the mount point
176 /mnt/myfilesystem. The Management Service is running on a node reachable
177 from this client via the NID cfs21@tcp0.
179 .B mount -t lustre cfs21@tcp0:/testfs/dir /mnt/myfilesystem
180 Like above example, but mount subdirectory 'dir' as fileset.
182 .B mount -t lustre cfs21@tcp0,cfs21ib@o2ib0:cfs22@tcp0,cfs22ib@o2ib0:/testfs/dir /mnt/myfilesystem
183 Like above example, but the Management Service is running on one of the service
184 nodes cfs21 and cfs22, which are two different hosts separated by a colon and
185 served as a failover pair. Lustre tries the first one, and if that fails, it
186 tries the second one. On each service node, the comma-separated NIDs refer to
187 different interfaces on the same host, and the Lustre client chooses the best
188 one for communication based on which network interfaces it has locally.
190 .B mount -t lustre /dev/sda1 /mnt/test/mdt
191 Start the Lustre metadata target service from /dev/sda1 on mountpoint /mnt/test/mdt.
193 .B mount -t lustre -L testfs-MDT0000 -o abort_recov /mnt/test/mdt
194 Start the testfs-MDT0000 service (by using the disk label), but abort the
197 Not very many mount options can be changed with
208 .BR tunefs.lustre (8),