--- /dev/null
- default: 12_hr
+ # -*- mode: YAML -*-
+ ---
+
+ options:
+ - name: host
+ type: str
+ level: basic
+ desc: local hostname
+ long_desc: if blank, ceph assumes the short hostname (hostname -s)
+ tags:
+ - network
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - name: fsid
+ type: uuid
+ level: basic
+ desc: cluster fsid (uuid)
+ tags:
+ - service
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - startup
+ - name: public_addr
+ type: addr
+ level: basic
+ desc: public-facing address to bind to
+ services:
+ - mon
+ - mds
+ - osd
+ - mgr
+ flags:
+ - startup
+ - name: public_addrv
+ type: addrvec
+ level: basic
+ desc: public-facing address to bind to
+ services:
+ - mon
+ - mds
+ - osd
+ - mgr
+ flags:
+ - startup
+ - name: public_bind_addr
+ type: addr
+ level: advanced
+ services:
+ - mon
+ flags:
+ - startup
+ - name: cluster_addr
+ type: addr
+ level: basic
+ desc: cluster-facing address to bind to
+ tags:
+ - network
+ services:
+ - osd
+ flags:
+ - startup
+ - name: public_network
+ type: str
+ level: advanced
+ desc: Network(s) from which to choose a public address to bind to
+ tags:
+ - network
+ services:
+ - mon
+ - mds
+ - osd
+ - mgr
+ flags:
+ - startup
+ - name: public_network_interface
+ type: str
+ level: advanced
+ desc: Interface name(s) from which to choose an address from a public_network to
+ bind to; public_network must also be specified.
+ tags:
+ - network
+ services:
+ - mon
+ - mds
+ - osd
+ - mgr
+ see_also:
+ - public_network
+ flags:
+ - startup
+ - name: cluster_network
+ type: str
+ level: advanced
+ desc: Network(s) from which to choose a cluster address to bind to
+ tags:
+ - network
+ services:
+ - osd
+ flags:
+ - startup
+ - name: cluster_network_interface
+ type: str
+ level: advanced
+ desc: Interface name(s) from which to choose an address from a cluster_network to
+ bind to; cluster_network must also be specified.
+ tags:
+ - network
+ services:
+ - mon
+ - mds
+ - osd
+ - mgr
+ see_also:
+ - cluster_network
+ flags:
+ - startup
+ - name: monmap
+ type: str
+ level: advanced
+ desc: path to MonMap file
+ long_desc: This option is normally used during mkfs, but can also be used to identify
+ which monitors to connect to.
+ services:
+ - mon
+ flags:
+ - no_mon_update
+ - create
+ - name: mon_host
+ type: str
+ level: basic
+ desc: list of hosts or addresses to search for a monitor
+ long_desc: This is a comma, whitespace, or semicolon separated list of IP addresses
+ or hostnames. Hostnames are resolved via DNS and all A or AAAA records are included
+ in the search list.
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - startup
+ - name: mon_host_override
+ type: str
+ level: advanced
+ desc: monitor(s) to use overriding the MonMap
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - startup
+ - name: mon_dns_srv_name
+ type: str
+ level: advanced
+ desc: name of DNS SRV record to check for monitor addresses
+ default: ceph-mon
+ tags:
+ - network
+ services:
+ - common
+ see_also:
+ - mon_host
+ flags:
+ - startup
+ - name: container_image
+ type: str
+ level: basic
+ desc: container image (used by cephadm orchestrator)
+ default: docker.io/ceph/daemon-base:latest-master-devel
+ flags:
+ - startup
+ - name: no_config_file
+ type: bool
+ level: advanced
+ desc: signal that we don't require a config file to be present
+ long_desc: When specified, we won't be looking for a configuration file, and will
+ instead expect that whatever options or values are required for us to work will
+ be passed as arguments.
+ default: false
+ tags:
+ - config
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - startup
+ - name: lockdep
+ type: bool
+ level: dev
+ desc: enable lockdep lock dependency analyzer
+ default: false
+ services:
+ - common
+ flags:
+ - no_mon_update
+ - startup
+ - name: lockdep_force_backtrace
+ type: bool
+ level: dev
+ desc: always gather current backtrace at every lock
+ default: false
+ services:
+ - common
+ see_also:
+ - lockdep
+ flags:
+ - startup
+ - name: run_dir
+ type: str
+ level: advanced
+ desc: path for the 'run' directory for storing pid and socket files
+ default: /var/run/ceph
+ services:
+ - common
+ see_also:
+ - admin_socket
+ flags:
+ - startup
+ - name: admin_socket
+ type: str
+ level: advanced
+ desc: path for the runtime control socket file, used by the 'ceph daemon' command
+ daemon_default: $run_dir/$cluster-$name.asok
+ services:
+ - common
+ flags:
+ - startup
+ - name: admin_socket_mode
+ type: str
+ level: advanced
+ desc: file mode to set for the admin socket file, e.g, '0755'
+ services:
+ - common
+ see_also:
+ - admin_socket
+ flags:
+ - startup
+ - name: daemonize
+ type: bool
+ level: advanced
+ desc: whether to daemonize (background) after startup
+ default: false
+ daemon_default: true
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ see_also:
+ - pid_file
+ - chdir
+ flags:
+ - no_mon_update
+ - startup
+ - name: setuser
+ type: str
+ level: advanced
+ desc: uid or user name to switch to on startup
+ long_desc: This is normally specified by the systemd unit file.
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ see_also:
+ - setgroup
+ flags:
+ - startup
+ - name: setgroup
+ type: str
+ level: advanced
+ desc: gid or group name to switch to on startup
+ long_desc: This is normally specified by the systemd unit file.
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ see_also:
+ - setuser
+ flags:
+ - startup
+ - name: setuser_match_path
+ type: str
+ level: advanced
+ desc: if set, setuser/setgroup is condition on this path matching ownership
+ long_desc: If setuser or setgroup are specified, and this option is non-empty, then
+ the uid/gid of the daemon will only be changed if the file or directory specified
+ by this option has a matching uid and/or gid. This exists primarily to allow
+ switching to user ceph for OSDs to be conditional on whether the osd data contents
+ have also been chowned after an upgrade. This is normally specified by the systemd
+ unit file.
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ see_also:
+ - setuser
+ - setgroup
+ flags:
+ - startup
+ - name: pid_file
+ type: str
+ level: advanced
+ desc: path to write a pid file (if any)
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ flags:
+ - startup
+ - name: chdir
+ type: str
+ level: advanced
+ desc: path to chdir(2) to after daemonizing
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ see_also:
+ - daemonize
+ flags:
+ - no_mon_update
+ - startup
+ - name: fatal_signal_handlers
+ type: bool
+ level: advanced
+ desc: whether to register signal handlers for SIGABRT etc that dump a stack trace
+ long_desc: This is normally true for daemons and values for libraries.
+ default: true
+ tags:
+ - service
+ services:
+ - mon
+ - mgr
+ - osd
+ - mds
+ flags:
+ - startup
+ - name: crash_dir
+ type: str
+ level: advanced
+ desc: Directory where crash reports are archived
+ default: /var/lib/ceph/crash
+ flags:
+ - startup
+ - name: restapi_log_level
+ type: str
+ level: advanced
+ desc: default set by python code
+ - name: restapi_base_url
+ type: str
+ level: advanced
+ desc: default set by python code
+ - name: erasure_code_dir
+ type: str
+ level: advanced
+ desc: directory where erasure-code plugins can be found
+ default: @CEPH_INSTALL_FULL_PKGLIBDIR@/erasure-code
+ services:
+ - mon
+ - osd
+ flags:
+ - startup
+ - name: log_file
+ type: str
+ level: basic
+ desc: path to log file
+ daemon_default: /var/log/ceph/$cluster-$name.log
+ see_also:
+ - log_to_file
+ - log_to_stderr
+ - err_to_stderr
+ - log_to_syslog
+ - err_to_syslog
+ - name: log_max_new
+ type: int
+ level: advanced
+ desc: max unwritten log entries to allow before waiting to flush to the log
+ default: 1000
+ see_also:
+ - log_max_recent
+ - name: log_max_recent
+ type: int
+ level: advanced
+ desc: recent log entries to keep in memory to dump in the event of a crash
+ long_desc: The purpose of this option is to log at a higher debug level only to
+ the in-memory buffer, and write out the detailed log messages only if there is
+ a crash. Only log entries below the lower log level will be written unconditionally
+ to the log. For example, debug_osd=1/5 will write everything <= 1 to the log
+ unconditionally but keep entries at levels 2-5 in memory. If there is a seg fault
+ or assertion failure, all entries will be dumped to the log.
+ default: 500
+ daemon_default: 10000
+ - name: log_to_file
+ type: bool
+ level: basic
+ desc: send log lines to a file
+ default: true
+ see_also:
+ - log_file
+ - name: log_to_stderr
+ type: bool
+ level: basic
+ desc: send log lines to stderr
+ default: true
+ daemon_default: false
+ - name: err_to_stderr
+ type: bool
+ level: basic
+ desc: send critical error log lines to stderr
+ default: false
+ daemon_default: true
+ - name: log_stderr_prefix
+ type: str
+ level: advanced
+ desc: String to prefix log messages with when sent to stderr
+ long_desc: This is useful in container environments when combined with mon_cluster_log_to_stderr. The
+ mon log prefixes each line with the channel name (e.g., 'default', 'audit'), while
+ log_stderr_prefix can be set to 'debug '.
+ see_also:
+ - mon_cluster_log_to_stderr
+ - name: log_to_syslog
+ type: bool
+ level: basic
+ desc: send log lines to syslog facility
+ default: false
+ - name: err_to_syslog
+ type: bool
+ level: basic
+ desc: send critical error log lines to syslog facility
+ default: false
+ - name: log_flush_on_exit
+ type: bool
+ level: advanced
+ desc: set a process exit handler to ensure the log is flushed on exit
+ default: false
+ - name: log_stop_at_utilization
+ type: float
+ level: basic
+ desc: stop writing to the log file when device utilization reaches this ratio
+ default: 0.97
+ see_also:
+ - log_file
+ min: 0
+ max: 1
+ - name: log_to_graylog
+ type: bool
+ level: basic
+ desc: send log lines to remote graylog server
+ default: false
+ see_also:
+ - err_to_graylog
+ - log_graylog_host
+ - log_graylog_port
+ - name: err_to_graylog
+ type: bool
+ level: basic
+ desc: send critical error log lines to remote graylog server
+ default: false
+ see_also:
+ - log_to_graylog
+ - log_graylog_host
+ - log_graylog_port
+ - name: log_graylog_host
+ type: str
+ level: basic
+ desc: address or hostname of graylog server to log to
+ default: 127.0.0.1
+ see_also:
+ - log_to_graylog
+ - err_to_graylog
+ - log_graylog_port
+ - name: log_graylog_port
+ type: int
+ level: basic
+ desc: port number for the remote graylog server
+ default: 12201
+ see_also:
+ - log_graylog_host
+ - name: log_to_journald
+ type: bool
+ level: basic
+ desc: send log lines to journald
+ default: false
+ see_also:
+ - err_to_journald
+ - name: err_to_journald
+ type: bool
+ level: basic
+ desc: send critical error log lines to journald
+ default: false
+ see_also:
+ - log_to_journald
+ - name: log_coarse_timestamps
+ type: bool
+ level: advanced
+ desc: timestamp log entries from coarse system clock to improve performance
+ default: true
+ tags:
+ - performance
+ - service
+ services:
+ - common
+ - name: clog_to_monitors
+ type: str
+ level: advanced
+ desc: Make daemons send cluster log messages to monitors
+ default: default=true
+ flags:
+ - runtime
+ - name: clog_to_syslog
+ type: str
+ level: advanced
+ desc: Make daemons send cluster log messages to syslog
+ default: 'false'
+ flags:
+ - runtime
+ - name: clog_to_syslog_level
+ type: str
+ level: advanced
+ desc: Syslog level for cluster log messages
+ default: info
+ see_also:
+ - clog_to_syslog
+ flags:
+ - runtime
+ - name: clog_to_syslog_facility
+ type: str
+ level: advanced
+ desc: Syslog facility for cluster log messages
+ default: default=daemon audit=local0
+ see_also:
+ - clog_to_syslog
+ flags:
+ - runtime
+ - name: clog_to_graylog
+ type: str
+ level: advanced
+ desc: Make daemons send cluster log to graylog
+ default: 'false'
+ flags:
+ - runtime
+ - name: clog_to_graylog_host
+ type: str
+ level: advanced
+ desc: Graylog host to cluster log messages
+ default: 127.0.0.1
+ see_also:
+ - clog_to_graylog
+ flags:
+ - runtime
+ - name: clog_to_graylog_port
+ type: str
+ level: advanced
+ desc: Graylog port number for cluster log messages
+ default: '12201'
+ see_also:
+ - clog_to_graylog
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_stderr
+ type: bool
+ level: advanced
+ desc: Make monitor send cluster log messages to stderr (prefixed by channel)
+ default: false
+ services:
+ - mon
+ see_also:
+ - log_stderr_prefix
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_syslog
+ type: str
+ level: advanced
+ desc: Make monitor send cluster log messages to syslog
+ default: default=false
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_syslog_level
+ type: str
+ level: advanced
+ desc: Syslog level for cluster log messages
+ default: info
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_to_syslog
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_syslog_facility
+ type: str
+ level: advanced
+ desc: Syslog facility for cluster log messages
+ default: daemon
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_to_syslog
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_file
+ type: bool
+ level: advanced
+ desc: Make monitor send cluster log messages to file
+ default: true
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_file
+ flags:
+ - runtime
+ - name: mon_cluster_log_file
+ type: str
+ level: advanced
+ desc: File(s) to write cluster log to
+ long_desc: This can either be a simple file name to receive all messages, or a list
+ of key/value pairs where the key is the log channel and the value is the filename,
+ which may include $cluster and $channel metavariables
+ default: default=/var/log/ceph/$cluster.$channel.log cluster=/var/log/ceph/$cluster.log
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_to_file
+ flags:
+ - runtime
+ - name: mon_cluster_log_file_level
+ type: str
+ level: advanced
+ desc: Lowest level to include is cluster log file
+ default: debug
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_file
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_graylog
+ type: str
+ level: advanced
+ desc: Make monitor send cluster log to graylog
+ default: 'false'
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_graylog_host
+ type: str
+ level: advanced
+ desc: Graylog host for cluster log messages
+ default: 127.0.0.1
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_to_graylog
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_graylog_port
+ type: str
+ level: advanced
+ desc: Graylog port for cluster log messages
+ default: '12201'
+ services:
+ - mon
+ see_also:
+ - mon_cluster_log_to_graylog
+ flags:
+ - runtime
+ - name: mon_cluster_log_to_journald
+ type: str
+ level: advanced
+ desc: Make monitor send cluster log to journald
+ default: 'false'
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: enable_experimental_unrecoverable_data_corrupting_features
+ type: str
+ level: advanced
+ desc: Enable named (or all with '*') experimental features that may be untested,
+ dangerous, and/or cause permanent data loss
+ flags:
+ - runtime
+ - name: plugin_dir
+ type: str
+ level: advanced
+ desc: Base directory for dynamically loaded plugins
+ default: @CEPH_INSTALL_FULL_PKGLIBDIR@
+ services:
+ - mon
+ - osd
+ flags:
+ - startup
+ - name: compressor_zlib_isal
+ type: bool
+ level: advanced
+ desc: Use Intel ISA-L accelerated zlib implementation if available
+ default: false
+ - name: compressor_zlib_level
+ type: int
+ level: advanced
+ desc: Zlib compression level to use
+ default: 5
+ - name: compressor_zlib_winsize
+ type: int
+ level: advanced
+ desc: Zlib compression winsize to use
+ default: -15
+ min: -15
+ max: 32
+ - name: compressor_zstd_level
+ type: int
+ level: advanced
+ desc: Zstd compression level to use
+ default: 1
+ - name: qat_compressor_enabled
+ type: bool
+ level: advanced
+ desc: Enable Intel QAT acceleration support for compression if available
+ default: false
+ - name: plugin_crypto_accelerator
+ type: str
+ level: advanced
+ desc: Crypto accelerator library to use
+ default: crypto_isal
+ - name: openssl_engine_opts
+ type: str
+ level: advanced
+ desc: Use engine for specific openssl algorithm
+ long_desc: 'Pass opts in this way: engine_id=engine1,dynamic_path=/some/path/engine1.so,default_algorithms=DIGESTS:engine_id=engine2,dynamic_path=/some/path/engine2.so,default_algorithms=CIPHERS,other_ctrl=other_value'
+ flags:
+ - startup
+ - name: mempool_debug
+ type: bool
+ level: dev
+ default: false
+ flags:
+ - no_mon_update
+ - name: thp
+ type: bool
+ level: dev
+ desc: enable transparent huge page (THP) support
+ long_desc: Ceph is known to suffer from memory fragmentation due to THP use. This
+ is indicated by RSS usage above configured memory targets. Enabling THP is currently
+ discouraged until selective use of THP by Ceph is implemented.
+ default: false
+ flags:
+ - startup
+ - name: key
+ type: str
+ level: advanced
+ desc: Authentication key
+ long_desc: A CephX authentication key, base64 encoded. It normally looks something
+ like 'AQAtut9ZdMbNJBAAHz6yBAWyJyz2yYRyeMWDag=='.
+ see_also:
+ - keyfile
+ - keyring
+ flags:
+ - no_mon_update
+ - startup
+ - name: keyfile
+ type: str
+ level: advanced
+ desc: Path to a file containing a key
+ long_desc: The file should contain a CephX authentication key and optionally a trailing
+ newline, but nothing else.
+ see_also:
+ - key
+ flags:
+ - no_mon_update
+ - startup
+ - name: keyring
+ type: str
+ level: advanced
+ desc: Path to a keyring file.
+ long_desc: A keyring file is an INI-style formatted file where the section names
+ are client or daemon names (e.g., 'osd.0') and each section contains a 'key' property
+ with CephX authentication key as the value.
+ default: @keyring_paths@
+ see_also:
+ - key
+ - keyfile
+ flags:
+ - no_mon_update
+ - startup
+ - name: heartbeat_interval
+ type: int
+ level: advanced
+ desc: Frequency of internal heartbeat checks (seconds)
+ default: 5
+ flags:
+ - startup
+ - name: heartbeat_file
+ type: str
+ level: advanced
+ desc: File to touch on successful internal heartbeat
+ long_desc: If set, this file will be touched every time an internal heartbeat check
+ succeeds.
+ see_also:
+ - heartbeat_interval
+ flags:
+ - startup
+ - name: heartbeat_inject_failure
+ type: int
+ level: dev
+ default: 0
+ - name: perf
+ type: bool
+ level: advanced
+ desc: Enable internal performance metrics
+ long_desc: If enabled, collect and expose internal health metrics
+ default: true
+ - name: ms_type
+ type: str
+ level: advanced
+ desc: Messenger implementation to use for network communication
+ default: async+posix
+ flags:
+ - startup
+ - name: ms_public_type
+ type: str
+ level: advanced
+ desc: Messenger implementation to use for the public network
+ long_desc: If not specified, use ms_type
+ see_also:
+ - ms_type
+ flags:
+ - startup
+ - name: ms_cluster_type
+ type: str
+ level: advanced
+ desc: Messenger implementation to use for the internal cluster network
+ long_desc: If not specified, use ms_type
+ see_also:
+ - ms_type
+ flags:
+ - startup
+ - name: ms_mon_cluster_mode
+ type: str
+ level: basic
+ desc: Connection modes (crc, secure) for intra-mon connections in order of preference
+ default: secure crc
+ see_also:
+ - ms_mon_service_mode
+ - ms_mon_client_mode
+ - ms_service_mode
+ - ms_cluster_mode
+ - ms_client_mode
+ flags:
+ - startup
+ - name: ms_mon_service_mode
+ type: str
+ level: basic
+ desc: Allowed connection modes (crc, secure) for connections to mons
+ default: secure crc
+ see_also:
+ - ms_service_mode
+ - ms_mon_cluster_mode
+ - ms_mon_client_mode
+ - ms_cluster_mode
+ - ms_client_mode
+ flags:
+ - startup
+ - name: ms_mon_client_mode
+ type: str
+ level: basic
+ desc: Connection modes (crc, secure) for connections from clients to monitors in
+ order of preference
+ default: secure crc
+ see_also:
+ - ms_mon_service_mode
+ - ms_mon_cluster_mode
+ - ms_service_mode
+ - ms_cluster_mode
+ - ms_client_mode
+ flags:
+ - startup
+ - name: ms_cluster_mode
+ type: str
+ level: basic
+ desc: Connection modes (crc, secure) for intra-cluster connections in order of preference
+ default: crc secure
+ see_also:
+ - ms_service_mode
+ - ms_client_mode
+ flags:
+ - startup
+ - name: ms_service_mode
+ type: str
+ level: basic
+ desc: Allowed connection modes (crc, secure) for connections to daemons
+ default: crc secure
+ see_also:
+ - ms_cluster_mode
+ - ms_client_mode
+ flags:
+ - startup
+ - name: ms_client_mode
+ type: str
+ level: basic
+ desc: Connection modes (crc, secure) for connections from clients in order of preference
+ default: crc secure
+ see_also:
+ - ms_cluster_mode
+ - ms_service_mode
+ flags:
+ - startup
+ - name: ms_learn_addr_from_peer
+ type: bool
+ level: advanced
+ desc: Learn address from what IP our first peer thinks we connect from
+ long_desc: Use the IP address our first peer (usually a monitor) sees that we are
+ connecting from. This is useful if a client is behind some sort of NAT and we
+ want to see it identified by its local (not NATed) address.
