1xfs_io(8) System Manager's Manual xfs_io(8)
2
6 xfs_io - debug the I/O path of an XFS filesystem
7
9 xfs_io [ -adfimrRstxT ] [ -c cmd ] ... [ -C cmd ] ... [ -p prog ] [
10 file ]
11 xfs_io -V
12
14 xfs_io is a debugging tool like xfs_db(8), but is aimed at examining
15 the regular file I/O paths rather than the raw XFS volume itself.
16 These code paths include not only the obvious read/write/mmap inter‐
17 faces for manipulating files, but also cover all of the XFS extensions
18 (such as space preallocation, additional inode flags, etc).
19
21 xfs_io commands may be run interactively (the default) or as arguments
22 on the command line. Interactive mode always runs commands on the cur‐
23 rent open file, whilst commands run from the command line may be re‐
24 peated on all open files rather than just the current open file. In
25 general, open file iteration will occur for commands that operate on
26 file content or state. In contrast, commands that operate on filesystem
27 or system-wide state will only be run on the current file regardless of
28 how many files are currently open. Multiple arguments may be given on
29 the command line and they are run in the sequence given. The program
30 exits one all commands have been run.
31 -c cmd Run the specified command on all currently open files. To
33 maintain compatibility with historical usage, commands that
34 can not be run on all open files will still be run but only
35 execute once on the current open file. Multiple -c arguments
36 may be given and may be interleaved on the command line in
37 any order with -C commands.
38 -C cmd Run the specified command only on the current open file.
40 Multiple -C arguments may be given and may be interleaved on
41 the command line in any order with -c commands.
42 -p prog Set the program name for prompts and some error messages, the
44 default value is xfs_io.
45 -f Create file if it does not already exist.
47 -r Open file read-only, initially. This is required if file is
49 immutable or append-only.
50 -i Start an idle thread. The purpose of this idle thread is to
52 test io from a multi threaded process. With single threaded
53 process, the file table is not shared and file structs are
54 not reference counted. Spawning an idle thread can help de‐
55 tecting file struct reference leaks.
56 -x Expert mode. Dangerous commands are only available in this
58 mode. These commands also tend to require additional privi‐
59 leges.
60 -V Prints the version number and exits.
62 The other open(2) options described below are also available from the
64 command line.
65
67 xfs_io maintains a number of open files and memory mappings. Files can
68 be initially opened on the command line (optionally), and additional
69 files can also be opened later.
70 xfs_io commands can be broken up into three groups. Some commands are
72 aimed at doing regular file I/O - read, write, sync, space prealloca‐
73 tion, etc.
74 The second set of commands exist for manipulating memory mapped regions
76 of a file - mapping, accessing, storing, unmapping, flushing, etc.
77 The remaining commands are for the navigation and display of data
79 structures relating to the open files, mappings, and the filesystems
80 where they reside.
81 Many commands have extensive online help. Use the help command for more
83 details on any command.
84
86 file [ N ]
87 Display a list of all open files and (optionally) switch to an
88 alternate current open file.
89 open [[ -acdfrstRTPL ] path ]
91 Closes the current file, and opens the file specified by path
92 instead. Without any arguments, displays statistics about the
93 current file - see the stat command.
94 -a opens append-only (O_APPEND).
95 -d opens for direct I/O (O_DIRECT).
96 -f creates the file if it doesn't already exist (O_CREAT).
97 -r opens read-only (O_RDONLY).
98 -s opens for synchronous I/O (O_SYNC).
99 -t truncates on open (O_TRUNC).
100 -n opens in non-blocking mode if possible (O_NONBLOCK).
101 -T create a temporary file not linked into the filesystem
102 namespace (O_TMPFILE). The pathname passed must refer to
103 a directory which is treated as virtual parent for the
104 newly created invisible file. Can not be used together
105 with the -r option.
106 -R marks the file as a realtime XFS file after opening it,
107 if it is not already marked as such.
108 -P opens the path as a referent only (O_PATH). This is in‐
109 compatible with other flags specifying other O_xxx flags
110 apart from -L.
111 -L doesn't follow symlinks (O_NOFOLLOW). This is incompati‐
112 ble with other flags specifying other O_xxx flags apart
113 from -P.
114 o See the open command.
116 close Closes the current open file, marking the next open file as cur‐
118 rent (if one exists).
119 c See the close command.
121 chmod -r | -w
123 Change the mode of the currently open file. The -r option will
124 set the file permissions to read-only (0444), whilst the -w op‐
125 tion will set the file permissions to read-write (0644). This
126 allows xfs_io to set up mismatches between the file permissions
127 and the open file descriptor read/write mode to exercise permis‐
128 sion checks inside various syscalls.
