Viewing: lctl.8
.TH LCTL 8 2026-03-06 Lustre "Lustre Configuration Utilities"
.SH NAME
lctl \- Lustre filesystem administrator configuration tool
.SH SYNOPSIS
.SY lctl
.SY lctl
.RB [ --device
.IR DEVICE ]
.I COMMAND
.RI [ ARGS ]
.YS
.SH DESCRIPTION
.B lctl
is used by a storage administrator to perform various Lustre operations,
allowing configuration, maintenance, and debugging features to be accessed.
It can be invoked non-interactivly to execute the specified
.BR COMMAND ,
or it can be run interactively without arguments to execute multiple commands.
In some cases,
.I COMMAND
must be executed on a specific
.IR DEVICE ,
which can be specified on the command-line,
or interactively before the command is run.
.PP
The most common commands are:
.BR debug_daemon ,
.BR debug_kernel ,
.BR device_list ,
.BR get_param ,
.BR set_param ,
.BR list_nids ,
.BR mark ,
and
.BR ping .
Most sub-commands are explained in separate man pages of the form
.BI lctl- COMMAND
as listed in the
.B SEE ALSO
section at the end.
Some sub-commands do not have their own detailed man page are listed below.
.SH OPTIONS
The following options can be used to invoke
.BR lctl .
.TP
.B --device
Specify the
.I DEVICE
name or number to be used for the operation. The
.B device_list
command shows a list of locally configured devices.
.TP
.BI help " COMMAND"
To get basic help on the meaning and syntax of a command.
.TP
.B --list-commands
Output a list of the commands supported by the lctl utility.
.TP
.BR --ignore_errors ", " ignore_errors
Ignore errors during script processing.
.TP
.B lustre_build_version
Output the build version of the Lustre kernel modules.
.TP
.BR -V ", " --version
Output the build version of the utility itself.
.TP
.BR exit ", " quit
Quit an interactive session.
.SH BASH COMPLETION
The
.B lctl
command supports
.BR bash-completion (1)
for tab completion of sub-command names and their options,
with proper package installation and supporing shell usage.
This can greatly simplify finding available commands,
their options, and in many cases option arguments.
.PP
To list commands, type
.RB ' lctl\ TAB ',
or after partially completing a command name.
To list long options (more descriptive and easily understood) type
.RI ' COMMAND
.BR --TAB ',
and to list short options type
.RI ' COMMAND
.BR -TAB '.
Some commands also allow context-specific completion of arguments to the
command-line option, for example generating a list of OBD devices for the
.B --device
option, or a list of OST pools for the
.B pool_*
commands.
.SH COMMANDS
.SS System Configuration
The on-line tool set for displaying, modifying, backup, or removal of Lustre
system configuration.
For detail, please see:
.BR lctl-get_param (8),
.BR lctl-set_param (8),
.BR lctl-llog_print (8),
and
.BR lctl-lcfg_* (8).
.SS Network Configuration
.TP
.BR network { up | down }|{ tcp | o2ib }
Start or stop LNET, or select a network type for other
.B lctl
LNET commands. See also
.BR lnetctl (8)
for most LNet configuration commands.
.TP
.B conn_list
Print all the connected remote NIDs for a given
.B network
type.
.TP
.B interface_list
Print the network interface information for a given
.B NETWORK
type.
.TP
.BI list_nids
Print all Network Identifiers on the local node. LNET must be running.
.TP
.B peer_list
Print the known peers for a given
.B NETWORK
type.
.TP
.BI ping " NID TIMEOUT"
Check LNET connectivity via an LNET ping. This will use the fabric
appropriate to the specified NID. By default lctl will attempt to
reach the remote node up to 120 seconds and then timeout. To disable
the timeout just specify an negative timeout value.
.TP
.BI replace_nids " DEVICE_NAME NIDS_LIST"
Replace the LNet NIDs. See
.BR lctl-replace_nids (8)
for details.
.TP
.B route_list
Print the complete routing table.
.TP
.BI which_nid " NIDLIST"
From a list of nids for a remote node, show which interface communication
will take place on.
.SS Device Selection
.TP
.BI device " DEVNAME"
This will select the specified OBD device.
