ceph/monitoring/snmp/CEPH-MIB.txt

   1 CEPH-MIB DEFINITIONS ::= BEGIN
   2
   3 IMPORTS
   4     MODULE-IDENTITY, NOTIFICATION-TYPE, enterprises
   5         FROM SNMPv2-SMI
   6     MODULE-COMPLIANCE, NOTIFICATION-GROUP
   7         FROM SNMPv2-CONF
   8 ;
   9
  10 -- Linting information:
  11 --
  12 -- # smilint -l 6 -i notification-not-reversible ./CEPH-MIB.txt
  13 --
  14 -- ignore: notification-not-reversible since our SNMP gateway doesn't use SNMPv1
  15 --
  16
  17 ceph MODULE-IDENTITY
  18     LAST-UPDATED
  19         "202111010000Z" -- Nov 01, 2021
  20     ORGANIZATION
  21         "The Ceph Project
  22          https://ceph.io"
  23     CONTACT-INFO
  24         "Email: <dev@ceph.io>
  25
  26         Send comments to: <dev@ceph.io>"
  27     DESCRIPTION
  28         "The MIB module for Ceph. In it's current form it only
  29         supports Notifications, since Ceph itself doesn't provide
  30         any SNMP agent functionality.
  31
  32         Notifications are provided through a Prometheus/Alertmanager
  33         webhook passing alerts to an external gateway service that is
  34         responsible for formatting, forwarding and authenticating to
  35         the SNMP receiver.
  36         "
  37     REVISION
  38         "202111010000Z" --Nov 01, 2021
  39     DESCRIPTION
  40         "Latest version including the following updates;
  41
  42         - MIB restructure to align with linting
  43         - names shortened and simplified (less verbose)
  44         - Simplified structure due to switch to https://github.com/maxwo/snmp_notifier
  45           - objects removed
  46           - notifications updated
  47         - Added module compliance
  48         - Updated to latest prometheus alert rule definitions
  49         "