129 pread [ -b bsize ] [ -qv ] [ -FBR [ -Z seed ] ] [ -V vectors ] offset
131 length
132 Reads a range of bytes in a specified blocksize from the given
133 offset.
134 -b can be used to set the blocksize into which the read(2)
135 requests will be split. The default blocksize is 4096
136 bytes.
137 -q quiet mode, do not write anything to standard output.
138 -v dump the contents of the buffer after reading, by default
139 only the count of bytes actually read is dumped.
140 -F read the buffers in a forward sequential direction.
141 -B read the buffers in a reverse sequential direction.
142 -R read the buffers in the give range in a random order.
143 -Z seed
144 specify the random number seed used for random reads.
145 -V vectors
146 Use the vectored IO read syscall preadv(2) with a number
147 of blocksize length iovecs. The number of iovecs is set
148 by the vectors parameter.
149 r See the pread command.
151 pwrite [ -i file ] [ -qdDwNOW ] [ -s skip ] [ -b size ] [ -S seed ] [
153 -FBR [ -Z zeed ] ] [ -V vectors ] offset length
154 Writes a range of bytes in a specified blocksize from the given
155 offset. The bytes written can be either a set pattern or read
156 in from another file before writing.
157 -i allows an input file to be specified as the source of the
158 data to be written.
159 -q quiet mode, do not write anything to standard output.
160 -d causes direct I/O, rather than the usual buffered I/O, to
161 be used when reading the input file.
162 -w call fdatasync(2) once all writes are complete (included
163 in timing results)
164 -N Perform the pwritev2(2) call with RWF_NOWAIT.
165 -D Perform the pwritev2(2) call with RWF_DSYNC.
166 -O perform pwrite once and return the (maybe partial) bytes
167 written.
168 -W call fsync(2) once all writes are complete (included in
169 timing results)
170 -s specifies the number of bytes to skip from the start of
171 the input file before starting to read.
172 -b used to set the blocksize into which the write(2) re‐
173 quests will be split. The default blocksize is 4096
174 bytes.
175 -S used to set the (repeated) fill pattern which is used
176 when the data to write is not coming from a file. The
177 default buffer fill pattern value is 0xcdcdcdcd.
178 -F write the buffers in a forward sequential direction.
179 -B write the buffers in a reverse sequential direction.
180 -R write the buffers in the give range in a random order.
181 -Z seed
182 specify the random number seed used for random write
183 -V vectors
184 Use the vectored IO write syscall pwritev(2) with a num‐
185 ber of blocksize length iovecs. The number of iovecs is
186 set by the vectors parameter.
187 w See the pwrite command.
189 bmap [ -adelpv ] [ -n nx ]
191 Prints the block mapping for the current open file. Refer to the
192 xfs_bmap(8) manual page for complete documentation.
193 fiemap [ -alv ] [ -n nx ] [ offset [ len ]]
195 Prints the block mapping for the current open file using the
196 fiemap ioctl. Options behave as described in the xfs_bmap(8)
197 manual page.
198 Optionally, this command also supports passing the start offset
200 from where to begin the mapping and the length of that region.
201 The kernel will return any full extents which intersect with the
202 requested range, and the fiemap command will print them in their
203 entirety. If the requested range starts or ends in a hole,
204 fiemap will print the hole, truncated to the requested range.
205 extsize [ -R | -D ] [ value ]
207 Display and/or modify the preferred extent size used when allo‐
208 cating space for the currently open file. If the -R option is
209 specified, a recursive descent is performed for all directory
210 entries below the currently open file (-D can be used to re‐
211 strict the output to directories only). If the target file is a
212 directory, then the inherited extent size is set for that direc‐
213 tory (new files created in that directory inherit that extent
214 size). The value should be specified in bytes, or using one of
215 the usual units suffixes (k, m, g, b, etc). The extent size is
216 always reported in units of bytes.
217 cowextsize [ -R | -D ] [ value ]
219 Display and/or modify the preferred copy-on-write extent size
220 used when allocating space for the currently open file. If the
221 -R option is specified, a recursive descent is performed for all
222 directory entries below the currently open file (-D can be used
223 to restrict the output to directories only). If the target file
224 is a directory, then the inherited CoW extent size is set for
225 that directory (new files created in that directory inherit that
226 CoW extent size). The value should be specified in bytes, or
227 using one of the usual units suffixes (k, m, g, b, etc). The ex‐
228 tent size is always reported in units of bytes.
