From 929cadd6fe210ce815786e3b8ee0a20c995eed20 Mon Sep 17 00:00:00 2001 From: Fan Yong Date: Sun, 14 May 2017 07:39:18 +0800 Subject: [PATCH] LU-9303 doc: man pages for snapshot components Including the separated lctl-barrier and lctl-snapshot man pages, the lctl-fork-lcfg and lctl-erase-lcfg sections in the lctl man page. Also some other small cleanup. Test-parameters: trivial Signed-off-by: Fan Yong Change-Id: Ied60b824afcfab5d2d030f12d39c9aa1bab0969a Reviewed-on: https://review.whamcloud.com/26453 Tested-by: Jenkins Reviewed-by: Joseph Gmitter Tested-by: Maloo Reviewed-by: Andreas Dilger Reviewed-by: Oleg Drokin --- lustre/doc/Makefile.am | 8 + lustre/doc/lctl-barrier.8 | 79 ++++++++++ lustre/doc/lctl-lcfg.8 | 37 +++++ lustre/doc/lctl-lfsck-query.8 | 6 +- lustre/doc/lctl-lfsck-start.8 | 6 +- lustre/doc/lctl-lfsck-stop.8 | 6 +- lustre/doc/lctl-snapshot-create.8 | 77 ++++++++++ lustre/doc/lctl-snapshot-destroy.8 | 54 +++++++ lustre/doc/lctl-snapshot-list.8 | 48 ++++++ lustre/doc/lctl-snapshot-modify.8 | 58 ++++++++ lustre/doc/lctl-snapshot-mount.8 | 47 ++++++ lustre/doc/lctl-snapshot-umount.8 | 40 +++++ lustre/doc/lctl.8 | 290 ++++++++----------------------------- 13 files changed, 518 insertions(+), 238 deletions(-) create mode 100644 lustre/doc/lctl-barrier.8 create mode 100644 lustre/doc/lctl-lcfg.8 create mode 100644 lustre/doc/lctl-snapshot-create.8 create mode 100644 lustre/doc/lctl-snapshot-destroy.8 create mode 100644 lustre/doc/lctl-snapshot-list.8 create mode 100644 lustre/doc/lctl-snapshot-modify.8 create mode 100644 lustre/doc/lctl-snapshot-mount.8 create mode 100644 lustre/doc/lctl-snapshot-umount.8 diff --git a/lustre/doc/Makefile.am b/lustre/doc/Makefile.am index 4e29038..11420c0 100644 --- a/lustre/doc/Makefile.am +++ b/lustre/doc/Makefile.am @@ -134,6 +134,14 @@ SERVER_MANFILES = \ lctl-nodemap-del-idmap.8 \ lctl-nodemap-del-range.8 \ lctl-nodemap-modify.8 \ + lctl-lcfg.8 \ + lctl-barrier.8 \ + lctl-snapshot-create.8 \ + lctl-snapshot-destroy.8 \ + lctl-snapshot-modify.8 \ + lctl-snapshot-list.8 \ + lctl-snapshot-mount.8 \ + lctl-snapshot-umount.8 \ lshowmount.8 \ mkfs.lustre.8 \ tunefs.lustre.8 diff --git a/lustre/doc/lctl-barrier.8 b/lustre/doc/lctl-barrier.8 new file mode 100644 index 0000000..9fe55ad --- /dev/null +++ b/lustre/doc/lctl-barrier.8 @@ -0,0 +1,79 @@ +.TH lctl-barrier 8 "2017 Apr 13" Lustre "Lustre write barrier on all MDTs" +.SH SYNOPSIS +.br +.B lctl barrier_freeze \fR{fsname} [timeout] +.br +.br +.B lctl barrier_thaw \fR{fsname} +.br +.br +.B lctl barrier_stat \fR{fsname} +.br +.br +.B lctl barrier_rescan \fR{fsname} [timeout] +.br +.SH DESCRIPTION +.TP +.B barrier_freeze \fR{fsname} [timeout] +Set write barrier on all MDTs. The command will not return until the +barrier is set (frozen) or failed. With the write barrier set, any +subsequent metadata modification will be blocked until the barrier is +thawed or expired. The barrier lifetime is started when triggering +freeze and will be terminated when barrier thawed. To avoid the system +being frozen for very long time if miss/fail to call barrier_thaw, you +can specify its lifetime via the +.I timeout +parameter in seconds, the default value is 30 (seconds). If the barrier +is not thawed before that, it will be expired automatically. The command +can only succeed when all registered MDTs are available. If some MDT is +registered but goes offline, then the freeze command will fail. To check +and update current status of MDTs, see the command +.B barrier_rescan +in subsequent section. +.TP +.B barrier_thaw \fR{fsname} +Reset write barrier on all MDTs. After the write barrier thawed, all the +blocked metadata modifications (because of the former +.B barrier_freeze +command) will be handled normally. +.TP +.B barrier_stat \fR{fsname} +.br +Query the write barrier status, the possible status and related meanings are +as following: +.br + 'init': has never set barrier on the system + 'freezing_p1': in the first stage of setting the write barrier + 'freezing_p2': in the second stage