+ default: true
+ - name: ms_tcp_nodelay
+ type: bool
+ level: advanced
+ desc: Disable Nagle's algorithm and send queued network traffic immediately
+ default: true
+ - name: ms_tcp_rcvbuf
+ type: size
+ level: advanced
+ desc: Size of TCP socket receive buffer
+ default: 0
+ - name: ms_tcp_prefetch_max_size
+ type: size
+ level: advanced
+ desc: Maximum amount of data to prefetch out of the socket receive buffer
+ default: 4_K
+ - name: ms_initial_backoff
+ type: float
+ level: advanced
+ desc: Initial backoff after a network error is detected (seconds)
+ default: 0.2
+ - name: ms_max_backoff
+ type: float
+ level: advanced
+ desc: Maximum backoff after a network error before retrying (seconds)
+ default: 15
+ see_also:
+ - ms_initial_backoff
+ - name: ms_crc_data
+ type: bool
+ level: dev
+ desc: Set and/or verify crc32c checksum on data payload sent over network
+ default: true
+ - name: ms_crc_header
+ type: bool
+ level: dev
+ desc: Set and/or verify crc32c checksum on header payload sent over network
+ default: true
+ - name: ms_die_on_bad_msg
+ type: bool
+ level: dev
+ desc: Induce a daemon crash/exit when a bad network message is received
+ default: false
+ - name: ms_die_on_unhandled_msg
+ type: bool
+ level: dev
+ desc: Induce a daemon crash/exit when an unrecognized message is received
+ default: false
+ - name: ms_die_on_old_message
+ type: bool
+ level: dev
+ desc: Induce a daemon crash/exit when a old, undecodable message is received
+ default: false
+ - name: ms_die_on_skipped_message
+ type: bool
+ level: dev
+ desc: Induce a daemon crash/exit if sender skips a message sequence number
+ default: false
+ - name: ms_die_on_bug
+ type: bool
+ level: dev
+ desc: Induce a crash/exit on various bugs (for testing purposes)
+ default: false
+ - name: ms_dispatch_throttle_bytes
+ type: size
+ level: advanced
+ desc: Limit messages that are read off the network but still being processed
+ default: 100_M
+ - name: ms_bind_exclude_lo_iface
+ type: bool
+ level: advanced
+ desc: Allow servers to bind loopback network interfaces (lo)
+ default: true
+ flags:
+ - startup
+ - name: ms_bind_ipv4
+ type: bool
+ level: advanced
+ desc: Bind servers to IPv4 address(es)
+ default: true
+ see_also:
+ - ms_bind_ipv6
+ - name: ms_bind_ipv6
+ type: bool
+ level: advanced
+ desc: Bind servers to IPv6 address(es)
+ default: false
+ see_also:
+ - ms_bind_ipv4
+ - name: ms_bind_prefer_ipv4
+ type: bool
+ level: advanced
+ desc: Prefer IPV4 over IPV6 address(es)
+ default: false
+ - name: ms_bind_msgr1
+ type: bool
+ level: advanced
+ desc: Bind servers to msgr1 (legacy) protocol address(es)
+ default: true
+ see_also:
+ - ms_bind_msgr2
+ - name: ms_bind_msgr2
+ type: bool
+ level: advanced
+ desc: Bind servers to msgr2 (nautilus+) protocol address(es)
+ default: true
+ see_also:
+ - ms_bind_msgr1
+ - name: ms_bind_port_min
+ type: int
+ level: advanced
+ desc: Lowest port number to bind daemon(s) to
+ default: 6800
+ - name: ms_bind_port_max
+ type: int
+ level: advanced
+ desc: Highest port number to bind daemon(s) to
+ default: 7300
+ # FreeBSD does not use SO_REAUSEADDR so allow for a bit more time per default
+ - name: ms_bind_retry_count
+ type: int
+ level: advanced
+ desc: Number of attempts to make while bind(2)ing to a port
+ default: @ms_bind_retry_count@
+ # FreeBSD does not use SO_REAUSEADDR so allow for a bit more time per default
+ - name: ms_bind_retry_delay
+ type: int
+ level: advanced
+ desc: Delay between bind(2) attempts (seconds)
+ default: @ms_bind_retry_delay@
+ - name: ms_bind_before_connect
+ type: bool
+ level: advanced
+ desc: Call bind(2) on client sockets
+ default: false
+ - name: ms_tcp_listen_backlog
+ type: int
+ level: advanced
+ desc: Size of queue of incoming connections for accept(2)
+ default: 512
+ - name: ms_connection_ready_timeout
+ type: uint
+ level: advanced
+ desc: Time before we declare a not yet ready connection as dead (seconds)
+ default: 10
+ - name: ms_connection_idle_timeout
+ type: uint
+ level: advanced
+ desc: Time before an idle connection is closed (seconds)
+ default: 900
+ - name: ms_pq_max_tokens_per_priority
+ type: uint
+ level: dev
+ default: 16_M
+ - name: ms_pq_min_cost
+ type: size
+ level: dev
+ default: 64_K
+ - name: ms_inject_socket_failures
+ type: uint
+ level: dev
+ desc: Inject a socket failure every Nth socket operation
+ default: 0
+ - name: ms_inject_delay_type
+ type: str
+ level: dev
+ desc: Entity type to inject delays for
+ flags:
+ - runtime
+ - name: ms_inject_delay_max
+ type: float
+ level: dev
+ desc: Max delay to inject
+ default: 1
+ - name: ms_inject_delay_probability
+ type: float
+ level: dev
+ default: 0
+ - name: ms_inject_internal_delays
+ type: float
+ level: dev
+ desc: Inject various internal delays to induce races (seconds)
+ default: 0
+ - name: ms_blackhole_osd
+ type: bool
+ level: dev
+ default: false
+ - name: ms_blackhole_mon
+ type: bool
+ level: dev
+ default: false
+ - name: ms_blackhole_mds
+ type: bool
+ level: dev
+ default: false
+ - name: ms_blackhole_mgr
+ type: bool
+ level: dev
+ default: false
+ - name: ms_blackhole_client
+ type: bool
+ level: dev
+ default: false
+ - name: ms_dump_on_send
+ type: bool
+ level: advanced
+ desc: Hexdump message to debug log on message send
+ default: false
+ - name: ms_dump_corrupt_message_level
+ type: int
+ level: advanced
+ desc: Log level at which to hexdump corrupt messages we receive
+ default: 1
+ - name: ms_async_op_threads
+ type: uint
+ level: advanced
+ desc: Threadpool size for AsyncMessenger (ms_type=async)
+ default: 3
+ min: 1
+ max: 24
+ - name: ms_async_rdma_device_name
+ type: str
+ level: advanced
+ - name: ms_async_rdma_enable_hugepage
+ type: bool
+ level: advanced
+ default: false
+ - name: ms_async_rdma_buffer_size
+ type: size
+ level: advanced
+ default: 128_K
+ - name: ms_async_rdma_send_buffers
+ type: uint
+ level: advanced
+ default: 1_K
+ - name: ms_async_rdma_receive_buffers
+ type: uint
+ level: advanced
+ default: 32_K
+ - name: ms_async_rdma_receive_queue_len
+ type: uint
+ level: advanced
+ default: 4_K
+ - name: ms_async_rdma_support_srq
+ type: bool
+ level: advanced
+ default: true
+ - name: ms_async_rdma_port_num
+ type: uint
+ level: advanced
+ default: 1
+ - name: ms_async_rdma_polling_us
+ type: uint
+ level: advanced
+ default: 1000
+ - name: ms_async_rdma_gid_idx
+ type: int
+ level: advanced
+ desc: use gid_idx to select GID for choosing RoCEv1 or RoCEv2
+ default: 0
+ - name: ms_async_rdma_local_gid
+ type: str
+ level: advanced
+ - name: ms_async_rdma_roce_ver
+ type: int
+ level: advanced
+ default: 1
+ - name: ms_async_rdma_sl
+ type: int
+ level: advanced
+ default: 3
+ - name: ms_async_rdma_dscp
+ type: int
+ level: advanced
+ default: 96
+ - name: ms_max_accept_failures
+ type: int
+ level: advanced
+ desc: The maximum number of consecutive failed accept() calls before considering
+ the daemon is misconfigured and abort it.
+ default: 4
+ - name: ms_async_rdma_cm
+ type: bool
+ level: advanced
+ default: false
+ - name: ms_async_rdma_type
+ type: str
+ level: advanced
+ default: ib
+ - name: ms_dpdk_port_id
+ type: int
+ level: advanced
+ default: 0
+ - name: ms_dpdk_coremask
+ type: str
+ level: advanced
+ default: '0xF'
+ see_also:
+ - ms_async_op_threads
+ - name: ms_dpdk_memory_channel
+ type: str
+ level: advanced
+ default: '4'
+ - name: ms_dpdk_hugepages
+ type: str
+ level: advanced
+ - name: ms_dpdk_pmd
+ type: str
+ level: advanced
+ - name: ms_dpdk_host_ipv4_addr
+ type: str
+ level: advanced
+ - name: ms_dpdk_gateway_ipv4_addr
+ type: str
+ level: advanced
+ - name: ms_dpdk_netmask_ipv4_addr
+ type: str
+ level: advanced
+ - name: ms_dpdk_lro
+ type: bool
+ level: advanced
+ default: true
+ - name: ms_dpdk_hw_flow_control
+ type: bool
+ level: advanced
+ default: true
+ - name: ms_dpdk_hw_queue_weight
+ type: float
+ level: advanced
+ default: 1
+ - name: ms_dpdk_debug_allow_loopback
+ type: bool
+ level: dev
+ default: false
+ - name: ms_dpdk_rx_buffer_count_per_core
+ type: int
+ level: advanced
+ default: 8192
+ - name: inject_early_sigterm
+ type: bool
+ level: dev
+ desc: send ourselves a SIGTERM early during startup
+ default: false
+ - name: mon_enable_op_tracker
+ type: bool
+ level: advanced
+ desc: enable/disable MON op tracking
+ default: true
+ services:
+ - mon
+ - name: mon_op_complaint_time
+ type: secs
+ level: advanced
+ desc: time after which to consider a monitor operation blocked after no updates
+ default: 30
+ services:
+ - mon
+ - name: mon_op_log_threshold
+ type: int
+ level: advanced
+ desc: max number of slow ops to display
+ default: 5
+ services:
+ - mon
+ - name: mon_op_history_size
+ type: uint
+ level: advanced
+ desc: max number of completed ops to track
+ default: 20
+ services:
+ - mon
+ - name: mon_op_history_duration
+ type: secs
+ level: advanced
+ desc: expiration time in seconds of historical MON OPS
+ default: 10_min
+ services:
+ - mon
+ - name: mon_op_history_slow_op_size
+ type: uint
+ level: advanced
+ desc: max number of slow historical MON OPS to keep
+ default: 20
+ services:
+ - mon
+ - name: mon_op_history_slow_op_threshold
+ type: secs
+ level: advanced
+ desc: duration of an op to be considered as a historical slow op
+ default: 10
+ services:
+ - mon
+ - name: mon_data
+ type: str
+ level: advanced
+ desc: path to mon database
+ default: /var/lib/ceph/mon/$cluster-$id
+ services:
+ - mon
+ flags:
+ - no_mon_update
+ - name: mon_initial_members
+ type: str
+ level: advanced
+ services:
+ - mon
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_compact_on_start
+ type: bool
+ level: advanced
+ default: false
+ services:
+ - mon
+ - name: mon_compact_on_bootstrap
+ type: bool
+ level: advanced
+ default: false
+ services:
+ - mon
+ - name: mon_compact_on_trim
+ type: bool
+ level: advanced
+ default: true
+ services:
+ - mon
+ - name: mon_osdmap_full_prune_enabled
+ type: bool
+ level: advanced
+ desc: enables pruning full osdmap versions when we go over a given number of maps
+ default: true
+ services:
+ - mon
+ see_also:
+ - mon_osdmap_full_prune_min
+ - mon_osdmap_full_prune_interval
+ - mon_osdmap_full_prune_txsize
+ - name: mon_osdmap_full_prune_min
+ type: uint
+ level: advanced
+ desc: minimum number of versions in the store to trigger full map pruning
+ default: 10000
+ services:
+ - mon
+ see_also:
+ - mon_osdmap_full_prune_enabled
+ - mon_osdmap_full_prune_interval
+ - mon_osdmap_full_prune_txsize
+ - name: mon_osdmap_full_prune_interval
+ type: uint
+ level: advanced
+ desc: interval between maps that will not be pruned; maps in the middle will be
+ pruned.
+ default: 10
+ services:
+ - mon
+ see_also:
+ - mon_osdmap_full_prune_enabled
+ - mon_osdmap_full_prune_interval
+ - mon_osdmap_full_prune_txsize
+ - name: mon_osdmap_full_prune_txsize
+ type: uint
+ level: advanced
+ desc: number of maps we will prune per iteration
+ default: 100
+ services:
+ - mon
+ see_also:
+ - mon_osdmap_full_prune_enabled
+ - mon_osdmap_full_prune_interval
+ - mon_osdmap_full_prune_txsize
+ - name: mon_osd_cache_size
+ type: int
+ level: advanced
+ desc: maximum number of OSDMaps to cache in memory
+ default: 500
+ services:
+ - mon
+ - name: mon_osd_cache_size_min
+ type: size
+ level: advanced
+ desc: The minimum amount of bytes to be kept mapped in memory for osd monitor caches.
+ default: 128_M
+ services:
+ - mon
+ - name: mon_memory_target
+ type: size
+ level: basic
+ desc: The amount of bytes pertaining to osd monitor caches and kv cache to be kept
+ mapped in memory with cache auto-tuning enabled
+ default: 2_G
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_memory_autotune
+ type: bool
+ level: basic
+ desc: Autotune the cache memory being used for osd monitors and kv database
+ default: true
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_cpu_threads
+ type: int
+ level: advanced
+ desc: worker threads for CPU intensive background work
+ default: 4
+ services:
+ - mon
+ - name: mon_osd_mapping_pgs_per_chunk
+ type: int
+ level: dev
+ desc: granularity of PG placement calculation background work
+ default: 4096
+ services:
+ - mon
+ - name: mon_clean_pg_upmaps_per_chunk
+ type: uint
+ level: dev
+ desc: granularity of PG upmap validation background work
+ default: 256
+ services:
+ - mon
+ - name: mon_osd_max_creating_pgs
+ type: int
+ level: advanced
+ desc: maximum number of PGs the mon will create at once
+ default: 1024
+ services:
+ - mon
+ - name: mon_osd_max_initial_pgs
+ type: int
+ level: advanced
+ desc: maximum number of PGs a pool will created with
+ long_desc: If the user specifies more PGs than this, the cluster will subsequently
+ split PGs after the pool is created in order to reach the target.
+ default: 1024
+ services:
+ - mon
+ - name: mon_tick_interval
+ type: int
+ level: advanced
+ desc: interval for internal mon background checks
+ default: 5
+ services:
+ - mon
+ - name: mon_session_timeout
+ type: int
+ level: advanced
+ desc: close inactive mon client connections after this many seconds
+ default: 5_min
+ services:
+ - mon
+ - name: mon_subscribe_interval
+ type: float
+ level: dev
+ desc: subscribe interval for pre-jewel clients
+ default: 1_day
+ services:
+ - mon
+ - name: mon_delta_reset_interval
+ type: float
+ level: advanced
+ desc: window duration for rate calculations in 'ceph status'
+ default: 10
+ services:
+ - mon
+ - mon
+ - name: mon_osd_laggy_halflife
+ type: int
+ level: advanced
+ desc: halflife of OSD 'lagginess' factor
+ default: 1_hr
+ services:
+ - mon
+ - name: mon_osd_laggy_weight
+ type: float
+ level: advanced
+ desc: how heavily to weight OSD marking itself back up in overall laggy_probability
+ long_desc: 1.0 means that an OSD marking itself back up (because it was marked down
+ but not actually dead) means a 100% laggy_probability; 0.0 effectively disables
+ tracking of laggy_probability.
+ default: 0.3
+ services:
+ - mon
+ min: 0
+ max: 1
+ - name: mon_osd_laggy_max_interval
+ type: int
+ level: advanced
+ desc: cap value for period for OSD to be marked for laggy_interval calculation
+ default: 5_min
+ services:
+ - mon
+ - name: mon_osd_adjust_heartbeat_grace
+ type: bool
+ level: advanced
+ desc: increase OSD heartbeat grace if peers appear to be laggy
+ long_desc: If an OSD is marked down but then marks itself back up, it implies it
+ wasn't actually down but was unable to respond to heartbeats. If this option
+ is true, we can use the laggy_probability and laggy_interval values calculated
+ to model this situation to increase the heartbeat grace period for this OSD so
+ that it isn't marked down again. laggy_probability is an estimated probability
+ that the given OSD is down because it is laggy (not actually down), and laggy_interval
+ is an estiate on how long it stays down when it is laggy.
+ default: true
+ services:
+ - mon
+ see_also:
+ - mon_osd_laggy_halflife
+ - mon_osd_laggy_weight
+ - mon_osd_laggy_max_interval
+ - name: mon_osd_adjust_down_out_interval
+ type: bool
+ level: advanced
+ desc: increase the mon_osd_down_out_interval if an OSD appears to be laggy
+ default: true
+ services:
+ - mon
+ see_also:
+ - mon_osd_adjust_heartbeat_grace
+ - name: mon_osd_auto_mark_in
+ type: bool
+ level: advanced
+ desc: mark any OSD that comes up 'in'
+ default: false
+ services:
+ - mon
+ - name: mon_osd_auto_mark_auto_out_in
+ type: bool
+ level: advanced
+ desc: mark any OSD that comes up that was automatically marked 'out' back 'in'
+ default: true
+ services:
+ - mon
+ see_also:
+ - mon_osd_down_out_interval
+ - name: mon_osd_auto_mark_new_in
+ type: bool
+ level: advanced
+ desc: mark any new OSD that comes up 'in'
+ default: true
+ services:
+ - mon
+ - name: mon_osd_destroyed_out_interval
+ type: int
+ level: advanced
+ desc: mark any OSD 'out' that has been 'destroy'ed for this long (seconds)
+ default: 10_min
+ services:
+ - mon
+ - name: mon_osd_down_out_interval
+ type: int
+ level: advanced
+ desc: mark any OSD 'out' that has been 'down' for this long (seconds)
+ default: 10_min
+ services:
+ - mon
+ - name: mon_osd_down_out_subtree_limit
+ type: str
+ level: advanced
+ desc: do not automatically mark OSDs 'out' if an entire subtree of this size is
+ down
+ default: rack
+ services:
+ - mon
+ see_also:
+ - mon_osd_down_out_interval
+ flags:
+ - runtime
+ - name: mon_osd_min_up_ratio
+ type: float
+ level: advanced
+ desc: do not automatically mark OSDs 'out' if fewer than this many OSDs are 'up'
+ default: 0.3
+ services:
+ - mon
+ see_also:
+ - mon_osd_down_out_interval
+ - name: mon_osd_min_in_ratio
+ type: float
+ level: advanced
+ desc: do not automatically mark OSDs 'out' if fewer than this many OSDs are 'in'
+ default: 0.75
+ services:
+ - mon
+ see_also:
+ - mon_osd_down_out_interval
+ - name: mon_osd_warn_op_age
+ type: float
+ level: advanced
+ desc: issue REQUEST_SLOW health warning if OSD ops are slower than this age (seconds)
+ default: 32
+ services:
+ - mgr
+ - name: mon_osd_warn_num_repaired
+ type: uint
+ level: advanced
+ desc: issue OSD_TOO_MANY_REPAIRS health warning if an OSD has more than this many
+ read repairs
+ default: 10
+ services:
+ - mon
+ - name: mon_osd_err_op_age_ratio
+ type: float
+ level: advanced
+ desc: issue REQUEST_STUCK health error if OSD ops are slower than is age (seconds)
+ default: 128
+ services:
+ - mgr
+ - name: mon_osd_prime_pg_temp
+ type: bool
+ level: dev
+ desc: minimize peering work by priming pg_temp values after a map change
+ default: true
+ services:
+ - mon
+ - name: mon_osd_prime_pg_temp_max_time
+ type: float
+ level: dev
+ desc: maximum time to spend precalculating PG mappings on map change (seconds)
+ default: 0.5
+ services:
+ - mon
+ - name: mon_osd_prime_pg_temp_max_estimate
+ type: float
+ level: advanced
+ desc: calculate all PG mappings if estimated fraction of PGs that change is above
+ this amount
+ default: 0.25
+ services:
+ - mon
+ - name: mon_stat_smooth_intervals
+ type: uint
+ level: advanced
+ desc: number of PGMaps stats over which we calc the average read/write throughput
+ of the whole cluster
+ default: 6
+ services:
+ - mgr
+ min: 1
+ - name: mon_election_timeout
+ type: float
+ level: advanced
+ desc: maximum time for a mon election (seconds)
+ default: 5
+ services:
+ - mon
+ - name: mon_election_default_strategy
+ type: uint
+ level: advanced
+ desc: The election strategy to set when constructing the first monmap.
+ default: 1
+ min: 1
+ max: 3
+ - name: mon_lease
+ type: float
+ level: advanced
+ desc: lease interval between quorum monitors (seconds)
+ long_desc: This setting controls how sensitive your mon quorum is to intermittent
+ network issues or other failures.
+ default: 5
+ services:
+ - mon
+ - name: mon_lease_renew_interval_factor
+ type: float
+ level: advanced
+ desc: multiple of mon_lease for the lease renewal interval
+ long_desc: Leases must be renewed before they time out. A smaller value means frequent
+ renewals, while a value close to 1 makes a lease expiration more likely.
+ default: 0.6
+ services:
+ - mon
+ see_also:
+ - mon_lease
+ min: 0
+ max: 0.9999999
+ - name: mon_lease_ack_timeout_factor
+ type: float
+ level: advanced
+ desc: multiple of mon_lease for the lease ack interval before calling new election
+ default: 2
+ services:
+ - mon
+ see_also:
+ - mon_lease
+ min: 1.0001
+ max: 100
+ - name: mon_accept_timeout_factor
+ type: float
+ level: advanced
+ desc: multiple of mon_lease for follower mons to accept proposed state changes before
+ calling a new election
+ default: 2
+ services:
+ - mon
+ see_also:
+ - mon_lease
+ - name: mon_elector_ping_timeout
+ type: float
+ level: advanced
+ desc: The time after which a ping 'times out' and a connection is considered down
+ default: 2
+ services:
+ - mon
+ see_also:
+ - mon_elector_ping_divisor
+ - name: mon_elector_ping_divisor
+ type: uint
+ level: advanced
+ desc: We will send a ping up to this many times per timeout per
+ default: 2
+ services:
+ - mon
+ see_also:
+ - mon_elector_ping_timeout
+ - name: mon_con_tracker_persist_interval
+ type: uint
+ level: advanced
+ desc: how many updates the ConnectionTracker takes before it persists to disk
+ default: 10
+ services:
+ - mon
+ min: 1
+ max: 100000
+ - name: mon_con_tracker_score_halflife
+ type: uint
+ level: advanced
+ desc: The 'halflife' used when updating/calculating peer connection scores
+ default: 43200
+ services:
+ - mon
+ min: 60
+ - name: mon_elector_ignore_propose_margin
+ type: float
+ level: advanced
+ desc: The difference in connection score allowed before a peon stops ignoring out-of-quorum
+ PROPOSEs
+ default: 0
+ services:
+ - mon
+ - name: mon_warn_on_degraded_stretch_mode
+ type: bool
+ level: advanced
+ desc: Issue a health warning if we are in degraded stretch mode
+ default: true
+ services:
+ - mon
+ - name: mon_stretch_cluster_recovery_ratio
+ type: float
+ level: advanced
+ desc: the ratio of up OSDs at which a degraded stretch cluster enters recovery
+ default: 0
+ services:
+ - mon
+ min: 0
+ max: 1
+ - name: mon_stretch_recovery_min_wait
+ type: float
+ level: advanced
+ desc: how long the monitors wait before considering fully-healthy PGs as evidence
+ the stretch mode is repaired
+ default: 15
+ services:
+ - mon
+ min: 1
+ - name: mon_stretch_pool_size
+ type: uint
+ level: dev
+ default: 4
+ services:
+ - mon
+ min: 3
+ max: 6
+ - name: mon_stretch_pool_min_size
+ type: uint
+ level: dev
+ default: 2
+ services:
+ - mon
+ min: 2
+ max: 4
+ - name: mon_clock_drift_allowed
+ type: float
+ level: advanced
+ desc: allowed clock drift (in seconds) between mons before issuing a health warning
+ default: 0.05
+ services:
+ - mon
+ - name: mon_clock_drift_warn_backoff
+ type: float
+ level: advanced
+ desc: exponential backoff factor for logging clock drift warnings in the cluster
+ log
+ default: 5
+ services:
+ - mon
+ - name: mon_timecheck_interval
+ type: float
+ level: advanced
+ desc: frequency of clock synchronization checks between monitors (seconds)
+ default: 5_min
+ services:
+ - mon
+ - name: mon_timecheck_skew_interval
+ type: float
+ level: advanced
+ desc: frequency of clock synchronization (re)checks between monitors while clocks
+ are believed to be skewed (seconds)
+ default: 30
+ services:
+ - mon
+ see_also:
+ - mon_timecheck_interval
+ - name: mon_pg_stuck_threshold
+ type: int
+ level: advanced
+ desc: number of seconds after which pgs can be considered stuck inactive, unclean,
+ etc
+ long_desc: see doc/control.rst under dump_stuck for more info
+ default: 1_min
+ services:
+ - mgr
+ - name: mon_pg_warn_min_per_osd
+ type: uint
+ level: advanced
+ desc: minimal number PGs per (in) osd before we warn the admin
+ default: 0
+ services:
+ - mgr
+ - name: mon_max_pg_per_osd
+ type: uint
+ level: advanced
+ desc: Max number of PGs per OSD the cluster will allow
+ long_desc: If the number of PGs per OSD exceeds this, a health warning will be visible
+ in `ceph status`. This is also used in automated PG management, as the threshold
+ at which some pools' pg_num may be shrunk in order to enable increasing the pg_num
+ of others.