229 allocsp size 0
231 Sets the size of the file to size and zeroes any additional
232 space allocated using the XFS_IOC_ALLOCSP/XFS_IOC_FREESP system
233 call described in the xfsctl(3) manual page. allocsp and freesp
234 do exactly the same thing.
235 These commands are no longer supported as of Linux 5.17.
237 freesp size 0
239 See the allocsp command.
240 fadvise [ -r | -s | [[ -d | -n | -w ] offset length ]]
242 On platforms which support it, allows hints be given to the sys‐
243 tem regarding the expected I/O patterns on the file. The range
244 arguments are required by some advise commands ([*] below), and
245 the others must have no range arguments. With no arguments, the
246 POSIX_FADV_NORMAL advice is implied (default readahead).
247 -d the data will not be accessed again in the near future
248 (POSIX_FADV_DONTNEED[*]).
249 -n data will be accessed once and not be reused
250 (POSIX_FADV_NOREUSE[*]).
251 -r expect access to data in random order (POSIX_FADV_RAN‐
252 DOM), which sets readahead to zero.
253 -s expect access to data in sequential order (POSIX_FADV_SE‐
254 QUENTIAL), which doubles the default readahead on the
255 file.
256 -w advises the specified data will be needed again
257 (POSIX_FADV_WILLNEED[*]) which forces the maximum reada‐
258 head.
259 fdatasync
261 Calls fdatasync(2) to flush the file's in-core data to disk.
262 fsync Calls fsync(2) to flush all in-core file state to disk.
264 s See the fsync command.
266 sync_range [ -a | -b | -w ] offset length
268 On platforms which support it, allows control of syncing a range
269 of the file to disk. With no options, SYNC_FILE_RANGE_WRITE is
270 implied on the range supplied.
271 -a wait for IO in the given range to finish after writing
272 (SYNC_FILE_RANGE_WAIT_AFTER).
273 -b wait for IO in the given range to finish before writing
274 (SYNC_FILE_RANGE_WAIT_BEFORE).
275 -w start writeback of dirty data in the given range
276 (SYNC_FILE_RANGE_WRITE).
277 sync Calls sync(2) to flush all filesystems' in-core data to disk.
279 syncfs Calls syncfs(2) to flush this filesystem's in-core data to disk.
281 resvsp offset length
283 Allocates reserved, unwritten space for part of a file using the
284 XFS_IOC_RESVSP system call described in the xfsctl(3) manual
285 page.
286 unresvsp offset length
288 Frees reserved space for part of a file using the XFS_IOC_UN‐
289 RESVSP system call described in the xfsctl(3) manual page.
290 falloc [ -k ] offset length
292 Allocates reserved, unwritten space for part of a file using the
293 fallocate routine as described in the fallocate(2) manual page.
294 -k will set the FALLOC_FL_KEEP_SIZE flag as described in
295 fallocate(2).
296 fcollapse offset length
298 Call fallocate with FALLOC_FL_COLLAPSE_RANGE flag as described
299 in the fallocate(2) manual page to de-allocates blocks and elim‐
300 inates the hole created in this process by shifting data blocks
301 into the hole.
302 finsert offset length
304 Call fallocate with FALLOC_FL_INSERT_RANGE flag as described in
305 the fallocate(2) manual page to create the hole by shifting data
306 blocks.
307 fpunch offset length
309 Punches (de-allocates) blocks in the file by calling fallocate
310 with the FALLOC_FL_PUNCH_HOLE flag as described in the fallo‐
311 cate(2) manual page.
312 funshare offset length
314 Call fallocate with FALLOC_FL_UNSHARE_RANGE flag as described in
315 the fallocate(2) manual page to unshare all shared blocks within
316 the range.
317 fzero [ -k ] offset length
319 Call fallocate with FALLOC_FL_ZERO_RANGE flag as described in
320 the fallocate(2) manual page to allocate and zero blocks within
321 the range. With the -k option, use the FALLOC_FL_KEEP_SIZE flag
322 as well.
323 zero offset length
325 Call xfsctl with XFS_IOC_ZERO_RANGE as described in the xf‐
326 sctl(3) manual page to allocate and zero blocks within the
327 range.
328 truncate offset
330 Truncates the current file at the given offset using ftrun‐
331 cate(2).
332 sendfile [ -q ] -i srcfile | -f N [ offset length ]
334 On platforms which support it, allows a direct in-kernel copy
335 between two file descriptors. The current open file is the tar‐
336 get, the source must be specified as another open file (-f) or
337 by path (-i).
