@@ -102,6 +102,86 @@ Mount Options
specified, the client's IP address is determined by looking at the
address its connection to the monitor originates from.
+ fsid=X
+ Specify the cluster's FSID/UUID.
+
+ name=X
+ RADOS user to authenticate as when using CephX. Default: guest
+
+ secret=X
+ Specify the secret key for use with CephX. This option is insecure
+ because it exposes the secret on the command line. To avoid this,
+ use the secretfile option.
+
+ key=X
+ Get secret key from the kernel keys api. More detail please see
+ Documentation/security/keys/core.rst.
+
+ osdkeepalive=X
+ The interval for sending the keepalive (tag + timestamp) to its OSD
+ to ensure any communications channel reset is detected. Default: 5
+ seconds.
+
+ osd_idle_ttl=X
+ The ttl for the osds in the lru list, will close and remove those
+ have not been used for more than a specified time. Default: 60
+ seconds.
+
+ mount_timeout=X
+ Specify the timeout value for mount (in seconds), in the case of
+ a non-responsive Ceph file system. Default: 60 seconds.
+
+ osd_request_timeout=X
+ Specify the timeout value for each osd request (in seconds), in
+ the case of non-responsive and will abort it. Default: 0 seconds,
+ means no timeout.
+
+ share
+ Share the client instance with other superblocks when mounting the
+ same cluster. This is the default.
+
+ noshare
+ Create a new client instance, instead of sharing an existing instance
+ of a client mounting the same cluster.
+
+ crc
+ Use CRC32C calculation for data writes. This is the default.
+
+ nocrc
+ Disable CRC32C calculation for data writes. If set, the storage node
+ must rely on TCP's error correction to detect data corruption
+ in the data payload.
+
+ cephx_require_signatures
+ Enable require cephx message signing feat. This is the default.
+
+ nocephx_require_signatures
+ Disable require cephx message signing feat.
+
+ cephx_sign_messages
+ Enable message signing. This is the default.
+
+ nocephx_sign_messages
+ Disable message signing.
+
+ tcp_nodelay
+ Disable Nagle's algorithm on client sockets. This is the default.
+
+ notcp_nodelay
+ Enable Nagle's algorithm on client sockets.
+
+ abort_on_full
+ Fail write requests with -ENOSPC when the cluster is full or the data
+ pool reaches its quota. The default behaviour is to block until the
+ full condition is cleared.
+
+ snapdirname=X
+ Specify the name of the hidden snapdir. The default is ".snap".
+
+ mds_namespace=X
+ Specify the name of one filesystem to mount if you have more than
+ one filesystem.
+
wsize=X
Specify the maximum write size in bytes. Default: 64 MB.
@@ -111,52 +191,119 @@ Mount Options
rasize=X
Specify the maximum readahead size in bytes. Default: 8 MB.
- mount_timeout=X
- Specify the timeout value for mount (in seconds), in the case
- of a non-responsive Ceph file system. The default is 60
- seconds.
+ caps_wanted_delay_min=X
+ Specify the minimum amount of time for telling the MDS we no
+ longer want caps, in case we reopen the file. Default: 5 seconds.
+
+ caps_wanted_delay_max=X
+ Specify the maximum amount of time for telling the MDS we no
+ longer want caps, in case we reopen the file. Default: 60 seconds.
caps_max=X
Specify the maximum number of caps to hold. Unused caps are released
when number of caps exceeds the limit. The default is 0 (no limit)
+ readdir_max_entries=X
+ Specify the maximum directy entries to read per-request. Default:
+ 1024.
+
+ readdir_max_bytes=X
+ Specify the maximum bytes could read per-request when reading directy
+ entries. Default: 512k.
+
+ congestion_kb=X
+ Specify the maximum writeback in flight, scale with available memory.
+ Default: calculated from available memory, but limit the default to
+ 256M, at least 1M.
+
+ dirstat
+ Enable funky cat dirname for stats.
+
+ nodirstat
+ Disable funky cat dirname for stats. This is the default.
+
rbytes
When stat() is called on a directory, set st_size to 'rbytes',
the summation of file sizes over all files nested beneath that
directory. This is the default.
norbytes
- When stat() is called on a directory, set st_size to the
- number of entries in that directory.
-
- nocrc
- Disable CRC32C calculation for data writes. If set, the storage node
- must rely on TCP's error correction to detect data corruption
- in the data payload.
+ When stat() is called on a directory, set st_size to the number
+ of entries in that directory.
dcache
- Use the dcache contents to perform negative lookups and
- readdir when the client has the entire directory contents in
- its cache. (This does not change correctness; the client uses
- cached metadata only when a lease or capability ensures it is
- valid.)
+ Use the dcache contents to perform negative lookups and readdir
+ when the client has the entire directory contents in its cache.
+ (This does not change correctness; the client uses cached metadata
+ only when a lease or capability ensures it is valid.) This is
+ the default.
nodcache
Do not use the dcache as above. This avoids a significant amount of
complex code, sacrificing performance without affecting correctness,
and is useful for tracking down bugs.
+ asyncreaddir
+ Enable to use the dcache as above for readdir. This is the default.
+
noasyncreaddir
- Do not use the dcache as above for readdir.
+ Disable to use the dcache as above for readdir.
- noquotadf
+ ino32
+ Enable and force the ceph fs to report 32 bit ino values. This is
+ useful for 64 bit kernels with 32 bit userspace.
+
+ noino32
+ Disable forcing the ceph fs to report 32 bit ino values. This is
+ the default.
+
+ fsc=X
+ Enable and use fscache cookie as a local presisent cache with a unique
+ qualifier.
+
+ fsc
+ Enable and use fscache cookie as a local presisent cache without any
+ unique qualifier.
+
+ nofsc
+ Disable and do not use fscache cookie as a local presisent cache.
+
+ poolperm
+ Enable the pool rd/wr permission check for read/write. This is the
+ default.
+
+ nopoolperm
+ Disable the pool rd/wr permission check for read/write.
+
+ require_active_mds
+ Enable mount waits if no mds is up.
+
+ norequire_active_mds
+ Disablee mount waits if no mds is up. This is the default.
+
+ quotadf
Report overall filesystem usage in statfs instead of using the root
- directory quota.
+ directory quota. This is the default.
- nocopyfrom
- Don't use the RADOS 'copy-from' operation to perform remote object
+ noquotadf
+ Disable and do not report overall filesystem usage in statfs instead
+ of using the root directory quota.
+
+ copyfrom
+ Enable and use the RADOS 'copy-from' operation to perform remote object
copies. Currently, it's only used in copy_file_range, which will revert
- to the default VFS implementation if this option is used.
+ to the default VFS implementation if this option is used. This is the
+ default.
+
+ nocopyfrom
+ Disable to use the RADOS 'copy-from' operation to perform remote object
+ copies.
+
+ acl
+ Enable the acl. This is the default.
+
+ noacl
+ Disable the acl.
recover_session=<no|clean>
Set auto reconnect mode in the case where the client is blacklisted. The