5 - name: client_cache_size
8 desc: soft maximum number of directory entries in client cache
9 fmt_desc: Set the number of inodes that the client keeps in the metadata cache.
14 - name: client_cache_mid
17 desc: mid-point of client cache LRU
18 fmt_desc: Set client cache midpoint. The midpoint splits the least recently used
19 lists into a hot and warm list.
24 - name: client_use_random_mds
27 desc: issue new requests to a random active MDS
28 fmt_desc: Choose random MDS for each request.
33 - name: client_mount_timeout
36 desc: timeout for mounting CephFS (seconds)
37 fmt_desc: Set the timeout for CephFS mount in seconds.
42 - name: client_tick_interval
45 desc: seconds between client upkeep ticks
46 fmt_desc: Set the interval in seconds between capability renewal and other upkeep.
53 desc: file containing trace of client operations
57 - name: client_readahead_min
60 desc: minimum bytes to readahead in a file
61 fmt_desc: Set the minimum number bytes that the client reads ahead.
66 - name: client_readahead_max_bytes
69 desc: maximum bytes to readahead in a file (zero is unlimited)
70 fmt_desc: Set the maximum number of bytes that the client reads ahead for
71 future read operations. Overridden by the ``client_readahead_max_periods``
77 # as multiple of file layout period (object size * num stripes)
78 - name: client_readahead_max_periods
81 desc: maximum stripe periods to readahead in a file
82 fmt_desc: Set the number of file layout periods (object size * number of
83 stripes) that the client reads ahead. Overrides the
84 ``client_readahead_max_bytes`` setting.
89 - name: client_reconnect_stale
92 desc: reconnect when the session becomes stale
96 - name: client_snapdir
99 desc: pseudo directory for snapshot access to a directory
100 fmt_desc: Set the snapshot directory name.
105 - name: client_mountpoint
108 desc: default mount-point
109 fmt_desc: Directory to mount on the CephFS file system. An alternative to the
110 ``-r`` option of the ``ceph-fuse`` command.
114 - name: client_mount_uid
117 desc: uid to mount as
121 fmt_desc: Set the user ID of CephFS mount.
123 - name: client_mount_gid
126 desc: gid to mount as
127 fmt_desc: Set the group ID of CephFS mount.
132 - name: client_notify_timeout
139 - name: osd_client_watch_timeout
146 - name: client_caps_release_delay
152 fmt_desc: Set the delay between capability releases in seconds. The delay
153 sets how many seconds a client waits to release capabilities that it no
154 longer needs in case the capabilities are needed for another user space
157 - name: client_quota_df
160 desc: show quota usage for statfs (df)
161 fmt_desc: Report root directory quota for the ``statfs`` operation.
169 desc: enable object caching
174 - name: client_oc_size
177 desc: maximum size of object cache
178 fmt_desc: Set how many bytes of data will the client cache.
185 # MB * n (dirty OR tx.. bigish)
186 - name: client_oc_max_dirty
189 desc: maximum size of dirty pages in object cache
190 fmt_desc: Set the maximum number of dirty bytes in the object cache.
197 # target dirty (keep this smallish)
198 - name: client_oc_target_dirty
201 desc: target size of dirty pages object cache
202 fmt_desc: Set the target size of dirty data. We recommend to keep this number low.
209 - name: client_oc_max_dirty_age
212 desc: maximum age of dirty pages in object cache (seconds)
213 fmt_desc: Set the maximum age in seconds of dirty data in the object cache
221 - name: client_oc_max_objects
224 desc: maximum number of objects in cache
225 fmt_desc: Set the maximum number of objects in the object cache.
232 # check if MDS reply contains wanted caps
233 - name: client_debug_getattr_caps
240 # always read synchronously (go to osds)
241 - name: client_debug_force_sync_read
247 fmt_desc: If set to ``true``, clients read data directly from OSDs instead
248 of using a local page cache.
250 - name: client_debug_inject_tick_delay
256 - name: client_max_inline_size
262 fmt_desc: Set the maximum size of inlined data stored in a file inode rather
263 than in a separate data object in RADOS. This setting only applies if the
264 ``inline_data`` flag is set on the MDS map.
266 # synthetic client bug for testing
267 - name: client_inject_release_failure
274 # synthetic client bug for testing
275 - name: client_inject_fixed_oldest_tid
282 - name: client_metadata
285 desc: metadata key=value comma-delimited pairs appended to session metadata
286 fmt_desc: Comma-delimited strings for client metadata sent to each MDS, in addition
287 to the automatically generated version, host name, and other metadata.