338 -q quiet mode, do not write anything to standard output.
339 readdir [ -v ] [ -o offset ] [ -l length ]
341 Read a range of directory entries from a given offset of a di‐
342 rectory.
343 -v verbose mode - dump dirent content as defined in read‐
344 dir(3)
345 -o specify starting offset
346 -l specify total length to read (in bytes)
347 seek -a | -d | -h [ -r ] [ -s ] offset
349 On platforms that support the lseek(2) SEEK_DATA and SEEK_HOLE
350 options, display the offsets of the specified segments.
351 -a Display both data and hole segments starting at the spec‐
352 ified offset.
353 -d Display the data segment starting at the specified off‐
354 set.
355 -h Display the hole segment starting at the specified off‐
356 set.
357 -r Recursively display all the specified segments starting
358 at the specified offset.
359 -s Display the starting lseek(2) offset. This offset will be
360 a calculated value when both data and holes are displayed
361 together or performing a recusively display.
362 reflink [ -C ] [ -q ] src_file [src_offset dst_offset length]
364 On filesystems that support the FICLONERANGE or
365 BTRFS_IOC_CLONE_RANGE ioctls, map length bytes at offset
366 dst_offset in the open file to the same physical blocks that are
367 mapped at offset src_offset in the file src_file , replacing any
368 contents that may already have been there. If a program writes
369 into a reflinked block range of either file, the dirty blocks
370 will be cloned, written to, and remapped ("copy on write") in
371 the affected file, leaving the other file(s) unchanged. If
372 src_offset, dst_offset, and length are omitted, all contents of
373 src_file will be reflinked into the open file.
374 -C Print timing statistics in a condensed format.
375 -q Do not print timing statistics at all.
376 dedupe [ -C ] [ -q ] src_file src_offset dst_offset length
378 On filesystems that support the FIDEDUPERANGE or
379 BTRFS_IOC_FILE_EXTENT_SAME ioctls, map length bytes at offset
380 dst_offset in the open file to the same physical blocks that are
381 mapped at offset src_offset in the file src_file , but only if
382 the contents of both ranges are identical. This is known as
383 block-based deduplication. If a program writes into a reflinked
384 block range of either file, the dirty blocks will be cloned,
385 written to, and remapped ("copy on write") in the affected file,
386 leaving the other file(s) unchanged.
387 -C Print timing statistics in a condensed format.
388 -q Do not print timing statistics at all.
389 copy_range [ -s src_offset ] [ -d dst_offset ] [ -l length ] src_file |
391 -f N
392 On filesystems that support the copy_file_range(2) system call,
393 copies data from the source file into the current open file.
394 The source must be specified either by path (src_file) or as an‐
395 other open file (-f). If length is not specified, this command
396 copies data from src_offset to the end of src_file into the
397 dst_file at dst_offset.
398 -s Copy data from src_file beginning from src_offset.
399 -d Copy data into the open file beginning at dst_offset.
400 -l Copy up to length bytes of data.
401 swapext donor_file
403 Swaps extent forks between files. The current open file is the
404 target. The donor file is specified by path. Note that file data
405 is not copied (file content moves with the fork(s)).
406 set_encpolicy [ -c mode ] [ -n mode ] [ -f flags ] [ -v version ] [
408 keyspec ]
409 On filesystems that support encryption, assign an encryption
410 policy to the current file. keyspec is a hex string which spec‐
411 ifies the encryption key to use. For v1 encryption policies,
412 keyspec must be a 16-character hex string (8 bytes). For v2
413 policies, keyspec must be a 32-character hex string (16 bytes).
414 If unspecified, an all-zeroes value is used.
415 -c mode
416 contents encryption mode (e.g. AES-256-XTS)
417 -n mode
418 filenames encryption mode (e.g. AES-256-CTS)
419 -f flags
420 policy flags (numeric)
421 -v version
422 policy version. Defaults to 1 or 2 depending on the
423 length of keyspec; or to 1 if keyspec is unspecified.
424 get_encpolicy [ -1 ] [ -t ]
426 On filesystems that support encryption, display the encryption
427 policy of the current file.
428 -1 Use only the old ioctl to get the encryption policy.
429 This only works if the file has a v1 encryption policy.
430 -t Test whether v2 encryption policies are supported.
431 Prints "supported", "unsupported", or an error message.
432 add_enckey [ -d descriptor ] [ -k key_id ]
434 On filesystems that support encryption, add an encryption key to
435 the filesystem containing the currently open file. By default,
436 the raw key in binary (typically 64 bytes long) is read from
437 standard input.
