#include <boost/lexical_cast.hpp>
#include <boost/regex.hpp>
+// Definitions for enums
+#include "common/perf_counters.h"
+
void Option::dump_value(const char *field_name,
const Option::value_t &v, Formatter *f) const
Option("public_network", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.add_service({"mon", "mds", "osd", "mgr"})
.add_tag("network")
- .set_description(""),
+ .set_description("Network(s) from which to choose a public address to bind to"),
+
+ Option("public_network_interface", Option::TYPE_STR, Option::LEVEL_ADVANCED)
+ .add_service({"mon", "mds", "osd", "mgr"})
+ .add_tag("network")
+ .set_description("Interface name(s) from which to choose an address from a public_network to bind to; public_network must also be specified.")
+ .add_see_also("public_network"),
Option("cluster_network", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.add_service("osd")
.add_tag("network")
- .set_description(""),
+ .set_description("Network(s) from which to choose a cluster address to bind to"),
+
+ Option("cluster_network_interface", Option::TYPE_STR, Option::LEVEL_ADVANCED)
+ .add_service({"mon", "mds", "osd", "mgr"})
+ .add_tag("network")
+ .set_description("Interface name(s) from which to choose an address from a cluster_network to bind to; cluster_network must also be specified.")
+ .add_see_also("cluster_network"),
Option("monmap", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_description("path to MonMap file")
.add_service("common"),
Option("mon_dns_srv_name", Option::TYPE_STR, Option::LEVEL_ADVANCED)
+ .set_default("ceph-mon")
.set_description("name of DNS SRV record to check for monitor addresses")
.add_service("common")
.add_tag("network")
Option("key", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("")
- .set_description(""),
+ .set_description("Authentication key")
+ .set_long_description("A CephX authentication key, base64 encoded. It normally looks something like 'AQAtut9ZdMbNJBAAHz6yBAWyJyz2yYRyeMWDag=='.")
+ .add_see_also("keyfile")
+ .add_see_also("keyring"),
Option("keyfile", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("")
- .set_description(""),
+ .set_description("Path to a file containing a key")
+ .set_long_description("The file should contain a CephX authentication key and optionally a trailing newline, but nothing else.")
+ .add_see_also("key"),
Option("keyring", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default(
"/usr/local/etc/ceph/keyring,/usr/local/etc/ceph/keyring.bin,"
#endif
)
- .set_description(""),
+ .set_description("Path to a keyring file.")
+ .set_long_description("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.")
+ .add_see_also("key")
+ .add_see_also("keyfile"),
Option("heartbeat_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(5)
.set_default(1)
.set_description(""),
- Option("mon_pg_warn_min_per_osd", Option::TYPE_INT, Option::LEVEL_ADVANCED)
+ Option("mon_pg_warn_min_per_osd", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .set_description("minimal number PGs per (in) osd before we warn the admin"),
- Option("mon_pg_warn_max_per_osd", Option::TYPE_INT, Option::LEVEL_ADVANCED)
- .set_default(300)
- .set_description(""),
+ Option("mon_max_pg_per_osd", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(200)
+ .set_description("Max number of PGs per OSD the cluster will allow"),
Option("mon_pg_warn_max_object_skew", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(10.0)
.set_default(100ul << 20)
.set_description(""),
- Option("mon_mgr_proxy_client_bytes_ratio", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ Option("mon_mgr_proxy_client_bytes_ratio", Option::TYPE_FLOAT, Option::LEVEL_DEV)
.set_default(.3)
- .set_description(""),
+ .set_description("ratio of mon_client_bytes that can be consumed by "
+ "proxied mgr commands before we error out to client"),
Option("mon_log_max_summary", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(50)
.set_default(50)
.set_description(""),
+ Option("mon_health_log_update_period", Option::TYPE_INT, Option::LEVEL_DEV)
+ .set_default(5)
+ .set_description("Minimum time in seconds between log messages about "
+ "each health check")
+ .set_min(0),
+
Option("mon_data_avail_crit", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(5)
.set_description(""),
.set_default(false)
.set_description(""),
+ Option("mon_fixup_legacy_erasure_code_profiles", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
+ .set_default(true)
+ .set_description("Automatically adjust ruleset-* to crush-* so that legacy apps can set modern erasure code profiles without modification"),
+
Option("mon_debug_deprecated_as_obsolete", Option::TYPE_BOOL, Option::LEVEL_DEV)
.set_default(false)
.set_description(""),
.set_description(""),
Option("osd_min_pg_log_entries", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
- .set_default(3000)
+ .set_default(1500)
.set_description("minimum number of entries to maintain in the PG log")
.add_service("osd")
.add_see_also("osd_max_pg_log_entries")
.set_default(100)
.set_description(""),
+ Option("osd_max_pg_per_osd_hard_ratio", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ .set_default(2)
+ .set_min(1)
+ .set_description("Maximum number of PG per OSD, a factor of 'mon_max_pg_per_osd'")
+ .set_long_description("OSD will refuse to instantiate PG if the number of PG it serves exceeds this number.")
