1CEPH(8)                              Ceph                              CEPH(8)
2
3
4

NAME

6       ceph - ceph administration tool
7

SYNOPSIS

9       ceph auth [ add | caps | del | export | get | get-key | get-or-create | get-or-create-key | import | list | print-key | print_key ] ...
10
11       ceph compact
12
13       ceph config [ dump | ls | help | get | show | show-with-defaults | set | rm | log | reset | assimilate-conf | generate-minimal-conf ] ...
14
15       ceph config-key [ rm | exists | get | ls | dump | set ] ...
16
17       ceph daemon <name> | <path> <command> ...
18
19       ceph daemonperf <name> | <path> [ interval [ count ] ]
20
21       ceph df {detail}
22
23       ceph fs [ ls | new | reset | rm | authorize ] ...
24
25       ceph fsid
26
27       ceph health {detail}
28
29       ceph injectargs <injectedargs> [ <injectedargs>... ]
30
31       ceph log <logtext> [ <logtext>... ]
32
33       ceph mds [ compat | fail | rm | rmfailed | set_state | stat | repaired ] ...
34
35       ceph mon [ add | dump | getmap | remove | stat ] ...
36
37       ceph osd [ blocklist | blocked-by | create | new | deep-scrub | df | down | dump | erasure-code-profile | find | getcrushmap | getmap | getmaxosd | in | ls | lspools | map | metadata | ok-to-stop | out | pause | perf | pg-temp | force-create-pg | primary-affinity | primary-temp | repair | reweight | reweight-by-pg | rm | destroy | purge | safe-to-destroy | scrub | set | setcrushmap | setmaxosd  | stat | tree | unpause | unset ] ...
38
39       ceph osd crush [ add | add-bucket | create-or-move | dump | get-tunable | link | move | remove | rename-bucket | reweight | reweight-all | reweight-subtree | rm | rule | set | set-tunable | show-tunables | tunables | unlink ] ...
40
41       ceph osd pool [ create | delete | get | get-quota | ls | mksnap | rename | rmsnap | set | set-quota | stats ] ...
42
43       ceph osd pool application [ disable | enable | get | rm | set ] ...
44
45       ceph osd tier [ add | add-cache | cache-mode | remove | remove-overlay | set-overlay ] ...
46
47       ceph pg [ debug | deep-scrub | dump | dump_json | dump_pools_json | dump_stuck | getmap | ls | ls-by-osd | ls-by-pool | ls-by-primary | map | repair | scrub | stat ] ...
48
49       ceph quorum_status
50
51       ceph report { <tags> [ <tags>... ] }
52
53       ceph status
54
55       ceph sync force {--yes-i-really-mean-it} {--i-know-what-i-am-doing}
56
57       ceph tell <name (type.id)> <command> [options...]
58
59       ceph version
60
61

DESCRIPTION

63       ceph is a control utility which is used for manual deployment and main‐
64       tenance of a Ceph cluster. It provides a diverse set of  commands  that
65       allows  deployment of monitors, OSDs, placement groups, MDS and overall
66       maintenance, administration of the cluster.
67

COMMANDS

69   auth
70       Manage authentication keys. It is used for adding, removing,  exporting
71       or  updating  of authentication keys for a particular  entity such as a
72       monitor or OSD. It uses some additional subcommands.
73
74       Subcommand add adds authentication info for a  particular  entity  from
75       input  file,  or random key if no input is given and/or any caps speci‐
76       fied in the command.
77
78       Usage:
79
80          ceph auth add <entity> {<caps> [<caps>...]}
81
82       Subcommand caps updates caps for name from caps specified in  the  com‐
83       mand.
84
85       Usage:
86
87          ceph auth caps <entity> <caps> [<caps>...]
88
89       Subcommand del deletes all caps for name.
90
91       Usage:
92
93          ceph auth del <entity>
94
95       Subcommand  export  writes  keyring  for  requested  entity,  or master
96       keyring if none given.
97
98       Usage:
99
100          ceph auth export {<entity>}
101
102       Subcommand get writes keyring file with requested key.
103
104       Usage:
105
106          ceph auth get <entity>
107
108       Subcommand get-key displays requested key.
109
110       Usage:
111
112          ceph auth get-key <entity>
113
114       Subcommand get-or-create adds authentication info for a particular  en‐
115       tity  from  input file, or random key if no input given and/or any caps
116       specified in the command.
117
118       Usage:
119
120          ceph auth get-or-create <entity> {<caps> [<caps>...]}
121
122       Subcommand get-or-create-key gets or adds key for name from system/caps
123       pairs  specified in the command.  If key already exists, any given caps
124       must match the existing caps for that key.
125
126       Usage:
127
128          ceph auth get-or-create-key <entity> {<caps> [<caps>...]}
129
130       Subcommand import reads keyring from input file.
131
132       Usage:
133
134          ceph auth import
135
136       Subcommand ls lists authentication state.
137
138       Usage:
139
140          ceph auth ls
141
142       Subcommand print-key displays requested key.
143
144       Usage:
145
146          ceph auth print-key <entity>
147
148       Subcommand print_key displays requested key.
149
150       Usage:
151
152          ceph auth print_key <entity>
153
154   compact
155       Causes compaction of monitor's leveldb storage.
156
157       Usage:
158
159          ceph compact
160
161   config
162       Configure the cluster. By default, Ceph daemons  and  clients  retrieve
163       their  configuration  options from monitor when they start, and are up‐
164       dated if any of the tracked options is changed at  run  time.  It  uses
165       following additional subcommand.