All other commands depend on the device being set.
.TP
.BR device_list
Show all the local Lustre OBDs. See
.BR lctl-device_list (8).
.SS Device Operations
.TP
.BI conf_param " \fR[" "-d\fR] " DEVICE \fR| FSNAME . PARAMETER = VALUE
Set a permanent configuration parameter for any device via the MGS. This
command must be run on the MGS node.
.IP
[NOTE]
The conf_param command is deprecated and should not be used for configuring
Lustre parameters. It only applies settings to targets present at the time the
command is executed; targets (such as OSTs) added or mounted later will not
automatically receive these settings. For reliable and consistent
configuration, use set_param instead. The set_param command immediately applies
parameter changes to all relevant targets, including those added in the future.
See
.BR lctl-set_param (8)
for details.
For example, replace:
lctl conf_param testfs-OST0000.osc.max_rpcs_in_flight=16
with:
lctl set_param -P osc.testfs-*.max_rpcs_in_flight=16
Update any scripts or procedures to use set_param in place of conf_param.
Use conf_param -d to remove existing conf_param settings; set_param -P
does not remove them.
.PP
The
.B -d
option deletes a parameter setting (use the default value at the next restart).
A null value for
.I VALUE
also deletes the parameter setting.
This is useful if an incorrect or obsolete parameter is in the configuration.
.RS 2
.TP
.B Parameters:
All of the writable parameters under
.B lctl list_param
(e.g.
.B lctl list_param -w osc.*.*
or
.B lctl list_param -F osc.*.* | grep =
) can be permanently set using
.B lctl conf_param
, but the format is slightly different. For conf_param,
the device is specified first, then the obdtype.
(See examples below.) Wildcards are not supported.
.br
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.)
.I DEVICE
is ignored for system wide parameters.
.TP
.B activate
Reactivate an import after deactivating, below.
This setting is only effective until the next restart (see
.BR conf_param).
.TP
.B deactivate
Deactivate an import, in particular meaning do not assign new file stripes
to an OSC. This command should be used on the OSC in the MDT LOV
corresponding to a failed OST device, to prevent further attempts at
communication with the failed OST.
.TP
.B abort_recovery
Abort the recovery process on a restarting MDT or OST device
.SS Changelogs
Changelog user can be registered and deregistered on particular device.
Changelog starts logging when any user is registered.
.PP
For more details see:
.TP
.BR lctl-changelog_register (8)
Register a new changelog user on specified MDT device with specified parameters.
.TP
.BR lctl-changelog_deregister (8)
Deregister an existing changelog user on the specified MDT.
.SS Nodemap
The nodemap feature allows UIDs, GIDs, and PROJIDs from remote systems to be
mapped to local sets of UIDs, GIDs, and PROJIDs while retaining POSIX ownership,
permissions and quota information. As a result, multiple sites with conflicting
user and group identifiers can operate on a single Lustre file system without
creating collisions in the UID, GID, or PROJID space.
.P
Nodemap commands must be run on the MGS from where the current nodemap
configuration is asynchronously propagated to all server nodes. The nodemap
configuration further persists across restarts. An exception represents dynamic
nodemaps (see lctl-nodemap-add (8)) which are defined on the local server only
and are not persistent.
.P
In addition to assigning client nodes to nodemaps, it is necessary to define a
privileged nodemap that covers all Lustre server nodes for ID mapping to work
correctly. The privileged nodemap should have both "admin" and "trusted"
properties set.
.P
The "default" nodemap is a special nodemap which cannot be removed and
represents a fallback nodemap for all nodes that are not assigned to any other
nodemap. Because of its special role, only some properties can be set on it,
such as "squash_uid". ID mapping is explicitly disabled on the "default"
nodemap. Care should be taken when modifying the "admin" and "trusted"
properties on the "default" nodemap, especially if Lustre servers are not
covered by any other nodemap.
.P
See also:
.TP
.BR lctl-nodemap-activate (8)
Activate/deactivate the nodemap feature.
.TP
.BR lctl-nodemap-add (8)
Add a new nodemap, to which NID ranges, identities, and properties can be added.
