1 .TH lctl 1 "2003 Oct 8" Lustre "configuration utilities"
3 lctl \- Low level Lustre filesystem configuration utility
8 .B lctl --device <devno> <command [args]>
12 is used to directly control Lustre via an ioctl interface, allowing
13 various configuration, maintenance, and debugging features to be accessed.
16 can be invoked in interactive mode by issuing lctl command. After that, commands are issued as below. The most common commands in lctl are
35 To get a complete listing of available commands, type
37 at the lctl prompt. To get basic help on the meaning and syntax of a
41 . Command completion is activated with the TAB key, and command history is available via the up- and down-arrow keys.
43 For non-interactive use, one uses the second invocation, which runs command after connecting to the device.
45 .SS Network Configuration
47 .BI network " <up/down>|<tcp/elan/myrinet>"
48 Start or stop LNET, or select a network type for other
53 Print all Network Identifiers on the local node. LNET must be running.
55 .BI which_nid " <nidlist>"
56 From a list of nids for a remote node, show which interface communication
59 .BI replace_nids " <devicename> <nid1>[,nid2,nid3 ...]"
60 Replace the LNET Network Identifiers for a given device,
61 as when the server's IP address has changed.
62 This command must be run on the MGS node.
63 Only MGS server should be started (command execution returns error
64 in another cases). To start the MGS service only:
65 mount -t lustre <MDT partition> -o nosvc <mount point>
66 Note the replace_nids command skips any invalidated records in the configuration log.
67 The previous log is backed up with the suffix '.bak'.
70 Check LNET connectivity via an LNET ping. This will use the fabric
71 appropriate to the specified NID.
74 Print the network interface information for a given
79 Print the known peers for a given
84 Print all the connected remote NIDs for a given
89 This command should print active transmits, and it is only used for elan network type.
92 Print the complete routing table.
96 .BI device " <devname> "
97 This will select the specified OBD device. All other commands depend on the device being set.
100 Show all the local Lustre OBDs. AKA
103 .SS Device Operations
105 .BI list_param " [-F|-R] <param_search ...>"
106 List the Lustre or LNet parameter name
108 Add '/', '@' or '=' for dirs, symlinks and writeable files, respectively.
111 Recursively list all parameters under the specified parameter search string. If
113 is unspecified, all the parameters will be shown.
118 # lctl list_param ost.*
125 # lctl list_param -F ost.* debug
134 # lctl list_param -R mdt
140 mdt.lustre-MDT0000.capa
142 mdt.lustre-MDT0000.capa_count
144 mdt.lustre-MDT0000.capa_key_timeout
146 mdt.lustre-MDT0000.capa_timeout
148 mdt.lustre-MDT0000.commit_on_sharing
150 mdt.lustre-MDT0000.evict_client
154 .BI get_param " [-n|-N|-F] <parameter ...>"
155 Get the value of Lustre or LNET parameter.
158 Print only the value and not parameter name.
161 Print only matched parameter names and not the values. (Especially useful when using patterns.)
164 When -N specified, add '/', '@' or '=' for directories, symlinks and writeable files, respectively.
169 # lctl get_param ost.*
176 # lctl get_param -n debug timeout
178 super warning dlmtrace error emerg ha rpctrace vfstrace config console
183 # lctl get_param -N ost.* debug
191 lctl "get_param -NF" is equivalent to "list_param -F".
193 .BI set_param " [-n] [-P] [-d] <parameter=value ...>"
194 Set the value of Lustre or LNET parameter.
197 Disable printing of the key name when printing values.
200 Set the parameter permanently, filesystem-wide.
201 This parameters are only visible to 2.5.0 and later clients, older clients will not see these parameters.
204 Remove the permanent setting (only with -P option)
209 # lctl set_param fail_loc=0 timeout=20
216 # lctl set_param -n fail_loc=0 timeout=20
223 # lctl set_param -P osc.*.max_dirty_mb=32
226 .BI conf_param " [-d] <device|fsname>.<parameter>=<value>"
227 Set a permanent configuration parameter for any device via the MGS. This
228 command must be run on the MGS node.
230 .B -d <device|fsname>.<parameter>
231 Delete a parameter setting (use the default value at the next restart). A null value for <value> also deletes the parameter setting.
235 All of the writable parameters under
238 .I lctl list_param -F osc.*.* | grep =
239 ) can be permanently set using
241 , but the format is slightly different. For conf_param, the device is specified first, then the obdtype. (See examples below.) Wildcards are not supported.
243 Additionally, failover nodes may be added (or removed), and some system-wide parameters may be set as well (sys.at_max, sys.at_min, sys.at_extra, sys.at_early_margin, sys.at_history, sys.timeout, sys.ldlm_timeout.) <device> is ignored for system wide parameters.
247 # lctl conf_param testfs.sys.at_max=1200
249 # lctl conf_param testfs.llite.max_read_ahead_mb=16
251 # lctl conf_param testfs-MDT0000.lov.stripesize=2M
253 # lctl conf_param lustre-OST0001.osc.active=0
255 # lctl conf_param testfs-OST0000.osc.max_dirty_mb=29.15
257 # lctl conf_param testfs-OST0000.ost.client_cache_seconds=15
259 # lctl conf_param testfs-OST0000.failover.node=1.2.3.4@tcp1
262 Reactivate an import after deactivating, below. This setting is only effective until the next restart (see
267 Deactivate an import, in particular meaning do not assign new file stripes
268 to an OSC. This command should be used on the OSC in the MDT LOV
269 corresponding to a failed OST device, to prevent further attempts at
270 communication with the failed OST.