438 -d descriptor
439 key descriptor, as a 16-character hex string (8 bytes).
440 If given, the key will be available for use by v1 encryp‐
441 tion policies that use this descriptor. Otherwise, the
442 key is added as a v2 policy key, and on success the re‐
443 sulting "key identifier" will be printed.
444 -k key_id
445 ID of kernel keyring key of type "fscrypt-provisioning".
446 If given, the raw key will be taken from here rather than
447 from standard input.
448 rm_enckey [ -a ] keyspec
450 On filesystems that support encryption, remove an encryption key
451 from the filesystem containing the currently open file. keyspec
452 is a hex string specifying the key to remove, as a 16-character
453 "key descriptor" or a 32-character "key identifier".
454 -a Remove the key for all users who have added it, not just
455 the current user. This is a privileged operation.
456 enckey_status keyspec
458 On filesystems that support encryption, display the status of an
459 encryption key. keyspec is a hex string specifying the key for
460 which to display the status, as a 16-character "key descriptor"
461 or a 32-character "key identifier".
462 lsattr [ -R | -D | -a | -v ]
464 List extended inode flags on the currently open file. If the -R
465 option is specified, a recursive descent is performed for all
466 directory entries below the currently open file (-D can be used
467 to restrict the output to directories only). This is a depth
468 first descent, it does not follow symlinks and it also does not
469 cross mount points.
470 The current inode flag letters are documented below. Please re‐
472 fer to the ioctl_xfs_fsgetxattr(2) documentation for more de‐
473 tails about what they mean.
474 r realtime file (XFS_XFLAG_REALTIME)
476 p prealloc (XFS_XFLAG_PREALLOC)
478 i immutable (XFS_XFLAG_IMMUTABLE)
480 a append only (XFS_XFLAG_APPEND)
482 s synchronous file writes (XFS_XFLAG_SYNC)
484 A noatime (XFS_XFLAG_NOATIME)
486 d nodump (XFS_XFLAG_NODUMP)
488 t inherit realtime flag (XFS_XFLAG_RTINHERIT)"
490 P inherit project id (XFS_XFLAG_PROJINHERIT)
492 n no symlink creation (XFS_XFLAG_NOSYMLINKS)
494 e extent size hint (XFS_XFLAG_EXTSIZE)
496 E inherit extent size hint (XFS_XFLAG_EXTSZINHERIT)
498 f nodefrag (XFS_XFLAG_NODEFRAG)
500 S filestream allocator (XFS_XFLAG_FILESTREAM)
502 x direct access persistent memory (XFS_XFLAG_DAX)
504 C copy on write extent hint (XFS_XFLAG_COWEXTSIZE)
506 X has extended attributes (XFS_XFLAG_HASATTR)
508 chattr [ -R | -D ] [ +/-riasAdtPneEfSxC ]
510 Change extended inode flags on the currently open file. The -R
511 and -D options have the same meaning as above.
512 See the lsattr command above for the list of inode flag letters.
514 flink path
516 Link the currently open file descriptor into the filesystem
517 namespace.
518 stat [ -v|-r ]
519 Selected statistics from stat(2) and the XFS_IOC_GETXATTR system
520 call on the current file. If the -v option is specified, the
521 atime (last access), mtime (last modify), and ctime (last
522 change) timestamps are also displayed. The -r option dumps raw
523 fields from the stat structure.
524 statx [ -v|-r ][ -m basic | -m all | -m <mask> ][ -FD ]
525 Selected statistics from stat(2) and the XFS_IOC_GETXATTR system
526 call on the current file.
527 -v Show timestamps.
528 -r Dump raw statx structure values.
529 -m basic
530 Set the field mask for the statx call to STATX_BA‐
531 SIC_STATS.
532 -m all
533 Set the the field mask for the statx call to STATX_ALL
534 (default).
535 -m <mask>
536 Specify a numeric field mask for the statx call.
537 -F Force the attributes to be synced with the server.
538 -D Don't sync attributes with the server.
539 chproj [ -R|-D ]
541 Modifies the project identifier associated with the current
542 path. The -R option will recursively descend if the current path
543 is a directory. The -D option will also recursively descend,
544 only setting modifying projects on subdirectories. See the
545 xfs_quota(8) manual page for more information about project
546 identifiers.
547 lsproj [ -R|-D ]
549 Displays the project identifier associated with the current
550 path. The -R and -D options behave as described above, in ch‐
551 proj.