166
167       Subcommand dump to dump all options for the cluster
168
169       Usage:
170
171          ceph config dump
172
173       Subcommand ls to list all option names for the cluster
174
175       Usage:
176
177          ceph config ls
178
179       Subcommand help to describe the specified configuration option
180
181       Usage:
182
183          ceph config help <option>
184
185       Subcommand get to dump the option(s) for the specified entity.
186
187       Usage:
188
189          ceph config get <who> {<option>}
190
191       Subcommand  show  to display the running configuration of the specified
192       entity. Please note, unlike get, which only shows the  options  managed
193       by  monitor,  show displays all the configurations being actively used.
194       These options are pulled from several sources, for instance,  the  com‐
195       piled-in default value, the monitor's configuration database, ceph.conf
196       file on the host. The options can even be overridden  at  runtime.  So,
197       there  is  chance  that the configuration options in the output of show
198       could be different from those in the output of get.
199
200       Usage:
201
202          ceph config show {<who>}
203
204       Subcommand show-with-defaults  to  display  the  running  configuration
205       along with the compiled-in defaults of the specified entity
206
207       Usage:
208
209          ceph config show {<who>}
210
211       Subcommand set to set an option for one or more specified entities
212
213       Usage:
214
215          ceph config set <who> <option> <value> {--force}
216
217       Subcommand rm to clear an option for one or more entities
218
219       Usage:
220
221          ceph config rm <who> <option>
222
223       Subcommand  log  to show recent history of config changes. If count op‐
224       tion is omitted it defeaults to 10.
225
226       Usage:
227
228          ceph config log {<count>}
229
230       Subcommand reset to revert configuration to  the  specified  historical
231       version
232
233       Usage:
234
235          ceph config reset <version>
236
237       Subcommand assimilate-conf to assimilate options from stdin, and return
238       a new, minimal conf file
239
240       Usage:
241
242          ceph config assimilate-conf -i <input-config-path> > <output-config-path>
243          ceph config assimilate-conf < <input-config-path>
244
245       Subcommand generate-minimal-conf to generate a minimal ceph.conf  file,
246       which can be used for bootstrapping a daemon or a client.
247
248       Usage:
249
250          ceph config generate-minimal-conf > <minimal-config-path>
251
252   config-key
253       Manage  configuration  key.  Config-key  is a general purpose key/value
254       service offered by the monitors. This service is mainly  used  by  Ceph
255       tools  and  daemons  for  persisting  various  settings.  Among  which,
256       ceph-mgr modules uses it for storing their options. It uses some  addi‐
257       tional subcommands.
258
259       Subcommand rm deletes configuration key.
260
261       Usage:
262
263          ceph config-key rm <key>
264
265       Subcommand exists checks for configuration keys existence.
266
267       Usage:
268
269          ceph config-key exists <key>
270
271       Subcommand get gets the configuration key.
272
273       Usage:
274
275          ceph config-key get <key>
276
277       Subcommand ls lists configuration keys.
278
279       Usage:
280
281          ceph config-key ls
282
283       Subcommand dump dumps configuration keys and values.
284
285       Usage:
286
287          ceph config-key dump
288
289       Subcommand set puts configuration key and value.
290
291       Usage:
292
293          ceph config-key set <key> {<val>}
294
295   daemon
296       Submit admin-socket commands.
297
298       Usage:
299
300          ceph daemon {daemon_name|socket_path} {command} ...
301
302       Example:
303
304          ceph daemon osd.0 help
305
306   daemonperf
307       Watch performance counters from a Ceph daemon.
308
309       Usage:
310
311          ceph daemonperf {daemon_name|socket_path} [{interval} [{count}]]
312
313   df
314       Show cluster's free space status.
315
316       Usage:
317
318          ceph df {detail}
319
320   features
321       Show  the  releases  and  features of all connected daemons and clients
322       connected to the cluster, along with the numbers of them in each bucket
323       grouped  by  the  corresponding features/releases. Each release of Ceph
324       supports a different set of features, expressed by  the  features  bit‐
325       mask. New cluster features require that clients support the feature, or
326       else they are not allowed to connect to these new features. As new fea‐
327       tures  or  capabilities are enabled after an upgrade, older clients are
328       prevented from connecting.
329
330       Usage:
331
332          ceph features
333
334   fs
335       Manage cephfs file systems. It uses some additional subcommands.
336
337       Subcommand ls to list file systems
338
339       Usage:
340
341          ceph fs ls
342
343       Subcommand new to make a new file system using named  pools  <metadata>
344       and <data>
345
346       Usage:
347
348          ceph fs new <fs_name> <metadata> <data>
349
350       Subcommand  reset  is  used for disaster recovery only: reset to a sin‐
351       gle-MDS map
352
353       Usage:
354
355          ceph fs reset <fs_name> {--yes-i-really-mean-it}
356
357       Subcommand rm to disable the named file system
358
359       Usage:
360
361          ceph fs rm <fs_name> {--yes-i-really-mean-it}
362
363       Subcommand authorize creates a new client that will be  authorized  for
364       the  given  path  in  <fs_name>. Pass / to authorize for the entire FS.
365       <perms> below can be r, rw or rwp.
366
367       Usage:
368
369          ceph fs authorize <fs_name> client.<client_id> <path> <perms> [<path> <perms>...]
370
371   fsid
372       Show cluster's FSID/UUID.
373
374       Usage:
375
376          ceph fsid
377
378   health
379       Show cluster's health.
380
381       Usage:
382
383          ceph health {detail}
384
385   heap
386       Show heap usage info (available only if compiled with tcmalloc)
387
388       Usage:
389
390          ceph tell <name (type.id)> heap dump|start_profiler|stop_profiler|stats
391
392       Subcommand release to make TCMalloc to releases  no-longer-used  memory
393       back to the kernel at once.
394
395       Usage:
396
397          ceph tell <name (type.id)> heap release
398
399       Subcommand  (get|set)_release_rate  get  or set the TCMalloc memory re‐
400       lease rate. TCMalloc releases no-longer-used memory back to the  kernel
401       gradually.  the  rate controls how quickly this happens.  Increase this
402       setting to make TCMalloc to return unused  memory  more  frequently.  0
403       means  never return memory to system, 1 means wait for 1000 pages after
404       releasing a page to system. It is 1.0 by default..
