Loading...
1
2The SGI XFS Filesystem
3======================
4
5XFS is a high performance journaling filesystem which originated
6on the SGI IRIX platform. It is completely multi-threaded, can
7support large files and large filesystems, extended attributes,
8variable block sizes, is extent based, and makes extensive use of
9Btrees (directories, extents, free space) to aid both performance
10and scalability.
11
12Refer to the documentation at http://oss.sgi.com/projects/xfs/
13for further details. This implementation is on-disk compatible
14with the IRIX version of XFS.
15
16
17Mount Options
18=============
19
20When mounting an XFS filesystem, the following options are accepted.
21
22 allocsize=size
23 Sets the buffered I/O end-of-file preallocation size when
24 doing delayed allocation writeout (default size is 64KiB).
25 Valid values for this option are page size (typically 4KiB)
26 through to 1GiB, inclusive, in power-of-2 increments.
27
28 attr2/noattr2
29 The options enable/disable (default is disabled for backward
30 compatibility on-disk) an "opportunistic" improvement to be
31 made in the way inline extended attributes are stored on-disk.
32 When the new form is used for the first time (by setting or
33 removing extended attributes) the on-disk superblock feature
34 bit field will be updated to reflect this format being in use.
35
36 barrier
37 Enables the use of block layer write barriers for writes into
38 the journal and unwritten extent conversion. This allows for
39 drive level write caching to be enabled, for devices that
40 support write barriers.
41
42 discard
43 Issue command to let the block device reclaim space freed by the
44 filesystem. This is useful for SSD devices, thinly provisioned
45 LUNs and virtual machine images, but may have a performance
46 impact. This option is incompatible with the nodelaylog option.
47
48 dmapi
49 Enable the DMAPI (Data Management API) event callouts.
50 Use with the "mtpt" option.
51
52 grpid/bsdgroups and nogrpid/sysvgroups
53 These options define what group ID a newly created file gets.
54 When grpid is set, it takes the group ID of the directory in
55 which it is created; otherwise (the default) it takes the fsgid
56 of the current process, unless the directory has the setgid bit
57 set, in which case it takes the gid from the parent directory,
58 and also gets the setgid bit set if it is a directory itself.
59
60 ihashsize=value
61 In memory inode hashes have been removed, so this option has
62 no function as of August 2007. Option is deprecated.
63
64 ikeep/noikeep
65 When ikeep is specified, XFS does not delete empty inode clusters
66 and keeps them around on disk. ikeep is the traditional XFS
67 behaviour. When noikeep is specified, empty inode clusters
68 are returned to the free space pool. The default is noikeep for
69 non-DMAPI mounts, while ikeep is the default when DMAPI is in use.
70
71 inode64
72 Indicates that XFS is allowed to create inodes at any location
73 in the filesystem, including those which will result in inode
74 numbers occupying more than 32 bits of significance. This is
75 provided for backwards compatibility, but causes problems for
76 backup applications that cannot handle large inode numbers.
77
78 largeio/nolargeio
79 If "nolargeio" is specified, the optimal I/O reported in
80 st_blksize by stat(2) will be as small as possible to allow user
81 applications to avoid inefficient read/modify/write I/O.
82 If "largeio" specified, a filesystem that has a "swidth" specified
83 will return the "swidth" value (in bytes) in st_blksize. If the
84 filesystem does not have a "swidth" specified but does specify
85 an "allocsize" then "allocsize" (in bytes) will be returned
86 instead.
87 If neither of these two options are specified, then filesystem
88 will behave as if "nolargeio" was specified.
89
90 logbufs=value
91 Set the number of in-memory log buffers. Valid numbers range
92 from 2-8 inclusive.
93 The default value is 8 buffers for filesystems with a
94 blocksize of 64KiB, 4 buffers for filesystems with a blocksize
95 of 32KiB, 3 buffers for filesystems with a blocksize of 16KiB
96 and 2 buffers for all other configurations. Increasing the
97 number of buffers may increase performance on some workloads
98 at the cost of the memory used for the additional log buffers
99 and their associated control structures.