+ default: 250
+ services:
+ - mgr
+ min: 1
+ - name: mon_target_pg_per_osd
+ type: uint
+ level: advanced
+ desc: Automated PG management creates this many PGs per OSD
+ long_desc: When creating pools, the automated PG management logic will attempt to
+ reach this target. In some circumstances, it may exceed this target, up to the
+ ``mon_max_pg_per_osd`` limit. Conversely, a lower number of PGs per OSD may be
+ created if the cluster is not yet fully utilised
+ default: 100
+ min: 1
+ - name: mon_pg_warn_max_object_skew
+ type: float
+ level: advanced
+ desc: max skew few average in objects per pg
+ default: 10
+ services:
+ - mgr
+ - name: mon_pg_warn_min_objects
+ type: int
+ level: advanced
+ desc: 'do not warn below this object #'
+ default: 10000
+ services:
+ - mgr
+ - name: mon_pg_warn_min_pool_objects
+ type: int
+ level: advanced
+ desc: 'do not warn on pools below this object #'
+ default: 1000
+ services:
+ - mgr
+ - name: mon_pg_check_down_all_threshold
+ type: float
+ level: advanced
+ desc: threshold of down osds after which we check all pgs
+ default: 0.5
+ services:
+ - mgr
+ - name: mon_cache_target_full_warn_ratio
+ type: float
+ level: advanced
+ desc: issue CACHE_POOL_NEAR_FULL health warning when cache pool utilization exceeds
+ this ratio of usable space
+ default: 0.66
+ services:
+ - mgr
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_osd_full_ratio
+ type: float
+ level: advanced
+ desc: full ratio of OSDs to be set during initial creation of the cluster
+ default: 0.95
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_osd_backfillfull_ratio
+ type: float
+ level: advanced
+ default: 0.9
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_osd_nearfull_ratio
+ type: float
+ level: advanced
+ desc: nearfull ratio for OSDs to be set during initial creation of cluster
+ default: 0.85
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_osd_initial_require_min_compat_client
+ type: str
+ level: advanced
+ default: luminous
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mon_allow_pool_delete
+ type: bool
+ level: advanced
+ desc: allow pool deletions
+ default: false
+ services:
+ - mon
+ - name: mon_fake_pool_delete
+ type: bool
+ level: advanced
+ desc: fake pool deletions by renaming the rados pool
+ default: false
+ services:
+ - mon
+ - name: mon_globalid_prealloc
+ type: uint
+ level: advanced
+ desc: number of globalid values to preallocate
+ long_desc: This setting caps how many new clients can authenticate with the cluster
+ before the monitors have to perform a write to preallocate more. Large values
+ burn through the 64-bit ID space more quickly.
+ default: 10000
+ services:
+ - mon
+ - name: mon_osd_report_timeout
+ type: int
+ level: advanced
+ desc: time before OSDs who do not report to the mons are marked down (seconds)
+ default: 15_min
+ services:
+ - mon
++- name: mon_warn_on_insecure_global_id_reclaim
++ type: bool
++ level: advanced
++ desc: issue AUTH_INSECURE_GLOBAL_ID_RECLAIM health warning if any connected
++ clients are insecurely reclaiming global_id
++ default: true
++ services:
++ - mon
++ see_also:
++ - mon_warn_on_insecure_global_id_reclaim_allowed
++ - auth_allow_insecure_global_id_reclaim
++ - auth_expose_insecure_global_id_reclaim
++- name: mon_warn_on_insecure_global_id_reclaim_allowed
++ type: bool
++ level: advanced
++ desc: issue AUTH_INSECURE_GLOBAL_ID_RECLAIM_ALLOWED health warning if insecure
++ global_id reclaim is allowed
++ default: true
++ services:
++ - mon
++ see_also:
++ - mon_warn_on_insecure_global_id_reclaim
++ - auth_allow_insecure_global_id_reclaim
++ - auth_expose_insecure_global_id_reclaim
+ - name: mon_warn_on_msgr2_not_enabled
+ type: bool
+ level: advanced
+ desc: issue MON_MSGR2_NOT_ENABLED health warning if monitors are all running Nautilus
+ but not all binding to a msgr2 port
+ default: true
+ services:
+ - mon
+ see_also:
+ - ms_bind_msgr2
+ - name: mon_warn_on_legacy_crush_tunables
+ type: bool
+ level: advanced
+ desc: issue OLD_CRUSH_TUNABLES health warning if CRUSH tunables are older than mon_crush_min_required_version
+ default: true
+ services:
+ - mgr
+ see_also:
+ - mon_crush_min_required_version
+ - name: mon_crush_min_required_version
+ type: str
+ level: advanced
+ desc: minimum ceph release to use for mon_warn_on_legacy_crush_tunables
+ default: hammer
+ services:
+ - mgr
+ see_also:
+ - mon_warn_on_legacy_crush_tunables
+ - name: mon_warn_on_crush_straw_calc_version_zero
+ type: bool
+ level: advanced
+ desc: issue OLD_CRUSH_STRAW_CALC_VERSION health warning if the CRUSH map's straw_calc_version
+ is zero
+ default: true
+ services:
+ - mgr
+ - name: mon_warn_on_osd_down_out_interval_zero
+ type: bool
+ level: advanced
+ desc: issue OSD_NO_DOWN_OUT_INTERVAL health warning if mon_osd_down_out_interval
+ is zero
+ long_desc: Having mon_osd_down_out_interval set to 0 means that down OSDs are not
+ marked out automatically and the cluster does not heal itself without administrator
+ intervention.
+ default: true
+ services:
+ - mgr
+ see_also:
+ - mon_osd_down_out_interval
+ - name: mon_warn_on_cache_pools_without_hit_sets
+ type: bool
+ level: advanced
+ desc: issue CACHE_POOL_NO_HIT_SET health warning for cache pools that do not have
+ hit sets configured
+ default: true
+ services:
+ - mgr
+ - name: mon_warn_on_pool_no_app
+ type: bool
+ level: dev
+ desc: issue POOL_APP_NOT_ENABLED health warning if pool has not application enabled
+ default: true
+ services:
+ - mgr
+ - name: mon_warn_on_pool_pg_num_not_power_of_two
+ type: bool
+ level: dev
+ desc: issue POOL_PG_NUM_NOT_POWER_OF_TWO warning if pool has a non-power-of-two
+ pg_num value
+ default: true
+ services:
+ - mon
+ - name: mon_warn_on_pool_no_redundancy
+ type: bool
+ level: advanced
+ desc: Issue a health warning if any pool is configured with no replicas
+ default: true
+ services:
+ - mon
+ see_also:
+ - osd_pool_default_size
+ - osd_pool_default_min_size
+ - name: mon_allow_pool_size_one
+ type: bool
+ level: advanced
+ desc: allow configuring pool with no replicas
+ default: false
+ services:
+ - mon
+ - name: mon_warn_on_misplaced
+ type: bool
+ level: advanced
+ desc: Issue a health warning if there are misplaced objects
+ default: false
+ services:
+ - mgr
+ - name: mon_warn_on_too_few_osds
+ type: bool
+ level: advanced
+ desc: Issue a health warning if there are fewer OSDs than osd_pool_default_size
+ default: true
+ services:
+ - mgr
+ - name: mon_warn_on_slow_ping_time
+ type: float
+ level: advanced
+ desc: Override mon_warn_on_slow_ping_ratio with specified threshold in milliseconds
+ default: 0
+ services:
+ - mgr
+ see_also:
+ - mon_warn_on_slow_ping_ratio
+ - name: mon_warn_on_slow_ping_ratio
+ type: float
+ level: advanced
+ desc: Issue a health warning if heartbeat ping longer than percentage of osd_heartbeat_grace
+ default: 0.05
+ services:
+ - mgr
+ see_also:
+ - osd_heartbeat_grace
+ - mon_warn_on_slow_ping_time
+ - name: mon_max_snap_prune_per_epoch
+ type: uint
+ level: advanced
+ desc: max number of pruned snaps we will process in a single OSDMap epoch
+ default: 100
+ services:
+ - mon
+ - name: mon_min_osdmap_epochs
+ type: int
+ level: advanced
+ desc: min number of OSDMaps to store
+ default: 500
+ services:
+ - mon
+ - name: mon_max_log_epochs
+ type: int
+ level: advanced
+ desc: max number of past cluster log epochs to store
+ default: 500
+ services:
+ - mon
+ - name: mon_max_mdsmap_epochs
+ type: int
+ level: advanced
+ desc: max number of FSMaps/MDSMaps to store
+ default: 500
+ services:
+ - mon
+ - name: mon_max_mgrmap_epochs
+ type: int
+ level: advanced
+ desc: max number of MgrMaps to store
+ default: 500
+ services:
+ - mon
+ - name: mon_max_osd
+ type: int
+ level: advanced
+ desc: max number of OSDs in a cluster
+ default: 10000
+ services:
+ - mon
+ - name: mon_probe_timeout
+ type: float
+ level: advanced
+ desc: timeout for querying other mons during bootstrap pre-election phase (seconds)
+ default: 2
+ services:
+ - mon
+ - name: mon_client_bytes
+ type: size
+ level: advanced
+ desc: max bytes of outstanding client messages mon will read off the network
+ default: 100_M
+ services:
+ - mon
+ - name: mon_daemon_bytes
+ type: size
+ level: advanced
+ desc: max bytes of outstanding mon messages mon will read off the network
+ default: 400_M
+ services:
+ - mon
+ - name: mon_mgr_proxy_client_bytes_ratio
+ type: float
+ level: dev
+ desc: ratio of mon_client_bytes that can be consumed by proxied mgr commands before
+ we error out to client
+ default: 0.3
+ services:
+ - mon
+ - name: mon_log_max_summary
+ type: uint
+ level: advanced
+ desc: number of recent cluster log messages to retain
+ default: 50
+ services:
+ - mon
+ - name: mon_max_log_entries_per_event
+ type: int
+ level: advanced
+ desc: max cluster log entries per paxos event
+ default: 4096
+ services:
+ - mon
+ - name: mon_reweight_min_pgs_per_osd
+ type: uint
+ level: advanced
+ default: 10
+ services:
+ - mgr
+ - name: mon_reweight_min_bytes_per_osd
+ type: size
+ level: advanced
+ default: 100_M
+ services:
+ - mgr
+ - name: mon_reweight_max_osds
+ type: int
+ level: advanced
+ default: 4
+ services:
+ - mgr
+ - name: mon_reweight_max_change
+ type: float
+ level: advanced
+ default: 0.05
+ services:
+ - mgr
+ - name: mon_health_to_clog
+ type: bool
+ level: advanced
+ desc: log monitor health to cluster log
+ default: true
+ services:
+ - mon
+ - name: mon_health_to_clog_interval
+ type: int
+ level: advanced
+ desc: frequency to log monitor health to cluster log
+ default: 10_min
+ services:
+ - mon
+ see_also:
+ - mon_health_to_clog
+ - name: mon_health_to_clog_tick_interval
+ type: float
+ level: dev
+ default: 1_min
+ services:
+ - mon
+ - name: mon_health_detail_to_clog
+ type: bool
+ level: dev
+ desc: log health detail to cluster log
+ default: true
+ - name: mon_health_max_detail
+ type: uint
+ level: advanced
+ desc: max detailed pgs to report in health detail
+ default: 50
+ services:
+ - mon
+ - name: mon_health_log_update_period
+ type: int
+ level: dev
+ desc: minimum time in seconds between log messages about each health check
+ default: 5
+ services:
+ - mon
+ min: 0
+ - name: mon_data_avail_crit
+ type: int
+ level: advanced
+ desc: issue MON_DISK_CRIT health error when mon available space below this percentage
+ default: 5
+ services:
+ - mon
+ - name: mon_data_avail_warn
+ type: int
+ level: advanced
+ desc: issue MON_DISK_LOW health warning when mon available space below this percentage
+ default: 30
+ services:
+ - mon
+ - name: mon_data_size_warn
+ type: size
+ level: advanced
+ desc: issue MON_DISK_BIG health warning when mon database is above this size
+ default: 15_G
+ services:
+ - mon
+ - name: mon_warn_pg_not_scrubbed_ratio
+ type: float
+ level: advanced
+ desc: Percentage of the scrub max interval past the scrub max interval to warn
+ default: 0.5
+ see_also:
+ - osd_scrub_max_interval
+ min: 0
+ - name: mon_warn_pg_not_deep_scrubbed_ratio
+ type: float
+ level: advanced
+ desc: Percentage of the deep scrub interval past the deep scrub interval to warn
+ default: 0.75
+ see_also:
+ - osd_deep_scrub_interval
+ min: 0
+ - name: mon_scrub_interval
+ type: secs
+ level: advanced
+ desc: frequency for scrubbing mon database
+ default: 1_day
+ services:
+ - mon
+ - name: mon_scrub_timeout
+ type: int
+ level: advanced
+ desc: timeout to restart scrub of mon quorum participant does not respond for the
+ latest chunk
+ default: 5_min
+ services:
+ - mon
+ - name: mon_scrub_max_keys
+ type: int
+ level: advanced
+ desc: max keys per on scrub chunk/step
+ default: 100
+ services:
+ - mon
+ - name: mon_scrub_inject_crc_mismatch
+ type: float
+ level: dev
+ desc: probability for injecting crc mismatches into mon scrub
+ default: 0
+ services:
+ - mon
+ - name: mon_scrub_inject_missing_keys
+ type: float
+ level: dev
+ desc: probability for injecting missing keys into mon scrub
+ default: 0
+ services:
+ - mon
+ - name: mon_config_key_max_entry_size
+ type: size
+ level: advanced
+ desc: Defines the number of bytes allowed to be held in a single config-key entry
+ default: 64_K
+ services:
+ - mon
+ - name: mon_sync_timeout
+ type: float
+ level: advanced
+ desc: timeout before canceling sync if syncing mon does not respond
+ default: 1_min
+ services:
+ - mon
+ - name: mon_sync_max_payload_size
+ type: size
+ level: advanced
+ desc: target max message payload for mon sync
+ default: 1_M
+ services:
+ - mon
+ - name: mon_sync_max_payload_keys
+ type: int
+ level: advanced
+ desc: target max keys in message payload for mon sync
+ default: 2000
+ services:
+ - mon
+ - name: mon_sync_debug
+ type: bool
+ level: dev
+ desc: enable extra debugging during mon sync
+ default: false
+ services:
+ - mon
+ - name: mon_inject_sync_get_chunk_delay
+ type: float
+ level: dev
+ desc: inject delay during sync (seconds)
+ default: 0
+ services:
+ - mon
+ - name: mon_osd_min_down_reporters
+ type: uint
+ level: advanced
+ desc: number of OSDs from different subtrees who need to report a down OSD for it
+ to count
+ default: 2
+ services:
+ - mon
+ see_also:
+ - mon_osd_reporter_subtree_level
+ - name: mon_osd_reporter_subtree_level
+ type: str
+ level: advanced
+ desc: in which level of parent bucket the reporters are counted
+ default: host
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_osd_snap_trim_queue_warn_on
+ type: int
+ level: advanced
+ desc: Warn when snap trim queue is that large (or larger).
+ long_desc: Warn when snap trim queue length for at least one PG crosses this value,
+ as this is indicator of snap trimmer not keeping up, wasting disk space
+ default: 32768
+ services:
+ - mon
+ - name: mon_osd_force_trim_to
+ type: int
+ level: dev
+ desc: force mons to trim osdmaps through this epoch
+ default: 0
+ services:
+ - mon
+ - name: mon_mds_force_trim_to
+ type: int
+ level: dev
+ desc: force mons to trim mdsmaps/fsmaps through this epoch
+ default: 0
+ services:
+ - mon
+ - name: mon_mds_skip_sanity
+ type: bool
+ level: advanced
+ desc: skip sanity checks on fsmap/mdsmap
+ default: false
+ services:
+ - mon
+ - name: mon_debug_extra_checks
+ type: bool
+ level: dev
+ desc: Enable some additional monitor checks
+ long_desc: Enable some additional monitor checks that would be too expensive to
+ run on production systems, or would only be relevant while testing or debugging.
+ default: false
+ services:
+ - mon
+ - name: mon_debug_block_osdmap_trim
+ type: bool
+ level: dev
+ desc: Block OSDMap trimming while the option is enabled.
+ long_desc: Blocking OSDMap trimming may be quite helpful to easily reproduce states
+ in which the monitor keeps (hundreds of) thousands of osdmaps.
+ default: false
+ services:
+ - mon
+ - name: mon_debug_deprecated_as_obsolete
+ type: bool
+ level: dev
+ desc: treat deprecated mon commands as obsolete
+ default: false
+ services:
+ - mon
+ - name: mon_debug_dump_transactions
+ type: bool
+ level: dev
+ desc: dump paxos transactions to log
+ default: false
+ services:
+ - mon
+ see_also:
+ - mon_debug_dump_location
+ - name: mon_debug_dump_json
+ type: bool
+ level: dev
+ desc: dump paxos transasctions to log as json
+ default: false
+ services:
+ - mon
+ see_also:
+ - mon_debug_dump_transactions
+ - name: mon_debug_dump_location
+ type: str
+ level: dev
+ desc: file to dump paxos transactions to
+ default: /var/log/ceph/$cluster-$name.tdump
+ services:
+ - mon
+ see_also:
+ - mon_debug_dump_transactions
+ - name: mon_debug_no_require_pacific
+ type: bool
+ level: dev
+ desc: do not set pacific feature for new mon clusters
+ default: false
+ services:
+ - mon
+ flags:
+ - cluster_create
+ - name: mon_debug_no_require_quincy
+ type: bool
+ level: dev
+ desc: do not set quincy feature for new mon clusters
+ default: false
+ services:
+ - mon
+ flags:
+ - cluster_create
+ - name: mon_debug_no_require_bluestore_for_ec_overwrites
+ type: bool
+ level: dev
+ desc: do not require bluestore OSDs to enable EC overwrites on a rados pool
+ default: false
+ services:
+ - mon
+ - name: mon_debug_no_initial_persistent_features
+ type: bool
+ level: dev
+ desc: do not set any monmap features for new mon clusters
+ default: false
+ services:
+ - mon
+ flags:
+ - cluster_create
+ - name: mon_inject_transaction_delay_max
+ type: float
+ level: dev
+ desc: max duration of injected delay in paxos
+ default: 10
+ services:
+ - mon
+ - name: mon_inject_transaction_delay_probability
+ type: float
+ level: dev
+ desc: probability of injecting a delay in paxos
+ default: 0
+ services:
+ - mon
+ - name: mon_inject_pg_merge_bounce_probability
+ type: float
+ level: dev
+ desc: probability of failing and reverting a pg_num decrement
+ default: 0
+ services:
+ - mon
+ - name: mon_sync_provider_kill_at
+ type: int
+ level: dev
+ desc: kill mon sync requester at specific point
+ default: 0
+ services:
+ - mon
+ - name: mon_sync_requester_kill_at
+ type: int
+ level: dev
+ desc: kill mon sync requestor at specific point
+ default: 0
+ services:
+ - mon
+ - name: mon_force_quorum_join
+ type: bool
+ level: advanced
+ desc: force mon to rejoin quorum even though it was just removed
+ default: false
+ services:
+ - mon
+ - name: mon_keyvaluedb
+ type: str
+ level: advanced
+ desc: database backend to use for the mon database
+ default: rocksdb
+ services:
+ - mon
+ enum_values:
+ - leveldb
+ - rocksdb
+ flags:
+ - create
+ - name: mon_debug_unsafe_allow_tier_with_nonempty_snaps
+ type: bool
+ level: dev
+ default: false
+ services:
+ - mon
+ - name: mon_osd_blocklist_default_expire
+ type: float
+ level: advanced
+ desc: Duration in seconds that blocklist entries for clients remain in the OSD map
+ default: 1_hr
+ services:
+ - mon
+ - name: mon_mds_blocklist_interval
+ type: float
+ level: dev
+ desc: Duration in seconds that blocklist entries for MDS daemons remain in the OSD
+ map
+ default: 1_day
+ services:
+ - mon
+ min: 1_hr
+ flags:
+ - runtime
+ - name: mon_mgr_blocklist_interval
+ type: float
+ level: dev
+ desc: Duration in seconds that blocklist entries for mgr daemons remain in the OSD
+ map
+ default: 1_day
+ services:
+ - mon
+ min: 1_hr
+ flags:
+ - runtime
+ - name: mon_osd_crush_smoke_test
+ type: bool
+ level: advanced
+ desc: perform a smoke test on any new CRUSH map before accepting changes
+ default: true
+ services:
+ - mon
+ - name: mon_smart_report_timeout
+ type: uint
+ level: advanced
+ desc: Timeout (in seconds) for smarctl to run, default is set to 5
+ default: 5
+ services:
+ - mon
+ - name: mon_auth_validate_all_caps
+ type: bool
+ level: advanced
+ desc: Whether to parse non-monitor capabilities set by the 'ceph auth ...' commands.
+ Disabling this saves CPU on the monitor, but allows invalid capabilities to be
+ set, and only be rejected later, when they are used.
+ default: true
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: mon_warn_on_older_version
+ type: bool
+ level: advanced
+ desc: issue DAEMON_OLD_VERSION health warning if daemons are not all running the
+ same version
+ default: true
+ services:
+ - mon
+ - name: mon_warn_older_version_delay
+ type: secs
+ level: advanced
+ desc: issue DAEMON_OLD_VERSION health warning after this amount of time has elapsed
+ default: 7_day
+ services:
+ - mon
+ - name: paxos_stash_full_interval
+ type: int
+ level: advanced
+ default: 25
+ services:
+ - mon
+ - name: paxos_max_join_drift
+ type: int
+ level: advanced
+ default: 10
+ services:
+ - mon
+ - name: paxos_propose_interval
+ type: float
+ level: advanced
+ default: 1
+ services:
+ - mon
+ - name: paxos_min_wait
+ type: float
+ level: advanced
+ default: 0.05
+ services:
+ - mon
+ - name: paxos_min
+ type: int
+ level: advanced
+ default: 500
+ services:
+ - mon
+ - name: paxos_trim_min
+ type: int
+ level: advanced
+ default: 250
+ services:
+ - mon
+ - name: paxos_trim_max
+ type: int
+ level: advanced
+ default: 500
+ services:
+ - mon
+ - name: paxos_service_trim_min
+ type: uint
+ level: advanced
+ default: 250
+ services:
+ - mon
+ - name: paxos_service_trim_max
+ type: uint
+ level: advanced
+ default: 500
+ services:
+ - mon
+ - name: paxos_service_trim_max_multiplier
+ type: uint
+ level: advanced
+ desc: factor by which paxos_service_trim_max will be multiplied to get a new upper
+ bound when trim sizes are high (0 disables it)
+ default: 20
+ services:
+ - mon
+ min: 0
+ flags:
+ - runtime
+ - name: paxos_kill_at
+ type: int
+ level: dev
+ default: 0
+ services:
+ - mon
+ - name: auth_cluster_required
+ type: str
+ level: advanced
+ desc: authentication methods required by the cluster
+ default: cephx
+ - name: auth_service_required
+ type: str
+ level: advanced
+ desc: authentication methods required by service daemons
+ default: cephx
+ - name: auth_client_required
+ type: str
+ level: advanced
+ desc: authentication methods allowed by clients
+ default: cephx, none
+ - name: auth_supported
+ type: str
+ level: advanced
+ desc: authentication methods required (deprecated)
+ - name: max_rotating_auth_attempts
+ type: int
+ level: advanced
+ desc: number of attempts to initialize rotating keys before giving up
+ default: 10
+ - name: rotating_keys_bootstrap_timeout
+ type: int
+ level: advanced
+ desc: timeout for obtaining rotating keys during bootstrap phase (seconds)
+ default: 30
+ - name: rotating_keys_renewal_timeout
+ type: int
+ level: advanced
+ desc: timeout for updating rotating keys (seconds)
+ default: 10
+ - name: cephx_require_signatures
+ type: bool
+ level: advanced
+ default: false
+ - name: cephx_require_version
+ type: int
+ level: advanced
+ desc: Cephx version required (1 = pre-mimic, 2 = mimic+)
+ default: 2
+ - name: cephx_cluster_require_signatures
+ type: bool
+ level: advanced
+ default: false
+ - name: cephx_cluster_require_version
+ type: int
+ level: advanced
+ desc: Cephx version required by the cluster from clients (1 = pre-mimic, 2 = mimic+)
+ default: 2
+ - name: cephx_service_require_signatures
+ type: bool
+ level: advanced
+ default: false
+ - name: cephx_service_require_version
+ type: int
+ level: advanced
+ desc: Cephx version required from ceph services (1 = pre-mimic, 2 = mimic+)
+ default: 2
+ - name: cephx_sign_messages
+ type: bool
+ level: advanced
+ default: true
+ - name: auth_mon_ticket_ttl
+ type: float
+ level: advanced
++ default: 72_hr
+ - name: auth_service_ticket_ttl
+ type: float
+ level: advanced
+ default: 1_hr
++- name: auth_allow_insecure_global_id_reclaim
++ type: bool
++ level: advanced
++ desc: Allow reclaiming global_id without presenting a valid ticket proving
++ previous possession of that global_id
++ long_desc: Allowing unauthorized global_id (re)use poses a security risk.