405
406       Usage:
407
408          ceph tell <name (type.id)> heap get_release_rate|set_release_rate {<val>}
409
410   injectargs
411       Inject configuration arguments into monitor.
412
413       Usage:
414
415          ceph injectargs <injected_args> [<injected_args>...]
416
417   log
418       Log supplied text to the monitor log.
419
420       Usage:
421
422          ceph log <logtext> [<logtext>...]
423
424   mds
425       Manage metadata server configuration and administration. It  uses  some
426       additional subcommands.
427
428       Subcommand  compat manages compatible features. It uses some additional
429       subcommands.
430
431       Subcommand rm_compat removes compatible feature.
432
433       Usage:
434
435          ceph mds compat rm_compat <int[0-]>
436
437       Subcommand rm_incompat removes incompatible feature.
438
439       Usage:
440
441          ceph mds compat rm_incompat <int[0-]>
442
443       Subcommand show shows mds compatibility settings.
444
445       Usage:
446
447          ceph mds compat show
448
449       Subcommand fail forces mds to status fail.
450
451       Usage:
452
453          ceph mds fail <role|gid>
454
455       Subcommand rm removes inactive mds.
456
457       Usage:
458
459          ceph mds rm <int[0-]> <name> (type.id)>
460
461       Subcommand rmfailed removes failed mds.
462
463       Usage:
464
465          ceph mds rmfailed <int[0-]>
466
467       Subcommand set_state sets mds state of <gid> to <numeric-state>.
468
469       Usage:
470
471          ceph mds set_state <int[0-]> <int[0-20]>
472
473       Subcommand stat shows MDS status.
474
475       Usage:
476
477          ceph mds stat
478
479       Subcommand repaired mark a damaged MDS rank as no longer damaged.
480
481       Usage:
482
483          ceph mds repaired <role>
484
485   mon
486       Manage monitor configuration and administration.  It  uses  some  addi‐
487       tional subcommands.
488
489       Subcommand add adds new monitor named <name> at <addr>.
490
491       Usage:
492
493          ceph mon add <name> <IPaddr[:port]>
494
495       Subcommand dump dumps formatted monmap (optionally from epoch)
496
497       Usage:
498
499          ceph mon dump {<int[0-]>}
500
501       Subcommand getmap gets monmap.
502
503       Usage:
504
505          ceph mon getmap {<int[0-]>}
506
507       Subcommand remove removes monitor named <name>.
508
509       Usage:
510
511          ceph mon remove <name>
512
513       Subcommand stat summarizes monitor status.
514
515       Usage:
516
517          ceph mon stat
518
519   mgr
520       Ceph manager daemon configuration and management.
521
522       Subcommand dump dumps the latest MgrMap, which describes the active and
523       standby manager daemons.
524
525       Usage:
526
527          ceph mgr dump
528
529       Subcommand fail will mark a manager daemon as failed, removing it  from
530       the  manager  map.   If  it is the active manager daemon a standby will
531       take its place.
532
533       Usage:
534
535          ceph mgr fail <name>
536
537       Subcommand module ls will list currently enabled manager modules (plug‐
538       ins).
539
540       Usage:
541
542          ceph mgr module ls
543
544       Subcommand  module enable will enable a manager module.  Available mod‐
545       ules are included in MgrMap and visible via mgr dump.
546
547       Usage:
548
549          ceph mgr module enable <module>
550
551       Subcommand module disable will disable an active manager module.
552
553       Usage:
554
555          ceph mgr module disable <module>
556
557       Subcommand metadata will report metadata about all manager daemons  or,
558       if the name is specified, a single manager daemon.
559
560       Usage:
561
562          ceph mgr metadata [name]
563
564       Subcommand versions will report a count of running daemon versions.
565
566       Usage:
567
568          ceph mgr versions
569
570       Subcommand  count-metadata  will  report a count of any daemon metadata
571       field.
572
573       Usage:
574
575          ceph mgr count-metadata <field>
576
577   osd
578       Manage OSD configuration and administration. It  uses  some  additional
579       subcommands.
580
581       Subcommand  blocklist  manage  blocklisted  clients. It uses some addi‐
582       tional subcommands.
583
584       Subcommand add add <addr> to blocklist (optionally until <expire>  sec‐
585       onds from now)
586
587       Usage:
588
589          ceph osd blocklist add <EntityAddr> {<float[0.0-]>}
590
591       Subcommand ls show blocklisted clients
592
593       Usage:
594
595          ceph osd blocklist ls
596
597       Subcommand rm remove <addr> from blocklist
598
599       Usage:
600
601          ceph osd blocklist rm <EntityAddr>
602
603       Subcommand  blocked-by  prints  a  histogram of which OSDs are blocking
604       their peers
605
606       Usage:
607
608          ceph osd blocked-by
609
610       Subcommand create creates new osd (with optional UUID and ID).
611
612       This command is DEPRECATED as of the Luminous release, and will be  re‐
613       moved in a future release.
614
615       Subcommand new should instead be used.
616
617       Usage:
618
619          ceph osd create {<uuid>} {<id>}
620
621       Subcommand  new can be used to create a new OSD or to recreate a previ‐
622       ously destroyed OSD with a specific id. The new OSD will have the spec‐
623       ified  uuid,  and the command expects a JSON file containing the base64
624       cephx key for auth entity client.osd.<id>, as well as  optional  base64
625       cepx  key  for dm-crypt lockbox access and a dm-crypt key. Specifying a
626       dm-crypt requires specifying the accompanying lockbox cephx key.