291 - name: client_acl_type
294 desc: ACL type to enforce (none or "posix_acl")
295 fmt_desc: Set the ACL type. Currently, only possible value is ``"posix_acl"`` to
296 enable POSIX ACL, or an empty string. This option only takes effect when the
297 ``fuse_default_permissions`` is set to ``false``.
301 - name: client_permissions
304 desc: client-enforced permission checking
305 fmt_desc: Check client permissions on all I/O operations.
310 - name: client_dirsize_rbytes
313 desc: set the directory size as the number of file bytes recursively used
314 long_desc: This option enables a CephFS feature that stores the recursive directory
315 size (the bytes used by files in the directory and its descendents) in the st_size
316 field of the stat structure.
321 - name: client_force_lazyio
327 - name: fuse_use_invalidate_cb
330 desc: use fuse 2.8+ invalidate callback to keep page cache consistent
334 - name: fuse_disable_pagecache
337 desc: disable page caching in the kernel for this FUSE mount
338 fmt_desc: If set to ``true``, kernel page cache is disabled for ``ceph-fuse``
339 mounts. When multiple clients read/write to a file at the same
340 time, readers may get stale data from page cache. Due to
341 limitations of FUSE, ``ceph-fuse`` can't disable page cache dynamically.
345 - name: fuse_allow_other
348 desc: pass allow_other to FUSE on mount
352 - name: fuse_default_permissions
355 desc: pass default_permisions to FUSE on mount
356 fmt_desc: When set to ``false``, ``ceph-fuse`` utility checks does its own
357 permissions checking, instead of relying on the permissions enforcement in
358 FUSE. Set to ``false`` together with the ``client acl type=posix_acl``
359 option to enable POSIX ACL.
365 - name: fuse_splice_read
368 desc: enable splice read to reduce the memory copies
372 - name: fuse_splice_write
375 desc: enable splice write to reduce the memory copies
379 - name: fuse_splice_move
382 desc: enable splice move to reduce the memory copies
386 - name: fuse_big_writes
389 desc: big_writes is deprecated in libfuse 3.0.0
393 - name: fuse_max_write
396 desc: set the maximum number of bytes in a single write operation
397 long_desc: Set the maximum number of bytes in a single write operation that may
398 pass atomically through FUSE. The FUSE default is 128kB and may be indicated by
399 setting this option to 0.
400 fmt_desc: Set the maximum number of bytes in a single write operation. A value of
401 0 indicates no change; the FUSE default of 128 kbytes remains in force.
405 - name: fuse_atomic_o_trunc
408 desc: pass atomic_o_trunc flag to FUSE on mount
415 desc: enable debugging for the libfuse
422 - name: fuse_multithreaded
425 desc: allow parallel processing through FUSE library
429 - name: fuse_require_active_mds
432 desc: require active MDSs in the file system when mounting
436 - name: fuse_syncfs_on_mksnap
439 desc: synchronize all local metadata/file changes after snapshot
443 - name: fuse_set_user_groups
446 desc: check for ceph-fuse to consider supplementary groups for permissions
450 # the client should try to use dentry invaldation instead of remounting, on kernels it believes that will work for
451 - name: client_try_dentry_invalidate
458 - name: client_die_on_failed_remount
464 - name: client_die_on_failed_dentry_invalidate
467 desc: kill the client when no dentry invalidation options are available
468 long_desc: The CephFS client requires a mechanism to invalidate dentries in the
469 caller (e.g. the kernel for ceph-fuse) when capabilities must be recalled. If
470 the client cannot do this then the MDS cache cannot shrink which can cause the
475 - name: client_check_pool_perm
478 desc: confirm access to inode's data pool/namespace described in file layout
483 - name: client_use_faked_inos
493 desc: CephFS file system name to mount
494 long_desc: Use this with ceph-fuse, or with any process that uses libcephfs. Programs
495 using libcephfs may also pass the filesystem name into mount(), which will override
496 this setting. If no filesystem name is given in mount() or this setting, the default
497 filesystem will be mounted (usually the first created).
502 - name: client_mds_namespace
509 - name: fake_statfs_for_testing
512 desc: Set a value for kb and compute kb_used from total of num_bytes
518 - name: debug_allow_any_pool_priority
521 desc: Allow any pool priority to be set to test conversion to new range
526 - name: client_asio_thread_count
529 desc: Size of thread pool for ASIO completions
536 - name: client_shutdown_timeout
539 desc: timeout for shutting down CephFS
540 long_desc: Timeout for shutting down CephFS via unmount or shutdown.