1 .TH lfs-df 1 "2016 Dec 7" Lustre "user utilities"
3 lfs df \- report Lustre filesystem disk usage
5 .BR "lfs df" " [" -i "] [" -h | -H ]
8 .IR <fsname> [. <pool> ]]
13 displays filesystem usage information by default for each Lustre
14 filesystem currently mounted on that node, or for the filesystem
17 if given. It displays the current usage and totals for each MDT and
18 OST separately, as well as a per-filesystem summary that matches
20 output for each filesystem.
26 usage of the OSTs (the MDT space usage is shown only for reference). With
30 (object) usage for each target and in the summary. For ZFS-backed
33 count accurately reflects the number of in-use objects on each target,
40 based on the current average (mean) space used per object on each target,
41 and may fluctuate over time to reflect the current usage pattern of
42 the target. The estimate becomes more accurate as the target becomes
43 more full, assuming the usage pattern is consistent.
46 may also report additional target status as the last column in the
47 display, if there are issues with that target. States include:
51 The target has a failed drive in the RAID device, or is undergoing
52 RAID reconstruction. This state is marked on the server automatically
55 or a (user-supplied) script that monitors the target device and sets
56 .B 'lctl set_param obdfilter.\fI<target>\fB.degraded=1'
57 on the OST. This target will be avoided for new allocations, but
58 will still be used for existing files located there or if there are
59 not enough non-degraded OSTs to make up a widely-striped file.
62 The target is configured to deny object precreation by the
63 .B 'lctl set_param obdfilter.\fI<target>\fB.no_precreate=1'
66 mount option. This may be done to add an OST to the filesystem without
67 allowing objects to be allocated on it yet, or for other reasons.
70 The target filesystem is marked read-only due to filesystem
71 corruption detected by ldiskfs or ZFS. No modifications are
72 allowed on this OST, and it needs to have
75 .BR zpool (8) " scrub"
76 run to repair the underlying filesystem.
79 The target filesystem has less than the minimum required free space and
80 will not be used for new object allocations until it has more free space.
83 The target filesystem has less than the minimum required free inodes and
84 will not be used for new object allocations until it has more free inodes.
87 The target filesystem is using a flash (non-rotational) storage device.
88 This lower-case status is only shown in conjunction with the
90 option, since it is not an error condition.
93 The various options supported by
95 are listed and explained below:
97 .BR -h ", " --human-readable
98 Print output in a human readable format (e.g. 16.3T, 4.25P).
99 Suffixes are base-2 units (i.e. 1 GiB = 1024 MiB).
104 but suffixes are SI base-10 units (i.e. 1 GB = 1000 MB).
107 Print information about the inode usage and totals for the MDTs and
108 OSTs rather than space usage. Note that the
114 counts typically reflect the
116 of values from the MDTs. If the total number of objects available
117 on the OSTs is smaller (factoring in the filesystem default
119 as one OST object is used for each stripe in a file)
124 values will be reduced to reflect the
126 number of files that could potentially be created with the default
127 stripe count. The actual total number of files that can be created
131 Do not attempt to contact any OST or MDT not currently connected to
132 the client. This avoids blocking the
134 output if a target is offline or unreachable, and only returns the
135 space on OSTs that can currently be accessed.
137 .BR -p ", " --pool= [ \fIfsname\fR .] \fIpool\fR
138 Limit the usage to report only MDTs and OSTs that are in the specified
140 If multiple filesystems are mounted, list OSTs in
142 for every filesystem, or limit the display to only a pool for a
143 specific filesystem if
145 is given. Specifying both the fsname and pool like:
147 .BI "lfs df --pool=" fsname.pool
149 is equivalent to specifying the mountpoint for the given
152 .BI "lfs df --pool=" "pool /mnt/fsname"
154 .BR -v ", " --verbose
155 Show deactivated MDTs and OSTs in the listing, along with any
156 additional status flags for each MDT and OST. By default, any
157 MDTs and OSTs that are deactivated by the administrator are not shown.
158 However, targets that are only temporarily inaccessible are still shown.
161 .B $ lfs df -hv /mnt/testfs
162 Lists space usage per OST and MDT for the
164 filesystem in human readable format.
167 UUID bytes Used Avail Use% Mounted on
169 testfs-MDT0000_UUID 13.0G 1.2G 11.0G 10% /testfs[MDT:0]
171 testfs-OST0000_UUID 3.6T 2.9T 585.7G 84% /testfs[OST:0]
173 testfs-OST0001_UUID 3.6T 3.1T 472.5G 87% /testfs[OST:1] D
175 testfs-OST0002_UUID 3.6T 3.0T 570.3G 84% /testfs[OST:2] DR
177 OST0003 : inactive device
179 testfs-OST0006_UUID 5.4T 4.9T 417.8G 92% /testfs[OST:3]
182 filesystem_summary: 16.2T 13.8T 2.0T 88% /testfs
186 The above example output shows that
188 is currently temporarily inactive or offline, while
192 are not shown at all, either because they are marked permanently offline
193 by the administrator (via
194 .BR "lctl set_param -P osc.testfs-OST000[45].active=0" )
195 or they were never added to the filesystem. The
199 targets are currently marked
201 (perhaps they both share the same underlying storage controller),
206 after detecting non-recoverable corruption in the backing filesystem.
209 List inode usage per OST and MDT for all mounted Lustre filesystems.
211 UUID Inodes IUsed IFree IUse% Mounted on
213 testfs-MDT0000_UUID 932.2k 884.6k 47.6k 95% /testfs[MDT:0]
215 testfs-OST0000_UUID 267.5k 179.6k 87.8k 67% /testfs[OST:0]
217 testfs-OST0001_UUID 268.9k 173.5k 95.4k 64% /testfs[OST:1] D
219 testfs-OST0002_UUID 267.5k 169.6k 97.9k 63% /testfs[OST:2] DR
221 OST0003 : inactive device
223 testfs-OST0006_UUID 426.1k 377.4k 48.7k 88% /testfs[OST:3]
226 filesystem_summary: 932.1k 884.6k 47.6k 95% /testfs
230 .B $ lfs df --pool ssd /mnt/testfs
231 List space usage for only the
237 .B $ lfs df -v /mnt/testfs
238 List all MDTs and OSTs for the
240 filesystem, even if not currently connected.