627
628       Usage:
629
630          ceph osd new {<uuid>} {<id>} -i {<params.json>}
631
632       The parameters JSON file is optional but if provided,  is  expected  to
633       maintain a form of the following format:
634
635          {
636              "cephx_secret": "AQBWtwhZdBO5ExAAIDyjK2Bh16ZXylmzgYYEjg==",
637              "crush_device_class": "myclass"
638          }
639
640       Or:
641
642          {
643              "cephx_secret": "AQBWtwhZdBO5ExAAIDyjK2Bh16ZXylmzgYYEjg==",
644              "cephx_lockbox_secret": "AQDNCglZuaeVCRAAYr76PzR1Anh7A0jswkODIQ==",
645              "dmcrypt_key": "<dm-crypt key>",
646              "crush_device_class": "myclass"
647          }
648
649       Or:
650
651          {
652              "crush_device_class": "myclass"
653          }
654
655       The  "crush_device_class"  property  is optional. If specified, it will
656       set the initial CRUSH device class for the new OSD.
657
658       Subcommand crush is used for CRUSH management. It uses some  additional
659       subcommands.
660
661       Subcommand  add adds or updates crushmap position and weight for <name>
662       with <weight> and location <args>.
663
664       Usage:
665
666          ceph osd crush add <osdname (id|osd.id)> <float[0.0-]> <args> [<args>...]
667
668       Subcommand add-bucket  adds  no-parent  (probably  root)  crush  bucket
669       <name> of type <type>.
670
671       Usage:
672
673          ceph osd crush add-bucket <name> <type>
674
675       Subcommand  create-or-move  creates  entry  or moves existing entry for
676       <name> <weight> at/to location <args>.
677
678       Usage:
679
680          ceph osd crush create-or-move <osdname (id|osd.id)> <float[0.0-]> <args>
681          [<args>...]
682
683       Subcommand dump dumps crush map.
684
685       Usage:
686
687          ceph osd crush dump
688
689       Subcommand get-tunable get crush tunable straw_calc_version
690
691       Usage:
692
693          ceph osd crush get-tunable straw_calc_version
694
695       Subcommand link links existing entry for <name> under location <args>.
696
697       Usage:
698
699          ceph osd crush link <name> <args> [<args>...]
700
701       Subcommand move moves existing entry for <name> to location <args>.
702
703       Usage:
704
705          ceph osd crush move <name> <args> [<args>...]
706
707       Subcommand remove removes <name> from crush map (everywhere, or just at
708       <ancestor>).
709
710       Usage:
711
712          ceph osd crush remove <name> {<ancestor>}
713
714       Subcommand rename-bucket renames bucket <srcname> to <dstname>
715
716       Usage:
717
718          ceph osd crush rename-bucket <srcname> <dstname>
719
720       Subcommand reweight change <name>'s weight to <weight> in crush map.
721
722       Usage:
723
724          ceph osd crush reweight <name> <float[0.0-]>
725
726       Subcommand  reweight-all recalculate the weights for the tree to ensure
727       they sum correctly
728
729       Usage:
730
731          ceph osd crush reweight-all
732
733       Subcommand reweight-subtree changes all leaf items  beneath  <name>  to
734       <weight> in crush map
735
736       Usage:
737
738          ceph osd crush reweight-subtree <name> <weight>
739
740       Subcommand  rm  removes  <name>  from crush map (everywhere, or just at
741       <ancestor>).
742
743       Usage:
744
745          ceph osd crush rm <name> {<ancestor>}
746
747       Subcommand rule is used for creating crush rules. It  uses  some  addi‐
748       tional subcommands.
749
750       Subcommand  create-erasure  creates crush rule <name> for erasure coded
751       pool created with <profile> (default default).
752
753       Usage:
754
755          ceph osd crush rule create-erasure <name> {<profile>}
756
757       Subcommand create-simple  creates  crush  rule  <name>  to  start  from
758       <root>, replicate across buckets of type <type>, using a choose mode of
759       <firstn|indep> (default firstn; indep best for erasure pools).
760
761       Usage:
762
763          ceph osd crush rule create-simple <name> <root> <type> {firstn|indep}
764
765       Subcommand dump dumps crush rule <name> (default all).
766
767       Usage:
768
769          ceph osd crush rule dump {<name>}
770
771       Subcommand ls lists crush rules.
772
773       Usage:
774
775          ceph osd crush rule ls
776
777       Subcommand rm removes crush rule <name>.
778
779       Usage:
780
781          ceph osd crush rule rm <name>
782
783       Subcommand set used alone, sets crush map from input file.
784
785       Usage:
786
787          ceph osd crush set
788
789       Subcommand set with osdname/osd.id update crushmap position and  weight
790       for <name> to <weight> with location <args>.
791
792       Usage:
793
794          ceph osd crush set <osdname (id|osd.id)> <float[0.0-]> <args> [<args>...]
795
796       Subcommand  set-tunable  set  crush  tunable <tunable> to <value>.  The
797       only tunable that can be set is straw_calc_version.
798
799       Usage:
800
801          ceph osd crush set-tunable straw_calc_version <value>
802
803       Subcommand show-tunables shows current crush tunables.
804
805       Usage:
806
807          ceph osd crush show-tunables
808
809       Subcommand tree shows the crush buckets and items in a tree view.
810
811       Usage:
812
813          ceph osd crush tree
814
815       Subcommand tunables sets crush tunables values to <profile>.
816
817       Usage:
818
819          ceph osd crush tunables legacy|argonaut|bobtail|firefly|hammer|optimal|default
820
821       Subcommand unlink unlinks <name> from crush map (everywhere, or just at
822       <ancestor>).
823
824       Usage:
825
826          ceph osd crush unlink <name> {<ancestor>}
827
828       Subcommand df shows OSD utilization
829
830       Usage:
831
832          ceph osd df {plain|tree}
833
834       Subcommand deep-scrub initiates deep scrub on specified osd.
835
836       Usage:
837
838          ceph osd deep-scrub <who>
839
840       Subcommand down sets osd(s) <id> [<id>...] down.
841
842       Usage:
843
844          ceph osd down <ids> [<ids>...]