+ .add_see_also("mon_max_pg_per_osd"),
+
Option("osd_op_complaint_time", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(30)
.set_description(""),
.set_default(false)
.set_description(""),
+ Option("osd_debug_shutdown", Option::TYPE_BOOL, Option::LEVEL_DEV)
+ .set_default(false)
+ .set_description("Turn up debug levels during shutdown"),
+
Option("osd_debug_crash_on_ignored_backoff", Option::TYPE_BOOL, Option::LEVEL_DEV)
.set_default(false)
.set_description(""),
// --------------------------
// bluestore
+ Option("bdev_inject_bad_size", Option::TYPE_BOOL, Option::LEVEL_DEV)
+ .set_default(false)
+ .set_description(""),
+
Option("bdev_debug_inflight_ios", Option::TYPE_BOOL, Option::LEVEL_DEV)
.set_default(false)
.set_description(""),
.set_description(""),
Option("bluefs_allocator", Option::TYPE_STR, Option::LEVEL_DEV)
- .set_default("bitmap")
+ .set_default("stupid")
.set_description(""),
Option("bluefs_preextend_wal_files", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(1*1024*1024*1024)
.set_description("minimum disk space allocated to BlueFS (e.g., at mkfs)"),
+ Option("bluestore_bluefs_min_free", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(1*1024*1024*1024)
+ .set_description("minimum free space allocated to BlueFS"),
+
Option("bluestore_bluefs_min_ratio", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(.02)
.set_description("Minimum fraction of free space devoted to BlueFS"),
.set_description("Key value database to use for bluestore"),
Option("bluestore_allocator", Option::TYPE_STR, Option::LEVEL_DEV)
- .set_default("bitmap")
- .add_tag("mkfs")
- .set_description(""),
+ .set_default("stupid")
+ .set_enum_allowed({"bitmap", "stupid"})
+ .set_description("Allocator policy"),
Option("bluestore_freelist_blocks_per_key", Option::TYPE_INT, Option::LEVEL_DEV)
.set_default(128)
// filestore
Option("filestore_rocksdb_options", Option::TYPE_STR, Option::LEVEL_ADVANCED)
- .set_default("")
+ .set_default("max_background_compactions=8,compaction_readahead_size=2097152,compression=kNoCompression")
.set_description(""),
Option("filestore_omap_backend", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default(0)
.set_description(""),
+ Option("mgr_stats_threshold", Option::TYPE_INT, Option::LEVEL_ADVANCED)
+ .set_default((int64_t)PerfCountersBuilder::PRIO_USEFUL)
+ .set_description("Lowest perfcounter priority collected by mgr")
+ .set_long_description("Daemons only set perf counter data to the manager "
+ "daemon if the counter has a priority higher than this.")
