ceph/doc/rados/configuration/pool-pg-config-ref.rst

   1 ======================================
   2  Pool, PG and CRUSH Config Reference
   3 ======================================
   4
   5 .. index:: pools; configuration
   6
   7 When you create pools and set the number of placement groups for the pool, Ceph
   8 uses default values when you don't specifically override the defaults. **We
   9 recommend** overridding some of the defaults. Specifically, we recommend setting
  10 a pool's replica size and overriding the default number of placement groups. You
  11 can specifically set these values when running `pool`_ commands. You can also
  12 override the defaults by adding new ones in the ``[global]`` section of  your
  13 Ceph configuration file.
  14
  15
  16 .. literalinclude:: pool-pg.conf
  17    :language: ini
  18
  19
  20
  21 ``mon max pool pg num``
  22
  23 :Description: The maximum number of placement groups per pool.
  24 :Type: Integer
  25 :Default: ``65536``
  26
  27
  28 ``mon pg create interval``
  29
  30 :Description: Number of seconds between PG creation in the same
  31               Ceph OSD Daemon.
  32
  33 :Type: Float
  34 :Default: ``30.0``
  35
  36
  37 ``mon pg stuck threshold``
  38
  39 :Description: Number of seconds after which PGs can be considered as
  40               being stuck.
  41
  42 :Type: 32-bit Integer
  43 :Default: ``300``
  44
  45 ``mon pg min inactive``
  46
  47 :Description: Issue a ``HEALTH_ERR`` in cluster log if the number of PGs stay
  48               inactive longer than ``mon_pg_stuck_threshold`` exceeds this
  49               setting. A non-positive number means disabled, never go into ERR.
  50 :Type: Integer
  51 :Default: ``1``
  52
  53
  54 ``mon pg warn min per osd``
  55
  56 :Description: Issue a ``HEALTH_WARN`` in cluster log if the average number
  57               of PGs per (in) OSD is under this number. (a non-positive number
  58               disables this)
  59 :Type: Integer
  60 :Default: ``30``
  61
  62
  63 ``mon pg warn max per osd``
  64
  65 :Description: Issue a ``HEALTH_WARN`` in cluster log if the average number
  66               of PGs per (in) OSD is above this number. (a non-positive number
  67               disables this)
  68 :Type: Integer
  69 :Default: ``300``
  70
  71
  72 ``mon pg warn min objects``
  73
  74 :Description: Do not warn if the total number of objects in cluster is below
  75               this number
  76 :Type: Integer
  77 :Default: ``1000``
  78
  79
  80 ``mon pg warn min pool objects``
  81
  82 :Description: Do not warn on pools whose object number is below this number
  83 :Type: Integer
  84 :Default: ``1000``
  85
  86
  87 ``mon pg check down all threshold``
  88
  89 :Description: Threshold of down OSDs percentage after which we check all PGs
  90               for stale ones.
  91 :Type: Float
  92 :Default: ``0.5``
  93
  94
  95 ``mon pg warn max object skew``
  96
  97 :Description: Issue a ``HEALTH_WARN`` in cluster log if the average object number
  98               of a certain pool is greater than ``mon pg warn max object skew`` times
  99               the average object number of the whole pool. (a non-positive number
 100               disables this)
 101 :Type: Float
 102 :Default: ``10``
 103
 104
 105 ``mon delta reset interval``
 106
 107 :Description: Seconds of inactivity before we reset the pg delta to 0. We keep
 108               track of the delta of the used space of each pool, so, for
 109               example, it would be easier for us to understand the progress of
 110               recovery or the performance of cache tier. But if there's no
 111               activity reported for a certain pool, we just reset the history of
 112               deltas of that pool.
 113 :Type: Integer
 114 :Default: ``10``
 115
 116
 117 ``mon osd max op age``
 118
 119 :Description: Maximum op age before we get concerned (make it a power of 2).
 120               A ``HEALTH_WARN`` will be issued if a request has been blocked longer
 121               than this limit.
 122 :Type: Float
 123 :Default: ``32.0``
 124
 125
 126 ``osd pg bits``
 127
 128 :Description: Placement group bits per Ceph OSD Daemon.
 129 :Type: 32-bit Integer
 130 :Default: ``6``
 131
 132
 133 ``osd pgp bits``
 134
 135 :Description: The number of bits per Ceph OSD Daemon for PGPs.
 136 :Type: 32-bit Integer
 137 :Default: ``6``
 138
 139
 140 ``osd crush chooseleaf type``
 141
 142 :Description: The bucket type to use for ``chooseleaf`` in a CRUSH rule. Uses
 143               ordinal rank rather than name.