845
846       Subcommand dump prints summary of OSD map.
847
848       Usage:
849
850          ceph osd dump {<int[0-]>}
851
852       Subcommand  erasure-code-profile  is used for managing the erasure code
853       profiles. It uses some additional subcommands.
854
855       Subcommand get gets erasure code profile <name>.
856
857       Usage:
858
859          ceph osd erasure-code-profile get <name>
860
861       Subcommand ls lists all erasure code profiles.
862
863       Usage:
864
865          ceph osd erasure-code-profile ls
866
867       Subcommand rm removes erasure code profile <name>.
868
869       Usage:
870
871          ceph osd erasure-code-profile rm <name>
872
873       Subcommand set creates erasure code profile <name> with  [<key[=value]>
874       ...]   pairs.  Add a --force at the end to override an existing profile
875       (IT IS RISKY).
876
877       Usage:
878
879          ceph osd erasure-code-profile set <name> {<profile> [<profile>...]}
880
881       Subcommand find find osd <id> in the CRUSH map and shows its location.
882
883       Usage:
884
885          ceph osd find <int[0-]>
886
887       Subcommand getcrushmap gets CRUSH map.
888
889       Usage:
890
891          ceph osd getcrushmap {<int[0-]>}
892
893       Subcommand getmap gets OSD map.
894
895       Usage:
896
897          ceph osd getmap {<int[0-]>}
898
899       Subcommand getmaxosd shows largest OSD id.
900
901       Usage:
902
903          ceph osd getmaxosd
904
905       Subcommand in sets osd(s) <id> [<id>...] in.
906
907       Usage:
908
909          ceph osd in <ids> [<ids>...]
910
911       Subcommand lost marks osd as permanently lost. THIS DESTROYS DATA IF NO
912       MORE REPLICAS EXIST, BE CAREFUL.
913
914       Usage:
915
916          ceph osd lost <int[0-]> {--yes-i-really-mean-it}
917
918       Subcommand ls shows all OSD ids.
919
920       Usage:
921
922          ceph osd ls {<int[0-]>}
923
924       Subcommand lspools lists pools.
925
926       Usage:
927
928          ceph osd lspools {<int>}
929
930       Subcommand map finds pg for <object> in <pool>.
931
932       Usage:
933
934          ceph osd map <poolname> <objectname>
935
936       Subcommand metadata fetches metadata for osd <id>.
937
938       Usage:
939
940          ceph osd metadata {int[0-]} (default all)
941
942       Subcommand out sets osd(s) <id> [<id>...] out.
943
944       Usage:
945
946          ceph osd out <ids> [<ids>...]
947
948       Subcommand  ok-to-stop checks whether the list of OSD(s) can be stopped
949       without immediately making data unavailable.  That is, all data  should
950       remain  readable and writeable, although data redundancy may be reduced
951       as some PGs may end up in a degraded (but active) state.  It  will  re‐
952       turn  a success code if it is okay to stop the OSD(s), or an error code
953       and informative message if it is not or if no conclusion can  be  drawn
954       at  the  current  time.  When --max <num> is provided, up to <num> OSDs
955       IDs will return (including the provided OSDs) that can all  be  stopped
956       simultaneously.  This allows larger sets of stoppable OSDs to be gener‐
957       ated easily by providing a single starting OSD and a  max.   Additional
958       OSDs are drawn from adjacent locations in the CRUSH hierarchy.
959
960       Usage:
961
962          ceph osd ok-to-stop <id> [<ids>...] [--max <num>]
963
964       Subcommand pause pauses osd.
965
966       Usage:
967
968          ceph osd pause
969
970       Subcommand perf prints dump of OSD perf summary stats.
971
972       Usage:
973
974          ceph osd perf
975
976       Subcommand  pg-temp set pg_temp mapping pgid:[<id> [<id>...]] (develop‐
977       ers only).
978
979       Usage:
980
981          ceph osd pg-temp <pgid> {<id> [<id>...]}
982
983       Subcommand force-create-pg forces creation of pg <pgid>.
984
985       Usage:
986
987          ceph osd force-create-pg <pgid>
988
989       Subcommand pool is used for managing data pools.  It  uses  some  addi‐
990       tional subcommands.
991
992       Subcommand create creates pool.
993
994       Usage:
995
996          ceph osd pool create <poolname> {<int[0-]>} {<int[0-]>} {replicated|erasure}
997          {<erasure_code_profile>} {<rule>} {<int>} {--autoscale-mode=<on,off,warn>}
998
999       Subcommand delete deletes pool.
1000
1001       Usage:
1002
1003          ceph osd pool delete <poolname> {<poolname>} {--yes-i-really-really-mean-it}
1004
1005       Subcommand get gets pool parameter <var>.
1006
1007       Usage:
1008
1009          ceph osd pool get <poolname> size|min_size|pg_num|pgp_num|crush_rule|write_fadvise_dontneed
1010
1011       Only for tiered pools:
1012
1013          ceph osd pool get <poolname> hit_set_type|hit_set_period|hit_set_count|hit_set_fpp|
1014          target_max_objects|target_max_bytes|cache_target_dirty_ratio|cache_target_dirty_high_ratio|
1015          cache_target_full_ratio|cache_min_flush_age|cache_min_evict_age|
1016          min_read_recency_for_promote|hit_set_grade_decay_rate|hit_set_search_last_n