100
101 logbsize=value
102 Set the size of each in-memory log buffer.
103 Size may be specified in bytes, or in kilobytes with a "k" suffix.
104 Valid sizes for version 1 and version 2 logs are 16384 (16k) and
105 32768 (32k). Valid sizes for version 2 logs also include
106 65536 (64k), 131072 (128k) and 262144 (256k).
107 The default value for machines with more than 32MiB of memory
108 is 32768, machines with less memory use 16384 by default.
109
110 logdev=device and rtdev=device
111 Use an external log (metadata journal) and/or real-time device.
112 An XFS filesystem has up to three parts: a data section, a log
113 section, and a real-time section. The real-time section is
114 optional, and the log section can be separate from the data
115 section or contained within it.
116
117 mtpt=mountpoint
118 Use with the "dmapi" option. The value specified here will be
119 included in the DMAPI mount event, and should be the path of
120 the actual mountpoint that is used.
121
122 noalign
123 Data allocations will not be aligned at stripe unit boundaries.
124
125 noatime
126 Access timestamps are not updated when a file is read.
127
128 norecovery
129 The filesystem will be mounted without running log recovery.
130 If the filesystem was not cleanly unmounted, it is likely to
131 be inconsistent when mounted in "norecovery" mode.
132 Some files or directories may not be accessible because of this.
133 Filesystems mounted "norecovery" must be mounted read-only or
134 the mount will fail.
135
136 nouuid
137 Don't check for double mounted file systems using the file system uuid.
138 This is useful to mount LVM snapshot volumes.
139
140 uquota/usrquota/uqnoenforce/quota
141 User disk quota accounting enabled, and limits (optionally)
142 enforced. Refer to xfs_quota(8) for further details.
143
144 gquota/grpquota/gqnoenforce
145 Group disk quota accounting enabled and limits (optionally)
146 enforced. Refer to xfs_quota(8) for further details.
147
148 pquota/prjquota/pqnoenforce
149 Project disk quota accounting enabled and limits (optionally)
150 enforced. Refer to xfs_quota(8) for further details.
151
152 sunit=value and swidth=value
153 Used to specify the stripe unit and width for a RAID device or
154 a stripe volume. "value" must be specified in 512-byte block
155 units.
156 If this option is not specified and the filesystem was made on
157 a stripe volume or the stripe width or unit were specified for
158 the RAID device at mkfs time, then the mount system call will
159 restore the value from the superblock. For filesystems that
160 are made directly on RAID devices, these options can be used
161 to override the information in the superblock if the underlying
162 disk layout changes after the filesystem has been created.
163 The "swidth" option is required if the "sunit" option has been
164 specified, and must be a multiple of the "sunit" value.
165
166 swalloc
167 Data allocations will be rounded up to stripe width boundaries
168 when the current end of file is being extended and the file
169 size is larger than the stripe width size.
170
171
172sysctls
173=======
174
175The following sysctls are available for the XFS filesystem:
176
177 fs.xfs.stats_clear (Min: 0 Default: 0 Max: 1)
178 Setting this to "1" clears accumulated XFS statistics
179 in /proc/fs/xfs/stat. It then immediately resets to "0".
180
181 fs.xfs.xfssyncd_centisecs (Min: 100 Default: 3000 Max: 720000)
182 The interval at which the xfssyncd thread flushes metadata
183 out to disk. This thread will flush log activity out, and
184 do some processing on unlinked inodes.
185
186 fs.xfs.xfsbufd_centisecs (Min: 50 Default: 100 Max: 3000)
187 The interval at which xfsbufd scans the dirty metadata buffers list.
188
189 fs.xfs.age_buffer_centisecs (Min: 100 Default: 1500 Max: 720000)
190 The age at which xfsbufd flushes dirty metadata buffers to disk.
191
192 fs.xfs.error_level (Min: 0 Default: 3 Max: 11)