273 Abort the recovery process on a restarting MDT or OST device
275 .SS Virtual Block Device Operation
276 Lustre is able to emulate a virtual block device upon regular file. It is necessary to be used when you are trying to setup a swap space via file.
278 .BI blockdev_attach " <file name> <device node>"
279 Attach the lustre regular file to a block device. If the device node is not existent, lctl will create it \- it is recommended to create it by lctl since the emulator uses a dynamical major number.
281 .BI blockdev_detach " <device node>"
282 Detach the virtual block device.
284 .BI blockdev_info " <device node>"
285 Acquire which lustre file was attached to the device node.
289 .BI changelog_register
290 Register a new changelog user for a particular device. Changelog entries
291 will not be purged beyond any registered users' set point. (See lfs changelog_clear.)
293 .BI changelog_deregister " <id>"
294 Unregister an existing changelog user. If the user's "clear" record number
295 is the minimum for the device, changelog records will be purged until the
299 An on-line Lustre consistency check and repair tool.
301 .B lfsck_start \fR<-M | --device [MDT,OST]_device>
302 \fR[-A | --all] [-c | --create_ostobj [on | off]]
303 \fR[-e | --error <continue | abort>] [-h | --help]
304 \fR[-n | --dryrun [on | off]] [-o | --orphan]
305 \fR[-r | --reset] [-s | --speed speed_limit]
306 \fR[-t | --type lfsck_type[,lfsck_type...]]
307 \fR[-w | --window_size size]
309 Start LFSCK on the specified MDT or OST device with specified parameters.
311 -M, --device <MDT,OST_device>
312 The MDT or OST device to start LFSCK/scrub on.
315 Start LFSCK on all available MDT devices.
317 -c, --create_ostobj [on | off]
318 Create the lost OST-object for dangling LOV EA: 'off' (default) or 'on'. Under
319 default mode, when the LFSCK find some MDT-object with dangling reference, it
320 will report the inconsistency but will not repair it. If 'on' is given, then
321 LFSCK will re-create the missed OST-object.
323 -e, --error <error_handle>
324 With error_handle as 'abort' then if a repair is impossible LFSCK will save
325 the current position stop with an error. Otherwise the default behavior is
326 to 'continue' if a repair is impossible.
329 Show the usage message.
331 -n, --dryrun [on | off]
332 Perform a trial run with no changes made, if 'on' or no argument is given.
333 Default is 'off', meaning that any inconsistencies found will be repaired.
336 Handle orphan objects, such as orphan OST-objects for layout LFSCK by
337 linking them under the .../.lustre/lost+found directory.
340 Set the current position of object iteration to the beginning of the specified
341 device. The non-specified parameters will also be reset to the default. By
342 default the iterator will resume the scanning from the last saved checkpoint
343 position, and other unspecified parameters will be the same as the prior
346 -s, --speed <speed_limit>
347 Set the upper limit of LFSCK processing in objects per second to reduce load
348 on the servers and storage. If no value is specified the saved value is used
349 (if resuming from a checkpoint). Otherwise the default value of 0 is used,
350 which means check the filesystem as quickly as possible.
352 -t, --type <lfsck_type[,lfsck_type...]>
353 The type of LFSCK checking/repair to execute. If no type is given and the
354 previous run was incomplete or internal consistency checks detected an error,
355 then the same types are used for the next run. Otherwise, the default is to
356 check all types of consistency. Any time LFSCK is triggered on an ldiskfs
357 MDT or OST then OI Scrub is run. Valid types are a comma-separated list of one or more of
359 to run only the local OI Scrub on ldiskfs targets,
361 for FID-in-dirent and linkEA checking on the MDT(s),
363 for MDT-OST cross-reference consistency, and
365 to run all of the available check types.
367 -w, --window_size <size>
368 Specifies the maximum number of in-flight request being processed at
369 one time. This controls the load placed on remote OSTs when running
371 checks. By default there are at most 1024 outstanding requests.
373 .B lfsck_stop \fR<-M | --device [MDT,OST]_device> [-A | --all] [-h | --help]
374 Stop LFSCK on the specified MDT or OST device.
376 -M, --device <[MDT,OST]_device>
377 The MDT or OST device to stop LFSCK/scrub on.
380 Stop LFSCK on all devices.
387 Start and stop the debug daemon, and control the output filename and size.
389 .BI debug_kernel " [file] [raw]"
390 Dump the kernel debug buffer to stdout or file.
392 .BI debug_file " <input> [output]"
393 Convert kernel-dumped debug log from binary to plain text format.
396 Clear the kernel debug buffer.
399 Insert marker text in the kernel debug buffer.
401 .BI filter " <subsystem id/debug mask>"
402 Filter kernel debug messages by subsystem or mask.
404 .BI show " <subsystem id/debug mask>"
405 Show specific type of messages.
407 .BI debug_list " <subs/types>"
408 List all the subsystem and debug types.
410 .BI modules " <path>"
411 Provide gdb-friendly module information.
414 The following options can be used to invoke lctl.
417 The device to be used for the operation. This can be specified by name or
421 .B --ignore_errors | ignore_errors
422 Ignore errors during script processing
424 .B lustre_build_version
425 Output the build version of the Lustre kernel modules
428 Output the build version of the lctl utility
431 Provides brief help on the various arguments
434 Quit the interactive lctl session
440 0 UP mgc MGC192.168.0.20@tcp bfbb24e3-7deb-2ffa-eab0-44dffe00f692 5
441 1 UP ost OSS OSS_uuid 3
442 2 UP obdfilter testfs-OST0000 testfs-OST0000_UUID 3
445 Debug log: 87 lines, 87 kept, 0 dropped.
457 .BR mount.lustre (8),