of setting the write barrier + 'frozen': the write barrier has been set successfully + 'thawing': in thawing the write barrier + 'thawed': the write barrier has been thawed + 'failed': fail to set write barrier + 'expired': the write barrier is expired + 'rescan': in scanning the MDTs status, see the command barrier_rescan + 'unknown': other cases +.br +If the barrier is in 'freezing_p1', 'freezing_p2' or 'frozen' status, then +the lifetime remaining will be returned also. +.TP +.B barrier_rescan \fR{fsname} [timeout] +.br +Scan the system to check which MDTs are active. The status of the MDTs is +required because the +.B barrier_freeze +will be unsuccessful if any of the MDTs are permenantly offline. During +the rescan, the MDT status is updated. If an MDT does not respond the +.B barrier_rescan +within the given +.I timeout +seconds (where the default value is 30 seconds), then it will be marked +as unavailable or inactive. + +.SH AVAILABILITY +.B lctl-barrier +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-snapshot-create (8) diff --git a/lustre/doc/lctl-lcfg.8 b/lustre/doc/lctl-lcfg.8 new file mode 100644 index 0000000..8d63c4b --- /dev/null +++ b/lustre/doc/lctl-lcfg.8 @@ -0,0 +1,37 @@ +.TH lctl-lcfg 8 "2017 Apr 13" Lustre "Maintain Lustre configuration" +.SH SYNOPSIS +.br +.B lctl fork_lcfg \fR{fsname} {newname} +.br +.br +.B lctl erase_lcfg \fR{fsname} +.br +.SH DESCRIPTION +.TP +.B fork_lcfg \fR{fsname} {newname} +Generate Lustre configuration for the given filesystem +.I newname +based on the specified Lustre system +.I fsname +configuration. It is not simply copy. Instead, it uses the +.I newname +as the filesystem name in the new configuration. It can be used to +backup the system configuration, or generate configuration for the +snapshot that has the same configuration as the original filesystem +but with different filesystem names. + +.TP +.B erase_lcfg \fR{fsname} +Permanently erase configuration for the named filesystem. It can be +used to remove the backup configuration or delete inactive filesystem +(or snapshot) from a shared MGS. + +.SH AVAILABILITY +.B lctl-lcfg +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-destroy (8) diff --git a/lustre/doc/lctl-lfsck-query.8 b/lustre/doc/lctl-lfsck-query.8 index bf2c69b..9ae8d59 100644 --- a/lustre/doc/lctl-lfsck-query.8 +++ b/lustre/doc/lctl-lfsck-query.8 @@ -28,11 +28,11 @@ Do not return until there is no on-going LFSCK scanning on any target associated with this filesystem (MDT or OST). .SH AVAILABILITY -.B lctl +.B lctl-lfsck-query is part of the -.BR Lustre (7) +.BR lustre (7) filesystem package. .SH SEE ALSO -.BR lustre (7), +.BR lctl (8), .BR lctl-lfsck-start (8), .BR lctl-lfsck-stop (8) diff --git a/lustre/doc/lctl-lfsck-start.8 b/lustre/doc/lctl-lfsck-start.8 index 3ca3ce4..30fc226 100644 --- a/lustre/doc/lctl-lfsck-start.8 +++ b/lustre/doc/lctl-lfsck-start.8 @@ -100,11 +100,11 @@ one time. This controls the load placed on remote OSTs when running checks. By default there are at most 1024 outstanding requests. .SH AVAILABILITY -.B lctl +.B lctl-lfsck-start is part of the -.BR Lustre (7) +.BR lustre (7) filesystem package. .SH SEE ALSO -.BR lustre (7), +.BR lctl (8), .BR lctl-lfsck-stop (8), .BR lctl-lfsck-query (8) diff --git a/lustre/doc/lctl-lfsck-stop.8 b/lustre/doc/lctl-lfsck-stop.8 index 0cc4e59..30dbbfc 100644 --- a/lustre/doc/lctl-lfsck-stop.8 +++ b/lustre/doc/lctl-lfsck-stop.8 @@ -23,11 +23,11 @@ Such LFSCK command can be executed on any MDT deivce in the system. Show this help. .SH AVAILABILITY -.B lctl +.B lctl-lfsck-stop is part of the -.BR Lustre (7) +.BR lustre (7) filesystem package. .SH SEE ALSO -.BR lustre (7), +.BR lctl (8), .BR lctl-lfsck-start (8), .BR lctl-lfsck-query (8) diff --git a/lustre/doc/lctl-snapshot-create.8 b/lustre/doc/lctl-snapshot-create.8 new file mode 100644 index 0000000..c6b9f68 --- /dev/null +++ b/lustre/doc/lctl-snapshot-create.8 @@ -0,0 +1,77 @@ +.TH lctl-snapshot-create 8 "2017 Apr 13" Lustre "create Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_create \fR[-b | --barrier [on | off]] [-c | --comment comment] + {-F | --fsname fsname} [-h | --help] {-n | --name ssname} + [-r | --rsh remote_shell] [-t | --timeout timeout] +.br +.SH DESCRIPTION +Create snapshot with the given name. The tool loads system configuration from +the file +.B /etc/ldev.conf +as described in the +.BR lctl (8) +.B SNAPSHOT +section. Then, the snapshot pieces are created on every Lustre target +(MGT/MDT/OST). +.SH OPTIONS +.TP +.BR -b ", " --barrier " [" on | off ] +Set write barrier on all MDTs before creating the snapshot. The default value is +.BR on . +If you are confident about the system consistency, or not require the full +consistency and want to avoid blocking applications when creating the snapshot, +then you can specify barrier +.BR off . +That will save your time of creating the snapshot. If the barrier is +.IR on , +then the timeout of the barrier can be specified via +.B -t +option as described in the subsequent section. +.TP +.BR -c ", " --comment " "\fIcomment +Add an optional comment to the +.B snapshot_create +request. The comment can include anything to describe what the snapshot is for +or for a reminder. The comment can be shown via +.BR snapshot_list . +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot's name must be specified. It follows the general ZFS snapshot name +rules, such as the max length is 256 bytes, cannot conflict with the reserved +names, and so on. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. +.TP +.BR -t ", " --timeout " "\fItimeout +If write barrier is +.BR on , +then the +.I timeout +specifies the write barrier's lifetime in second. The default vaule is 30. + +.SH AVAILABILITY +.B lctl-snapshot-create +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-destroy (8), +.BR lctl-snapshot-modify (8), +.BR lctl-snapshot-list (8), +.BR lctl-snapshot-mount (8), +.BR lctl-snapshot-umount (8) diff --git a/lustre/doc/lctl-snapshot-destroy.8 b/lustre/doc/lctl-snapshot-destroy.8 new file mode 100644 index 0000000..09387de --- /dev/null +++ b/lustre/doc/lctl-snapshot-destroy.8 @@ -0,0 +1,54 @@ +.TH lctl-snapshot-destroy 8 "2017 Apr 13" Lustre "destroy Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_destroy \fR[-f | --force] {-F | --fsname fsname} [-h | --help] + {-n | --name ssname} [-r | --rsh remote_shell] +.br +.SH DESCRIPTION +Destroy the specified snapshot. The tool loads system configuration from +the file +.B /etc/ldev.conf +as described in the +.BR lctl (8) +.B SNAPSHOT +section. Then, the snapshot pieces are destroyed on every Lustre target +(MGT/MDT/OST). +.SH OPTIONS +.TP +.BR -f ", " --force +Destroy the specified snapshot by force. If the snapshot is mounted (see +.BR snapshot_mount ), +it will be umounted firstly, then destroyed. Even if some pieces of the +snapshot are lost or broken for some reason(s), the remained parts of the +snapshot still can be destroyed with this option specified. +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot (to be destroyed) name must be specified. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. + +.SH AVAILABILITY +.B lctl-snapshot-destroy +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-modify (8), +.BR lctl-snapshot-list (8), +.BR lctl-snapshot-mount (8), +.BR lctl-snapshot-umount (8) diff --git a/lustre/doc/lctl-snapshot-list.8 b/lustre/doc/lctl-snapshot-list.8 new file mode 100644 index 0000000..54c4354 --- /dev/null +++ b/lustre/doc/lctl-snapshot-list.8 @@ -0,0 +1,48 @@ +.TH lctl-snapshot-list 8 "2017 Apr 13" Lustre "query Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_list \fR[-d | --detail] {-F | --fsname fsname} [-h | --help] + [-n | --name ssname] [-r | --rsh remote_shell] +.br +.SH DESCRIPTION +Query the snapshot information, such as fsname of the snapshot, comment, +create time, the latest modification time, whether mounted or not, and so on. +.SH OPTIONS +.TP +.BR -d ", " --detail +List all the information available for each piece of the snapshot on every +target (MGT/MDT/OST). Usually, the information for each piece of the snapshot +are the same unless some error occurred during the snapshot operations, such +as partly modified or mount. This option allows to check related issues. +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot's name to be queried. If no snapshot name is specified, then all +the snapshots belonging to current Lustre filesystem will be listed. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. + +.SH AVAILABILITY +.B lctl-snapshot-list +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-destroy (8), +.BR lctl-snapshot-modify (8), +.BR lctl-snapshot-mount (8), +.BR lctl-snapshot-umount (8) diff --git a/lustre/doc/lctl-snapshot-modify.8 b/lustre/doc/lctl-snapshot-modify.8 new file mode 100644 index 0000000..c05e311 --- /dev/null +++ b/lustre/doc/lctl-snapshot-modify.8 @@ -0,0 +1,58 @@ +.TH lctl-snapshot-modify 8 "2017 Apr 13" Lustre "modify Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_modify \fR[-c | --comment comment] {-F | --fsname fsname} + [-h | --help] {-n | --name ssname} [-N | --new new_ssname] + [-r | --rsh remote_shell] +.br +.SH DESCRIPTION +Modify the specified snapshot. The tool loads system configuration from +the file +.B /etc/ldev.conf +as described in the +.BR lctl (8) +.B SNAPSHOT +section. Then, the snapshot pieces are modified on every Lustre target +(MGT/MDT/OST). +.SH OPTIONS +.TP +.BR -c ", " --comment " "\fIcomment +Add comment (if it had not been specified with +.BR snapshot_create ) +or change the comment for the given snapshot. +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot (to be modified) name must be specified. +.TP +.BR -N ", " --new " "\fInew_ssname +Rename the snapshot to the new name. It follows the general ZFS snapshot name +rules, such as the max length is 256 bytes, cannot conflict with the reserved +names, and so on. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. + +.SH AVAILABILITY +.B lctl-snapshot-modify +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-destroy (8), +.BR lctl-snapshot-list (8), +.BR lctl-snapshot-mount (8), +.BR lctl-snapshot-umount (8) diff --git a/lustre/doc/lctl-snapshot-mount.8 b/lustre/doc/lctl-snapshot-mount.8 new file mode 100644 index 0000000..c24a0a3 --- /dev/null +++ b/lustre/doc/lctl-snapshot-mount.8 @@ -0,0 +1,47 @@ +.TH lctl-snapshot-mount 8 "2017 Apr 13" Lustre "mount Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_mount \fR{-F | --fsname fsname} [-h | --help] + {-n | --name ssname} [-r | --rsh remote_shell] +.br +.SH DESCRIPTION +Mount the specified snapshot on the servers. Since it is a read-only mode +Lustre filesystem, if the snapshot is mounted, then it cannot be renamed. +It is the user's duty to mount client (must as read only mode with "-o ro") +to the snapshot when needed. +.B NOTE: +the snapshot has its own fsname that is different from the original +filesystem fsname, it can be queried via +.BR snapshot_list . +.SH OPTIONS +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot (to be mounted) name must be specified. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. + +.SH AVAILABILITY +.B lctl-snapshot-mount +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-destroy (8), +.BR lctl-snapshot-modify (8), +.BR lctl-snapshot-list (8), +.BR lctl-snapshot-umount (8) diff --git a/lustre/doc/lctl-snapshot-umount.8 b/lustre/doc/lctl-snapshot-umount.8 new file mode 100644 index 0000000..a4af22b --- /dev/null +++ b/lustre/doc/lctl-snapshot-umount.8 @@ -0,0 +1,40 @@ +.TH lctl-snapshot-umount 8 "2017 Apr 13" Lustre "umount Lustre snapshot" +.SH SYNOPSIS +.TP +.B lctl snapshot_umount \fR{-F | --fsname fsname} [-h | --help] + {-n | --name ssname} [-r | --rsh remote_shell] +.br +.SH DESCRIPTION +Umount the specified snapshot on the servers. +.SH OPTIONS +.TP +.BR -F ", " --fsname " "\fIfsname +The filesystem name. +.TP +.BR -h ", " --help +For help information. +.TP +.BR -n ", " --name " "\fIssname +The snapshot (to be umounted) name must be specified. +.TP +.BR -r ", " --rsh " "\fIremote_shell +Specify a