193 A volume knob for error reporting when internal errors occur.
194 This will generate detailed messages & backtraces for filesystem
195 shutdowns, for example. Current threshold values are:
196
197 XFS_ERRLEVEL_OFF: 0
198 XFS_ERRLEVEL_LOW: 1
199 XFS_ERRLEVEL_HIGH: 5
200
201 fs.xfs.panic_mask (Min: 0 Default: 0 Max: 127)
202 Causes certain error conditions to call BUG(). Value is a bitmask;
203 AND together the tags which represent errors which should cause panics:
204
205 XFS_NO_PTAG 0
206 XFS_PTAG_IFLUSH 0x00000001
207 XFS_PTAG_LOGRES 0x00000002
208 XFS_PTAG_AILDELETE 0x00000004
209 XFS_PTAG_ERROR_REPORT 0x00000008
210 XFS_PTAG_SHUTDOWN_CORRUPT 0x00000010
211 XFS_PTAG_SHUTDOWN_IOERROR 0x00000020
212 XFS_PTAG_SHUTDOWN_LOGERROR 0x00000040
213
214 This option is intended for debugging only.
215
216 fs.xfs.irix_symlink_mode (Min: 0 Default: 0 Max: 1)
217 Controls whether symlinks are created with mode 0777 (default)
218 or whether their mode is affected by the umask (irix mode).
219
220 fs.xfs.irix_sgid_inherit (Min: 0 Default: 0 Max: 1)
221 Controls files created in SGID directories.
222 If the group ID of the new file does not match the effective group
223 ID or one of the supplementary group IDs of the parent dir, the
224 ISGID bit is cleared if the irix_sgid_inherit compatibility sysctl
225 is set.
226
227 fs.xfs.inherit_sync (Min: 0 Default: 1 Max: 1)
228 Setting this to "1" will cause the "sync" flag set
229 by the xfs_io(8) chattr command on a directory to be
230 inherited by files in that directory.
231
232 fs.xfs.inherit_nodump (Min: 0 Default: 1 Max: 1)
233 Setting this to "1" will cause the "nodump" flag set
234 by the xfs_io(8) chattr command on a directory to be
235 inherited by files in that directory.
236
237 fs.xfs.inherit_noatime (Min: 0 Default: 1 Max: 1)
238 Setting this to "1" will cause the "noatime" flag set
239 by the xfs_io(8) chattr command on a directory to be
240 inherited by files in that directory.
241
242 fs.xfs.inherit_nosymlinks (Min: 0 Default: 1 Max: 1)
243 Setting this to "1" will cause the "nosymlinks" flag set
244 by the xfs_io(8) chattr command on a directory to be
245 inherited by files in that directory.
246
247 fs.xfs.rotorstep (Min: 1 Default: 1 Max: 256)
248 In "inode32" allocation mode, this option determines how many
249 files the allocator attempts to allocate in the same allocation
250 group before moving to the next allocation group. The intent
251 is to control the rate at which the allocator moves between
252 allocation groups when allocating extents for new files.
1
2The SGI XFS Filesystem
3======================
4
5XFS is a high performance journaling filesystem which originated
6on the SGI IRIX platform. It is completely multi-threaded, can
7support large files and large filesystems, extended attributes,
8variable block sizes, is extent based, and makes extensive use of
9Btrees (directories, extents, free space) to aid both performance
10and scalability.
11
12Refer to the documentation at http://oss.sgi.com/projects/xfs/
13for further details. This implementation is on-disk compatible
14with the IRIX version of XFS.
15
16
17Mount Options
18=============
19
20When mounting an XFS filesystem, the following options are accepted.
21For boolean mount options, the names with the (*) suffix is the
22default behaviour.
23
24 allocsize=size
25 Sets the buffered I/O end-of-file preallocation size when
26 doing delayed allocation writeout (default size is 64KiB).
27 Valid values for this option are page size (typically 4KiB)
28 through to 1GiB, inclusive, in power-of-2 increments.
29
30 The default behaviour is for dynamic end-of-file
31 preallocation size, which uses a set of heuristics to
32 optimise the preallocation size based on the current
33 allocation patterns within the file and the access patterns
34 to the file. Specifying a fixed allocsize value turns off
35 the dynamic behaviour.