1017
1018       Only for erasure coded pools:
1019
1020          ceph osd pool get <poolname> erasure_code_profile
1021
1022       Use all to get all pool parameters that apply to the pool's type:
1023
1024          ceph osd pool get <poolname> all
1025
1026       Subcommand get-quota obtains object or byte limits for pool.
1027
1028       Usage:
1029
1030          ceph osd pool get-quota <poolname>
1031
1032       Subcommand ls list pools
1033
1034       Usage:
1035
1036          ceph osd pool ls {detail}
1037
1038       Subcommand mksnap makes snapshot <snap> in <pool>.
1039
1040       Usage:
1041
1042          ceph osd pool mksnap <poolname> <snap>
1043
1044       Subcommand rename renames <srcpool> to <destpool>.
1045
1046       Usage:
1047
1048          ceph osd pool rename <poolname> <poolname>
1049
1050       Subcommand rmsnap removes snapshot <snap> from <pool>.
1051
1052       Usage:
1053
1054          ceph osd pool rmsnap <poolname> <snap>
1055
1056       Subcommand set sets pool parameter <var> to <val>.
1057
1058       Usage:
1059
1060          ceph osd pool set <poolname> size|min_size|pg_num|
1061          pgp_num|crush_rule|hashpspool|nodelete|nopgchange|nosizechange|
1062          hit_set_type|hit_set_period|hit_set_count|hit_set_fpp|debug_fake_ec_pool|
1063          target_max_bytes|target_max_objects|cache_target_dirty_ratio|
1064          cache_target_dirty_high_ratio|
1065          cache_target_full_ratio|cache_min_flush_age|cache_min_evict_age|
1066          min_read_recency_for_promote|write_fadvise_dontneed|hit_set_grade_decay_rate|
1067          hit_set_search_last_n
1068          <val> {--yes-i-really-mean-it}
1069
1070       Subcommand set-quota sets object or byte limit on pool.
1071
1072       Usage:
1073
1074          ceph osd pool set-quota <poolname> max_objects|max_bytes <val>
1075
1076       Subcommand stats obtain stats from all pools, or from specified pool.
1077
1078       Usage:
1079
1080          ceph osd pool stats {<name>}
1081
1082       Subcommand  application  is  used for adding an annotation to the given
1083       pool. By default, the possible applications are object, block, and file
1084       storage  (corresponding app-names are "rgw", "rbd", and "cephfs"). How‐
1085       ever, there might be other applications as well. Based on the  applica‐
1086       tion, there may or may not be some processing conducted.
1087
1088       Subcommand disable disables the given application on the given pool.
1089
1090       Usage:
1091
1092          ceph osd pool application disable <pool-name> <app> {--yes-i-really-mean-it}
1093
1094       Subcommand  enable  adds  an  annotation to the given pool for the men‐
1095       tioned application.
1096
1097       Usage:
1098
1099          ceph osd pool application enable <pool-name> <app> {--yes-i-really-mean-it}
1100
1101       Subcommand get displays the value for the given key that is  associated
1102       with  the given application of the given pool. Not passing the optional
1103       arguments would display all key-value pairs for  all  applications  for
1104       all pools.
1105
1106       Usage:
1107
1108          ceph osd pool application get {<pool-name>} {<app>} {<key>}
1109
1110       Subcommand rm removes the key-value pair for the given key in the given
1111       application of the given pool.
1112
1113       Usage:
1114
1115          ceph osd pool application rm <pool-name> <app> <key>
1116
1117       Subcommand set associates or updates, if it already exists, a key-value
1118       pair with the given application for the given pool.
1119
1120       Usage:
1121
1122          ceph osd pool application set <pool-name> <app> <key> <value>
1123
1124       Subcommand   primary-affinity  adjust  osd  primary-affinity  from  0.0
1125       <=<weight> <= 1.0
1126
1127       Usage:
1128
1129          ceph osd primary-affinity <osdname (id|osd.id)> <float[0.0-1.0]>
1130
1131       Subcommand primary-temp sets primary_temp mapping pgid:<id>|-1  (devel‐
1132       opers only).
1133
1134       Usage:
1135
1136          ceph osd primary-temp <pgid> <id>
1137
1138       Subcommand repair initiates repair on a specified osd.
1139
1140       Usage:
1141
1142          ceph osd repair <who>
1143
1144       Subcommand reweight reweights osd to 0.0 < <weight> < 1.0.
1145
1146       Usage:
1147
1148          osd reweight <int[0-]> <float[0.0-1.0]>
1149
1150       Subcommand  reweight-by-pg  reweight  OSDs  by  PG  distribution [over‐
1151       load-percentage-for-consideration, default 120].
1152
1153       Usage:
1154
1155          ceph osd reweight-by-pg {<int[100-]>} {<poolname> [<poolname...]}
1156          {--no-increasing}
1157
1158       Subcommand reweight-by-utilization reweights OSDs by  utilization.   It
1159       only  reweights outlier OSDs whose utilization exceeds the average, eg.
1160       the default 120% limits reweight to those OSDs that are more  than  20%
1161       over the average.  [overload-threshold, default 120 [max_weight_change,
1162       default 0.05 [max_osds_to_adjust, default 4]]]
1163
1164       Usage:
1165
1166          ceph osd reweight-by-utilization {<int[100-]> {<float[0.0-]> {<int[0-]>}}}
1167          {--no-increasing}
1168
1169       Subcommand rm removes osd(s) <id> [<id>...] from the OSD map.
1170
1171       Usage:
1172
1173          ceph osd rm <ids> [<ids>...]
1174
1175       Subcommand destroy marks OSD id as destroyed, removing  its  cephx  en‐
1176       tity's  keys  and all of its dm-crypt and daemon-private config key en‐
1177       tries.
1178
1179       This command will not remove the OSD from crush, nor will it remove the
1180       OSD from the OSD map. Instead, once the command successfully completes,
1181       the OSD will show marked as destroyed.
1182
1183       In order to mark an OSD as destroyed, the OSD must first be  marked  as
1184       lost.
1185
1186       Usage:
1187
1188          ceph osd destroy <id> {--yes-i-really-mean-it}
1189
1190       Subcommand  purge performs a combination of osd destroy, osd rm and osd
1191       crush remove.