shell to communicate with remote targets. The default value is +.BR ssh . +It is the system admin's duty to guarantee that the specified +.I remote_shell +works well among targets without password authentication. + +.SH AVAILABILITY +.B lctl-snapshot-umount +is part of the +.BR lustre (7) +filesystem package. +.SH SEE ALSO +.BR lctl (8), +.BR lctl-lcfg (8), +.BR lctl-barrier (8), +.BR lctl-snapshot-create (8), +.BR lctl-snapshot-destroy (8), +.BR lctl-snapshot-modify (8), +.BR lctl-snapshot-list (8), +.BR lctl-snapshot-mount (8) diff --git a/lustre/doc/lctl.8 b/lustre/doc/lctl.8 index c5042bd..bfb7949 100644 --- a/lustre/doc/lctl.8 +++ b/lustre/doc/lctl.8 @@ -39,6 +39,12 @@ command, type For non-interactive use, one uses the second invocation, which runs command after connecting to the device. +.SS System Configuration +The on-line tool set for backup or removal of Lustre system configuration. For detail, please see: +.PP +\fBlctl-lcfg\fR(8) +.RS 4 + .SS Network Configuration .TP .BR network " <" up / down >|< tcp / o2ib > @@ -377,73 +383,37 @@ Stop LFSCK on the specified MDT or OST device. .RS 4 Get the LFSCK global status via the specified MDT device. .RE + .SS BARRIER -The tools set for write (modify) barrier on all MDTs. -.TP -.B barrier_freeze \fR [timeout] -.br -Set write barrier on all MDTs. The barrier_freeze command will not return -until the barrier is set (frozen) or failed. With the write barrier set, -any subsequent metadata modification will be blocked until the barrier is -thawed or expired. The barrier lifetime is started when triggering -barrier_freeze, and will be terminated when barrier thawed. To avoid the -system being frozen for very long time if miss/fail to call barrier_thaw, -you can specify its lifetime via the 'timeout' parameter in second, the -default value is 60 (seconds). If the barrier is not thawed before that, -it will be expired automatically. -A barrier_freeze can only succeed when all registered MDTs are available. -If some MDT has ever registered but become offline, then barrier_freeze -will fail. To check and update current status of MDTs, see the command -barrier_rescan. -.TP -.B barrier_thaw \fR -.br -Reset write barrier on all MDTs. With the write barrier thawed, all blocked -metadata modifications (by the former barrier_freeze) will be handled normally. -.TP -.B barrier_stat \fR -.br -Query the write barrier status, the possible status and related meanings are -as following: -.br - 'init': has never set barrier on the system - 'freezing_p1': in the first stage of setting the write barrier - 'freezing_p2': in the second stage of setting the write barrier - 'frozen': the write barrier has been set successfully - 'thawing': in thawing the write barrier - 'thawed': the write barrier has been thawed - 'failed': fail to set write barrier - 'expired': the write barrier is expired - 'rescan': in scanning the MDTs status, see the command barrier_rescan - 'unknown': other cases -.br -If the barrier is in 'freezing_p1', 'freezing_p2' or 'frozen' status, then -the left lifetime will be returned also. -.TP -.B barrier_rescan \fR [timeout] -.br -Scan the system to check which MDTs are active. The status of the MDTs is -required because a barrier_freeze will be unsuccessful if any of the MDTs -are permenantly offline. During barrier_rescan, the MDT status is updated. -If an MDT does not respond the barrier_rescan within the given "timeout" -seconds (where the default value is 60 seconds), then it will be marked -as unavailable or inactive. +The tools set for write (modify) barrier on all MDTs. For detail, please see: +.PP +\fBlctl-barrier\fR(8) +.RS 4 .SS SNAPSHOT ZFS backend based snapshot tools set. The tool loads system configuration -from the file /etc/ldev.conf on the MGS, and call related ZFS commands to +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 /etc/ldev.conf is not only for snapshot, but also +The configuration file +.B /etc/ldev.conf +is not only for snapshot, but also for other purpose. The format is: foreign/-