36
37 attr2
38 noattr2
39 The options enable/disable an "opportunistic" improvement to
40 be made in the way inline extended attributes are stored
41 on-disk. When the new form is used for the first time when
42 attr2 is selected (either when setting or removing extended
43 attributes) the on-disk superblock feature bit field will be
44 updated to reflect this format being in use.
45
46 The default behaviour is determined by the on-disk feature
47 bit indicating that attr2 behaviour is active. If either
48 mount option it set, then that becomes the new default used
49 by the filesystem.
50
51 CRC enabled filesystems always use the attr2 format, and so
52 will reject the noattr2 mount option if it is set.
53
54 barrier (*)
55 nobarrier
56 Enables/disables the use of block layer write barriers for
57 writes into the journal and for data integrity operations.
58 This allows for drive level write caching to be enabled, for
59 devices that support write barriers.
60
61 discard
62 nodiscard (*)
63 Enable/disable the issuing of commands to let the block
64 device reclaim space freed by the filesystem. This is
65 useful for SSD devices, thinly provisioned LUNs and virtual
66 machine images, but may have a performance impact.
67
68 Note: It is currently recommended that you use the fstrim
69 application to discard unused blocks rather than the discard
70 mount option because the performance impact of this option
71 is quite severe.
72
73 grpid/bsdgroups
74 nogrpid/sysvgroups (*)
75 These options define what group ID a newly created file
76 gets. When grpid is set, it takes the group ID of the
77 directory in which it is created; otherwise it takes the
78 fsgid of the current process, unless the directory has the
79 setgid bit set, in which case it takes the gid from the
80 parent directory, and also gets the setgid bit set if it is
81 a directory itself.
82
83 filestreams
84 Make the data allocator use the filestreams allocation mode
85 across the entire filesystem rather than just on directories
86 configured to use it.
87
88 ikeep
89 noikeep (*)
90 When ikeep is specified, XFS does not delete empty inode
91 clusters and keeps them around on disk. When noikeep is
92 specified, empty inode clusters are returned to the free
93 space pool.
94
95 inode32
96 inode64 (*)
97 When inode32 is specified, it indicates that XFS limits
98 inode creation to locations which will not result in inode
99 numbers with more than 32 bits of significance.
100
101 When inode64 is specified, it indicates that XFS is allowed
102 to create inodes at any location in the filesystem,
103 including those which will result in inode numbers occupying
104 more than 32 bits of significance.
105
106 inode32 is provided for backwards compatibility with older
107 systems and applications, since 64 bits inode numbers might
108 cause problems for some applications that cannot handle
109 large inode numbers. If applications are in use which do
110 not handle inode numbers bigger than 32 bits, the inode32
111 option should be specified.
112
113
114 largeio
115 nolargeio (*)
116 If "nolargeio" is specified, the optimal I/O reported in
117 st_blksize by stat(2) will be as small as possible to allow
118 user applications to avoid inefficient read/modify/write
119 I/O. This is typically the page size of the machine, as
120 this is the granularity of the page cache.
121
122 If "largeio" specified, a filesystem that was created with a
123 "swidth" specified will return the "swidth" value (in bytes)
124 in st_blksize. If the filesystem does not have a "swidth"
125 specified but does specify an "allocsize" then "allocsize"
126 (in bytes) will be returned instead. Otherwise the behaviour
127 is the same as if "nolargeio" was specified.
128
129 logbufs=value
130 Set the number of in-memory log buffers. Valid numbers
131 range from 2-8 inclusive.
132
133 The default value is 8 buffers.
134
135 If the memory cost of 8 log buffers is too high on small
136 systems, then it may be reduced at some cost to performance
137 on metadata intensive workloads. The logbsize option below
138 controls the size of each buffer and so is also relevant to
139 this case.
140
141 logbsize=value
142 Set the size of each in-memory log buffer. The size may be
143 specified in bytes, or in kilobytes with a "k" suffix.
144 Valid sizes for version 1 and version 2 logs are 16384 (16k)
145 and 32768 (32k). Valid sizes for version 2 logs also
146 include 65536 (64k), 131072 (128k) and 262144 (256k). The
147 logbsize must be an integer multiple of the log
148 stripe unit configured at mkfs time.