++ Unfortunately, older clients may omit their ticket on reconnects and
++ therefore rely on this being allowed for preserving their global_id for
++ the lifetime of the client instance. Setting this value to false would
++ immediately prevent new connections from those clients (assuming
++ auth_expose_insecure_global_id_reclaim set to true) and eventually break
++ existing sessions as well (regardless of auth_expose_insecure_global_id_reclaim
++ setting).
++ default: true
++ see_also:
++ - mon_warn_on_insecure_global_id_reclaim
++ - mon_warn_on_insecure_global_id_reclaim_allowed
++ - auth_expose_insecure_global_id_reclaim
++- name: auth_expose_insecure_global_id_reclaim
++ type: bool
++ level: advanced
++ desc: Force older clients that may omit their ticket on reconnects to
++ reconnect as part of establishing a session
++ long_desc: 'In permissive mode (auth_allow_insecure_global_id_reclaim set
++ to true), this helps with identifying clients that are not patched. In
++ enforcing mode (auth_allow_insecure_global_id_reclaim set to false), this
++ is a fail-fast mechanism: don''t establish a session that will almost
++ inevitably be broken later.'
++ default: true
++ see_also:
++ - mon_warn_on_insecure_global_id_reclaim
++ - mon_warn_on_insecure_global_id_reclaim_allowed
++ - auth_allow_insecure_global_id_reclaim
+ - name: auth_debug
+ type: bool
+ level: dev
+ default: false
+ - name: mon_client_hunt_parallel
+ type: uint
+ level: advanced
+ default: 3
+ - name: mon_client_hunt_interval
+ type: float
+ level: advanced
+ default: 3
+ - name: mon_client_log_interval
+ type: float
+ level: advanced
+ desc: How frequently we send queued cluster log messages to mon
+ default: 1
+ - name: mon_client_ping_interval
+ type: float
+ level: advanced
+ default: 10
+ - name: mon_client_ping_timeout
+ type: float
+ level: advanced
+ default: 30
+ - name: mon_client_hunt_interval_backoff
+ type: float
+ level: advanced
+ default: 1.5
+ - name: mon_client_hunt_interval_min_multiple
+ type: float
+ level: advanced
+ default: 1
+ - name: mon_client_hunt_interval_max_multiple
+ type: float
+ level: advanced
+ default: 10
+ - name: mon_client_max_log_entries_per_message
+ type: int
+ level: advanced
+ default: 1000
+ - name: mon_client_directed_command_retry
+ type: int
+ level: dev
+ desc: Number of times to try sending a command directed at a specific monitor
+ default: 2
+ - name: mon_max_pool_pg_num
+ type: uint
+ level: advanced
+ default: 64_K
+ - name: mon_pool_quota_warn_threshold
+ type: int
+ level: advanced
+ desc: percent of quota at which to issue warnings
+ default: 0
+ services:
+ - mgr
+ - name: mon_pool_quota_crit_threshold
+ type: int
+ level: advanced
+ desc: percent of quota at which to issue errors
+ default: 0
+ services:
+ - mgr
+ - name: crush_location
+ type: str
+ level: advanced
+ - name: crush_location_hook
+ type: str
+ level: advanced
+ - name: crush_location_hook_timeout
+ type: int
+ level: advanced
+ default: 10
+ - name: objecter_tick_interval
+ type: float
+ level: dev
+ default: 5
+ - name: objecter_timeout
+ type: float
+ level: advanced
+ desc: Seconds before in-flight op is considered 'laggy' and we query mon for the
+ latest OSDMap
+ default: 10
+ - name: objecter_inflight_op_bytes
+ type: size
+ level: advanced
+ desc: Max in-flight data in bytes (both directions)
+ default: 100_M
+ - name: objecter_inflight_ops
+ type: uint
+ level: advanced
+ desc: Max in-flight operations
+ default: 1_K
+ - name: objecter_completion_locks_per_session
+ type: uint
+ level: dev
+ default: 32
+ - name: objecter_inject_no_watch_ping
+ type: bool
+ level: dev
+ default: false
+ - name: objecter_retry_writes_after_first_reply
+ type: bool
+ level: dev
+ default: false
+ - name: objecter_debug_inject_relock_delay
+ type: bool
+ level: dev
+ default: false
+ - name: filer_max_purge_ops
+ type: uint
+ level: advanced
+ desc: Max in-flight operations for purging a striped range (e.g., MDS journal)
+ default: 10
+ - name: filer_max_truncate_ops
+ type: uint
+ level: advanced
+ desc: Max in-flight operations for truncating/deleting a striped sequence (e.g.,
+ MDS journal)
+ default: 128
+ - name: journaler_write_head_interval
+ type: int
+ level: advanced
+ desc: Interval in seconds between journal header updates (to help bound replay time)
+ default: 15
+ # * journal object size
+ - name: journaler_prefetch_periods
+ type: uint
+ level: advanced
+ desc: Number of striping periods to prefetch while reading MDS journal
+ default: 10
+ # we need at least 2 periods to make progress.
+ min: 2
+ # * journal object size
+ - name: journaler_prezero_periods
+ type: uint
+ level: advanced
+ desc: Number of striping periods to zero head of MDS journal write position
+ default: 5
+ # we need to zero at least two periods, minimum, to ensure that we
+ # have a full empty object/period in front of us.
+ min: 2
+ - name: osd_calc_pg_upmaps_aggressively
+ type: bool
+ level: advanced
+ desc: try to calculate PG upmaps more aggressively, e.g., by doing a fairly exhaustive
+ search of existing PGs that can be unmapped or upmapped
+ default: true
+ flags:
+ - runtime
+ - name: osd_calc_pg_upmaps_local_fallback_retries
+ type: uint
+ level: advanced
+ desc: 'Maximum number of PGs we can attempt to unmap or upmap for a specific overfull
+ or underfull osd per iteration '
+ default: 100
+ flags:
+ - runtime
+ - name: osd_numa_prefer_iface
+ type: bool
+ level: advanced
+ desc: prefer IP on network interface on same numa node as storage
+ default: true
+ see_also:
+ - osd_numa_auto_affinity
+ flags:
+ - startup
+ - name: osd_numa_auto_affinity
+ type: bool
+ level: advanced
+ desc: automatically set affinity to numa node when storage and network match
+ default: true
+ flags:
+ - startup
+ - name: osd_numa_node
+ type: int
+ level: advanced
+ desc: set affinity to a numa node (-1 for none)
+ default: -1
+ see_also:
+ - osd_numa_auto_affinity
+ flags:
+ - startup
+ - name: osd_smart_report_timeout
+ type: uint
+ level: advanced
+ desc: Timeout (in seconds) for smarctl to run, default is set to 5
+ default: 5
+ - name: osd_check_max_object_name_len_on_startup
+ type: bool
+ level: dev
+ default: true
+ - name: osd_max_backfills
+ type: uint
+ level: advanced
+ desc: 'Maximum number of concurrent local and remote backfills or recoveries per
+ OSD '
+ long_desc: There can be osd_max_backfills local reservations AND the same remote
+ reservations per OSD. So a value of 1 lets this OSD participate as 1 PG primary
+ in recovery and 1 shard of another recovering PG.
+ default: 1
+ flags:
+ - runtime
+ - name: osd_min_recovery_priority
+ type: int
+ level: advanced
+ desc: Minimum priority below which recovery is not performed
+ long_desc: The purpose here is to prevent the cluster from doing *any* lower priority
+ work (e.g., rebalancing) below this threshold and focus solely on higher priority
+ work (e.g., replicating degraded objects).
+ default: 0
+ - name: osd_backfill_retry_interval
+ type: float
+ level: advanced
+ desc: how frequently to retry backfill reservations after being denied (e.g., due
+ to a full OSD)
+ default: 30
+ - name: osd_recovery_retry_interval
+ type: float
+ level: advanced
+ desc: how frequently to retry recovery reservations after being denied (e.g., due
+ to a full OSD)
+ default: 30
+ - name: osd_agent_max_ops
+ type: int
+ level: advanced
+ desc: maximum concurrent tiering operations for tiering agent
+ default: 4
+ - name: osd_agent_max_low_ops
+ type: int
+ level: advanced
+ desc: maximum concurrent low-priority tiering operations for tiering agent
+ default: 2
+ - name: osd_agent_min_evict_effort
+ type: float
+ level: advanced
+ desc: minimum effort to expend evicting clean objects
+ default: 0.1
+ min: 0
+ max: 0.99
+ - name: osd_agent_quantize_effort
+ type: float
+ level: advanced
+ desc: size of quantize unit for eviction effort
+ default: 0.1
+ - name: osd_agent_delay_time
+ type: float
+ level: advanced
+ desc: how long agent should sleep if it has no work to do
+ default: 5
+ - name: osd_find_best_info_ignore_history_les
+ type: bool
+ level: dev
+ desc: ignore last_epoch_started value when peering AND PROBABLY LOSE DATA
+ long_desc: THIS IS AN EXTREMELY DANGEROUS OPTION THAT SHOULD ONLY BE USED AT THE
+ DIRECTION OF A DEVELOPER. It makes peering ignore the last_epoch_started value
+ when peering, which can allow the OSD to believe an OSD has an authoritative view
+ of a PG's contents even when it is in fact old and stale, typically leading to
+ data loss (by believing a stale PG is up to date).
+ default: false
+ - name: osd_agent_hist_halflife
+ type: int
+ level: advanced
+ desc: halflife of agent atime and temp histograms
+ default: 1000
+ - name: osd_agent_slop
+ type: float
+ level: advanced
+ desc: slop factor to avoid switching tiering flush and eviction mode
+ default: 0.02
+ - name: osd_uuid
+ type: uuid
+ level: advanced
+ desc: uuid label for a new OSD
+ flags:
+ - create
+ - name: osd_data
+ type: str
+ level: advanced
+ desc: path to OSD data
+ default: /var/lib/ceph/osd/$cluster-$id
+ flags:
+ - no_mon_update
+ - name: osd_journal
+ type: str
+ level: advanced
+ desc: path to OSD journal (when FileStore backend is in use)
+ default: /var/lib/ceph/osd/$cluster-$id/journal
+ flags:
+ - no_mon_update
+ - name: osd_journal_size
+ type: size
+ level: advanced
+ desc: size of FileStore journal (in MiB)
+ default: 5_K
+ flags:
+ - create
+ - name: osd_journal_flush_on_shutdown
+ type: bool
+ level: advanced
+ desc: flush FileStore journal contents during clean OSD shutdown
+ default: true
+ - name: osd_compact_on_start
+ type: bool
+ level: advanced
+ desc: compact OSD's object store's OMAP on start
+ default: false
+ - name: osd_os_flags
+ type: uint
+ level: dev
+ desc: flags to skip filestore omap or journal initialization
+ default: 0
+ - name: osd_max_write_size
+ type: size
+ level: advanced
+ desc: Maximum size of a RADOS write operation in megabytes
+ long_desc: This setting prevents clients from doing very large writes to RADOS. If
+ you set this to a value below what clients expect, they will receive an error
+ when attempting to write to the cluster.
+ default: 90
+ min: 4
+ - name: osd_max_pgls
+ type: uint
+ level: advanced
+ desc: maximum number of results when listing objects in a pool
+ default: 1_K
+ - name: osd_client_message_size_cap
+ type: size
+ level: advanced
+ desc: maximum memory to devote to in-flight client requests
+ long_desc: If this value is exceeded, the OSD will not read any new client data
+ off of the network until memory is freed.
+ default: 500_M
+ - name: osd_client_message_cap
+ type: uint
+ level: advanced
+ desc: maximum number of in-flight client requests
+ default: 0
+ - name: osd_crush_update_weight_set
+ type: bool
+ level: advanced
+ desc: update CRUSH weight-set weights when updating weights
+ long_desc: If this setting is true, we will update the weight-set weights when adjusting
+ an item's weight, effectively making changes take effect immediately, and discarding
+ any previous optimization in the weight-set value. Setting this value to false
+ will leave it to the balancer to (slowly, presumably) adjust weights to approach
+ the new target value.
+ default: true
+ - name: osd_crush_chooseleaf_type
+ type: int
+ level: dev
+ desc: default chooseleaf type for osdmaptool --create
+ default: 1
+ flags:
+ - cluster_create
+ - name: osd_pool_use_gmt_hitset
+ type: bool
+ level: dev
+ desc: use UTC for hitset timestamps
+ long_desc: This setting only exists for compatibility with hammer (and older) clusters.
+ default: true
+ - name: osd_crush_update_on_start
+ type: bool
+ level: advanced
+ desc: update OSD CRUSH location on startup
+ default: true
+ - name: osd_class_update_on_start
+ type: bool
+ level: advanced
+ desc: set OSD device class on startup
+ default: true
+ - name: osd_crush_initial_weight
+ type: float
+ level: advanced
+ desc: if >= 0, initial CRUSH weight for newly created OSDs
+ long_desc: If this value is negative, the size of the OSD in TiB is used.
+ default: -1
+ - name: osd_pool_default_ec_fast_read
+ type: bool
+ level: advanced
+ desc: set ec_fast_read for new erasure-coded pools
+ default: false
+ services:
+ - mon
+ - name: osd_pool_default_crush_rule
+ type: int
+ level: advanced
+ desc: CRUSH rule for newly created pools
+ default: -1
+ services:
+ - mon
+ - name: osd_pool_erasure_code_stripe_unit
+ type: size
+ level: advanced
+ desc: the amount of data (in bytes) in a data chunk, per stripe
+ default: 4_K
+ services:
+ - mon
+ - name: osd_pool_default_size
+ type: uint
+ level: advanced
+ desc: the number of copies of an object for new replicated pools
+ default: 3
+ services:
+ - mon
+ min: 0
+ max: 10
+ flags:
+ - runtime
+ - name: osd_pool_default_min_size
+ type: uint
+ level: advanced
+ desc: the minimal number of copies allowed to write to a degraded pool for new replicated
+ pools
+ long_desc: 0 means no specific default; ceph will use size-size/2
+ default: 0
+ services:
+ - mon
+ see_also:
+ - osd_pool_default_size
+ min: 0
+ max: 255
+ flags:
+ - runtime
+ - name: osd_pool_default_pg_num
+ type: uint
+ level: advanced
+ desc: number of PGs for new pools
+ default: 32
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: osd_pool_default_pgp_num
+ type: uint
+ level: advanced
+ desc: number of PGs for placement purposes (0 to match pg_num)
+ default: 0
+ services:
+ - mon
+ see_also:
+ - osd_pool_default_pg_num
+ flags:
+ - runtime
+ - name: osd_pool_default_type
+ type: str
+ level: advanced
+ desc: default type of pool to create
+ default: replicated
+ services:
+ - mon
+ enum_values:
+ - replicated
+ - erasure
+ flags:
+ - runtime
+ - name: osd_pool_default_erasure_code_profile
+ type: str
+ level: advanced
+ desc: default erasure code profile for new erasure-coded pools
+ default: plugin=jerasure technique=reed_sol_van k=2 m=2
+ services:
+ - mon
+ flags:
+ - runtime
+ - name: osd_erasure_code_plugins
+ type: str
+ level: advanced
+ desc: erasure code plugins to load
+ default: jerasure lrc isa
+ services:
+ - mon
+ - osd
+ flags:
+ - startup
+ - name: osd_allow_recovery_below_min_size
+ type: bool
+ level: dev
+ desc: allow replicated pools to recover with < min_size active members
+ default: true
+ services:
+ - osd
+ - name: osd_pool_default_flags
+ type: int
+ level: dev
+ desc: (integer) flags to set on new pools
+ default: 0
+ services:
+ - mon
+ - name: osd_pool_default_flag_hashpspool
+ type: bool
+ level: advanced
+ desc: set hashpspool (better hashing scheme) flag on new pools
+ default: true
+ services:
+ - mon
+ - name: osd_pool_default_flag_nodelete
+ type: bool
+ level: advanced
+ desc: set nodelete flag on new pools
+ default: false
+ services:
+ - mon
+ - name: osd_pool_default_flag_nopgchange
+ type: bool
+ level: advanced
+ desc: set nopgchange flag on new pools
+ default: false
+ services:
+ - mon
+ - name: osd_pool_default_flag_nosizechange
+ type: bool
+ level: advanced
+ desc: set nosizechange flag on new pools
+ default: false
+ services:
+ - mon
+ - name: osd_pool_default_hit_set_bloom_fpp
+ type: float
+ level: advanced
+ default: 0.05
+ services:
+ - mon
+ see_also:
+ - osd_tier_default_cache_hit_set_type
+ - name: osd_pool_default_cache_target_dirty_ratio
+ type: float
+ level: advanced
+ default: 0.4
+ - name: osd_pool_default_cache_target_dirty_high_ratio
+ type: float
+ level: advanced
+ default: 0.6
+ - name: osd_pool_default_cache_target_full_ratio
+ type: float
+ level: advanced
+ default: 0.8
+ - name: osd_pool_default_cache_min_flush_age
+ type: int
+ level: advanced
+ default: 0
+ - name: osd_pool_default_cache_min_evict_age
+ type: int
+ level: advanced
+ default: 0
+ - name: osd_pool_default_cache_max_evict_check_size
+ type: int
+ level: advanced
+ default: 10
+ - name: osd_pool_default_pg_autoscale_mode
+ type: str
+ level: advanced
+ desc: Default PG autoscaling behavior for new pools
+ default: 'on'
+ enum_values:
+ - 'off'
+ - 'warn'
+ - 'on'
+ flags:
+ - runtime
+ - name: osd_pool_default_read_lease_ratio
+ type: float
+ level: dev
+ desc: Default read_lease_ratio for a pool, as a multiple of osd_heartbeat_grace
+ long_desc: This should be <= 1.0 so that the read lease will have expired by the
+ time we decide to mark a peer OSD down.
+ default: 0.8
+ see_also:
+ - osd_heartbeat_grace
+ flags:
+ - runtime
+ - name: osd_hit_set_min_size
+ type: int
+ level: advanced
+ default: 1000
+ - name: osd_hit_set_max_size
+ type: int
+ level: advanced
+ default: 100000
+ - name: osd_hit_set_namespace
+ type: str
+ level: advanced
+ default: .ceph-internal
+ - name: osd_tier_promote_max_objects_sec
+ type: uint
+ level: advanced
+ default: 25
+ - name: osd_tier_promote_max_bytes_sec
+ type: size
+ level: advanced
+ default: 5_M
+ - name: osd_tier_default_cache_mode
+ type: str
+ level: advanced
+ default: writeback
+ enum_values:
+ - none
+ - writeback
+ - forward
+ - readonly
+ - readforward
+ - readproxy
+ - proxy
+ flags:
+ - runtime
+ - name: osd_tier_default_cache_hit_set_count
+ type: uint
+ level: advanced
+ default: 4
+ - name: osd_tier_default_cache_hit_set_period
+ type: uint
+ level: advanced
+ default: 1200
+ - name: osd_tier_default_cache_hit_set_type
+ type: str
+ level: advanced
+ default: bloom
+ enum_values:
+ - bloom
+ - explicit_hash
+ - explicit_object
+ flags:
+ - runtime
+ - name: osd_tier_default_cache_min_read_recency_for_promote
+ type: uint
+ level: advanced
+ desc: number of recent HitSets the object must appear in to be promoted (on read)
+ default: 1
+ - name: osd_tier_default_cache_min_write_recency_for_promote
+ type: uint
+ level: advanced
+ desc: number of recent HitSets the object must appear in to be promoted (on write)
+ default: 1
+ - name: osd_tier_default_cache_hit_set_grade_decay_rate
+ type: uint
+ level: advanced
+ default: 20
+ - name: osd_tier_default_cache_hit_set_search_last_n
+ type: uint
+ level: advanced
+ default: 1
+ - name: osd_objecter_finishers
+ type: int
+ level: advanced
+ default: 1
+ flags:
+ - startup
+ - name: osd_map_dedup
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_map_cache_size
+ type: int
+ level: advanced
+ default: 50
+ - name: osd_map_message_max
+ type: int
+ level: advanced
+ desc: maximum number of OSDMaps to include in a single message
+ default: 40
+ - name: osd_map_message_max_bytes
+ type: size
+ level: advanced
+ desc: maximum number of bytes worth of OSDMaps to include in a single message
+ default: 10_M
+ - name: osd_map_share_max_epochs
+ type: int
+ level: advanced
+ default: 40
+ - name: osd_pg_epoch_max_lag_factor
+ type: float
+ level: advanced
+ desc: Max multiple of the map cache that PGs can lag before we throttle map injest
+ default: 2
+ see_also:
+ - osd_map_cache_size
+ - name: osd_inject_bad_map_crc_probability
+ type: float
+ level: dev
+ default: 0
+ - name: osd_inject_failure_on_pg_removal
+ type: bool
+ level: dev
+ default: false
+ - name: osd_max_markdown_period
+ type: int
+ level: advanced
+ default: 10_min
+ - name: osd_max_markdown_count
+ type: int
+ level: advanced
+ default: 5
+ - name: osd_op_pq_max_tokens_per_priority
+ type: uint
+ level: advanced
+ default: 4_M
+ - name: osd_op_pq_min_cost
+ type: size
+ level: advanced
+ default: 64_K
+ - name: osd_recover_clone_overlap
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_num_cache_shards
+ type: size
+ level: advanced
+ desc: The number of cache shards to use in the object store.
+ default: 32
+ flags:
+ - startup
+ - name: osd_op_num_threads_per_shard
+ type: int
+ level: advanced
+ default: 0
+ flags:
+ - startup
+ - name: osd_op_num_threads_per_shard_hdd
+ type: int
+ level: advanced
+ default: 1
+ see_also:
+ - osd_op_num_threads_per_shard
+ flags:
+ - startup
+ - name: osd_op_num_threads_per_shard_ssd
+ type: int
+ level: advanced
+ default: 2
+ see_also:
+ - osd_op_num_threads_per_shard
+ flags:
+ - startup
+ - name: osd_op_num_shards
+ type: int
+ level: advanced
+ default: 0
+ flags:
+ - startup
+ - name: osd_op_num_shards_hdd
+ type: int
+ level: advanced
+ default: 5
+ see_also:
+ - osd_op_num_shards
+ flags:
+ - startup
+ - name: osd_op_num_shards_ssd
+ type: int
+ level: advanced
+ default: 8
+ see_also:
+ - osd_op_num_shards
+ flags:
+ - startup
+ - name: osd_skip_data_digest
+ type: bool
+ level: dev
+ desc: Do not store full-object checksums if the backend (bluestore) does its own
+ checksums. Only usable with all BlueStore OSDs.
