.br
.B lfs changelog_clear <mdtname> <id> <endrec>
.br
-.B lfs check <mds|osts|servers>
+.B lfs check <mgts|mdts|osts|all>
.br
-.B lfs data_version [-n] \fB<filename>\fR
+.B lfs data_version [-nrw] \fB<filename>\fR
.br
.B lfs df [-ihlv] [--pool|-p <fsname>[.<pool>]] [path]
.br
[[\fB!\fR] \fB--component-flags|\fB--comp-flags\fR <[\fB^\fR]\fIflag\fB,\fR...>]
[[\fB!\fR] \fB--component-end|\fB--comp-end\fR|\fB-E\fR [\fB+-\fR]\fIn\fR[\fBKMGTPE\fR]]
[[\fB!\fR] \fB--component-start|\fB--comp-start\fR [\fB+-\fR]\fIn\fR[\fBKMGTPE\fR]]
+ [[\fB!\fR] \fB--mirror-count|\fB-N\fR [\fB+-\fR]\fIn\fR]
+ [[\fB!\fR] \fB--mirror-state\fR <[^]\fIstate\fR>]
[[\fB!\fR] \fB--gid\fR|\fB-g\fR|\fB--group\fR|\fB-G\fR <\fIgname\fR>|<\fIgid\fR>]
[[\fB!\fR] \fB--layout\fR|\fB-L mdt\fR,\fBraid0\fR,\fBreleased\fR]
[\fB--maxdepth\fR|\fB-D\fI n\fR]
.br
.B lfs quotacheck [-ug] <filesystem>
.br
+.B lfs quota <-U|-G|-P> <filesystem>
+.br
.B lfs quotaon [-ugf] <filesystem>
.br
.B lfs quotaoff [-ug] <filesystem>
.B lfs setstripe --component-del {--component-id|-I id |
\fB--component-flags <flags>} <filename>
.br
+.B lfs setstripe --yaml=<yaml_template_file> <filename>
+.br
.B lfs --version
.br
.B lfs --list-commands
free up disk space. An <endrec> of 0 indicates the current last record.
Changelog consumers must be registered on the MDT node using \fBlctl\fR.
.TP
-.B check
-Display the status of MDS or OSTs (as specified in the command) or all the servers (MDS and OSTs)
-.TP
-.B data_version [-n] <filename>
-Display current version of file data. If -n is specified, data version is read
-without taking lock. As a consequence, data version could be outdated if there
-is dirty caches on filesystem clients, but this will not force data flushes and
-has less impact on filesystem.
+.B check <mgts|mdts|osts|all>
+Display the status of the MGTs, MDTs or OSTs (as specified in the command) or
+all the servers (MGTs, MDTs and OSTs).
+.TP
+.B data_version [-nrw] <filename>
+Display the current version of file data. If -n is specified, the data version
+is read without taking a lock. As a consequence, the data version could be
+outdated if there are dirty caches on filesystem clients, but this option will
+not force data flushes and has less of an impact on the filesystem. If -r is
+specified, the data version is read after dirty pages on clients are flushed. If
+-w is specified, the data version is read after all caching pages on clients are
+flushed.
-Even without -n, race conditions are possible and data version should be
+Even with -r or -w, race conditions are possible and the data version should be
checked before and after an operation to be confident the data did not change
during it.
+
+The data version is the sum of the last committed transaction numbers of all
+data objects of a file. It is used by HSM policy engines for verifying that file
+data has not been changed during an archive operation or before a release
+operation, and by OST migration, primarily for verifying that file data has not
+been changed during a data copy, when done in non-blocking mode.
.TP
.B getname [-h]|[path ...]
Report all the Lustre mount points and the corresponding Lustre filesystem
Quit the interactive lfs session
.SH EXAMPLES
.TP
-.B $ lfs check servers
-Check the status of all servers (MDT, OST)
+.B $ lfs check all
+Check the status of all servers (MGT, MDT, OST)
.TP
.B $ lfs osts
List all the OSTs
.B $ lfs quota -u bob /mnt/lustre
List quotas of user `bob'
.TP
+.B $ lfs quota -U /mnt/lustre
+List user quotas of system default setting
+.TP
.B $ lfs quota -t -u /mnt/lustre
Show grace times for user quotas on /mnt/lustre
.TP