149
150 The default value for for version 1 logs is 32768, while the
151 default value for version 2 logs is MAX(32768, log_sunit).
152
153 logdev=device and rtdev=device
154 Use an external log (metadata journal) and/or real-time device.
155 An XFS filesystem has up to three parts: a data section, a log
156 section, and a real-time section. The real-time section is
157 optional, and the log section can be separate from the data
158 section or contained within it.
159
160 noalign
161 Data allocations will not be aligned at stripe unit
162 boundaries. This is only relevant to filesystems created
163 with non-zero data alignment parameters (sunit, swidth) by
164 mkfs.
165
166 norecovery
167 The filesystem will be mounted without running log recovery.
168 If the filesystem was not cleanly unmounted, it is likely to
169 be inconsistent when mounted in "norecovery" mode.
170 Some files or directories may not be accessible because of this.
171 Filesystems mounted "norecovery" must be mounted read-only or
172 the mount will fail.
173
174 nouuid
175 Don't check for double mounted file systems using the file
176 system uuid. This is useful to mount LVM snapshot volumes,
177 and often used in combination with "norecovery" for mounting
178 read-only snapshots.
179
180 noquota
181 Forcibly turns off all quota accounting and enforcement
182 within the filesystem.
183
184 uquota/usrquota/uqnoenforce/quota
185 User disk quota accounting enabled, and limits (optionally)
186 enforced. Refer to xfs_quota(8) for further details.
187
188 gquota/grpquota/gqnoenforce
189 Group disk quota accounting enabled and limits (optionally)
190 enforced. Refer to xfs_quota(8) for further details.
191
192 pquota/prjquota/pqnoenforce
193 Project disk quota accounting enabled and limits (optionally)
194 enforced. Refer to xfs_quota(8) for further details.
195
196 sunit=value and swidth=value
197 Used to specify the stripe unit and width for a RAID device
198 or a stripe volume. "value" must be specified in 512-byte
199 block units. These options are only relevant to filesystems
200 that were created with non-zero data alignment parameters.
201
202 The sunit and swidth parameters specified must be compatible
203 with the existing filesystem alignment characteristics. In
204 general, that means the only valid changes to sunit are
205 increasing it by a power-of-2 multiple. Valid swidth values
206 are any integer multiple of a valid sunit value.
207
208 Typically the only time these mount options are necessary if
209 after an underlying RAID device has had it's geometry
210 modified, such as adding a new disk to a RAID5 lun and
211 reshaping it.
212
213 swalloc
214 Data allocations will be rounded up to stripe width boundaries
215 when the current end of file is being extended and the file
216 size is larger than the stripe width size.
217
218 wsync
219 When specified, all filesystem namespace operations are
220 executed synchronously. This ensures that when the namespace
221 operation (create, unlink, etc) completes, the change to the
222 namespace is on stable storage. This is useful in HA setups
223 where failover must not result in clients seeing
224 inconsistent namespace presentation during or after a
225 failover event.
226
227
228Deprecated Mount Options
229========================
230
231None at present.
232
233
234Removed Mount Options
235=====================
236
237 Name Removed
238 ---- -------
239 delaylog/nodelaylog v4.0
240 ihashsize v4.0
241 irixsgid v4.0
242 osyncisdsync/osyncisosync v4.0
243
244
245sysctls
246=======
247
248The following sysctls are available for the XFS filesystem:
249
250 fs.xfs.stats_clear (Min: 0 Default: 0 Max: 1)
251 Setting this to "1" clears accumulated XFS statistics
252 in /proc/fs/xfs/stat. It then immediately resets to "0".
253
254 fs.xfs.xfssyncd_centisecs (Min: 100 Default: 3000 Max: 720000)
255 The interval at which the filesystem flushes metadata
256 out to disk and runs internal cache cleanup routines.
257
258 fs.xfs.filestream_centisecs (Min: 1 Default: 3000 Max: 360000)
259 The interval at which the filesystem ages filestreams cache
260 references and returns timed-out AGs back to the free stream
261 pool.