+ default: false
+ - name: osd_op_queue
+ type: str
+ level: advanced
+ desc: which operation priority queue algorithm to use
+ long_desc: which operation priority queue algorithm to use; mclock_scheduler is
+ currently experimental
+ default: wpq
+ see_also:
+ - osd_op_queue_cut_off
+ enum_values:
+ - wpq
+ - mclock_scheduler
+ - debug_random
+ - name: osd_op_queue_cut_off
+ type: str
+ level: advanced
+ desc: the threshold between high priority ops and low priority ops
+ long_desc: the threshold between high priority ops that use strict priority ordering
+ and low priority ops that use a fairness algorithm that may or may not incorporate
+ priority
+ default: high
+ see_also:
+ - osd_op_queue
+ enum_values:
+ - low
+ - high
+ - debug_random
+ - name: osd_mclock_scheduler_client_res
+ type: uint
+ level: advanced
+ desc: IO proportion reserved for each client (default)
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_client_wgt
+ type: uint
+ level: advanced
+ desc: IO share for each client (default) over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_client_lim
+ type: uint
+ level: advanced
+ desc: IO limit for each client (default) over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 999999
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_recovery_res
+ type: uint
+ level: advanced
+ desc: IO proportion reserved for background recovery (default)
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_recovery_wgt
+ type: uint
+ level: advanced
+ desc: IO share for each background recovery over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_recovery_lim
+ type: uint
+ level: advanced
+ desc: IO limit for background recovery over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 999999
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_best_effort_res
+ type: uint
+ level: advanced
+ desc: IO proportion reserved for background best_effort (default)
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_best_effort_wgt
+ type: uint
+ level: advanced
+ desc: IO share for each background best_effort over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 1
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_background_best_effort_lim
+ type: uint
+ level: advanced
+ desc: IO limit for background best_effort over reservation
+ long_desc: Only considered for osd_op_queue = mclock_scheduler
+ default: 999999
+ see_also:
+ - osd_op_queue
+ - name: osd_mclock_scheduler_anticipation_timeout
+ type: float
+ level: advanced
+ desc: mclock anticipation timeout in seconds
+ long_desc: the amount of time that mclock waits until the unused resource is forfeited
+ default: 0
+ - name: osd_mclock_cost_per_io_usec
+ type: float
+ level: dev
+ desc: Cost per IO in microseconds to consider per OSD (overrides _ssd and _hdd if
+ non-zero)
+ long_desc: This option specifies the cost factor to consider in usec per OSD. This
+ is considered by the mclock scheduler to set an additional cost factor in QoS
+ calculations. Only considered for osd_op_queue = mclock_scheduler
+ default: 0
+ flags:
+ - runtime
+ - name: osd_mclock_cost_per_io_usec_hdd
+ type: float
+ level: dev
+ desc: Cost per IO in microseconds to consider per OSD (for rotational media)
+ long_desc: This option specifies the cost factor to consider in usec per OSD for
+ rotational device type. This is considered by the mclock_scheduler to set an additional
+ cost factor in QoS calculations. Only considered for osd_op_queue = mclock_scheduler
+ default: 25000
+ flags:
+ - runtime
+ - name: osd_mclock_cost_per_io_usec_ssd
+ type: float
+ level: dev
+ desc: Cost per IO in microseconds to consider per OSD (for solid state media)
+ long_desc: This option specifies the cost factor to consider in usec per OSD for
+ solid state device type. This is considered by the mclock_scheduler to set an
+ additional cost factor in QoS calculations. Only considered for osd_op_queue =
+ mclock_scheduler
+ default: 50
+ flags:
+ - runtime
+ - name: osd_mclock_cost_per_byte_usec
+ type: float
+ level: dev
+ desc: Cost per byte in microseconds to consider per OSD (overrides _ssd and _hdd
+ if non-zero)
+ long_desc: This option specifies the cost per byte to consider in microseconds per
+ OSD. This is considered by the mclock scheduler to set an additional cost factor
+ in QoS calculations. Only considered for osd_op_queue = mclock_scheduler
+ default: 0
+ flags:
+ - runtime
+ - name: osd_mclock_cost_per_byte_usec_hdd
+ type: float
+ level: dev
+ desc: Cost per byte in microseconds to consider per OSD (for rotational media)
+ long_desc: This option specifies the cost per byte to consider in microseconds per
+ OSD for rotational device type. This is considered by the mclock_scheduler to
+ set an additional cost factor in QoS calculations. Only considered for osd_op_queue
+ = mclock_scheduler
+ default: 5
+ flags:
+ - runtime
+ - name: osd_mclock_cost_per_byte_usec_ssd
+ type: float
+ level: dev
+ desc: Cost per byte in microseconds to consider per OSD (for solid state media)
+ long_desc: This option specifies the cost per byte to consider in microseconds per
+ OSD for solid state device type. This is considered by the mclock_scheduler to
+ set an additional cost factor in QoS calculations. Only considered for osd_op_queue
+ = mclock_scheduler
+ default: 0
+ flags:
+ - runtime
+ - name: osd_mclock_max_capacity_iops
+ type: float
+ level: basic
+ desc: Max IOPs capacity (at 4KiB block size) to consider per OSD (overrides _ssd
+ and _hdd if non-zero)
+ long_desc: This option specifies the max osd capacity in iops per OSD. Helps in
+ QoS calculations when enabling a dmclock profile. Only considered for osd_op_queue
+ = mclock_scheduler
+ default: 0
+ flags:
+ - runtime
+ - name: osd_mclock_max_capacity_iops_hdd
+ type: float
+ level: basic
+ desc: Max IOPs capacity (at 4KiB block size) to consider per OSD (for rotational
+ media)
+ long_desc: This option specifies the max OSD capacity in iops per OSD. Helps in
+ QoS calculations when enabling a dmclock profile. Only considered for osd_op_queue
+ = mclock_scheduler
+ default: 315
+ flags:
+ - runtime
+ - name: osd_mclock_max_capacity_iops_ssd
+ type: float
+ level: basic
+ desc: Max IOPs capacity (at 4KiB block size) to consider per OSD (for solid state
+ media)
+ long_desc: This option specifies the max OSD capacity in iops per OSD. Helps in
+ QoS calculations when enabling a dmclock profile. Only considered for osd_op_queue
+ = mclock_scheduler
+ default: 21500
+ flags:
+ - runtime
+ - name: osd_mclock_profile
+ type: str
+ level: advanced
+ desc: Which mclock profile to use
+ long_desc: This option specifies the mclock profile to enable - one among the set
+ of built-in profiles or a custom profile. Only considered for osd_op_queue = mclock_scheduler
+ default: high_client_ops
+ see_also:
+ - osd_op_queue
+ enum_values:
+ - balanced
+ - high_recovery_ops
+ - high_client_ops
+ - custom
+ flags:
+ - runtime
+ - name: osd_ignore_stale_divergent_priors
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_read_ec_check_for_errors
+ type: bool
+ level: advanced
+ default: false
+ # Only use clone_overlap for recovery if there are fewer than
+ # osd_recover_clone_overlap_limit entries in the overlap set
+ - name: osd_recover_clone_overlap_limit
+ type: uint
+ level: advanced
+ default: 10
+ flags:
+ - runtime
+ - name: osd_debug_feed_pullee
+ type: int
+ level: dev
+ desc: Feed a pullee, and force primary to pull a currently missing object from it
+ default: -1
+ - name: osd_backfill_scan_min
+ type: int
+ level: advanced
+ default: 64
+ - name: osd_backfill_scan_max
+ type: int
+ level: advanced
+ default: 512
+ - name: osd_op_thread_timeout
+ type: int
+ level: advanced
+ default: 15
+ - name: osd_op_thread_suicide_timeout
+ type: int
+ level: advanced
+ default: 150
+ - name: osd_recovery_sleep
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next recovery or backfill op
+ default: 0
+ flags:
+ - runtime
+ - name: osd_recovery_sleep_hdd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next recovery or backfill op for HDDs
+ default: 0.1
+ flags:
+ - runtime
+ - name: osd_recovery_sleep_ssd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next recovery or backfill op for SSDs
+ default: 0
+ see_also:
+ - osd_recovery_sleep
+ flags:
+ - runtime
+ - name: osd_recovery_sleep_hybrid
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next recovery or backfill op when data is
+ on HDD and journal is on SSD
+ default: 0.025
+ see_also:
+ - osd_recovery_sleep
+ flags:
+ - runtime
+ - name: osd_snap_trim_sleep
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next snap trim (overrides values below)
+ default: 0
+ - name: osd_snap_trim_sleep_hdd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next snap trim for HDDs
+ default: 5
+ - name: osd_snap_trim_sleep_ssd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next snap trim for SSDs
+ default: 0
+ - name: osd_snap_trim_sleep_hybrid
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next snap trim when data is on HDD and journal
+ is on SSD
+ default: 2
+ - name: osd_scrub_invalid_stats
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_command_thread_timeout
+ type: int
+ level: advanced
+ default: 10_min
+ - name: osd_command_thread_suicide_timeout
+ type: int
+ level: advanced
+ default: 15_min
+ - name: osd_heartbeat_interval
+ type: int
+ level: dev
+ desc: Interval (in seconds) between peer pings
+ default: 6
+ min: 1
+ max: 1_min
+ - name: osd_heartbeat_grace
+ type: int
+ level: advanced
+ default: 20
+ - name: osd_heartbeat_stale
+ type: int
+ level: advanced
+ desc: Interval (in seconds) we mark an unresponsive heartbeat peer as stale.
+ long_desc: Automatically mark unresponsive heartbeat sessions as stale and tear
+ them down. The primary benefit is that OSD doesn't need to keep a flood of blocked
+ heartbeat messages around in memory.
+ default: 10_min
+ - name: osd_heartbeat_min_peers
+ type: int
+ level: advanced
+ default: 10
+ - name: osd_heartbeat_use_min_delay_socket
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_heartbeat_min_size
+ type: size
+ level: advanced
+ desc: Minimum heartbeat packet size in bytes. Will add dummy payload if heartbeat
+ packet is smaller than this.
+ default: 2000
+ - name: osd_pg_max_concurrent_snap_trims
+ type: uint
+ level: advanced
+ default: 2
+ - name: osd_max_trimming_pgs
+ type: uint
+ level: advanced
+ default: 2
+ - name: osd_heartbeat_min_healthy_ratio
+ type: float
+ level: advanced
+ default: 0
+ - name: osd_mon_heartbeat_interval
+ type: int
+ level: advanced
+ default: 30
+ - name: osd_mon_heartbeat_stat_stale
+ type: int
+ level: advanced
+ desc: Stop reporting on heartbeat ping times not updated for this many seconds.
+ long_desc: Stop reporting on old heartbeat information unless this is set to zero
+ default: 1_hr
+ - name: osd_mon_report_interval
+ type: int
+ level: advanced
+ desc: Frequency of OSD reports to mon for peer failures, fullness status changes
+ default: 5
+ - name: osd_mon_report_max_in_flight
+ type: int
+ level: advanced
+ default: 2
+ - name: osd_beacon_report_interval
+ type: int
+ level: advanced
+ default: 5_min
+ - name: osd_pg_stat_report_interval_max
+ type: int
+ level: advanced
+ default: 500
+ - name: osd_mon_ack_timeout
+ type: float
+ level: advanced
+ default: 30
+ - name: osd_stats_ack_timeout_factor
+ type: float
+ level: advanced
+ default: 2
+ - name: osd_stats_ack_timeout_decay
+ type: float
+ level: advanced
+ default: 0.9
+ - name: osd_max_snap_prune_intervals_per_epoch
+ type: uint
+ level: dev
+ desc: Max number of snap intervals to report to mgr in pg_stat_t
+ default: 512
+ - name: osd_default_data_pool_replay_window
+ type: int
+ level: advanced
+ default: 45
+ - name: osd_auto_mark_unfound_lost
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_recovery_delay_start
+ type: float
+ level: advanced
+ default: 0
+ - name: osd_recovery_max_active
+ type: uint
+ level: advanced
+ desc: Number of simultaneous active recovery operations per OSD (overrides _ssd
+ and _hdd if non-zero)
+ default: 0
+ see_also:
+ - osd_recovery_max_active_hdd
+ - osd_recovery_max_active_ssd
+ flags:
+ - runtime
+ - name: osd_recovery_max_active_hdd
+ type: uint
+ level: advanced
+ desc: Number of simultaneous active recovery operations per OSD (for rotational
+ devices)
+ default: 3
+ see_also:
+ - osd_recovery_max_active
+ - osd_recovery_max_active_ssd
+ flags:
+ - runtime
+ - name: osd_recovery_max_active_ssd
+ type: uint
+ level: advanced
+ desc: Number of simultaneous active recovery operations per OSD (for non-rotational
+ solid state devices)
+ default: 10
+ see_also:
+ - osd_recovery_max_active
+ - osd_recovery_max_active_hdd
+ flags:
+ - runtime
+ - name: osd_recovery_max_single_start
+ type: uint
+ level: advanced
+ default: 1
+ - name: osd_recovery_max_chunk
+ type: size
+ level: advanced
+ default: 8_M
+ - name: osd_recovery_max_omap_entries_per_chunk
+ type: uint
+ level: advanced
+ default: 8096
+ - name: osd_copyfrom_max_chunk
+ type: size
+ level: advanced
+ default: 8_M
+ - name: osd_push_per_object_cost
+ type: size
+ level: advanced
+ default: 1000
+ - name: osd_max_push_cost
+ type: size
+ level: advanced
+ default: 8_M
+ - name: osd_max_push_objects
+ type: uint
+ level: advanced
+ default: 10
+ - name: osd_max_scrubs
+ type: int
+ level: advanced
+ desc: Maximum concurrent scrubs on a single OSD
+ default: 1
+ - name: osd_scrub_during_recovery
+ type: bool
+ level: advanced
+ desc: Allow scrubbing when PGs on the OSD are undergoing recovery
+ default: false
+ - name: osd_repair_during_recovery
+ type: bool
+ level: advanced
+ desc: Allow requested repairing when PGs on the OSD are undergoing recovery
+ default: false
+ - name: osd_scrub_begin_hour
+ type: int
+ level: advanced
+ desc: Restrict scrubbing to this hour of the day or later
+ long_desc: Use osd_scrub_begin_hour=0 and osd_scrub_end_hour=0 for the entire day.
+ default: 0
+ see_also:
+ - osd_scrub_end_hour
+ min: 0
+ max: 23
+ - name: osd_scrub_end_hour
+ type: int
+ level: advanced
+ desc: Restrict scrubbing to hours of the day earlier than this
+ long_desc: Use osd_scrub_begin_hour=0 and osd_scrub_end_hour=0 for the entire day.
+ default: 0
+ see_also:
+ - osd_scrub_begin_hour
+ min: 0
+ max: 23
+ - name: osd_scrub_begin_week_day
+ type: int
+ level: advanced
+ desc: Restrict scrubbing to this day of the week or later
+ long_desc: 0 = Sunday, 1 = Monday, etc. Use osd_scrub_begin_week_day=0 osd_scrub_end_week_day=0
+ for the entire week.
+ default: 0
+ see_also:
+ - osd_scrub_end_week_day
+ min: 0
+ max: 6
+ - name: osd_scrub_end_week_day
+ type: int
+ level: advanced
+ desc: Restrict scrubbing to days of the week earlier than this
+ long_desc: 0 = Sunday, 1 = Monday, etc. Use osd_scrub_begin_week_day=0 osd_scrub_end_week_day=0
+ for the entire week.
+ default: 0
+ see_also:
+ - osd_scrub_begin_week_day
+ min: 0
+ max: 6
+ - name: osd_scrub_load_threshold
+ type: float
+ level: advanced
+ desc: Allow scrubbing when system load divided by number of CPUs is below this value
+ default: 0.5
+ - name: osd_scrub_min_interval
+ type: float
+ level: advanced
+ desc: Scrub each PG no more often than this interval
+ default: 1_day
+ see_also:
+ - osd_scrub_max_interval
+ - name: osd_scrub_max_interval
+ type: float
+ level: advanced
+ desc: Scrub each PG no less often than this interval
+ default: 7_day
+ see_also:
+ - osd_scrub_min_interval
+ - name: osd_scrub_interval_randomize_ratio
+ type: float
+ level: advanced
+ desc: Ratio of scrub interval to randomly vary
+ long_desc: This prevents a scrub 'stampede' by randomly varying the scrub intervals
+ so that they are soon uniformly distributed over the week
+ default: 0.5
+ see_also:
+ - osd_scrub_min_interval
+ - name: osd_scrub_backoff_ratio
+ type: float
+ level: dev
+ desc: Backoff ratio for scheduling scrubs
+ long_desc: This is the precentage of ticks that do NOT schedule scrubs, 66% means
+ that 1 out of 3 ticks will schedule scrubs
+ default: 0.66
+ - name: osd_scrub_chunk_min
+ type: int
+ level: advanced
+ desc: Minimum number of objects to scrub in a single chunk
+ default: 5
+ see_also:
+ - osd_scrub_chunk_max
+ - name: osd_scrub_chunk_max
+ type: int
+ level: advanced
+ desc: Maximum number of objects to scrub in a single chunk
+ default: 25
+ see_also:
+ - osd_scrub_chunk_min
+ - name: osd_scrub_sleep
+ type: float
+ level: advanced
+ desc: Duration to inject a delay during scrubbing
+ default: 0
+ - name: osd_scrub_extended_sleep
+ type: float
+ level: advanced
+ desc: Duration to inject a delay during scrubbing out of scrubbing hours
+ default: 0
+ see_also:
+ - osd_scrub_begin_hour
+ - osd_scrub_end_hour
+ - osd_scrub_begin_week_day
+ - osd_scrub_end_week_day
+ - name: osd_scrub_auto_repair
+ type: bool
+ level: advanced
+ desc: Automatically repair damaged objects detected during scrub
+ default: false
+ - name: osd_scrub_auto_repair_num_errors
+ type: uint
+ level: advanced
+ desc: Maximum number of detected errors to automatically repair
+ default: 5
+ see_also:
+ - osd_scrub_auto_repair
+ - name: osd_scrub_max_preemptions
+ type: uint
+ level: advanced
+ desc: Set the maximum number of times we will preempt a deep scrub due to a client
+ operation before blocking client IO to complete the scrub
+ default: 5
+ min: 0
+ max: 30
+ - name: osd_deep_scrub_interval
+ type: float
+ level: advanced
+ desc: Deep scrub each PG (i.e., verify data checksums) at least this often
+ default: 7_day
+ - name: osd_deep_scrub_randomize_ratio
+ type: float
+ level: advanced
+ desc: Scrubs will randomly become deep scrubs at this rate (0.15 -> 15% of scrubs
+ are deep)
+ long_desc: This prevents a deep scrub 'stampede' by spreading deep scrubs so they
+ are uniformly distributed over the week
+ default: 0.15
+ - name: osd_deep_scrub_stride
+ type: size
+ level: advanced
+ desc: Number of bytes to read from an object at a time during deep scrub
+ default: 512_K
+ - name: osd_deep_scrub_keys
+ type: int
+ level: advanced
+ desc: Number of keys to read from an object at a time during deep scrub
+ default: 1024
+ - name: osd_deep_scrub_update_digest_min_age
+ type: int
+ level: advanced
+ desc: Update overall object digest only if object was last modified longer ago than
+ this
+ default: 2_hr
+ - name: osd_deep_scrub_large_omap_object_key_threshold
+ type: uint
+ level: advanced
+ desc: Warn when we encounter an object with more omap keys than this
+ default: 200000
+ services:
+ - osd
+ see_also:
+ - osd_deep_scrub_large_omap_object_value_sum_threshold
+ - name: osd_deep_scrub_large_omap_object_value_sum_threshold
+ type: size
+ level: advanced
+ desc: Warn when we encounter an object with more omap key bytes than this
+ default: 1_G
+ services:
+ - osd
+ see_also:
+ - osd_deep_scrub_large_omap_object_key_threshold
+ - name: osd_class_dir
+ type: str
+ level: advanced
+ default: @CMAKE_INSTALL_LIBDIR@/rados-classes
+ - name: osd_open_classes_on_start
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_class_load_list
+ type: str
+ level: advanced
+ default: cephfs hello journal lock log numops otp rbd refcount rgw rgw_gc timeindex
+ user version cas cmpomap queue 2pc_queue fifo
+ - name: osd_class_default_list
+ type: str
+ level: advanced
+ default: cephfs hello journal lock log numops otp rbd refcount rgw rgw_gc timeindex
+ user version cas cmpomap queue 2pc_queue fifo
+ - name: osd_check_for_log_corruption
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_use_stale_snap
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_rollback_to_cluster_snap
+ type: str
+ level: advanced
+ - name: osd_default_notify_timeout
+ type: uint
+ level: advanced
+ desc: default number of seconds after which notify propagation times out. used if
+ a client has not specified other value
+ default: 30
+ - name: osd_kill_backfill_at
+ type: int
+ level: dev
+ default: 0
+ - name: osd_pg_epoch_persisted_max_stale
+ type: uint
+ level: advanced
+ default: 40
+ - name: osd_target_pg_log_entries_per_osd
+ type: uint
+ level: dev
+ desc: target number of PG entries total on an OSD - limited per pg by the min and
+ max options below
+ default: 300000
+ see_also:
+ - osd_max_pg_log_entries
+ - osd_min_pg_log_entries
+ - name: osd_min_pg_log_entries
+ type: uint
+ level: dev
+ desc: minimum number of entries to maintain in the PG log
+ default: 250
+ services:
+ - osd
+ see_also:
+ - osd_max_pg_log_entries
+ - osd_pg_log_dups_tracked
+ - osd_target_pg_log_entries_per_osd
+ - name: osd_max_pg_log_entries
+ type: uint
+ level: dev
+ desc: maximum number of entries to maintain in the PG log
+ default: 10000
+ services:
+ - osd
+ see_also:
+ - osd_min_pg_log_entries
+ - osd_pg_log_dups_tracked
+ - osd_target_pg_log_entries_per_osd
+ - name: osd_pg_log_dups_tracked
+ type: uint
+ level: dev
+ desc: how many versions back to track in order to detect duplicate ops; this is
+ combined with both the regular pg log entries and additional minimal dup detection
+ entries
+ default: 3000
+ services:
+ - osd
+ see_also:
+ - osd_min_pg_log_entries
+ - osd_max_pg_log_entries
+ - name: osd_object_clean_region_max_num_intervals
+ type: int
+ level: dev
+ desc: number of intervals in clean_offsets
+ long_desc: partial recovery uses multiple intervals to record the clean part of
+ the objectwhen the number of intervals is greater than osd_object_clean_region_max_num_intervals,
+ minimum interval will be trimmed(0 will recovery the entire object data interval)
+ default: 10
+ services:
+ - osd
+ - name: osd_force_recovery_pg_log_entries_factor
+ type: float
+ level: dev
+ default: 1.3
+ - name: osd_pg_log_trim_min
+ type: uint
+ level: dev
+ desc: Minimum number of log entries to trim at once. This lets us trim in larger
+ batches rather than with each write.
+ default: 100
+ see_also:
+ - osd_max_pg_log_entries
+ - osd_min_pg_log_entries
+ - name: osd_force_auth_primary_missing_objects
+ type: uint
+ level: advanced
+ desc: Approximate missing objects above which to force auth_log_shard to be primary
+ temporarily
+ default: 100
+ - name: osd_async_recovery_min_cost
+ type: uint
+ level: advanced
+ desc: A mixture measure of number of current log entries difference and historical
+ missing objects, above which we switch to use asynchronous recovery when appropriate
+ default: 100
+ flags:
+ - runtime
+ - name: osd_max_pg_per_osd_hard_ratio
+ type: float
+ level: advanced
+ desc: Maximum number of PG per OSD, a factor of 'mon_max_pg_per_osd'
+ long_desc: OSD will refuse to instantiate PG if the number of PG it serves exceeds
+ this number.
+ default: 3
+ see_also:
+ - mon_max_pg_per_osd
+ min: 1
+ - name: osd_pg_log_trim_max
+ type: uint
+ level: advanced
+ desc: maximum number of entries to remove at once from the PG log
+ default: 10000
+ services:
+ - osd
+ see_also:
+ - osd_min_pg_log_entries
+ - osd_max_pg_log_entries
+ - name: osd_op_complaint_time
+ type: float
+ level: advanced
+ default: 30
+ - name: osd_command_max_records
+ type: int
+ level: advanced
+ default: 256
+ - name: osd_max_pg_blocked_by
+ type: uint
+ level: advanced
+ default: 16
+ - name: osd_op_log_threshold
+ type: int
+ level: advanced
+ default: 5
+ - name: osd_backoff_on_unfound
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_backoff_on_degraded
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_backoff_on_peering
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_debug_shutdown
+ type: bool
+ level: dev
+ desc: Turn up debug levels during shutdown
+ default: false
+ - name: osd_debug_crash_on_ignored_backoff
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_inject_dispatch_delay_probability
+ type: float
+ level: dev
+ default: 0
+ - name: osd_debug_inject_dispatch_delay_duration
+ type: float
+ level: dev
+ default: 0.1
+ - name: osd_debug_drop_ping_probability
+ type: float
+ level: dev
+ default: 0
+ - name: osd_debug_drop_ping_duration
+ type: int
+ level: dev
+ default: 0
+ - name: osd_debug_op_order
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_verify_missing_on_start
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_verify_snaps
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_verify_stray_on_activate
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_skip_full_check_in_backfill_reservation
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_reject_backfill_probability
+ type: float
+ level: dev
+ default: 0
+ - name: osd_debug_inject_copyfrom_error
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_misdirected_ops
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_skip_full_check_in_recovery
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_random_push_read_error
+ type: float
+ level: dev
+ default: 0
+ - name: osd_debug_verify_cached_snaps
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_deep_scrub_sleep
+ type: float
+ level: dev
+ desc: Inject an expensive sleep during deep scrub IO to make it easier to induce
+ preemption
+ default: 0
+ - name: osd_debug_no_acting_change
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_no_purge_strays
+ type: bool
+ level: dev
+ default: false
+ - name: osd_debug_pretend_recovery_active
+ type: bool
+ level: dev
+ default: false
+ - name: osd_enable_op_tracker
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_num_op_tracker_shard
+ type: uint
+ level: advanced
+ default: 32
+ - name: osd_op_history_size
+ type: uint
+ level: advanced
+ default: 20
+ - name: osd_op_history_duration
+ type: uint
+ level: advanced
+ default: 600
+ - name: osd_op_history_slow_op_size
+ type: uint
+ level: advanced
+ default: 20
+ - name: osd_op_history_slow_op_threshold
+ type: float
+ level: advanced
+ default: 10
+ - name: osd_target_transaction_size
+ type: int
+ level: advanced
+ default: 30
+ - name: osd_delete_sleep
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next removal transaction (overrides values
+ below)
+ default: 0
+ - name: osd_delete_sleep_hdd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next removal transaction for HDDs
+ default: 5
+ - name: osd_delete_sleep_ssd
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next removal transaction for SSDs
+ default: 1
+ - name: osd_delete_sleep_hybrid
+ type: float
+ level: advanced
+ desc: Time in seconds to sleep before next removal transaction when data is on HDD
+ and journal is on SSD
+ default: 1
+ - name: osd_failsafe_full_ratio
+ type: float
+ level: advanced
+ default: 0.97
+ - name: osd_fast_shutdown
+ type: bool
+ level: advanced
+ desc: Fast, immediate shutdown
+ long_desc: Setting this to false makes the OSD do a slower teardown of all state
+ when it receives a SIGINT or SIGTERM or when shutting down for any other reason. That
+ slow shutdown is primarilyy useful for doing memory leak checking with valgrind.