.TP
.BR lctl-nodemap-add-idmap (8)
Add a UID or GID mapping to a nodemap.
.TP
.BR lctl-nodemap-add-range (8)
Define a range of NIDs for a nodemap.
.TP
.BR lctl-nodemap-add-offset (8)
Set a UID/GID/PROJID offset value
.TP
.BR lctl-nodemap-del (8)
Delete an existing nodemap.
.TP
.BR lctl-nodemap-del-idmap (8)
Delete an existing UID or GID mapping from a nodemap.
.TP
.BR lctl-nodemap-del-range (8)
Delete an existing NID range from a nodemap.
.TP
.BR lctl-nodemap-del-offset (8)
Remove a UID/GID/PROJID offset from a nodemap.
.TP
.BR lctl-nodemap-fileset-add (8)
Add a primary or alternate fileset to a nodemap.
.TP
.BR lctl-nodemap-fileset-del (8)
Delete a type of fileset from a nodemap.
.TP
.BR lctl-nodemap-fileset-modify (8)
Modify a fileset in a nodemap, changing its path, type, or access mode.
.TP
.BR lctl-nodemap-modify (8)
Modify a nodemap property.
.TP
.BR lctl-nodemap-info (8)
Print nodemap information.
.TP
.BR lctl-nodemap-set-cap (8)
Set user capabilities on a nodemap.
.TP
.BR lctl-nodemap-set-sepol (8)
Set SELinux policy info on a nodemap.
.SS Configuration logs
.TP
.BI clear_conf " DEVICE" \fR| FSNAME
This command runs on MGS node having MGS device mounted with -o nosvc.
It cleans up configuration files stored in the CONFIGS/ directory
of any records marked SKIP. If the device name is given, then the
specific logs for that filesystem (e.g. testfs-MDT0000) is processed.
Otherwise, if a filesystem name is given then all configuration files for the
specified filesystem are cleared.
.SS LFSCK
An on-line Lustre consistency check and repair tool. It is used for totally
replacing the old lfsck tool for kinds of Lustre inconsistency verification,
including: corrupted or lost OI mapping, corrupted or lost link EA, corrupted
or lost FID in name entry, dangling name entry, multiple referenced name entry,
unmatched MDT-object and name entry pairs, orphan MDT-object, incorrect
MDT-object links count, corrupted namespace, corrupted or lost LOV EA, lost
OST-object, multiple referenced OST-object, unmatched MDT-object and OST-object
pairs, orphan OST-object, and so on.
.P
See also:
.TP
.BR lctl-lfsck-start (8)
Start LFSCK on the specified MDT or OST device with specified parameters.
.TP
.BR lctl-lfsck-stop (8)
Stop LFSCK on the specified MDT or OST device.
.TP
.BR lctl-lfsck-query (8)
Get the LFSCK global status via the specified MDT device.
.SS Barrier
The tools set for write (modify) barrier on all MDTs. For detail, please see:
.TP
.BR lctl-barrier (8)
.SS Snapshot
ZFS backend based snapshot tools set. The tool loads system configuration
from the file
.B /etc/ldev.conf
on the MGS, and call related ZFS commands to
maintain Lustre snapshot pieces on all targets (MGS/MDT/OST).
The configuration file
.B /etc/ldev.conf
is not only for snapshot, but also
for other purpose.
.P
The format is:
.EX
.IB "HOST " foreign/- "LABEL DEVICE"\c
.RI [ JOURNAL_PATH "]\c
.B /- \c
.RI [ RAIDTAB ]
.EE
.P
The format of
.I LABEL
is:
.EX
.IB FSNAME -\c
.RI { ROLE }{ INDEX "} or {" ROLE }{ INDEX }
.EE
.P
The format of
.I DEVICE
is:
.EX
.RB [ md | zfs: ]\c
.RI [ POOL_DIR\c
.BR / ]\c
.IB POOL / FILESYSTEM
.EE
.P
Snapshot only uses the fields
.IR HOST ,
.I LABEL
and
.IR DEVICE .