552 parent [ -cpv ]
554 By default this command prints out the parent inode numbers, in‐
555 ode generation numbers and basenames of all the hardlinks which
556 point to the inode of the current file.
557 -p the output is similar to the default output except path‐
558 names up to the mount-point are printed out instead of
559 the component name.
560 -c the file's filesystem will check all the parent at‐
561 tributes for consistency.
562 -v verbose output will be printed.
563 [NOTE: Not currently operational on Linux.]
564 utimes atime_sec atime_nsec mtime_sec mtime_nsec
566 The utimes command changes the atime and mtime of the current
567 file. sec uses UNIX timestamp notation and is the seconds
568 elapsed since 1970-01-01 00:00:00 UTC. nsec is the nanoseconds
569 since the sec. This value needs to be in the range 0-999999999
570 with UTIME_NOW and UTIME_OMIT being exceptions. Each (sec,
571 nsec) pair constitutes a single timestamp value.
572
576 mmap [ N | [[ -rwxS ] [-s size ] offset length ]]
577 With no arguments, mmap shows the current mappings. Specifying a
578 single numeric argument N sets the current mapping. If two argu‐
579 ments are specified (a range specified by offset and length), a
580 new mapping is created spanning the range, and the protection
581 mode can be given as a combination of PROT_READ (-r), PROT_WRITE
582 (-w), and PROT_EXEC (-x). The mapping will be created with the
583 MAP_SHARED flag by default, or with the Linux specific (MAP_SYNC
584 | MAP_SHARED_VALIDATE) flags if -S is given. -s size is used to
585 do a mmap(size) && munmap(size) operation at first, try to re‐
586 serve some extendible free memory space, if size is bigger than
587 length parameter. But there's not guarantee that the memory af‐
588 ter length ( up to size ) will stay free. e.g. "mmap -rw -s
589 8192 1024" will mmap 0 ~ 1024 bytes memory, but try to reserve
590 1024 ~ 8192 free space(no guarantee). This free space will help‐
591 ful for "mremap 8192" without MREMAP_MAYMOVE flag.
592 mm See the mmap command.
594 mremap [ -f <new_address> ] [ -m ] new_length
596 Changes the current mapping size to new_length. Whether the
597 mapping may be moved is controlled by the flags passed;
598 MREMAP_FIXED (-f), or MREMAP_MAYMOVE (-m). new_length specifies
599 a page-aligned address to which the mapping must be moved. It
600 can be set to 139946004389888, 4096k or 1g etc.
601 mrm See the mremap command.
603 munmap Unmaps the current memory mapping.
605 mu See the munmap command.
607 mread [ -f | -v ] [ -r ] [ offset length ]
609 Accesses a segment of the current memory mapping, optionally
610 dumping it to the standard output stream (with -v or -f option)
611 for inspection. The accesses are performed sequentially from the
612 start offset by default, but can also be done from the end back‐
613 wards through the mapping if the -r option in specified. The
614 two verbose modes differ only in the relative offsets they dis‐
615 play, the -f option is relative to file start, whereas -v shows
616 offsets relative to the start of the mapping.
617 mr See the mread command.
619 mwrite [ -r ] [ -S seed ] [ offset length ]
621 Stores a byte into memory for a range within a mapping. The de‐
622 fault stored value is 'X', repeated to fill the range specified,
623 but this can be changed using the -S option. The memory stores
624 are performed sequentially from the start offset by default, but
625 can also be done from the end backwards through the mapping if
626 the -r option in specified.
627 mw See the mwrite command.
629 msync [ -i ] [ -a | -s ] [ offset length ]
631 Writes all modified copies of pages over the specified range (or
632 entire mapping if no range specified) to their backing storage
633 locations. Also, optionally invalidates (-i) so that subsequent
634 references to the pages will be obtained from their backing
635 storage locations (instead of cached copies). The flush can be
636 done synchronously (-s) or asynchronously (-a).
637 ms See the msync command.
639 madvise [ -d | -r | -s | -w ] [ offset length ]
641 Modifies page cache behavior when operating on the current map‐
642 ping. The range arguments are required by some advise commands
643 ([*] below). With no arguments, the POSIX_MADV_NORMAL advice is
644 implied (default readahead).
645 -d the pages will not be needed (POSIX_MADV_DONTNEED[*]).
646 -r expect random page references (POSIX_MADV_RANDOM), which
647 sets readahead to zero.
648 -s expect sequential page references (POSIX_MADV_SEQUEN‐
649 TIAL), which doubles the default readahead on the file.
650 -w advises the specified pages will be needed again
651 (POSIX_MADV_WILLNEED[*]) which forces the maximum reada‐
652 head.