+ default: true
+ - name: osd_fast_shutdown_notify_mon
+ type: bool
+ level: advanced
+ desc: Tell mon about OSD shutdown on immediate shutdown
+ long_desc: Tell the monitor the OSD is shutting down on immediate shutdown. This
+ helps with cluster log messages from other OSDs reporting it immediately failed.
+ default: false
+ see_also:
+ - osd_fast_shutdown
+ - osd_mon_shutdown_timeout
+ - name: osd_fast_fail_on_connection_refused
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_pg_object_context_cache_count
+ type: int
+ level: advanced
+ default: 64
+ - name: osd_tracing
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_function_tracing
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_fast_info
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_debug_pg_log_writeout
+ type: bool
+ level: dev
+ default: false
+ - name: osd_loop_before_reset_tphandle
+ type: uint
+ level: advanced
+ default: 64
+ - name: threadpool_default_timeout
+ type: int
+ level: advanced
+ default: 1_min
+ - name: threadpool_empty_queue_max_wait
+ type: int
+ level: advanced
+ default: 2
+ - name: leveldb_log_to_ceph_log
+ type: bool
+ level: advanced
+ default: true
+ - name: leveldb_write_buffer_size
+ type: size
+ level: advanced
+ default: 8_M
+ - name: leveldb_cache_size
+ type: size
+ level: advanced
+ default: 128_M
+ - name: leveldb_block_size
+ type: size
+ level: advanced
+ default: 0
+ - name: leveldb_bloom_size
+ type: int
+ level: advanced
+ default: 0
+ - name: leveldb_max_open_files
+ type: int
+ level: advanced
+ default: 0
+ - name: leveldb_compression
+ type: bool
+ level: advanced
+ default: true
+ - name: leveldb_paranoid
+ type: bool
+ level: advanced
+ default: false
+ - name: leveldb_log
+ type: str
+ level: advanced
+ default: /dev/null
+ - name: leveldb_compact_on_mount
+ type: bool
+ level: advanced
+ default: false
+ - name: rocksdb_log_to_ceph_log
+ type: bool
+ level: advanced
+ default: true
+ - name: rocksdb_cache_size
+ type: size
+ level: advanced
+ default: 512_M
+ flags:
+ - runtime
+ - name: rocksdb_cache_row_ratio
+ type: float
+ level: advanced
+ default: 0
+ - name: rocksdb_cache_shard_bits
+ type: int
+ level: advanced
+ default: 4
+ - name: rocksdb_cache_type
+ type: str
+ level: advanced
+ default: binned_lru
+ - name: rocksdb_block_size
+ type: size
+ level: advanced
+ default: 4_K
+ - name: rocksdb_perf
+ type: bool
+ level: advanced
+ default: false
+ - name: rocksdb_collect_compaction_stats
+ type: bool
+ level: advanced
+ default: false
+ - name: rocksdb_collect_extended_stats
+ type: bool
+ level: advanced
+ default: false
+ - name: rocksdb_collect_memory_stats
+ type: bool
+ level: advanced
+ default: false
+ - name: rocksdb_delete_range_threshold
+ type: uint
+ level: advanced
+ desc: The number of keys required to invoke DeleteRange when deleting muliple keys.
+ default: 1_M
+ - name: rocksdb_bloom_bits_per_key
+ type: uint
+ level: advanced
+ desc: Number of bits per key to use for RocksDB's bloom filters.
+ long_desc: 'RocksDB bloom filters can be used to quickly answer the question of
+ whether or not a key may exist or definitely does not exist in a given RocksDB
+ SST file without having to read all keys into memory. Using a higher bit value
+ decreases the likelihood of false positives at the expense of additional disk
+ space and memory consumption when the filter is loaded into RAM. The current
+ default value of 20 was found to provide significant performance gains when getattr
+ calls are made (such as during new object creation in bluestore) without significant
+ memory overhead or cache pollution when combined with rocksdb partitioned index
+ filters. See: https://github.com/facebook/rocksdb/wiki/Partitioned-Index-Filters
+ for more information.'
+ default: 20
+ - name: rocksdb_cache_index_and_filter_blocks
+ type: bool
+ level: dev
+ desc: Whether to cache indices and filters in block cache
+ long_desc: By default RocksDB will load an SST file's index and bloom filters into
+ memory when it is opened and remove them from memory when an SST file is closed. Thus,
+ memory consumption by indices and bloom filters is directly tied to the number
+ of concurrent SST files allowed to be kept open. This option instead stores cached
+ indicies and filters in the block cache where they directly compete with other
+ cached data. By default we set this option to true to better account for and
+ bound rocksdb memory usage and keep filters in memory even when an SST file is
+ closed.
+ default: true
+ - name: rocksdb_cache_index_and_filter_blocks_with_high_priority
+ type: bool
+ level: dev
+ desc: Whether to cache indices and filters in the block cache with high priority
+ long_desc: A downside of setting rocksdb_cache_index_and_filter_blocks to true is
+ that regular data can push indices and filters out of memory. Setting this option
+ to true means they are cached with higher priority than other data and should
+ typically stay in the block cache.
+ default: false
+ - name: rocksdb_pin_l0_filter_and_index_blocks_in_cache
+ type: bool
+ level: dev
+ desc: Whether to pin Level 0 indices and bloom filters in the block cache
+ long_desc: A downside of setting rocksdb_cache_index_and_filter_blocks to true is
+ that regular data can push indices and filters out of memory. Setting this option
+ to true means that level 0 SST files will always have their indices and filters
+ pinned in the block cache.
+ default: false
+ - name: rocksdb_index_type
+ type: str
+ level: dev
+ desc: 'Type of index for SST files: binary_search, hash_search, two_level'
+ long_desc: 'This option controls the table index type. binary_search is a space
+ efficient index block that is optimized for block-search-based index. hash_search
+ may improve prefix lookup performance at the expense of higher disk and memory
+ usage and potentially slower compactions. two_level is an experimental index
+ type that uses two binary search indexes and works in conjunction with partition
+ filters. See: http://rocksdb.org/blog/2017/05/12/partitioned-index-filter.html'
+ default: binary_search
+ - name: rocksdb_partition_filters
+ type: bool
+ level: dev
+ desc: (experimental) partition SST index/filters into smaller blocks
+ long_desc: 'This is an experimental option for rocksdb that works in conjunction
+ with two_level indices to avoid having to keep the entire filter/index in cache
+ when cache_index_and_filter_blocks is true. The idea is to keep a much smaller
+ top-level index in heap/cache and then opportunistically cache the lower level
+ indices. See: https://github.com/facebook/rocksdb/wiki/Partitioned-Index-Filters'
+ default: false
+ - name: rocksdb_metadata_block_size
+ type: size
+ level: dev
+ desc: The block size for index partitions. (0 = rocksdb default)
+ default: 4_K
+ - name: mon_rocksdb_options
+ type: str
+ level: advanced
+ default: write_buffer_size=33554432,compression=kNoCompression,level_compaction_dynamic_level_bytes=true
+ - name: osd_client_op_priority
+ type: uint
+ level: advanced
+ default: 63
+ - name: osd_recovery_op_priority
+ type: uint
+ level: advanced
+ desc: Priority to use for recovery operations if not specified for the pool
+ default: 3
+ - name: osd_peering_op_priority
+ type: uint
+ level: dev
+ default: 255
+ - name: osd_snap_trim_priority
+ type: uint
+ level: advanced
+ default: 5
+ - name: osd_snap_trim_cost
+ type: size
+ level: advanced
+ default: 1_M
+ - name: osd_pg_delete_priority
+ type: uint
+ level: advanced
+ default: 5
+ - name: osd_pg_delete_cost
+ type: size
+ level: advanced
+ default: 1_M
+ - name: osd_scrub_priority
+ type: uint
+ level: advanced
+ desc: Priority for scrub operations in work queue
+ default: 5
+ - name: osd_scrub_cost
+ type: size
+ level: advanced
+ desc: Cost for scrub operations in work queue
+ default: 50_M
+ - name: osd_requested_scrub_priority
+ type: uint
+ level: advanced
+ default: 120
+ - name: osd_recovery_priority
+ type: uint
+ level: advanced
+ desc: Priority of recovery in the work queue
+ long_desc: Not related to a pool's recovery_priority
+ default: 5
+ - name: osd_recovery_cost
+ type: size
+ level: advanced
+ default: 20_M
+ - name: osd_recovery_op_warn_multiple
+ type: uint
+ level: advanced
+ default: 16
+ - name: osd_mon_shutdown_timeout
+ type: float
+ level: advanced
+ default: 5
+ - name: osd_shutdown_pgref_assert
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_max_object_size
+ type: size
+ level: advanced
+ default: 128_M
+ - name: osd_max_object_name_len
+ type: uint
+ level: advanced
+ default: 2_K
+ - name: osd_max_object_namespace_len
+ type: uint
+ level: advanced
+ default: 256
+ - name: osd_max_attr_name_len
+ type: uint
+ level: advanced
+ default: 100
+ - name: osd_max_attr_size
+ type: uint
+ level: advanced
+ default: 0
+ - name: osd_max_omap_entries_per_request
+ type: uint
+ level: advanced
+ default: 1_K
+ - name: osd_max_omap_bytes_per_request
+ type: size
+ level: advanced
+ default: 1_G
+ - name: osd_max_write_op_reply_len
+ type: size
+ level: advanced
+ desc: Max size of the per-op payload for requests with the RETURNVEC flag set
+ long_desc: This value caps the amount of data (per op; a request may have many ops)
+ that will be sent back to the client and recorded in the PG log.
+ default: 32
+ - name: osd_objectstore
+ type: str
+ level: advanced
+ desc: backend type for an OSD (like filestore or bluestore)
+ default: bluestore
+ enum_values:
+ - bluestore
+ - filestore
+ - memstore
+ - kstore
+ flags:
+ - create
+ - name: osd_objectstore_tracing
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_objectstore_fuse
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_bench_small_size_max_iops
+ type: uint
+ level: advanced
+ default: 100
+ - name: osd_bench_large_size_max_throughput
+ type: size
+ level: advanced
+ default: 100_M
+ - name: osd_bench_max_block_size
+ type: size
+ level: advanced
+ default: 64_M
+ - name: osd_bench_duration
+ type: uint
+ level: advanced
+ default: 30
+ - name: osd_blkin_trace_all
+ type: bool
+ level: advanced
+ default: false
+ - name: osdc_blkin_trace_all
+ type: bool
+ level: advanced
+ default: false
+ - name: osd_discard_disconnected_ops
+ type: bool
+ level: advanced
+ default: true
+ - name: osd_memory_target
+ type: size
+ level: basic
+ desc: When tcmalloc and cache autotuning is enabled, try to keep this many bytes
+ mapped in memory.
+ long_desc: The minimum value must be at least equal to osd_memory_base + osd_memory_cache_min.
+ default: 4_G
+ see_also:
+ - bluestore_cache_autotune
+ - osd_memory_cache_min
+ - osd_memory_base
+ min: 896_M
+ flags:
+ - runtime
+ - name: osd_memory_target_cgroup_limit_ratio
+ type: float
+ level: advanced
+ desc: Set the default value for osd_memory_target to the cgroup memory limit (if
+ set) times this value
+ long_desc: A value of 0 disables this feature.
+ default: 0.8
+ see_also:
+ - osd_memory_target
+ min: 0
+ max: 1
+ - name: osd_memory_base
+ type: size
+ level: dev
+ desc: When tcmalloc and cache autotuning is enabled, estimate the minimum amount
+ of memory in bytes the OSD will need.
+ default: 768_M
+ see_also:
+ - bluestore_cache_autotune
+ flags:
+ - runtime
+ - name: osd_memory_expected_fragmentation
+ type: float
+ level: dev
+ desc: When tcmalloc and cache autotuning is enabled, estimate the percent of memory
+ fragmentation.
+ default: 0.15
+ see_also:
+ - bluestore_cache_autotune
+ min: 0
+ max: 1
+ flags:
+ - runtime
+ - name: osd_memory_cache_min
+ type: size
+ level: dev
+ desc: When tcmalloc and cache autotuning is enabled, set the minimum amount of memory
+ used for caches.
+ default: 128_M
+ see_also:
+ - bluestore_cache_autotune
+ min: 128_M
+ flags:
+ - runtime
+ - name: osd_memory_cache_resize_interval
+ type: float
+ level: dev
+ desc: When tcmalloc and cache autotuning is enabled, wait this many seconds between
+ resizing caches.
+ default: 1
+ see_also:
+ - bluestore_cache_autotune
+ - name: memstore_device_bytes
+ type: size
+ level: advanced
+ default: 1_G
+ - name: memstore_page_set
+ type: bool
+ level: advanced
+ default: false
+ - name: memstore_page_size
+ type: size
+ level: advanced
+ default: 64_K
+ - name: memstore_debug_omit_block_device_write
+ type: bool
+ level: dev
+ desc: write metadata only
+ default: false
+ see_also:
+ - bluestore_debug_omit_block_device_write
+ - name: objectstore_blackhole
+ type: bool
+ level: advanced
+ default: false
+ - name: bdev_debug_inflight_ios
+ type: bool
+ level: dev
+ default: false
+ - name: bdev_inject_crash
+ type: int
+ level: dev
+ default: 0
+ - name: bdev_inject_crash_flush_delay
+ type: int
+ level: dev
+ default: 2
+ - name: bdev_aio
+ type: bool
+ level: advanced
+ default: true
+ - name: bdev_aio_poll_ms
+ type: int
+ level: advanced
+ default: 250
+ - name: bdev_aio_max_queue_depth
+ type: int
+ level: advanced
+ default: 1024
+ - name: bdev_aio_reap_max
+ type: int
+ level: advanced
+ default: 16
+ - name: bdev_block_size
+ type: size
+ level: advanced
+ default: 4_K
+ - name: bdev_debug_aio
+ type: bool
+ level: dev
+ default: false
+ - name: bdev_debug_aio_suicide_timeout
+ type: float
+ level: dev
+ default: 1_min
+ - name: bdev_debug_aio_log_age
+ type: float
+ level: dev
+ default: 5
+ - name: bdev_nvme_unbind_from_kernel
+ type: bool
+ level: advanced
+ default: false
+ - name: bdev_enable_discard
+ type: bool
+ level: advanced
+ default: false
+ - name: bdev_async_discard
+ type: bool
+ level: advanced
+ default: false
+ - name: bdev_flock_retry_interval
+ type: float
+ level: advanced
+ desc: interval to retry the flock
+ default: 0.1
+ - name: bdev_flock_retry
+ type: uint
+ level: advanced
+ desc: times to retry the flock
+ long_desc: The number of times to retry on getting the block device lock. Programs
+ such as systemd-udevd may compete with Ceph for this lock. 0 means 'unlimited'.
+ default: 3
+ - name: bluefs_alloc_size
+ type: size
+ level: advanced
+ desc: Allocation unit size for DB and WAL devices
+ default: 1_M
+ - name: bluefs_shared_alloc_size
+ type: size
+ level: advanced
+ desc: Allocation unit size for primary/shared device
+ default: 64_K
+ - name: bluefs_max_prefetch
+ type: size
+ level: advanced
+ default: 1_M
+ - name: bluefs_min_log_runway
+ type: size
+ level: advanced
+ default: 1_M
+ - name: bluefs_max_log_runway
+ type: size
+ level: advanced
+ default: 4_M
+ - name: bluefs_log_compact_min_ratio
+ type: float
+ level: advanced
+ default: 5
+ - name: bluefs_log_compact_min_size
+ type: size
+ level: advanced
+ default: 16_M
+ - name: bluefs_min_flush_size
+ type: size
+ level: advanced
+ default: 512_K
+ - name: bluefs_compact_log_sync
+ type: bool
+ level: advanced
+ default: false
+ - name: bluefs_buffered_io
+ type: bool
+ level: advanced
+ desc: Enabled buffered IO for bluefs reads.
+ long_desc: When this option is enabled, bluefs will in some cases perform buffered
+ reads. This allows the kernel page cache to act as a secondary cache for things
+ like RocksDB compaction. For example, if the rocksdb block cache isn't large
+ enough to hold blocks from the compressed SST files itself, they can be read from
+ page cache instead of from the disk.
+ default: true
+ - name: bluefs_sync_write
+ type: bool
+ level: advanced
+ default: false
+ - name: bluefs_allocator
+ type: str
+ level: dev
+ default: hybrid
+ enum_values:
+ - bitmap
+ - stupid
+ - avl
+ - hybrid
+ - name: bluefs_log_replay_check_allocations
+ type: bool
+ level: advanced
+ desc: Enables checks for allocations consistency during log replay
+ default: true
+ - name: bluefs_replay_recovery
+ type: bool
+ level: dev
+ desc: Attempt to read bluefs log so large that it became unreadable.
+ long_desc: If BlueFS log grows to extreme sizes (200GB+) it is likely that it becames
+ unreadable. This options enables heuristics that scans devices for missing data.
+ DO NOT ENABLE BY DEFAULT
+ default: false
+ - name: bluefs_replay_recovery_disable_compact
+ type: bool
+ level: advanced
+ default: false
+ - name: bluefs_check_for_zeros
+ type: bool
+ level: dev
+ desc: Check data read for suspicious pages
+ long_desc: Looks into data read to check if there is a 4K block entirely filled
+ with zeros. If this happens, we re-read data. If there is difference, we print
+ error to log.
+ default: false
+ see_also:
+ - bluestore_retry_disk_reads
+ flags:
+ - runtime
+ - name: bluestore_bluefs
+ type: bool
+ level: dev
+ desc: Use BlueFS to back rocksdb
+ long_desc: BlueFS allows rocksdb to share the same physical device(s) as the rest
+ of BlueStore. It should be used in all cases unless testing/developing an alternative
+ metadata database for BlueStore.
+ default: true
+ flags:
+ - create
+ - name: bluestore_bluefs_env_mirror
+ type: bool
+ level: dev
+ desc: Mirror bluefs data to file system for testing/validation
+ default: false
+ flags:
+ - create
+ - name: bluestore_bluefs_min
+ type: size
+ level: advanced
+ desc: minimum disk space allocated to BlueFS (e.g., at mkfs)
+ default: 1_G
+ - name: bluestore_bluefs_min_free
+ type: size
+ level: advanced
+ default: 1_G
+ desc: minimum free space allocated to BlueFS
+ - name: bluestore_bluefs_max_free
+ type: size
+ level: advanced
+ default: 10_G
+ desc: Maximum free space allocated to BlueFS
+ - name: bluestore_bluefs_min_ratio
+ type: float
+ level: advanced
+ default: 0.02
+ desc: Minimum fraction of free space devoted to BlueFS
+ - name: bluestore_bluefs_max_ratio
+ type: float
+ level: advanced
+ default: 0.9
+ desc: Maximum fraction of free storage devoted to BlueFS
+ - name: bluestore_bluefs_gift_ratio
+ type: float
+ level: advanced
+ default: 0.02
+ desc: Maximum fraction of free space to give to BlueFS at once
+ - name: bluestore_bluefs_reclaim_ratio
+ type: float
+ level: advanced
+ default: 0.2
+ desc: Maximum fraction of free space to reclaim from BlueFS at once
+ - name: bluestore_bluefs_balance_interval
+ type: float
+ level: advanced
+ default: 1
+ desc: How frequently (in seconds) to balance free space between BlueFS and BlueStore
+ - name: bluestore_bluefs_alloc_failure_dump_interval
+ type: float
+ level: advanced
+ desc: How frequently (in seconds) to dump allocator onBlueFS space allocation failure
+ default: 0
+ - name: bluestore_spdk_mem
+ type: size
+ level: dev
+ desc: Amount of dpdk memory size in MB
+ long_desc: If running multiple SPDK instances per node, you must specify the amount
+ of dpdk memory size in MB each instance will use, to make sure each instance uses
+ its own dpdk memory
+ default: 512
+ - name: bluestore_spdk_coremask
+ type: str
+ level: dev
+ desc: A hexadecimal bit mask of the cores to run on. Note the core numbering can
+ change between platforms and should be determined beforehand
+ default: '0x1'
+ - name: bluestore_spdk_max_io_completion
+ type: uint
+ level: dev
+ desc: Maximal I/Os to be batched completed while checking queue pair completions,
+ 0 means let spdk library determine it
+ default: 0
+ - name: bluestore_spdk_io_sleep
+ type: uint
+ level: dev
+ desc: Time period to wait if there is no completed I/O from polling
+ default: 5
+ - name: bluestore_block_path
+ type: str
+ level: dev
+ desc: Path to block device/file
+ flags:
+ - create
+ - name: bluestore_block_size
+ type: size
+ level: dev
+ desc: Size of file to create for backing bluestore
+ default: 100_G
+ flags:
+ - create
+ - name: bluestore_block_create
+ type: bool
+ level: dev
+ desc: Create bluestore_block_path if it doesn't exist
+ default: true
+ see_also:
+ - bluestore_block_path
+ - bluestore_block_size
+ flags:
+ - create
+ - name: bluestore_block_db_path
+ type: str
+ level: dev
+ desc: Path for db block device
+ flags:
+ - create
+ - name: bluestore_block_db_size
+ type: uint
+ level: dev
+ desc: Size of file to create for bluestore_block_db_path
+ default: 0
+ flags:
+ - create
+ - name: bluestore_block_db_create
+ type: bool
+ level: dev
+ desc: Create bluestore_block_db_path if it doesn't exist
+ default: false
+ see_also:
+ - bluestore_block_db_path
+ - bluestore_block_db_size
+ flags:
+ - create
+ - name: bluestore_block_wal_path
+ type: str
+ level: dev
+ desc: Path to block device/file backing bluefs wal
+ flags:
+ - create
+ - name: bluestore_block_wal_size
+ type: size
+ level: dev
+ desc: Size of file to create for bluestore_block_wal_path
+ default: 96_M
+ flags:
+ - create
+ - name: bluestore_block_wal_create
+ type: bool
+ level: dev
+ desc: Create bluestore_block_wal_path if it doesn't exist
+ default: false
+ see_also:
+ - bluestore_block_wal_path
+ - bluestore_block_wal_size
+ flags:
+ - create
+ - name: bluestore_block_preallocate_file
+ type: bool
+ level: dev
+ desc: Preallocate file created via bluestore_block*_create
+ default: false
+ flags:
+ - create
+ - name: bluestore_ignore_data_csum
+ type: bool
+ level: dev
+ desc: Ignore checksum errors on read and do not generate an EIO error
+ default: false
+ flags:
+ - runtime
+ - name: bluestore_csum_type
+ type: str
+ level: advanced
+ desc: Default checksum algorithm to use
+ long_desc: crc32c, xxhash32, and xxhash64 are available. The _16 and _8 variants
+ use only a subset of the bits for more compact (but less reliable) checksumming.