+ .set_min_max((int64_t)PerfCountersBuilder::PRIO_DEBUGONLY,
+ (int64_t)PerfCountersBuilder::PRIO_CRITICAL),
+
Option("journal_zero_on_create", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
.set_description(""),
Option("mgr_module_path", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default(CEPH_PKGLIBDIR "/mgr")
- .set_description(""),
+ .add_service("mgr")
+ .set_description("Filesystem path to manager modules."),
- Option("mgr_initial_modules", Option::TYPE_STR, Option::LEVEL_ADVANCED)
- .set_default("restful status")
- .set_description(""),
+ Option("mgr_initial_modules", Option::TYPE_STR, Option::LEVEL_BASIC)
+ .set_default("restful status balancer")
+ .add_service("mon")
+ .set_description("List of manager modules to enable when the cluster is "
+ "first started")
+ .set_long_description("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."),
Option("mgr_data", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("/var/lib/ceph/mgr/$cluster-$id")
- .set_description(""),
+ .add_service("mgr")
+ .set_description("Filesystem path to the ceph-mgr data directory, used to "
+ "contain keyring."),
Option("mgr_tick_period", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(2)
- .set_description(""),
+ .add_service("mgr")
+ .set_description("Period in seconds of beacon messages to monitor"),
- Option("mgr_stats_period", Option::TYPE_INT, Option::LEVEL_ADVANCED)
+ Option("mgr_stats_period", Option::TYPE_INT, Option::LEVEL_BASIC)
.set_default(5)
- .set_description(""),
-
- Option("mgr_client_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .add_service("mgr")
+ .set_description("Period in seconds of OSD/MDS stats reports to manager")
+ .set_long_description("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."),
+
+ Option("mgr_client_bytes", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(128*1048576)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_client_messages", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_client_messages", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(512)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_osd_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_osd_bytes", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(512*1048576)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_osd_messages", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_osd_messages", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(8192)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_mds_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_mds_bytes", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(128*1048576)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_mds_messages", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_mds_messages", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(128)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_mon_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_mon_bytes", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(128*1048576)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_mon_messages", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ Option("mgr_mon_messages", Option::TYPE_UINT, Option::LEVEL_DEV)
.set_default(128)
- .set_description(""),
+ .add_service("mgr"),
- Option("mgr_connect_retry_interval", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ Option("mgr_connect_retry_interval", Option::TYPE_FLOAT, Option::LEVEL_DEV)
.set_default(1.0)
- .set_description(""),
+ .add_service("common"),
Option("mgr_service_beacon_grace", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(60.0)
- .set_description(""),
+ .add_service("mgr")
+ .set_description("Period in seconds from last beacon to manager dropping "
+ "state about a monitored service (RGW, rbd-mirror etc)"),
- Option("mon_mgr_digest_period", Option::TYPE_INT, Option::LEVEL_ADVANCED)
+ Option("mon_mgr_digest_period", Option::TYPE_INT, Option::LEVEL_DEV)
.set_default(5)
- .set_description(""),
+ .add_service("mon")
+ .set_description("Period in seconds between monitor-to-manager "
+ "health/status updates"),
Option("mon_mgr_beacon_grace", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .add_service("mon")
+ .set_description("Period in seconds from last beacon to monitor marking "
+ "a manager daemon as failed"),
Option("mon_mgr_inactive_grace", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(60)
- .set_description(""),
+ .add_service("mon")
+ .set_description("Period in seconds after cluster creation during which "
+ "cluster may have no active manager")
+ .set_long_description("This grace period enables the cluster to come "
+ "up cleanly without raising spurious health check "
+ "failures about managers that aren't online yet"),
Option("mon_mgr_mkfs_grace", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(60)
- .set_description(""),
+ .add_service("mon")
+ .set_description("Period in seconds that the cluster may have no active "
+ "manager before this is reported as an ERR rather than "
+ "a WARN"),
Option("mutex_perf_counter", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
.set_default(1 * 1024 * 1024)
.set_description(""),
+ Option("rgw_max_attr_size", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(0)