653 mincore
655 Dumps a list of pages or ranges of pages that are currently in
656 core, for the current memory mapping.
657
660 bulkstat [ -a agno ] [ -d ] [ -e endino ] [ -n batchsize ] [ -q ] [ -s
661 startino ] [ -v version"]
662 Display raw stat information about a bunch of inodes in an XFS
663 filesystem. Options are as follows:
664 -a agno
665 Display only results from the given allocation group.
666 If not specified, all results returned will be dis‐
667 played.
668 -d Print debugging information about call results.
669 -e endino
670 Stop displaying records when this inode number is
671 reached. Defaults to stopping when the system call
672 stops returning results.
673 -n batchsize
674 Retrieve at most this many records per call. Defaults
675 to 4,096.
676 -q Run quietly. Does not parse or output retrieved bulk‐
677 stat information.
678 -s startino
679 Display inode allocation records starting with this
680 inode. Defaults to the first inode in the filesystem.
681 If the given inode is not allocated, results will be‐
682 gin with the next allocated inode in the filesystem.
683 -v version
684 Use a particular version of the kernel interface.
685 Currently supported versions are 1 and 5.
686 bulkstat_single [ -d ] [ -v version ] [ inum... | special... ]
688 Display raw stat information about individual inodes in an XFS
689 filesystem. The -d and -v options are the same as the bulkstat
690 command. Arguments must be inode numbers or any of the special
691 values:
692 root Display information about the root directory inode.
693 freeze Suspend all write I/O requests to the filesystem of the current
695 file. Only available in expert mode and requires privileges.
696 thaw Undo the effects of a filesystem freeze operation. Only avail‐
698 able in expert mode and requires privileges.
699 inject [ tag ]
701 Inject errors into a filesystem to observe filesystem behavior
702 at specific points under adverse conditions. Without the tag ar‐
703 gument, displays the list of error tags available. Only avail‐
704 able in expert mode and requires privileges.
705 resblks [ blocks ]
707 Get and/or set count of reserved filesystem blocks using the
708 XFS_IOC_GET_RESBLKS or XFS_IOC_SET_RESBLKS system calls. Note
709 -- this can be useful for exercising out of space behavior.
710 Only available in expert mode and requires privileges.
711 shutdown [ -f ]
713 Force the filesystem to shut down, preventing any further IO.
714 XFS and other filesystems implement this functionality, although
715 implementation details may differ slightly. Only available in
716 expert mode and requires privileges.
717 By default, the filesystem will not attempt to flush completed
719 transactions to disk before shutting down the filesystem. This
720 simulates a disk failure or crash.
721 -f Force the filesystem to flush all completed transactions
722 to disk before shutting down, matching XFS behavior when
723 critical corruption is encountered.
724 statfs [ -c ] [ -g ] [ -s ]
726 Report selected statistics on the filesystem where the current
727 file resides. The default behavior is to enable all three re‐
728 porting options:
729 -c Display XFS_IOC_FSCOUNTERS summary counter data.
730 -g Display XFS_IOC_FSGEOMETRY filesystem geometry data.
731 -s Display statfs(2) data.
732 inode [ [ -n ] number ] [ -v ]
734 The inode command queries physical information about an inode.
735 With no arguments, it will return 1 or 0, indicating whether or
736 not any inode numbers greater than 32 bits are currently in use
737 in the filesystem. If given an inode number as an argument, the
738 command will return the same inode number if it is in use, or 0
739 if not. With -n number , the next used inode number after this
740 number will be returned, or zero if the supplied inode number is
741 the highest one in use. With -v the command will also report the
742 number of bits (32 or 64) used by the inode number printed in
743 the result; if no inode number was specified on the command
744 line, the maximum possible inode number in the system will be
745 printed along with its size.
746 inumbers [ -a agno ] [ -d ] [ -e endino ] [ -n batchsize ] [ -s
748 startino ] [ -v version ]
749 Prints allocation information about groups of inodes in an XFS
750 filesystem. Callers can use this information to figure out
751 which inodes are allocated. Options are as follows:
752 -a agno
753 Display only results from the given allocation group.
754 If not specified, all results returned will be dis‐
755 played.
756 -d Print debugging information about call results.
757 -e endino
758 Stop displaying records when this inode number is
759 reached. Defaults to stopping when the system call
760 stops returning results.
761 -n batchsize
762 Retrieve at most this many records per call. Defaults
763 to 4,096.
764 -s startino
765 Display inode allocation records starting with this
766 inode. Defaults to the first inode in the filesystem.