1192
1193       Usage:
1194
1195          ceph osd purge <id> {--yes-i-really-mean-it}
1196
1197       Subcommand safe-to-destroy checks whether it is safe to remove  or  de‐
1198       stroy  an  OSD  without reducing overall data redundancy or durability.
1199       It will return a success code if it is definitely  safe,  or  an  error
1200       code  and  informative  message if it is not or if no conclusion can be
1201       drawn at the current time.
1202
1203       Usage:
1204
1205          ceph osd safe-to-destroy <id> [<ids>...]
1206
1207       Subcommand scrub initiates scrub on specified osd.
1208
1209       Usage:
1210
1211          ceph osd scrub <who>
1212
1213       Subcommand set sets cluster-wide <flag> by updating OSD map.  The  full
1214       flag  is  not honored anymore since the Mimic release, and ceph osd set
1215       full is not supported in the Octopus release.
1216
1217       Usage:
1218
1219          ceph osd set pause|noup|nodown|noout|noin|nobackfill|
1220          norebalance|norecover|noscrub|nodeep-scrub|notieragent
1221
1222       Subcommand setcrushmap sets crush map from input file.
1223
1224       Usage:
1225
1226          ceph osd setcrushmap
1227
1228       Subcommand setmaxosd sets new maximum osd value.
1229
1230       Usage:
1231
1232          ceph osd setmaxosd <int[0-]>
1233
1234       Subcommand set-require-min-compat-client enforces  the  cluster  to  be
1235       backward  compatible with the specified client version. This subcommand
1236       prevents you from making any changes (e.g., crush  tunables,  or  using
1237       new features) that would violate the current setting. Please note, This
1238       subcommand will fail if any connected daemon or client is not  compati‐
1239       ble  with  the features offered by the given <version>. To see the fea‐
1240       tures and releases of all clients connected to cluster, please see ceph
1241       features.
1242
1243       Usage:
1244
1245          ceph osd set-require-min-compat-client <version>
1246
1247       Subcommand stat prints summary of OSD map.
1248
1249       Usage:
1250
1251          ceph osd stat
1252
1253       Subcommand  tier  is  used  for managing tiers. It uses some additional
1254       subcommands.
1255
1256       Subcommand add adds the tier <tierpool> (the second one) to  base  pool
1257       <pool> (the first one).
1258
1259       Usage:
1260
1261          ceph osd tier add <poolname> <poolname> {--force-nonempty}
1262
1263       Subcommand  add-cache  adds a cache <tierpool> (the second one) of size
1264       <size> to existing pool <pool> (the first one).
1265
1266       Usage:
1267
1268          ceph osd tier add-cache <poolname> <poolname> <int[0-]>
1269
1270       Subcommand cache-mode specifies the caching mode for cache tier <pool>.
1271
1272       Usage:
1273
1274          ceph osd tier cache-mode <poolname> writeback|readproxy|readonly|none
1275
1276       Subcommand remove removes the tier <tierpool>  (the  second  one)  from
1277       base pool <pool> (the first one).
1278
1279       Usage:
1280
1281          ceph osd tier remove <poolname> <poolname>
1282
1283       Subcommand  remove-overlay  removes  the  overlay  pool  for  base pool
1284       <pool>.
1285
1286       Usage:
1287
1288          ceph osd tier remove-overlay <poolname>
1289
1290       Subcommand set-overlay set the overlay pool for base pool <pool> to  be
1291       <overlaypool>.
1292
1293       Usage:
1294
1295          ceph osd tier set-overlay <poolname> <poolname>
1296
1297       Subcommand tree prints OSD tree.
1298
1299       Usage:
1300
1301          ceph osd tree {<int[0-]>}
1302
1303       Subcommand unpause unpauses osd.
1304
1305       Usage:
1306
1307          ceph osd unpause
1308
1309       Subcommand unset unsets cluster-wide <flag> by updating OSD map.
1310
1311       Usage:
1312
1313          ceph osd unset pause|noup|nodown|noout|noin|nobackfill|
1314          norebalance|norecover|noscrub|nodeep-scrub|notieragent
1315
1316   pg
1317       It  is used for managing the placement groups in OSDs. It uses some ad‐
1318       ditional subcommands.
1319
1320       Subcommand debug shows debug info about pgs.
1321
1322       Usage:
1323
1324          ceph pg debug unfound_objects_exist|degraded_pgs_exist
1325
1326       Subcommand deep-scrub starts deep-scrub on <pgid>.
1327
1328       Usage:
1329
1330          ceph pg deep-scrub <pgid>
1331
1332       Subcommand dump shows human-readable versions of  pg  map  (only  'all'
1333       valid with plain).
1334
1335       Usage:
1336
1337          ceph pg dump {all|summary|sum|delta|pools|osds|pgs|pgs_brief} [{all|summary|sum|delta|pools|osds|pgs|pgs_brief...]}
1338
1339       Subcommand  dump_json  shows  human-readable  version of pg map in json
1340       only.