+ .set_description("The maximum length of metadata value. 0 skips the check"),
+
+ Option("rgw_max_attr_name_len", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(0)
+ .set_description("The maximum length of metadata name. 0 skips the check"),
+
+ Option("rgw_max_attrs_num_in_req", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(0)
+ .set_description("The maximum number of metadata items that can be put via single request"),
+
Option("rgw_override_bucket_index_max_shards", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(0)
.set_description(""),
.set_description(""),
Option("rgw_dynamic_resharding", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
- .set_default(false)
+ .set_default(true)
.set_description(""),
Option("rgw_max_objs_per_shard", Option::TYPE_INT, Option::LEVEL_ADVANCED)
return std::vector<Option>({
Option("rbd_default_pool", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("rbd")
- .set_description("")
+ .set_description("default pool for storing new images")
.set_validator([](std::string *value, std::string *error_message){
boost::regex pattern("^[^@/]+$");
if (!boost::regex_match (*value, pattern)) {
Option("rbd_default_data_pool", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("")
- .set_description("")
+ .set_description("default pool for storing data blocks for new images")
.set_validator([](std::string *value, std::string *error_message){
boost::regex pattern("^[^@/]*$");
if (!boost::regex_match (*value, pattern)) {
Option("rbd_default_features", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("layering,exclusive-lock,object-map,fast-diff,deep-flatten")
- .set_description("")
+ .set_description("default v2 image features for new images")
+ .set_long_description(
+ "RBD features are only applicable for v2 images. This setting accepts "
+ "either an integer bitmask value or comma-delimited string of RBD "
+ "feature names. This setting is always internally stored as an integer "
+ "bitmask value. The mapping between feature bitmask value and feature "
+ "name is as follows: +1 -> layering, +2 -> striping, "
+ "+4 -> exclusive-lock, +8 -> object-map, +16 -> fast-diff, "
+ "+32 -> deep-flatten, +64 -> journaling, +128 -> data-pool")
.set_safe()
.set_validator([](std::string *value, std::string *error_message){
static const std::map<std::string, uint64_t> FEATURE_MAP = {
Option("rbd_op_threads", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(1)
- .set_description(""),
+ .set_description("number of threads to utilize for internal processing"),
Option("rbd_op_thread_timeout", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(60)
- .set_description(""),
+ .set_description("time in seconds for detecting a hung thread"),
Option("rbd_non_blocking_aio", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("process AIO ops from a dispatch thread to prevent blocking"),
Option("rbd_cache", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("whether to enable caching (writeback unless rbd_cache_max_dirty is 0)"),
Option("rbd_cache_writethrough_until_flush", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("whether to make writeback caching writethrough until "
+ "flush is called, to be sure the user of librbd will send "
+ "flushes so that writeback is safe"),
Option("rbd_cache_size", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(32<<20)
- .set_description(""),
+ .set_description("cache size in bytes"),
Option("rbd_cache_max_dirty", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(24<<20)
- .set_description(""),
+ .set_description("dirty limit in bytes - set to 0 for write-through caching"),
Option("rbd_cache_target_dirty", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(16<<20)
- .set_description(""),
+ .set_description("target dirty limit in bytes"),
Option("rbd_cache_max_dirty_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(1.0)
- .set_description(""),
+ .set_description("seconds in cache before writeback starts"),
Option("rbd_cache_max_dirty_object", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("dirty limit for objects - set to 0 for auto calculate from rbd_cache_size"),
Option("rbd_cache_block_writes_upfront", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("whether to block writes to the cache before the aio_write call completes"),
Option("rbd_concurrent_management_ops", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(10)
.set_min(1)
- .set_description(""),
+ .set_description("how many operations can be in flight for a management operation like deleting or resizing an image"),
Option("rbd_balance_snap_reads", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("distribute snap read requests to random OSD"),
Option("rbd_localize_snap_reads", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("localize snap read requests to closest OSD"),
Option("rbd_balance_parent_reads", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("distribute parent read requests to random OSD"),
Option("rbd_localize_parent_reads", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("localize parent requests to closest OSD"),
Option("rbd_readahead_trigger_requests", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(10)