262
263 fs.xfs.speculative_prealloc_lifetime
264 (Units: seconds Min: 1 Default: 300 Max: 86400)
265 The interval at which the background scanning for inodes
266 with unused speculative preallocation runs. The scan
267 removes unused preallocation from clean inodes and releases
268 the unused space back to the free pool.
269
270 fs.xfs.error_level (Min: 0 Default: 3 Max: 11)
271 A volume knob for error reporting when internal errors occur.
272 This will generate detailed messages & backtraces for filesystem
273 shutdowns, for example. Current threshold values are:
274
275 XFS_ERRLEVEL_OFF: 0
276 XFS_ERRLEVEL_LOW: 1
277 XFS_ERRLEVEL_HIGH: 5
278
279 fs.xfs.panic_mask (Min: 0 Default: 0 Max: 255)
280 Causes certain error conditions to call BUG(). Value is a bitmask;
281 OR together the tags which represent errors which should cause panics:
282
283 XFS_NO_PTAG 0
284 XFS_PTAG_IFLUSH 0x00000001
285 XFS_PTAG_LOGRES 0x00000002
286 XFS_PTAG_AILDELETE 0x00000004
287 XFS_PTAG_ERROR_REPORT 0x00000008
288 XFS_PTAG_SHUTDOWN_CORRUPT 0x00000010
289 XFS_PTAG_SHUTDOWN_IOERROR 0x00000020
290 XFS_PTAG_SHUTDOWN_LOGERROR 0x00000040
291 XFS_PTAG_FSBLOCK_ZERO 0x00000080
292
293 This option is intended for debugging only.
294
295 fs.xfs.irix_symlink_mode (Min: 0 Default: 0 Max: 1)
296 Controls whether symlinks are created with mode 0777 (default)
297 or whether their mode is affected by the umask (irix mode).
298
299 fs.xfs.irix_sgid_inherit (Min: 0 Default: 0 Max: 1)
300 Controls files created in SGID directories.
301 If the group ID of the new file does not match the effective group
302 ID or one of the supplementary group IDs of the parent dir, the
303 ISGID bit is cleared if the irix_sgid_inherit compatibility sysctl
304 is set.
305
306 fs.xfs.inherit_sync (Min: 0 Default: 1 Max: 1)
307 Setting this to "1" will cause the "sync" flag set
308 by the xfs_io(8) chattr command on a directory to be
309 inherited by files in that directory.
310
311 fs.xfs.inherit_nodump (Min: 0 Default: 1 Max: 1)
312 Setting this to "1" will cause the "nodump" flag set
313 by the xfs_io(8) chattr command on a directory to be
314 inherited by files in that directory.
315
316 fs.xfs.inherit_noatime (Min: 0 Default: 1 Max: 1)
317 Setting this to "1" will cause the "noatime" flag set
318 by the xfs_io(8) chattr command on a directory to be
319 inherited by files in that directory.
320
321 fs.xfs.inherit_nosymlinks (Min: 0 Default: 1 Max: 1)
322 Setting this to "1" will cause the "nosymlinks" flag set
323 by the xfs_io(8) chattr command on a directory to be
324 inherited by files in that directory.
325
326 fs.xfs.inherit_nodefrag (Min: 0 Default: 1 Max: 1)
327 Setting this to "1" will cause the "nodefrag" flag set
328 by the xfs_io(8) chattr command on a directory to be
329 inherited by files in that directory.
330
331 fs.xfs.rotorstep (Min: 1 Default: 1 Max: 256)
332 In "inode32" allocation mode, this option determines how many
333 files the allocator attempts to allocate in the same allocation
334 group before moving to the next allocation group. The intent
335 is to control the rate at which the allocator moves between
336 allocation groups when allocating extents for new files.
337
338Deprecated Sysctls
339==================
340
341None at present.
342
343
344Removed Sysctls
345===============
346
347 Name Removed
348 ---- -------
349 fs.xfs.xfsbufd_centisec v4.0
350 fs.xfs.age_buffer_centisecs v4.0