.TP Example:
.EX
.B # cat /etc/ldev.conf
host-mdt1 - myfs-MDT0000 zfs:/tmp/myfs-mdt1/mdt1
host-mdt2 - myfs-MDT0001 zfs:myfs-mdt2/mdt2
host-ost1 - OST0000 zfs:/tmp/myfs-ost1/ost1
host-ost2 - OST0001 zfs:myfs-ost2/ost2
.P
See also:
.TP
.BR lctl-snapshot-create (8)
Create snapshot with the given name.
.TP
.BR lctl-snapshot-destroy (8)
Destroy the specified snapshot.
.TP
.BR lctl-snapshot-modify (8)
Modify the specified snapshot.
.TP
.BR lctl-snapshot-list (8)
Query the snapshot information.
.TP
.BR lctl-snapshot-mount (8)
Mount the specified snapshot.
.TP
.BR lctl-snapshot-umount (8)
Umount the specified snapshot.
.SS Debug
.TP
.B debug_daemon
Start and stop the debug daemon, and control the output filename and size.
.TP
.BR debug_kernel " [" \fIFILE "] [" \fIRAW ]
Dump the kernel debug buffer to stdout or file.
.TP
.BI debug_file " INPUT " \fR[ OUTPUT \fR]
Convert kernel-dumped debug log from binary to plain text format.
.TP
.BI clear
Clear the kernel debug buffer.
.TP
.BI mark " TEXT"
Insert marker text in the kernel debug buffer.
.TP
.BI filter " SUBSYSTEM_ID" \fR| DEBUG_MASK
Filter kernel debug messages by subsystem or mask.
.TP
.BI show " SUBSYSTEM_ID" \fR| DEBUG_MASK
Show specific type of messages.
.TP
.BI debug_list " SUBS" \fR| TYPES
List all the subsystem and debug types.
.TP
.BI modules " PATH"
Provide gdb-friendly module information.
.SH EXAMPLES
List the devices configured on the local node:
.EX
.B # lctl dl
0 UP mgc MGC192.168.0.20@tcp bfbb24e3-7deb-2ffa-eab0-44dffe00f692 5
1 UP ost OSS OSS_uuid 3
2 UP obdfilter testfs-OST0000 testfs-OST0000_UUID 3
.EE
Dump the kernel debug log to a file for review:
.EX
.B # lctl dk /tmp/debug.log
Debug log: 87 lines, 87 kept, 0 dropped.
.EE
.SH AVAILABILITY
.B lctl
is part of the
.BR lustre (7)
filesystem package since release 0.5.0
.\" Added in commit 0.4.2-6-gbefd9c343f
.SH SEE ALSO
.BR lfs (1),
.BR lustre (7),
.BR lctl (8),
.BR lctl-barrier (8),
.BR lctl-changelog_deregister (8),
.BR lctl-changelog_register (8),
.BR lctl-get_param (8),
.BR lctl-lcfg (8),
.BR lctl-lfsck-query (8),
.BR lctl-lfsck-start (8),
.BR lctl-lfsck-stop (8),
.BR lctl-list_param (8),
.BR lctl-llog_catlist (8),
.BR lctl-llog_info (8),
.BR lctl-llog_print (8),
.BR lctl-network (8),
.BR lctl-nodemap-activate (8),
.BR lctl-nodemap-add (8),
.BR lctl-nodemap-add-idmap (8),
.BR lctl-nodemap-add-offset (8),
.BR lctl-nodemap-add-range (8),
.BR lctl-nodemap-del (8),
.BR lctl-nodemap-del-idmap (8),
.BR lctl-nodemap-del-offset (8),
.BR lctl-nodemap-del-range (8),
.BR lctl-nodemap-modify (8),
.BR lctl-nodemap-set-capabilities (8),
.BR lctl-pcc (8),
.BR lctl-replace-nids (8),
.BR lctl-set_param (8),
.BR lctl-snapshot-create (8),
.BR lctl-snapshot-destroy (8),
.BR lctl-snapshot-list (8),
.BR lctl-snapshot-modify (8),
.BR lctl-snapshot-mount (8),
.BR lctl-snapshot-umount (8),
.BR mkfs.lustre (8),
.BR mount.lustre (8)