- .set_description(""),
+ .set_description("number of sequential requests necessary to trigger readahead"),
Option("rbd_readahead_max_bytes", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(512 * 1024)
- .set_description(""),
+ .set_description("set to 0 to disable readahead"),
Option("rbd_readahead_disable_after_bytes", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(50 * 1024 * 1024)
- .set_description(""),
+ .set_description("how many bytes are read in total before readahead is disabled"),
Option("rbd_clone_copy_on_read", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("copy-up parent image blocks to clone upon read request"),
Option("rbd_blacklist_on_break_lock", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("whether to blacklist clients whose lock was broken"),
Option("rbd_blacklist_expire_seconds", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("number of seconds to blacklist - set to 0 for OSD default"),
Option("rbd_request_timed_out_seconds", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .set_description("number of seconds before maintenance request times out"),
Option("rbd_skip_partial_discard", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("when trying to discard a range inside an object, set to true to skip zeroing the range"),
Option("rbd_enable_alloc_hint", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("when writing a object, it will issue a hint to osd backend to indicate the expected size object need"),
Option("rbd_tracing", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("true if LTTng-UST tracepoints should be enabled"),
Option("rbd_blkin_trace_all", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("create a blkin trace for all RBD requests"),
Option("rbd_validate_pool", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("validate empty pools for RBD compatibility"),
Option("rbd_validate_names", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("validate new image names for RBD compatibility"),
Option("rbd_auto_exclusive_lock_until_manual_request", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(true)
- .set_description(""),
+ .set_description("automatically acquire/release exclusive lock until it is explicitly requested"),
Option("rbd_mirroring_resync_after_disconnect", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
.set_default(false)
- .set_description(""),
+ .set_description("automatically start image resync after mirroring is disconnected due to being laggy"),
Option("rbd_mirroring_replay_delay", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("time-delay in seconds for rbd-mirror asynchronous replication"),
Option("rbd_default_format", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(2)
- .set_description(""),
+ .set_description("default image format for new images"),
Option("rbd_default_order", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(22)
- .set_description(""),
+ .set_description("default order (data block object size) for new images"),
Option("rbd_default_stripe_count", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("default stripe count for new images"),
Option("rbd_default_stripe_unit", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("default stripe width for new images"),
Option("rbd_default_map_options", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("")
- .set_description(""),
+ .set_description("default krbd map options"),
Option("rbd_journal_order", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_min(12)
.set_default(24)
- .set_description(""),
+ .set_description("default order (object size) for journal data objects"),
Option("rbd_journal_splay_width", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(4)
- .set_description(""),
+ .set_description("number of active journal objects"),
Option("rbd_journal_commit_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(5)
- .set_description(""),
+ .set_description("commit time interval, seconds"),
Option("rbd_journal_object_flush_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("maximum number of pending commits per journal object"),
Option("rbd_journal_object_flush_bytes", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("maximum number of pending bytes per journal object"),
Option("rbd_journal_object_flush_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("maximum age (in seconds) for pending commits"),
Option("rbd_journal_pool", Option::TYPE_STR, Option::LEVEL_ADVANCED)
.set_default("")
- .set_description(""),
+ .set_description("pool for journal objects"),
Option("rbd_journal_max_payload_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(16384)
- .set_description(""),
+ .set_description("maximum journal payload size before splitting"),
Option("rbd_journal_max_concurrent_object_sets", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(0)
- .set_description(""),
+ .set_description("maximum number of object sets a journal client can be behind before it is automatically unregistered"),
+ });
+}
+static std::vector<Option> get_rbd_mirror_options() {
+ return std::vector<Option>({
Option("rbd_mirror_journal_commit_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(5)
