This document is for a development version of Ceph.

ceph-osd -- ceph object storage daemon


ceph-osd -i osdnum [ --osd-data datapath ] [ --osd-journal journal ] [ --mkfs ] [ --mkjournal ] [--flush-journal] [--check-allows-journal] [--check-wants-journal] [--check-needs-journal] [ --mkkey ] [ --osdspec-affinity ]


ceph-osd is the object storage daemon for the Ceph distributed file system. It manages data on local storage with redundancy and provides access to that data over the network.

For Filestore-backed clusters, the argument of the --osd-data datapath option (which is datapath in this example) should be a directory on an XFS file system where the object data resides. The journal is optional. The journal improves performance only when it resides on a different disk than the disk specified by datapath . The storage medium on which the journal is stored should be a low-latency medium (ideally, an SSD device).


-f, --foreground

Foreground: do not daemonize after startup (run in foreground). Do not generate a pid file. Useful when run via ceph-run(8).


Debug mode: like -f, but also send all log output to stderr.

--setuser userorgid

Set uid after starting. If a username is specified, the user record is looked up to get a uid and a gid, and the gid is also set as well, unless --setgroup is also specified.

--setgroup grouporgid

Set gid after starting. If a group name is specified the group record is looked up to get a gid.

--osd-data osddata

Use object store at osddata.

--osd-journal journal

Journal updates to journal.


Check whether a journal is desired.


Check whether a journal is allowed.


Check whether a journal is required.


Create an empty object repository. This also initializes the journal (if one is defined).


Generate a new secret key. This is normally used in combination with --mkfs as it is more convenient than generating a key by hand with ceph-authtool(8).


Create a new journal file to match an existing object repository. This is useful if the journal device or file is wiped out due to a disk or file system failure.


Flush the journal to permanent store. This runs in the foreground so you know when it’s completed. This can be useful if you want to resize the journal or need to otherwise destroy it: this guarantees you won’t lose data.


Print the cluster fsid (uuid) and exit.


Print the OSD’s fsid and exit. The OSD’s uuid is generated at --mkfs time and is thus unique to a particular instantiation of this OSD.


Print the journal’s uuid. The journal fsid is set to match the OSD fsid at --mkfs time.

-c ceph.conf, --conf=ceph.conf

Use ceph.conf configuration file instead of the default /etc/ceph/ceph.conf for runtime configuration options.

-m monaddress[:port]

Connect to specified monitor (instead of looking through ceph.conf).


Set an affinity to a certain OSDSpec. This option can only be used in conjunction with --mkfs.


ceph-osd is part of Ceph, a massively scalable, open-source, distributed storage system. Please refer to the Ceph documentation at for more information.

See also

ceph(8), ceph-mds(8), ceph-mon(8), ceph-authtool(8)

Brought to you by the Ceph Foundation

The Ceph Documentation is a community resource funded and hosted by the non-profit Ceph Foundation. If you would like to support this and our other efforts, please consider joining now.