+ default: crc32c
+ enum_values:
+ - none
+ - crc32c
+ - crc32c_16
+ - crc32c_8
+ - xxhash32
+ - xxhash64
+ flags:
+ - runtime
+ - name: bluestore_retry_disk_reads
+ type: uint
+ level: advanced
+ desc: Number of read retries on checksum validation error
+ long_desc: Retries to read data from the disk this many times when checksum validation
+ fails to handle spurious read errors gracefully.
+ default: 3
+ min: 0
+ max: 255
+ flags:
+ - runtime
+ - name: bluestore_min_alloc_size
+ type: uint
+ level: advanced
+ desc: Minimum allocation size to allocate for an object
+ long_desc: A smaller allocation size generally means less data is read and then
+ rewritten when a copy-on-write operation is triggered (e.g., when writing to something
+ that was recently snapshotted). Similarly, less data is journaled before performing
+ an overwrite (writes smaller than min_alloc_size must first pass through the BlueStore
+ journal). Larger values of min_alloc_size reduce the amount of metadata required
+ to describe the on-disk layout and reduce overall fragmentation.
+ default: 0
+ flags:
+ - create
+ - name: bluestore_min_alloc_size_hdd
+ type: size
+ level: advanced
+ desc: Default min_alloc_size value for rotational media
+ default: 4_K
+ see_also:
+ - bluestore_min_alloc_size
+ flags:
+ - create
+ - name: bluestore_min_alloc_size_ssd
+ type: size
+ level: advanced
+ desc: Default min_alloc_size value for non-rotational (solid state) media
+ default: 4_K
+ see_also:
+ - bluestore_min_alloc_size
+ flags:
+ - create
+ - name: bluestore_max_alloc_size
+ type: size
+ level: advanced
+ desc: Maximum size of a single allocation (0 for no max)
+ default: 0
+ flags:
+ - create
+ - name: bluestore_prefer_deferred_size
+ type: size
+ level: advanced
+ desc: Writes smaller than this size will be written to the journal and then asynchronously
+ written to the device. This can be beneficial when using rotational media where
+ seeks are expensive, and is helpful both with and without solid state journal/wal
+ devices.
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_prefer_deferred_size_hdd
+ type: size
+ level: advanced
+ desc: Default bluestore_prefer_deferred_size for rotational media
+ default: 64_K
+ see_also:
+ - bluestore_prefer_deferred_size
+ flags:
+ - runtime
+ - name: bluestore_prefer_deferred_size_ssd
+ type: size
+ level: advanced
+ desc: Default bluestore_prefer_deferred_size for non-rotational (solid state) media
+ default: 0
+ see_also:
+ - bluestore_prefer_deferred_size
+ flags:
+ - runtime
+ - name: bluestore_compression_mode
+ type: str
+ level: advanced
+ desc: Default policy for using compression when pool does not specify
+ long_desc: '''none'' means never use compression. ''passive'' means use compression
+ when clients hint that data is compressible. ''aggressive'' means use compression
+ unless clients hint that data is not compressible. This option is used when the
+ per-pool property for the compression mode is not present.'
+ default: none
+ enum_values:
+ - none
+ - passive
+ - aggressive
+ - force
+ flags:
+ - runtime
+ - name: bluestore_compression_algorithm
+ type: str
+ level: advanced
+ desc: Default compression algorithm to use when writing object data
+ long_desc: This controls the default compressor to use (if any) if the per-pool
+ property is not set. Note that zstd is *not* recommended for bluestore due to
+ high CPU overhead when compressing small amounts of data.
+ default: snappy
+ enum_values:
+ - ''
+ - snappy
+ - zlib
+ - zstd
+ - lz4
+ flags:
+ - runtime
+ - name: bluestore_compression_min_blob_size
+ type: size
+ level: advanced
+ desc: Maximum chunk size to apply compression to when random access is expected
+ for an object.
+ long_desc: Chunks larger than this are broken into smaller chunks before being compressed
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_compression_min_blob_size_hdd
+ type: size
+ level: advanced
+ desc: Default value of bluestore_compression_min_blob_size for rotational media
+ default: 8_K
+ see_also:
+ - bluestore_compression_min_blob_size
+ flags:
+ - runtime
+ - name: bluestore_compression_min_blob_size_ssd
+ type: size
+ level: advanced
+ desc: Default value of bluestore_compression_min_blob_size for non-rotational (solid
+ state) media
+ default: 8_K
+ see_also:
+ - bluestore_compression_min_blob_size
+ flags:
+ - runtime
+ - name: bluestore_compression_max_blob_size
+ type: size
+ level: advanced
+ desc: Maximum chunk size to apply compression to when non-random access is expected
+ for an object.
+ long_desc: Chunks larger than this are broken into smaller chunks before being compressed
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_compression_max_blob_size_hdd
+ type: size
+ level: advanced
+ desc: Default value of bluestore_compression_max_blob_size for rotational media
+ default: 64_K
+ see_also:
+ - bluestore_compression_max_blob_size
+ flags:
+ - runtime
+ - name: bluestore_compression_max_blob_size_ssd
+ type: size
+ level: advanced
+ desc: Default value of bluestore_compression_max_blob_size for non-rotational (solid
+ state) media
+ default: 64_K
+ see_also:
+ - bluestore_compression_max_blob_size
+ flags:
+ - runtime
+ - name: bluestore_gc_enable_blob_threshold
+ type: int
+ level: dev
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_gc_enable_total_threshold
+ type: int
+ level: dev
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_max_blob_size
+ type: size
+ level: dev
+ long_desc: Bluestore blobs are collections of extents (ie on-disk data) originating
+ from one or more objects. Blobs can be compressed, typically have checksum data,
+ may be overwritten, may be shared (with an extent ref map), or split. This setting
+ controls the maximum size a blob is allowed to be.
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_max_blob_size_hdd
+ type: size
+ level: dev
+ default: 64_K
+ see_also:
+ - bluestore_max_blob_size
+ flags:
+ - runtime
+ - name: bluestore_max_blob_size_ssd
+ type: size
+ level: dev
+ default: 64_K
+ see_also:
+ - bluestore_max_blob_size
+ flags:
+ - runtime
+ - name: bluestore_compression_required_ratio
+ type: float
+ level: advanced
+ desc: Compression ratio required to store compressed data
+ long_desc: If we compress data and get less than this we discard the result and
+ store the original uncompressed data.
+ default: 0.875
+ flags:
+ - runtime
+ - name: bluestore_extent_map_shard_max_size
+ type: size
+ level: dev
+ desc: Max size (bytes) for a single extent map shard before splitting
+ default: 1200
+ - name: bluestore_extent_map_shard_target_size
+ type: size
+ level: dev
+ desc: Target size (bytes) for a single extent map shard
+ default: 500
+ - name: bluestore_extent_map_shard_min_size
+ type: size
+ level: dev
+ desc: Min size (bytes) for a single extent map shard before merging
+ default: 150
+ - name: bluestore_extent_map_shard_target_size_slop
+ type: float
+ level: dev
+ desc: Ratio above/below target for a shard when trying to align to an existing extent
+ or blob boundary
+ default: 0.2
+ - name: bluestore_extent_map_inline_shard_prealloc_size
+ type: size
+ level: dev
+ desc: Preallocated buffer for inline shards
+ default: 256
+ - name: bluestore_cache_trim_interval
+ type: float
+ level: advanced
+ desc: How frequently we trim the bluestore cache
+ default: 0.05
+ - name: bluestore_cache_trim_max_skip_pinned
+ type: uint
+ level: dev
+ desc: Max pinned cache entries we consider before giving up
+ default: 64
+ - name: bluestore_cache_type
+ type: str
+ level: dev
+ desc: Cache replacement algorithm
+ default: 2q
+ enum_values:
+ - 2q
+ - lru
+ - name: bluestore_2q_cache_kin_ratio
+ type: float
+ level: dev
+ desc: 2Q paper suggests .5
+ default: 0.5
+ - name: bluestore_2q_cache_kout_ratio
+ type: float
+ level: dev
+ desc: 2Q paper suggests .5
+ default: 0.5
+ - name: bluestore_cache_size
+ type: size
+ level: dev
+ desc: Cache size (in bytes) for BlueStore
+ long_desc: This includes data and metadata cached by BlueStore as well as memory
+ devoted to rocksdb's cache(s).
+ default: 0
+ - name: bluestore_cache_size_hdd
+ type: size
+ level: dev
+ desc: Default bluestore_cache_size for rotational media
+ default: 1_G
+ see_also:
+ - bluestore_cache_size
+ - name: bluestore_cache_size_ssd
+ type: size
+ level: dev
+ desc: Default bluestore_cache_size for non-rotational (solid state) media
+ default: 3_G
+ see_also:
+ - bluestore_cache_size
+ - name: bluestore_cache_meta_ratio
+ type: float
+ level: dev
+ desc: Ratio of bluestore cache to devote to metadata
+ default: 0.4
+ see_also:
+ - bluestore_cache_size
+ - name: bluestore_cache_kv_ratio
+ type: float
+ level: dev
+ desc: Ratio of bluestore cache to devote to kv database (rocksdb)
+ default: 0
+ see_also:
+ - bluestore_cache_size
+ - name: bluestore_cache_kv_onode_ratio
+ type: float
+ level: dev
+ desc: Ratio of bluestore cache to devote to kv onode column family (rocksdb)
+ default: 0
+ see_also:
+ - bluestore_cache_size
+ - name: bluestore_cache_autotune
+ type: bool
+ level: dev
+ desc: Automatically tune the ratio of caches while respecting min values.
+ default: true
+ see_also:
+ - bluestore_cache_size
+ - bluestore_cache_meta_ratio
+ - name: bluestore_cache_autotune_interval
+ type: float
+ level: dev
+ desc: The number of seconds to wait between rebalances when cache autotune is enabled.
+ default: 5
+ see_also:
+ - bluestore_cache_autotune
+ - name: bluestore_alloc_stats_dump_interval
+ type: float
+ level: dev
+ desc: The period (in second) for logging allocation statistics.
+ default: 1_day
+ - name: bluestore_kvbackend
+ type: str
+ level: dev
+ desc: Key value database to use for bluestore
+ default: rocksdb
+ flags:
+ - create
+ - name: bluestore_allocator
+ type: str
+ level: advanced
+ desc: Allocator policy
+ long_desc: Allocator to use for bluestore. Stupid should only be used for testing.
+ default: hybrid
+ enum_values:
+ - bitmap
+ - stupid
+ - avl
+ - hybrid
+ - zoned
+ - name: bluestore_freelist_blocks_per_key
+ type: size
+ level: dev
+ desc: Block (and bits) per database key
+ default: 128
+ - name: bluestore_bitmapallocator_blocks_per_zone
+ type: size
+ level: dev
+ default: 1_K
+ - name: bluestore_bitmapallocator_span_size
+ type: size
+ level: dev
+ default: 1_K
+ - name: bluestore_max_deferred_txc
+ type: uint
+ level: advanced
+ desc: Max transactions with deferred writes that can accumulate before we force
+ flush deferred writes
+ default: 32
+ - name: bluestore_max_defer_interval
+ type: float
+ level: advanced
+ desc: max duration to force deferred submit
+ default: 3
+ - name: bluestore_rocksdb_options
+ type: str
+ level: advanced
+ desc: Full set of rocksdb settings to override
+ default: compression=kNoCompression,max_write_buffer_number=4,min_write_buffer_number_to_merge=1,recycle_log_file_num=4,write_buffer_size=268435456,writable_file_max_buffer_size=0,compaction_readahead_size=2097152,max_background_compactions=2,max_total_wal_size=1073741824
+ - name: bluestore_rocksdb_options_annex
+ type: str
+ level: advanced
+ desc: An addition to bluestore_rocksdb_options. Allows setting rocksdb options without
+ repeating the existing defaults.
+ - name: bluestore_rocksdb_cf
+ type: bool
+ level: advanced
+ desc: Enable use of rocksdb column families for bluestore metadata
+ default: true
+ verbatim: |
+ #ifdef WITH_SEASTAR
+ // This is necessary as the Seastar's allocator imposes restrictions
+ // on the number of threads that entered malloc/free/*. Unfortunately,
+ // RocksDB sharding in BlueStore dramatically lifted the number of
+ // threads spawn during RocksDB's init.
+ .set_validator([](std::string *value, std::string *error_message) {
+ if (const bool parsed_value = strict_strtob(value->c_str(), error_message);
+ error_message->empty() && parsed_value) {
+ *error_message = "invalid BlueStore sharding configuration."
+ " Be aware any change takes effect only on mkfs!";
+ return -EINVAL;
+ } else {
+ return 0;
+ }
+ })
+ #endif
+ - name: bluestore_rocksdb_cfs
+ type: str
+ level: dev
+ desc: Definition of column families and their sharding
+ long_desc: 'Space separated list of elements: column_def [ ''='' rocksdb_options
+ ]. column_def := column_name [ ''('' shard_count [ '','' hash_begin ''-'' [ hash_end
+ ] ] '')'' ]. Example: ''I=write_buffer_size=1048576 O(6) m(7,10-)''. Interval
+ [hash_begin..hash_end) defines characters to use for hash calculation. Recommended
+ hash ranges: O(0-13) P(0-8) m(0-16). Sharding of S,T,C,M,B prefixes is inadvised'
+ default: m(3) p(3,0-12) O(3,0-13)=block_cache={type=binned_lru} L P
+ - name: bluestore_fsck_on_mount
+ type: bool
+ level: dev
+ desc: Run fsck at mount
+ default: false
+ - name: bluestore_fsck_on_mount_deep
+ type: bool
+ level: dev
+ desc: Run deep fsck at mount when bluestore_fsck_on_mount is set to true
+ default: false
+ - name: bluestore_fsck_quick_fix_on_mount
+ type: bool
+ level: dev
+ desc: Do quick-fix for the store at mount
+ default: false
+ - name: bluestore_fsck_on_umount
+ type: bool
+ level: dev
+ desc: Run fsck at umount
+ default: false
+ - name: bluestore_fsck_on_umount_deep
+ type: bool
+ level: dev
+ desc: Run deep fsck at umount when bluestore_fsck_on_umount is set to true
+ default: false
+ - name: bluestore_fsck_on_mkfs
+ type: bool
+ level: dev
+ desc: Run fsck after mkfs
+ default: true
+ - name: bluestore_fsck_on_mkfs_deep
+ type: bool
+ level: dev
+ desc: Run deep fsck after mkfs
+ default: false
+ - name: bluestore_sync_submit_transaction
+ type: bool
+ level: dev
+ desc: Try to submit metadata transaction to rocksdb in queuing thread context
+ default: false
+ - name: bluestore_fsck_read_bytes_cap
+ type: size
+ level: advanced
+ desc: Maximum bytes read at once by deep fsck
+ default: 64_M
+ flags:
+ - runtime
+ - name: bluestore_fsck_quick_fix_threads
+ type: int
+ level: advanced
+ desc: Number of additional threads to perform quick-fix (shallow fsck) command
+ default: 2
+ - name: bluestore_throttle_bytes
+ type: size
+ level: advanced
+ desc: Maximum bytes in flight before we throttle IO submission
+ default: 64_M
+ flags:
+ - runtime
+ - name: bluestore_throttle_deferred_bytes
+ type: size
+ level: advanced
+ desc: Maximum bytes for deferred writes before we throttle IO submission
+ default: 128_M
+ flags:
+ - runtime
+ - name: bluestore_throttle_cost_per_io
+ type: size
+ level: advanced
+ desc: Overhead added to transaction cost (in bytes) for each IO
+ default: 0
+ flags:
+ - runtime
+ - name: bluestore_throttle_cost_per_io_hdd
+ type: uint
+ level: advanced
+ desc: Default bluestore_throttle_cost_per_io for rotational media
+ default: 670000
+ see_also:
+ - bluestore_throttle_cost_per_io
+ flags:
+ - runtime
+ - name: bluestore_throttle_cost_per_io_ssd
+ type: uint
+ level: advanced
+ desc: Default bluestore_throttle_cost_per_io for non-rotation (solid state) media
+ default: 4000
+ see_also:
+ - bluestore_throttle_cost_per_io
+ flags:
+ - runtime
+ - name: bluestore_deferred_batch_ops
+ type: uint
+ level: advanced
+ desc: Max number of deferred writes before we flush the deferred write queue
+ default: 0
+ min: 0
+ max: 65535
+ flags:
+ - runtime
+ - name: bluestore_deferred_batch_ops_hdd
+ type: uint
+ level: advanced
+ desc: Default bluestore_deferred_batch_ops for rotational media
+ default: 64
+ see_also:
+ - bluestore_deferred_batch_ops
+ min: 0
+ max: 65535
+ flags:
+ - runtime
+ - name: bluestore_deferred_batch_ops_ssd
+ type: uint
+ level: advanced
+ desc: Default bluestore_deferred_batch_ops for non-rotational (solid state) media
+ default: 16
+ see_also:
+ - bluestore_deferred_batch_ops
+ min: 0
+ max: 65535
+ flags:
+ - runtime
+ - name: bluestore_nid_prealloc
+ type: int
+ level: dev
+ desc: Number of unique object ids to preallocate at a time
+ default: 1024
+ - name: bluestore_blobid_prealloc
+ type: uint
+ level: dev
+ desc: Number of unique blob ids to preallocate at a time
+ default: 10_K
+ - name: bluestore_clone_cow
+ type: bool
+ level: advanced
+ desc: Use copy-on-write when cloning objects (versus reading and rewriting them
+ at clone time)
+ default: true
+ flags:
+ - runtime
+ - name: bluestore_default_buffered_read
+ type: bool
+ level: advanced
+ desc: Cache read results by default (unless hinted NOCACHE or WONTNEED)
+ default: true
+ flags:
+ - runtime
+ - name: bluestore_default_buffered_write
+ type: bool
+ level: advanced
+ desc: Cache writes by default (unless hinted NOCACHE or WONTNEED)
+ default: false
+ flags:
+ - runtime
+ - name: bluestore_debug_no_reuse_blocks
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_small_allocations
+ type: int
+ level: dev
+ default: 0
+ - name: bluestore_debug_too_many_blobs_threshold
+ type: int
+ level: dev
+ default: 24576
+ - name: bluestore_debug_freelist
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_prefill
+ type: float
+ level: dev
+ desc: simulate fragmentation
+ default: 0
+ - name: bluestore_debug_prefragment_max
+ type: size
+ level: dev
+ default: 1_M
+ - name: bluestore_debug_inject_read_err
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_randomize_serial_transaction
+ type: int
+ level: dev
+ default: 0
+ - name: bluestore_debug_omit_block_device_write
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_fsck_abort
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_omit_kv_commit
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_permit_any_bdev_label
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_random_read_err
+ type: float
+ level: dev
+ default: 0
+ - name: bluestore_debug_inject_bug21040
+ type: bool
+ level: dev
+ default: false
+ - name: bluestore_debug_inject_csum_err_probability
+ type: float
+ level: dev
+ desc: inject crc verification errors into bluestore device reads
+ default: 0
+ - name: bluestore_fsck_error_on_no_per_pool_stats
+ type: bool
+ level: advanced
+ desc: Make fsck error (instead of warn) when bluestore lacks per-pool stats, e.g.,
+ after an upgrade
+ default: false
+ - name: bluestore_warn_on_bluefs_spillover
+ type: bool
+ level: advanced
+ desc: Enable health indication on bluefs slow device usage
+ default: true
+ - name: bluestore_warn_on_legacy_statfs
+ type: bool
+ level: advanced
+ desc: Enable health indication on lack of per-pool statfs reporting from bluestore
+ default: true
+ - name: bluestore_warn_on_spurious_read_errors
+ type: bool
+ level: advanced
+ desc: Enable health indication when spurious read errors are observed by OSD
+ default: true
+ - name: bluestore_fsck_error_on_no_per_pool_omap
+ type: bool
+ level: advanced
+ desc: Make fsck error (instead of warn) when objects without per-pool omap are found
+ default: false
+ - name: bluestore_fsck_error_on_no_per_pg_omap
+ type: bool
+ level: advanced
+ desc: Make fsck error (instead of warn) when objects without per-pg omap are found
+ default: false
+ - name: bluestore_warn_on_no_per_pool_omap
+ type: bool
+ level: advanced
+ desc: Enable health indication on lack of per-pool omap
+ default: true
+ - name: bluestore_warn_on_no_per_pg_omap
+ type: bool
+ level: advanced
+ desc: Enable health indication on lack of per-pg omap
+ default: false
+ - name: bluestore_log_op_age
+ type: float
+ level: advanced
+ desc: log operation if it's slower than this age (seconds)
+ default: 5
+ - name: bluestore_log_omap_iterator_age
+ type: float
+ level: advanced
+ desc: log omap iteration operation if it's slower than this age (seconds)
+ default: 5
+ - name: bluestore_log_collection_list_age
+ type: float
+ level: advanced
+ desc: log collection list operation if it's slower than this age (seconds)
+ default: 1_min
+ - name: bluestore_debug_enforce_settings
+ type: str
+ level: dev
+ desc: Enforces specific hw profile settings
+ long_desc: '''hdd'' enforces settings intended for BlueStore above a rotational
+ drive. ''ssd'' enforces settings intended for BlueStore above a solid drive. ''default''
+ - using settings for the actual hardware.'
+ default: default
+ enum_values:
+ - default
+ - hdd
+ - ssd
+ - name: bluestore_avl_alloc_bf_threshold
+ type: uint
+ level: dev
+ desc: Sets threshold at which shrinking max free chunk size triggers enabling best-fit
+ mode.
+ long_desc: 'AVL allocator works in two modes: near-fit and best-fit. By default,
+ it uses very fast near-fit mode, in which it tries to fit a new block near the
+ last allocated block of similar size. The second mode is much slower best-fit
+ mode, in which it tries to find an exact match for the requested allocation. This
+ mode is used when either the device gets fragmented or when it is low on free
+ space. When the largest free block is smaller than ''bluestore_avl_alloc_bf_threshold'',
+ best-fit mode is used.'
+ default: 128_K
+ see_also:
+ - bluestore_avl_alloc_bf_free_pct
+ - name: bluestore_avl_alloc_bf_free_pct
+ type: uint
+ level: dev
+ desc: Sets threshold at which shrinking free space (in %, integer) triggers enabling
+ best-fit mode.
+ long_desc: 'AVL allocator works in two modes: near-fit and best-fit. By default,
+ it uses very fast near-fit mode, in which it tries to fit a new block near the
+ last allocated block of similar size. The second mode is much slower best-fit
+ mode, in which it tries to find an exact match for the requested allocation. This
+ mode is used when either the device gets fragmented or when it is low on free
+ space. When free space is smaller than ''bluestore_avl_alloc_bf_free_pct'', best-fit
+ mode is used.'
+ default: 4
+ see_also:
+ - bluestore_avl_alloc_bf_threshold
+ - name: bluestore_hybrid_alloc_mem_cap
+ type: uint
+ level: dev
+ desc: Maximum RAM hybrid allocator should use before enabling bitmap supplement
+ default: 64_M
+ - name: bluestore_volume_selection_policy
+ type: str
+ level: dev
+ desc: Determines bluefs volume selection policy
+ long_desc: Determines bluefs volume selection policy. 'use_some_extra' policy allows
+ to override RocksDB level granularity and put high level's data to faster device
+ even when the level doesn't completely fit there. 'fit_to_fast' policy enables
+ using 100% of faster disk capacity and allows the user to turn on 'level_compaction_dynamic_level_bytes'
+ option in RocksDB options.
+ default: use_some_extra
+ enum_values:
+ - rocksdb_original
+ - use_some_extra
+ - fit_to_fast
+ - name: bluestore_volume_selection_reserved_factor
+ type: float
+ level: advanced
+ desc: DB level size multiplier. Determines amount of space at DB device to bar from
+ the usage when 'use some extra' policy is in action. Reserved size is determined
+ as sum(L_max_size[0], L_max_size[L-1]) + L_max_size[L] * this_factor
+ default: 2
+ flags:
+ - startup
+ - name: bluestore_volume_selection_reserved
+ type: int
+ level: advanced
+ desc: Space reserved at DB device and not allowed for 'use some extra' policy usage.