- .set_description(""),
+ .set_description("commit time interval, seconds"),
Option("rbd_mirror_journal_poll_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(5)
- .set_description(""),
+ .set_description("maximum age (in seconds) between successive journal polls"),
Option("rbd_mirror_journal_max_fetch_bytes", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(32768)
- .set_description(""),
+ .set_description("maximum bytes to read from each journal data object per fetch"),
Option("rbd_mirror_sync_point_update_age", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .set_description("number of seconds between each update of the image sync point object number"),
Option("rbd_mirror_concurrent_image_syncs", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(5)
- .set_description(""),
+ .set_description("maximum number of image syncs in parallel"),
Option("rbd_mirror_pool_replayers_refresh_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .set_description("interval to refresh peers in rbd-mirror daemon"),
Option("rbd_mirror_delete_retry_interval", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(30)
- .set_description(""),
+ .set_description("interval to check and retry the failed requests in deleter"),
Option("rbd_mirror_image_state_check_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(30)
.set_min(1)
- .set_description(""),
+ .set_description("interval to get images from pool watcher and set sources in replayer"),
Option("rbd_mirror_leader_heartbeat_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(5)
.set_min(1)
- .set_description(""),
+ .set_description("interval (in seconds) between mirror leader heartbeats"),
Option("rbd_mirror_leader_max_missed_heartbeats", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(2)
- .set_description(""),
+ .set_description("number of missed heartbeats for non-lock owner to attempt to acquire lock"),
Option("rbd_mirror_leader_max_acquire_attempts_before_break", Option::TYPE_INT, Option::LEVEL_ADVANCED)
.set_default(3)
- .set_description(""),
+ .set_description("number of failed attempts to acquire lock after missing heartbeats before breaking lock"),
});
}
.set_description(""),
Option("mds_cache_size", Option::TYPE_INT, Option::LEVEL_ADVANCED)
- .set_default(100000)
- .set_description(""),
+ .set_default(0)
+ .set_description("maximum number of inodes in MDS cache (<=0 is unlimited)")
+ .set_long_description("This tunable is no longer recommended. Use mds_cache_memory_limit."),
+
+ Option("mds_cache_memory_limit", Option::TYPE_UINT, Option::LEVEL_BASIC)
+ .set_default(1*(1LL<<30))
+ .set_description("target maximum memory usage of MDS cache")
+ .set_long_description("This sets a target maximum memory usage of the MDS cache and is the primary tunable to limit the MDS memory usage. The MDS will try to stay under a reservation of this limit (by default 95%; 1 - mds_cache_reservation) by trimming unused metadata in its cache and recalling cached items in the client caches. It is possible for the MDS to exceed this limit due to slow recall from clients. The mds_health_cache_threshold (150%) sets a cache full threshold for when the MDS signals a cluster health warning."),
+
+ Option("mds_cache_reservation", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ .set_default(.05)
+ .set_description("amount of memory to reserve"),
+
+ Option("mds_health_cache_threshold", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ .set_default(1.5)
+ .set_description("threshold for cache size to generate health warning"),
Option("mds_cache_mid", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(.7)
.set_default(10)
.set_description(""),
- Option("mds_health_cache_threshold", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
- .set_default(1.5)
- .set_description(""),
-
Option("mds_reconnect_timeout", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
.set_default(45)
.set_description(""),
Option("mds_client_writeable_range_max_inc_objs", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
.set_default(1024)
.set_description(""),
+
+ Option("mds_min_caps_per_client", Option::TYPE_UINT, Option::LEVEL_ADVANCED)
+ .set_default(100)
+ .set_description("minimum number of capabilities a client may hold"),
+
+ Option("mds_max_ratio_caps_per_client", Option::TYPE_FLOAT, Option::LEVEL_ADVANCED)
+ .set_default(.8)
+ .set_description("maximum ratio of current caps that may be recalled during MDS cache pressure"),
});
}
.set_description(""),
Option("fuse_set_user_groups", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
- .set_default(false)
- .set_description(""),
+ .set_default(true)
+ .set_description("check for ceph-fuse to consider supplementary groups for permissions"),
Option("client_try_dentry_invalidate", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
- .set_default(true)
+ .set_default(false)
.set_description(""),
Option("client_die_on_failed_remount", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
ingest(get_rgw_options(), "rgw");
ingest(get_rbd_options(), "rbd");
+ ingest(get_rbd_mirror_options(), "rbd-mirror");
ingest(get_mds_options(), "mds");
ingest(get_mds_client_options(), "mds_client");
projects / ceph.git / blobdiff