767 If the given inode is not allocated, results will be‐
768 gin with the next allocated inode in the filesystem.
769 -v version
770 Use a particular version of the kernel interface.
771 Currently supported versions are 1 and 5.
772 scrub type [ agnumber | ino gen ]
774 Scrub internal XFS filesystem metadata. The type parameter
775 specifies which type of metadata to scrub. For AG metadata, one
776 AG number must be specified. For file metadata, the scrub is
777 applied to the open file unless the inode number and generation
778 number are specified.
779 repair type [ agnumber | ino gen ]
781 Repair internal XFS filesystem metadata. The type parameter
782 specifies which type of metadata to repair. For AG metadata,
783 one AG number must be specified. For file metadata, the repair
784 is applied to the open file unless the inode number and genera‐
785 tion number are specified.
786 label [ -c | -s label ]
788 On filesystems that support online label manipulation, get, set,
789 or clear the filesystem label. With no options, print the cur‐
790 rent filesystem label. The -c option clears the filesystem la‐
791 bel by setting it to the null string. The -s label option sets
792 the filesystem label to label. If the label is longer than the
793 filesystem will accept, xfs_io will print an error message. XFS
794 filesystem labels can be at most 12 characters long.
795 fsmap [ -d | -l | -r ] [ -m | -v ] [ -n nx ] [ start ] [ end ]
797 Prints the mapping of disk blocks used by the filesystem hosting
798 the current file. The map lists each extent used by files, al‐
799 location group metadata, journalling logs, and static filesystem
800 metadata, as well as any regions that are unused. Each line of
801 the listings takes the following form:
802 extent: major:minor [startblock..endblock]: owner startoff‐
804 set..endoffset length
805 Static filesystem metadata, allocation group metadata, btrees,
807 journalling logs, and free space are marked by replacing the
808 startoffset..endoffset with the appropriate marker. All blocks,
809 offsets, and lengths are specified in units of 512-byte blocks,
810 no matter what the filesystem's block size is. The optional
811 start and end arguments can be used to constrain the output to a
812 particular range of disk blocks. If these two options are spec‐
813 ified, exactly one of -d, -l, or -r must also be set.
814 -d Display only extents from the data device. This op‐
815 tion only applies for XFS filesystems.
816 -l Display only extents from the external log device.
817 This option only applies to XFS filesystems.
818 -r Display only extents from the realtime device. This
819 option only applies to XFS filesystems.
820 -m Display results in a machine readable format (CSV).
821 This option is not compatible with the -v flag. The
822 columns of the output are: extent number, device ma‐
823 jor, device minor, physical start, physical end,
824 owner, offset start, offset end, length. The start,
825 end, and length numbers are provided in units of 512b.
826 The owner field is a special string that takes the
827 form:
828 inode_%lld_data
830 for inode data.
831 inode_%lld_data_bmbt
832 for inode data extent maps.
833 inode_%lld_attr
834 for inode extended attribute data.
835 inode_%lld_attr_bmbt
836 for inode extended attribute extent maps.
837 special_%u:%u
838 for other filesystem metadata.
839 -n num_extents
842 If this option is given, fsmap obtains the extent list
843 of the file in groups of num_extents extents. In the
844 absence of -n, fsmap queries the system for extents in
845 groups of 131,072 records.
846 -v Shows verbose information. When this flag is speci‐
848 fied, additional AG specific information is appended
849 to each line in the following form:
850 agno (startagblock..endagblock) nblocks flags
852 A second -v option will print out the flags legend.
854 This option is not compatible with the -m flag.
855
859 help [ command ]
860 Display a brief description of one or all commands.
861 print Display a list of all open files and memory mapped regions. The
863 current file and current mapping are distinguishable from any
864 others.
865 p See the print command.
867 quit Exit xfs_io.
869 q See the quit command.
871 log_writes -d device -m mark
873 Create a mark named mark in the dm-log-writes log specified by
874 device. This is intended to be equivalent to the shell command:
875 dmsetup message device 0 mark mark
877 lw See the log_writes command.
879 crc32cselftest
881 Test the internal crc32c implementation to make sure that it
882 computes results correctly.
883
885 mkfs.xfs(8), xfsctl(3), xfs_bmap(8), xfs_db(8), xfs(5), fdatasync(2),
886 fstat(2), fstatfs(2), fsync(2), ftruncate(2), futimens(3), mmap(2),
887 msync(2), open(2), pread(2), pwrite(2), readdir(3), dmsetup(8).
888 xfs_io(8)