+ Overrides 'bluestore_volume_selection_reserved_factor' setting and introduces
+ straightforward limit.
+ default: 0
+ flags:
+ - startup
+ - name: bdev_ioring
+ type: bool
+ level: advanced
+ desc: Enables Linux io_uring API instead of libaio
+ default: false
+ - name: bdev_ioring_hipri
+ type: bool
+ level: advanced
+ desc: Enables Linux io_uring API Use polled IO completions
+ default: false
+ - name: bdev_ioring_sqthread_poll
+ type: bool
+ level: advanced
+ desc: Enables Linux io_uring API Offload submission/completion to kernel thread
+ default: false
+ - name: bluestore_kv_sync_util_logging_s
+ type: float
+ level: advanced
+ desc: KV sync thread utilization logging period
+ long_desc: How often (in seconds) to print KV sync thread utilization, not logged
+ when set to 0 or when utilization is 0%
+ default: 10
+ flags:
+ - runtime
+ - name: kstore_max_ops
+ type: uint
+ level: advanced
+ default: 512
+ - name: kstore_max_bytes
+ type: size
+ level: advanced
+ default: 64_M
+ - name: kstore_backend
+ type: str
+ level: advanced
+ default: rocksdb
+ - name: kstore_rocksdb_options
+ type: str
+ level: advanced
+ desc: Options to pass through when RocksDB is used as the KeyValueDB for kstore.
+ default: compression=kNoCompression
+ - name: kstore_fsck_on_mount
+ type: bool
+ level: advanced
+ desc: Whether or not to run fsck on mount for kstore.
+ default: false
+ - name: kstore_fsck_on_mount_deep
+ type: bool
+ level: advanced
+ desc: Whether or not to run deep fsck on mount for kstore
+ default: true
+ - name: kstore_nid_prealloc
+ type: uint
+ level: advanced
+ default: 1_K
+ - name: kstore_sync_transaction
+ type: bool
+ level: advanced
+ default: false
+ - name: kstore_sync_submit_transaction
+ type: bool
+ level: advanced
+ default: false
+ - name: kstore_onode_map_size
+ type: uint
+ level: advanced
+ default: 1_K
+ - name: kstore_default_stripe_size
+ type: size
+ level: advanced
+ default: 64_K
+ - name: filestore_rocksdb_options
+ type: str
+ level: dev
+ desc: Options to pass through when RocksDB is used as the KeyValueDB for filestore.
+ default: max_background_jobs=10,compaction_readahead_size=2097152,compression=kNoCompression
+ - name: filestore_omap_backend
+ type: str
+ level: dev
+ desc: The KeyValueDB to use for filestore metadata (ie omap).
+ default: rocksdb
+ enum_values:
+ - leveldb
+ - rocksdb
+ - name: filestore_omap_backend_path
+ type: str
+ level: dev
+ desc: The path where the filestore KeyValueDB should store it's database(s).
+ - name: filestore_wbthrottle_enable
+ type: bool
+ level: advanced
+ desc: Enabling throttling of operations to backing file system
+ default: true
+ - name: filestore_wbthrottle_btrfs_bytes_start_flusher
+ type: size
+ level: advanced
+ desc: Start flushing (fsyncing) when this many bytes are written(btrfs)
+ default: 40_M
+ - name: filestore_wbthrottle_btrfs_bytes_hard_limit
+ type: size
+ level: advanced
+ desc: Block writes when this many bytes haven't been flushed (fsynced) (btrfs)
+ default: 400_M
+ - name: filestore_wbthrottle_btrfs_ios_start_flusher
+ type: uint
+ level: advanced
+ desc: Start flushing (fsyncing) when this many IOs are written (brtrfs)
+ default: 500
+ - name: filestore_wbthrottle_btrfs_ios_hard_limit
+ type: uint
+ level: advanced
+ desc: Block writes when this many IOs haven't been flushed (fsynced) (btrfs)
+ default: 5000
+ - name: filestore_wbthrottle_btrfs_inodes_start_flusher
+ type: uint
+ level: advanced
+ desc: Start flushing (fsyncing) when this many distinct inodes have been modified
+ (btrfs)
+ default: 500
+ - name: filestore_wbthrottle_xfs_bytes_start_flusher
+ type: size
+ level: advanced
+ desc: Start flushing (fsyncing) when this many bytes are written(xfs)
+ default: 40_M
+ - name: filestore_wbthrottle_xfs_bytes_hard_limit
+ type: size
+ level: advanced
+ desc: Block writes when this many bytes haven't been flushed (fsynced) (xfs)
+ default: 400_M
+ - name: filestore_wbthrottle_xfs_ios_start_flusher
+ type: uint
+ level: advanced
+ desc: Start flushing (fsyncing) when this many IOs are written (xfs)
+ default: 500
+ - name: filestore_wbthrottle_xfs_ios_hard_limit
+ type: uint
+ level: advanced
+ desc: Block writes when this many IOs haven't been flushed (fsynced) (xfs)
+ default: 5000
+ - name: filestore_wbthrottle_xfs_inodes_start_flusher
+ type: uint
+ level: advanced
+ desc: Start flushing (fsyncing) when this many distinct inodes have been modified
+ (xfs)
+ default: 500
+ - name: filestore_wbthrottle_btrfs_inodes_hard_limit
+ type: uint
+ level: advanced
+ desc: Block writing when this many inodes have outstanding writes (btrfs)
+ default: 5000
+ - name: filestore_wbthrottle_xfs_inodes_hard_limit
+ type: uint
+ level: advanced
+ desc: Block writing when this many inodes have outstanding writes (xfs)
+ default: 5000
+ - name: filestore_odsync_write
+ type: bool
+ level: dev
+ desc: Write with O_DSYNC
+ default: false
+ - name: filestore_index_retry_probability
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_debug_inject_read_err
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_debug_random_read_err
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_debug_omap_check
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_omap_header_cache_size
+ type: size
+ level: dev
+ default: 1_K
+ - name: filestore_max_inline_xattr_size
+ type: size
+ level: dev
+ default: 0
+ - name: filestore_max_inline_xattr_size_xfs
+ type: size
+ level: dev
+ default: 64_K
+ - name: filestore_max_inline_xattr_size_btrfs
+ type: size
+ level: dev
+ default: 2_K
+ - name: filestore_max_inline_xattr_size_other
+ type: size
+ level: dev
+ default: 512
+ - name: filestore_max_inline_xattrs
+ type: uint
+ level: dev
+ default: 0
+ - name: filestore_max_inline_xattrs_xfs
+ type: uint
+ level: dev
+ default: 10
+ - name: filestore_max_inline_xattrs_btrfs
+ type: uint
+ level: dev
+ default: 10
+ - name: filestore_max_inline_xattrs_other
+ type: uint
+ level: dev
+ default: 2
+ - name: filestore_max_xattr_value_size
+ type: size
+ level: dev
+ default: 0
+ - name: filestore_max_xattr_value_size_xfs
+ type: size
+ level: dev
+ default: 64_K
+ - name: filestore_max_xattr_value_size_btrfs
+ type: size
+ level: dev
+ default: 64_K
+ - name: filestore_max_xattr_value_size_other
+ type: size
+ level: dev
+ default: 1_K
+ - name: filestore_sloppy_crc
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_sloppy_crc_block_size
+ type: size
+ level: dev
+ default: 64_K
+ - name: filestore_max_alloc_hint_size
+ type: size
+ level: dev
+ default: 1_M
+ - name: filestore_max_sync_interval
+ type: float
+ level: advanced
+ desc: Period between calls to syncfs(2) and journal trims (seconds)
+ default: 5
+ - name: filestore_min_sync_interval
+ type: float
+ level: dev
+ desc: Minimum period between calls to syncfs(2)
+ default: 0.01
+ - name: filestore_btrfs_snap
+ type: bool
+ level: dev
+ default: true
+ - name: filestore_btrfs_clone_range
+ type: bool
+ level: advanced
+ desc: Use btrfs clone_range ioctl to efficiently duplicate objects
+ default: true
+ - name: filestore_zfs_snap
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_fsync_flushes_journal_data
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_fiemap
+ type: bool
+ level: advanced
+ desc: Use fiemap ioctl(2) to determine which parts of objects are sparse
+ default: false
+ - name: filestore_punch_hole
+ type: bool
+ level: advanced
+ desc: Use fallocate(2) FALLOC_FL_PUNCH_HOLE to efficiently zero ranges of objects
+ default: false
+ - name: filestore_seek_data_hole
+ type: bool
+ level: advanced
+ desc: Use lseek(2) SEEK_HOLE and SEEK_DATA to determine which parts of objects are
+ sparse
+ default: false
+ - name: filestore_splice
+ type: bool
+ level: advanced
+ desc: Use splice(2) to more efficiently copy data between files
+ default: false
+ - name: filestore_fadvise
+ type: bool
+ level: advanced
+ desc: Use posix_fadvise(2) to pass hints to file system
+ default: true
+ - name: filestore_collect_device_partition_information
+ type: bool
+ level: advanced
+ desc: Collect metadata about the backing file system on OSD startup
+ default: true
+ - name: filestore_xfs_extsize
+ type: bool
+ level: advanced
+ desc: Use XFS extsize ioctl(2) to hint allocator about expected write sizes
+ default: false
+ - name: filestore_journal_parallel
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_journal_writeahead
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_journal_trailing
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_queue_max_ops
+ type: uint
+ level: advanced
+ desc: Max IO operations in flight
+ default: 50
+ - name: filestore_queue_max_bytes
+ type: size
+ level: advanced
+ desc: Max (written) bytes in flight
+ default: 100_M
+ - name: filestore_caller_concurrency
+ type: int
+ level: dev
+ default: 10
+ - name: filestore_expected_throughput_bytes
+ type: float
+ level: advanced
+ desc: Expected throughput of backend device (aids throttling calculations)
+ default: 209715200
+ - name: filestore_expected_throughput_ops
+ type: float
+ level: advanced
+ desc: Expected through of backend device in IOPS (aids throttling calculations)
+ default: 200
+ - name: filestore_queue_max_delay_multiple
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_high_delay_multiple
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_max_delay_multiple_bytes
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_high_delay_multiple_bytes
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_max_delay_multiple_ops
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_high_delay_multiple_ops
+ type: float
+ level: dev
+ default: 0
+ - name: filestore_queue_low_threshhold
+ type: float
+ level: dev
+ default: 0.3
+ - name: filestore_queue_high_threshhold
+ type: float
+ level: dev
+ default: 0.9
+ - name: filestore_op_threads
+ type: int
+ level: advanced
+ desc: Threads used to apply changes to backing file system
+ default: 2
+ - name: filestore_op_thread_timeout
+ type: int
+ level: advanced
+ desc: Seconds before a worker thread is considered stalled
+ default: 1_min
+ - name: filestore_op_thread_suicide_timeout
+ type: int
+ level: advanced
+ desc: Seconds before a worker thread is considered dead
+ default: 3_min
+ - name: filestore_commit_timeout
+ type: float
+ level: advanced
+ desc: Seconds before backing file system is considered hung
+ default: 10_min
+ - name: filestore_fiemap_threshold
+ type: size
+ level: dev
+ default: 4_K
+ - name: filestore_merge_threshold
+ type: int
+ level: dev
+ default: -10
+ - name: filestore_split_multiple
+ type: int
+ level: dev
+ default: 2
+ - name: filestore_split_rand_factor
+ type: uint
+ level: dev
+ default: 20
+ - name: filestore_update_to
+ type: int
+ level: dev
+ default: 1000
+ - name: filestore_blackhole
+ type: bool
+ level: dev
+ default: false
+ - name: filestore_fd_cache_size
+ type: int
+ level: dev
+ default: 128
+ - name: filestore_fd_cache_shards
+ type: int
+ level: dev
+ default: 16
+ - name: filestore_ondisk_finisher_threads
+ type: int
+ level: dev
+ default: 1
+ - name: filestore_apply_finisher_threads
+ type: int
+ level: dev
+ default: 1
+ - name: filestore_dump_file
+ type: str
+ level: dev
+ - name: filestore_kill_at
+ type: int
+ level: dev
+ default: 0
+ - name: filestore_inject_stall
+ type: int
+ level: dev
+ default: 0
+ - name: filestore_fail_eio
+ type: bool
+ level: dev
+ default: true
+ - name: filestore_debug_verify_split
+ type: bool
+ level: dev
+ default: false
+ - name: journal_dio
+ type: bool
+ level: dev
+ default: true
+ - name: journal_aio
+ type: bool
+ level: dev
+ default: true
+ - name: journal_force_aio
+ type: bool
+ level: dev
+ default: false
+ - name: journal_block_size
+ type: size
+ level: dev
+ default: 4_K
+ - name: journal_block_align
+ type: bool
+ level: dev
+ default: true
+ - name: journal_write_header_frequency
+ type: uint
+ level: dev
+ default: 0
+ - name: journal_max_write_bytes
+ type: size
+ level: advanced
+ desc: Max bytes in flight to journal
+ default: 10_M
+ - name: journal_max_write_entries
+ type: int
+ level: advanced
+ desc: Max IOs in flight to journal
+ default: 100
+ - name: journal_throttle_low_threshhold
+ type: float
+ level: dev
+ default: 0.6
+ - name: journal_throttle_high_threshhold
+ type: float
+ level: dev
+ default: 0.9
+ - name: journal_throttle_high_multiple
+ type: float
+ level: dev
+ default: 0
+ - name: journal_throttle_max_multiple
+ type: float
+ level: dev
+ default: 0
+ - name: journal_align_min_size
+ type: size
+ level: dev
+ default: 64_K
+ - name: journal_replay_from
+ type: int
+ level: dev
+ default: 0
+ - name: mgr_stats_threshold
+ type: int
+ level: advanced
+ desc: Lowest perfcounter priority collected by mgr
+ long_desc: Daemons only set perf counter data to the manager daemon if the counter
+ has a priority higher than this.
+ default: 5
+ min: 0
+ max: 11
+ - name: journal_zero_on_create
+ type: bool
+ level: dev
+ default: false
+ - name: journal_ignore_corruption
+ type: bool
+ level: dev
+ default: false
+ - name: journal_discard
+ type: bool
+ level: dev
+ default: false
+ - name: fio_dir
+ type: str
+ level: advanced
+ default: /tmp/fio
+ - name: rados_mon_op_timeout
+ type: secs
+ level: advanced
+ desc: timeout for operations handled by monitors such as statfs (0 is unlimited)
+ default: 0
+ min: 0
+ flags:
+ - runtime
+ - name: rados_osd_op_timeout
+ type: secs
+ level: advanced
+ desc: timeout for operations handled by osds such as write (0 is unlimited)
+ default: 0
+ min: 0
+ flags:
+ - runtime
+ - name: rados_tracing
+ type: bool
+ level: advanced
+ default: false
+ - name: cephadm_path
+ type: str
+ level: advanced
+ desc: Path to cephadm utility
+ default: /usr/sbin/cephadm
+ services:
+ - mgr
+ - name: mgr_module_path
+ type: str
+ level: advanced
+ desc: Filesystem path to manager modules.
+ default: @CEPH_INSTALL_DATADIR@/mgr
+ services:
+ - mgr
+ - name: mgr_disabled_modules
+ type: str
+ level: advanced
+ desc: List of manager modules never get loaded
+ long_desc: A comma delimited list of module names. This list is read by manager
+ when it starts. By default, manager loads all modules found in specified 'mgr_module_path',
+ and it starts the enabled ones as instructed. The modules in this list will not
+ be loaded at all.
+ default: @mgr_disabled_modules@
+ services:
+ - mgr
+ see_also:
+ - mgr_module_path
+ flags:
+ - startup
+ - name: mgr_initial_modules
+ type: str
+ level: basic
+ desc: List of manager modules to enable when the cluster is first started
+ long_desc: This list of module names is read by the monitor when the cluster is
+ first started after installation, to populate the list of enabled manager modules. Subsequent
+ updates are done using the 'mgr module [enable|disable]' commands. List may be
+ comma or space separated.
+ default: restful iostat
+ services:
+ - mon
+ flags:
+ - no_mon_update
+ - cluster_create
+ - name: mgr_data
+ type: str
+ level: advanced
+ desc: Filesystem path to the ceph-mgr data directory, used to contain keyring.
+ default: /var/lib/ceph/mgr/$cluster-$id
+ services:
+ - mgr
+ flags:
+ - no_mon_update
+ - name: mgr_tick_period
+ type: secs
+ level: advanced
+ desc: Period in seconds of beacon messages to monitor
+ default: 2
+ services:
+ - mgr
+ - name: mgr_stats_period
+ type: int
+ level: basic
+ desc: Period in seconds of OSD/MDS stats reports to manager
+ long_desc: Use this setting to control the granularity of time series data collection
+ from daemons. Adjust upwards if the manager CPU load is too high, or if you simply
+ do not require the most up to date performance counter data.
+ default: 5
+ services:
+ - mgr
+ - name: mgr_client_bytes
+ type: size
+ level: dev
+ default: 128_M
+ services:
+ - mgr
+ - name: mgr_client_messages
+ type: uint
+ level: dev
+ default: 512
+ services:
+ - mgr
+ - name: mgr_osd_bytes
+ type: size
+ level: dev
+ default: 512_M
+ services:
+ - mgr
+ - name: mgr_osd_messages
+ type: uint
+ level: dev
+ default: 8_K
+ services:
+ - mgr
+ - name: mgr_mds_bytes
+ type: size
+ level: dev
+ default: 128_M
+ services:
+ - mgr
+ - name: mgr_mds_messages
+ type: uint
+ level: dev
+ default: 128
+ services:
+ - mgr
+ - name: mgr_mon_bytes
+ type: size
+ level: dev
+ default: 128_M
+ services:
+ - mgr
+ - name: mgr_mon_messages
+ type: uint
+ level: dev
+ default: 128
+ services:
+ - mgr
+ - name: mgr_connect_retry_interval
+ type: float
+ level: dev
+ default: 1
+ services:
+ - common
+ - name: mgr_service_beacon_grace
+ type: float
+ level: advanced
+ desc: Period in seconds from last beacon to manager dropping state about a monitored
+ service (RGW, rbd-mirror etc)
+ default: 1_min
+ services:
+ - mgr
+ - name: mgr_client_service_daemon_unregister_timeout
+ type: float
+ level: dev
+ desc: Time to wait during shutdown to deregister service with mgr
+ default: 1
+ - name: mgr_debug_aggressive_pg_num_changes
+ type: bool
+ level: dev
+ desc: Bypass most throttling and safety checks in pg[p]_num controller
+ default: false
+ services:
+ - mgr
+ - name: mon_mgr_digest_period
+ type: int
+ level: dev
+ desc: Period in seconds between monitor-to-manager health/status updates
+ default: 5
+ services:
+ - mon
+ - name: mon_mgr_beacon_grace
+ type: secs
+ level: advanced
+ desc: Period in seconds from last beacon to monitor marking a manager daemon as
+ failed
+ default: 30
+ services:
+ - mon
+ - name: mon_mgr_inactive_grace
+ type: int
+ level: advanced
+ desc: Period in seconds after cluster creation during which cluster may have no
+ active manager
+ long_desc: This grace period enables the cluster to come up cleanly without raising
+ spurious health check failures about managers that aren't online yet
+ default: 1_min
+ services:
+ - mon
+ - name: mon_mgr_mkfs_grace
+ type: int
+ level: advanced
+ desc: Period in seconds that the cluster may have no active manager before this
+ is reported as an ERR rather than a WARN
+ default: 2_min
+ services:
+ - mon
+ - name: throttler_perf_counter
+ type: bool
+ level: advanced
+ default: true
+ - name: event_tracing
+ type: bool
+ level: advanced
+ default: false
+ - name: bluestore_tracing
+ type: bool
+ level: advanced
+ desc: Enable bluestore event tracing.
+ default: false
+ - name: bluestore_throttle_trace_rate
+ type: float
+ level: advanced
+ desc: Rate at which to sample bluestore transactions (per second)
+ default: 0
+ - name: debug_deliberately_leak_memory
+ type: bool
+ level: dev
+ default: false
+ - name: debug_asserts_on_shutdown
+ type: bool
+ level: dev
+ desc: Enable certain asserts to check for refcounting bugs on shutdown; see http://tracker.ceph.com/issues/21738
+ default: false
+ - name: debug_asok_assert_abort
+ type: bool
+ level: dev
+ desc: allow commands 'assert' and 'abort' via asok for testing crash dumps etc
+ default: false
+ - name: target_max_misplaced_ratio
+ type: float
+ level: basic
+ desc: Max ratio of misplaced objects to target when throttling data rebalancing
+ activity
+ default: 0.05
+ - name: device_failure_prediction_mode
+ type: str
+ level: basic
+ desc: Method used to predict device failures
+ long_desc: To disable prediction, use 'none', 'local' uses a prediction model that
+ runs inside the mgr daemon. 'cloud' will share metrics with a cloud service and
+ query the service for devicelife expectancy.
+ default: none
+ enum_values:
+ - none
+ - local
+ - cloud
+ flags:
+ - runtime
+ - name: gss_ktab_client_file
+ type: str
+ level: advanced
+ desc: GSS/KRB5 Keytab file for client authentication
+ long_desc: This sets the full path for the GSS/Kerberos client keytab file location.
+ default: /var/lib/ceph/$name/gss_client_$name.ktab
+ services:
+ - mon
+ - osd
+ - name: gss_target_name
+ type: str
+ level: advanced
+ long_desc: This sets the gss target service name.
+ default: ceph
+ services:
+ - mon
+ - osd
+ - name: debug_disable_randomized_ping
+ type: bool
+ level: dev
+ desc: Disable heartbeat ping randomization for testing purposes
+ default: false
+ - name: debug_heartbeat_testing_span
+ type: int
+ level: dev
+ desc: Override 60 second periods for testing only
+ default: 0
+ - name: librados_thread_count
+ type: uint
+ level: advanced
+ desc: Size of thread pool for Objecter
+ default: 2
+ tags:
+ - client
+ min: 1
+ - name: osd_asio_thread_count
+ type: uint
+ level: advanced
+ desc: Size of thread pool for ASIO completions
+ default: 2
+ tags:
+ - osd
+ min: 1
+ - name: cephsqlite_lock_renewal_interval
+ type: millisecs
+ level: advanced
+ desc: number of milliseconds before lock is renewed
+ default: 2000
+ tags:
+ - client
+ see_also:
+ - cephsqlite_lock_renewal_timeout
+ min: 100
+ - name: cephsqlite_lock_renewal_timeout
+ type: millisecs
+ level: advanced
+ desc: number of milliseconds before transaction lock times out
+ long_desc: The amount of time before a running libcephsqlite VFS connection has
+ to renew a lock on the database before the lock is automatically lost. If the
+ lock is lost, the VFS will abort the process to prevent database corruption.
+ default: 30000
+ tags:
+ - client
+ see_also:
+ - cephsqlite_lock_renewal_interval
+ min: 100
+ - name: cephsqlite_blocklist_dead_locker
+ type: bool
+ level: advanced
+ desc: blocklist the last dead owner of the database lock
+ long_desc: Require that the Ceph SQLite VFS blocklist the last dead owner of the
+ database when cleanup was incomplete. DO NOT CHANGE THIS UNLESS YOU UNDERSTAND
+ THE RAMIFICATIONS. CORRUPTION MAY RESULT.
+ default: true
+ tags:
+ - client
+ - name: crimson_osd_obc_lru_size
+ type: uint
+ level: advanced
+ desc: Number of obcs to cache
+ default: 10
+ - name: crimson_osd_scheduler_concurrency
+ type: uint
+ level: advanced
+ desc: The maximum number concurrent IO operations, 0 for unlimited
+ default: 0
+ - name: crimson_alien_op_num_threads
+ type: uint
+ level: advanced
+ desc: The number of threads for serving alienized ObjectStore
+ default: 6
+ flags:
+ - startup
+ - name: crimson_alien_thread_cpu_cores
+ type: str
+ level: advanced
+ desc: Cpu cores on which alienstore threads will run
+ - name: bdev_type
+ type: str
+ level: advanced
+ desc: Explicitly set the device type to select the driver if it's needed
+ enum_values:
+ - aio
+ - spdk
+ - pmem
+ - hm_smr
projects / ceph-ci.git / commitdiff