1341
1342       Usage:
1343
1344          ceph pg dump_json {all|summary|sum|delta|pools|osds|pgs|pgs_brief} [{all|summary|sum|delta|pools|osds|pgs|pgs_brief...]}
1345
1346       Subcommand dump_pools_json shows pg pools info in json only.
1347
1348       Usage:
1349
1350          ceph pg dump_pools_json
1351
1352       Subcommand dump_stuck shows information about stuck pgs.
1353
1354       Usage:
1355
1356          ceph pg dump_stuck {inactive|unclean|stale|undersized|degraded [inactive|unclean|stale|undersized|degraded...]}
1357          {<int>}
1358
1359       Subcommand getmap gets binary pg map to -o/stdout.
1360
1361       Usage:
1362
1363          ceph pg getmap
1364
1365       Subcommand ls lists pg with specific pool, osd, state
1366
1367       Usage:
1368
1369          ceph pg ls {<int>} {<pg-state> [<pg-state>...]}
1370
1371       Subcommand ls-by-osd lists pg on osd [osd]
1372
1373       Usage:
1374
1375          ceph pg ls-by-osd <osdname (id|osd.id)> {<int>}
1376          {<pg-state> [<pg-state>...]}
1377
1378       Subcommand ls-by-pool lists pg with pool = [poolname]
1379
1380       Usage:
1381
1382          ceph pg ls-by-pool <poolstr> {<int>} {<pg-state> [<pg-state>...]}
1383
1384       Subcommand ls-by-primary lists pg with primary = [osd]
1385
1386       Usage:
1387
1388          ceph pg ls-by-primary <osdname (id|osd.id)> {<int>}
1389          {<pg-state> [<pg-state>...]}
1390
1391       Subcommand map shows mapping of pg to osds.
1392
1393       Usage:
1394
1395          ceph pg map <pgid>
1396
1397       Subcommand repair starts repair on <pgid>.
1398
1399       Usage:
1400
1401          ceph pg repair <pgid>
1402
1403       Subcommand scrub starts scrub on <pgid>.
1404
1405       Usage:
1406
1407          ceph pg scrub <pgid>
1408
1409       Subcommand stat shows placement group status.
1410
1411       Usage:
1412
1413          ceph pg stat
1414
1415   quorum
1416       Cause a specific MON to enter or exit quorum.
1417
1418       Usage:
1419
1420          ceph tell mon.<id> quorum enter|exit
1421
1422   quorum_status
1423       Reports status of monitor quorum.
1424
1425       Usage:
1426
1427          ceph quorum_status
1428
1429   report
1430       Reports full status of cluster, optional title tag strings.
1431
1432       Usage:
1433
1434          ceph report {<tags> [<tags>...]}
1435
1436   status
1437       Shows cluster status.
1438
1439       Usage:
1440
1441          ceph status
1442
1443   tell
1444       Sends a command to a specific daemon.
1445
1446       Usage:
1447
1448          ceph tell <name (type.id)> <command> [options...]
1449
1450       List all available commands.
1451
1452       Usage:
1453
1454          ceph tell <name (type.id)> help
1455
1456   version
1457       Show mon daemon version
1458
1459       Usage:
1460
1461          ceph version
1462

OPTIONS

1464       -i infile
1465              will specify an input file to be passed along as a payload  with
1466              the  command  to the monitor cluster. This is only used for spe‐
1467              cific monitor commands.
1468
1469       -o outfile
1470              will write any payload returned by the monitor cluster with  its
1471              reply  to  outfile.   Only  specific  monitor commands (e.g. osd
1472              getmap) return a payload.
1473
1474       --setuser user
1475              will apply the appropriate user ownership to the file  specified
1476              by the option '-o'.
1477
1478       --setgroup group
1479              will apply the appropriate group ownership to the file specified
1480              by the option '-o'.
1481
1482       -c ceph.conf, --conf=ceph.conf
1483              Use  ceph.conf  configuration  file  instead  of   the   default
1484              /etc/ceph/ceph.conf   to   determine  monitor  addresses  during
1485              startup.
1486
1487       --id CLIENT_ID, --user CLIENT_ID
1488              Client id for authentication.
1489
1490       --name CLIENT_NAME, -n CLIENT_NAME
1491              Client name for authentication.
1492
1493       --cluster CLUSTER
1494              Name of the Ceph cluster.
1495
1496       --admin-daemon ADMIN_SOCKET, daemon DAEMON_NAME
1497              Submit admin-socket commands via admin sockets in /var/run/ceph.
1498
1499       --admin-socket ADMIN_SOCKET_NOPE
1500              You probably mean --admin-daemon
1501
1502       -s, --status
1503              Show cluster status.
1504
1505       -w, --watch
1506              Watch live cluster changes on the default 'cluster' channel
1507
1508       -W, --watch-channel
1509              Watch live cluster  changes  on  any  channel  (cluster,  audit,
1510              cephadm, or * for all)
1511
1512       --watch-debug
1513              Watch debug events.
1514
1515       --watch-info
1516              Watch info events.
1517
1518       --watch-sec
1519              Watch security events.
1520
1521       --watch-warn
1522              Watch warning events.
1523
1524       --watch-error
1525              Watch error events.
1526
1527       --version, -v
1528              Display version.
1529
1530       --verbose
1531              Make verbose.
1532
1533       --concise
1534              Make less verbose.
1535
1536       -f {json,json-pretty,xml,xml-pretty,plain}, --format
1537              Format of output.
1538
1539       --connect-timeout CLUSTER_TIMEOUT
1540              Set a timeout for connecting to the cluster.
1541
1542       --no-increasing
1543              --no-increasing  is off by default. So increasing the osd weight
1544              is    allowed    using    the     reweight-by-utilization     or
1545              test-reweight-by-utilization  commands.   If this option is used
1546              with these commands, it will help not  to  increase  osd  weight
1547              even the osd is under utilized.
1548
1549       --block
1550              block until completion (scrub and deep-scrub only)
1551

AVAILABILITY

1553       ceph  is  part  of Ceph, a massively scalable, open-source, distributed
1554       storage  system.  Please   refer   to   the   Ceph   documentation   at
1555       http://ceph.com/docs for more information.
1556

SEE ALSO

1558       ceph-mon(8), ceph-osd(8), ceph-mds(8)
1559
1561       2010-2021,  Inktank Storage, Inc. and contributors. Licensed under Cre‐
1562       ative Commons Attribution Share Alike 3.0 (CC-BY-SA-3.0)
1563
1564
1565
1566
1567dev                              May 13, 2021                          CEPH(8)
Impressum