 144
 145 :Type: 32-bit Integer
 146 :Default: ``1``. Typically a host containing one or more Ceph OSD Daemons.
 147
 148
 149 ``osd crush initial weight``
 150
 151 :Description: The initial crush weight for newly added osds into crushmap.
 152
 153 :Type: Double
 154 :Default: ``the size of newly added osd in TB``. By default, the initial crush
 155           weight for the newly added osd is set to its volume size in TB.
 156           See `Weighting Bucket Items`_ for details.
 157
 158
 159 ``osd pool default crush rule``
 160
 161 :Description: The default CRUSH rule to use when creating a replicated pool.
 162 :Type: 8-bit Integer
 163 :Default: ``-1``, which means "pick the rule with the lowest numerical ID and
 164           use that".  This is to make pool creation work in the absence of rule 0.
 165
 166
 167 ``osd pool erasure code stripe unit``
 168
 169 :Description: Sets the default size, in bytes, of a chunk of an object
 170               stripe for erasure coded pools. Every object of size S
 171               will be stored as N stripes, with each data chunk
 172               receiving ``stripe unit`` bytes. Each stripe of ``N *
 173               stripe unit`` bytes will be encoded/decoded
 174               individually. This option can is overridden by the
 175               ``stripe_unit`` setting in an erasure code profile.
 176
 177 :Type: Unsigned 32-bit Integer
 178 :Default: ``4096``
 179
 180
 181 ``osd pool default size``
 182
 183 :Description: Sets the number of replicas for objects in the pool. The default
 184               value is the same as
 185               ``ceph osd pool set {pool-name} size {size}``.
 186
 187 :Type: 32-bit Integer
 188 :Default: ``3``
 189
 190
 191 ``osd pool default min size``
 192
 193 :Description: Sets the minimum number of written replicas for objects in the
 194              pool in order to acknowledge a write operation to the client.
 195              If minimum is not met, Ceph will not acknowledge the write to the
 196              client. This setting ensures a minimum number of replicas when
 197              operating in ``degraded`` mode.
 198
 199 :Type: 32-bit Integer
 200 :Default: ``0``, which means no particular minimum. If ``0``,
 201           minimum is ``size - (size / 2)``.
 202
 203
 204 ``osd pool default pg num``
 205
 206 :Description: The default number of placement groups for a pool. The default
 207               value is the same as ``pg_num`` with ``mkpool``.
 208
 209 :Type: 32-bit Integer
 210 :Default: ``8``
 211
 212
 213 ``osd pool default pgp num``
 214
 215 :Description: The default number of placement groups for placement for a pool.
 216               The default value is the same as ``pgp_num`` with ``mkpool``.
 217               PG and PGP should be equal (for now).
 218
 219 :Type: 32-bit Integer
 220 :Default: ``8``
 221
 222
 223 ``osd pool default flags``
 224
 225 :Description: The default flags for new pools.
 226 :Type: 32-bit Integer
 227 :Default: ``0``
 228
 229
 230 ``osd max pgls``
 231
 232 :Description: The maximum number of placement groups to list. A client
 233               requesting a large number can tie up the Ceph OSD Daemon.
 234
 235 :Type: Unsigned 64-bit Integer
 236 :Default: ``1024``
 237 :Note: Default should be fine.
 238
 239
 240 ``osd min pg log entries``
 241
 242 :Description: The minimum number of placement group logs to maintain
 243               when trimming log files.
 244
 245 :Type: 32-bit Int Unsigned
 246 :Default: ``1000``
 247
 248
 249 ``osd default data pool replay window``
 250
 251 :Description: The time (in seconds) for an OSD to wait for a client to replay
 252               a request.
 253
 254 :Type: 32-bit Integer
 255 :Default: ``45``
 256
 257 ``osd max pg per osd hard ratio``
 258
 259 :Description: The ratio of number of PGs per OSD allowed by the cluster before
 260               OSD refuses to create new PGs. OSD stops creating new PGs if the number
 261               of PGs it serves exceeds
 262               ``osd max pg per osd hard ratio`` \* ``mon max pg per osd``.
 263
 264 :Type: Float
 265 :Default: ``2``
 266
 267 .. _pool: ../../operations/pools
 268 .. _Monitoring OSDs and PGs: ../../operations/monitoring-osd-pg#peering
 269 .. _Weighting Bucket Items: ../../operations/crush-map#weightingbucketitems