  50     ::= { enterprises 50495 }
  51
  52 cephCluster       OBJECT IDENTIFIER ::= { ceph 1 }
  53 cephConformance   OBJECT IDENTIFIER ::= { ceph 2 }
  54
  55 -- cephMetadata is a placeholder for possible future expansion via an agent
  56 -- where we could provide an overview of the clusters configuration
  57 cephMetadata      OBJECT IDENTIFIER ::= { cephCluster 1 }
  58 cephNotifications OBJECT IDENTIFIER ::= { cephCluster 2 }
  59
  60 prometheus OBJECT IDENTIFIER ::= { cephNotifications 1 }
  61
  62 --
  63 -- Notifications: first we define the notification 'branches' for the
  64 -- different categories of notifications / alerts
  65 promGeneric       OBJECT IDENTIFIER ::= { prometheus 1 }
  66 promHealthStatus  OBJECT IDENTIFIER ::= { prometheus 2 }
  67 promMon           OBJECT IDENTIFIER ::= { prometheus 3 }
  68 promOsd           OBJECT IDENTIFIER ::= { prometheus 4 }
  69 promMds           OBJECT IDENTIFIER ::= { prometheus 5 }
  70 promMgr           OBJECT IDENTIFIER ::= { prometheus 6 }
  71 promPGs           OBJECT IDENTIFIER ::= { prometheus 7 }
  72 promNode          OBJECT IDENTIFIER ::= { prometheus 8 }
  73 promPool          OBJECT IDENTIFIER ::= { prometheus 9 }
  74 promRados         OBJECT IDENTIFIER ::= { prometheus 10 }
  75 promCephadm       OBJECT IDENTIFIER ::= { prometheus 11 }
  76 promPrometheus    OBJECT IDENTIFIER ::= { prometheus 12 }
  77
  78 promGenericNotification NOTIFICATION-TYPE
  79     STATUS      current
  80     DESCRIPTION "Generic alert issued when the Prometheus rule doesn't provide an OID."
  81 ::= { promGeneric 1 }
  82
  83 promGenericDaemonCrash NOTIFICATION-TYPE
  84     STATUS      current
  85     DESCRIPTION "One or more daemons have crashed recently, and are yet to be archived"
  86 ::= { promGeneric 2 }
  87
  88 promHealthStatusError NOTIFICATION-TYPE
  89     STATUS      current
  90     DESCRIPTION "Ceph in health_error state for too long."
  91 ::= { promHealthStatus 1 }
  92
  93 promHealthStatusWarning NOTIFICATION-TYPE
  94     STATUS      current
  95     DESCRIPTION "Ceph in health_warn for too long."
  96 ::= { promHealthStatus 2 }
  97
  98 promMonLowQuorum NOTIFICATION-TYPE
  99     STATUS      current
 100     DESCRIPTION "Monitor count in quorum is low."
 101 ::= { promMon 1 }
 102
 103 promMonDiskSpaceCritical NOTIFICATION-TYPE
 104     STATUS      current
 105     DESCRIPTION "Monitor diskspace is critically low."
 106 ::= { promMon 2 }
 107
 108 promOsdDownHigh NOTIFICATION-TYPE
 109     STATUS      current
 110     DESCRIPTION "A high number of OSDs are down."
 111 ::= { promOsd 1 }
 112
 113 promOsdDown NOTIFICATION-TYPE
 114     STATUS      current
 115     DESCRIPTION "One or more Osds down."
 116 ::= { promOsd 2 }
 117
 118 promOsdNearFull NOTIFICATION-TYPE
 119     STATUS      current
 120     DESCRIPTION "An OSD is dangerously full."
 121 ::= { promOsd 3 }
 122
 123 promOsdFlapping NOTIFICATION-TYPE
 124     STATUS      current
 125     DESCRIPTION "An OSD was marked down at back up at least once a minute for 5 minutes."
 126 ::= { promOsd 4 }
 127
 128 promOsdHighPgDeviation NOTIFICATION-TYPE
 129     STATUS      current
 130     DESCRIPTION "An OSD deviates by more then 30% from average PG count."
 131 ::= { promOsd 5 }
 132
 133 promOsdFull NOTIFICATION-TYPE
 134     STATUS      current
 135     DESCRIPTION "An OSD has reached its full threshold."
 136 ::= { promOsd 6 }
 137
 138 promOsdHighPredictedFailures NOTIFICATION-TYPE
 139     STATUS      current
 140     DESCRIPTION "Normal self healing unable to cope with the number of devices predicted to fail."
 141 ::= { promOsd 7 }
 142
 143 promOsdHostDown NOTIFICATION-TYPE
 144     STATUS      current
 145     DESCRIPTION "Ceph OSD host is down."
 146 ::= { promOsd 8 }
 147
 148 promMdsDamaged NOTIFICATION-TYPE
 149     STATUS      current
 150     DESCRIPTION "Cephfs filesystem is damaged."
 151 ::= { promMds 1 }
 152
 153 promMdsReadOnly NOTIFICATION-TYPE
 154     STATUS      current
 155     DESCRIPTION "Cephfs filesystem marked as READ-ONLY"
 156 ::= { promMds 2 }
 157
 158 promMdsOffline NOTIFICATION-TYPE
 159     STATUS      current
 160     DESCRIPTION "Cephfs filesystem is unavailable/offline."
 161 ::= { promMds 3 }
 162
 163 promMdsDegraded NOTIFICATION-TYPE
 164     STATUS      current
 165     DESCRIPTION "Cephfs filesystem is in a degraded state."
 166 ::= { promMds 4 }
 167
 168 promMdsNoStandby NOTIFICATION-TYPE
 169     STATUS      current
 170     DESCRIPTION "Cephfs MDS daemon failure, no standby available"
 171 ::= { promMds 5 }
 172
 173 promMgrModuleCrash NOTIFICATION-TYPE
 174     STATUS      current
 175     DESCRIPTION "Ceph mgr module has crashed recently"
 176 ::= { promMgr 1 }
 177
 178 promMgrPrometheusInactive NOTIFICATION-TYPE
 179     STATUS      current
 180     DESCRIPTION "Ceph mgr prometheus module not responding"
 181 ::= { promMgr 2 }
 182
 183 promPGsInactive NOTIFICATION-TYPE
 184     STATUS      current
 185     DESCRIPTION "One or more PGs are inactive for more than 5 minutes."
 186 ::= { promPGs 1 }
 187
 188 promPGsUnclean NOTIFICATION-TYPE
 189     STATUS      current
 190     DESCRIPTION "One or more PGs are not clean for more than 15 minutes."
 191 ::= { promPGs 2 }
 192
 193 promPGsUnavailable NOTIFICATION-TYPE
 194     STATUS      current
 195     DESCRIPTION "One or more PGs is unavailable, blocking I/O to those objects."
 196 ::= { promPGs 3 }
 197
 198 promPGsDamaged NOTIFICATION-TYPE
 199     STATUS      current
 200     DESCRIPTION "One or more PGs is damaged."
 201 ::= { promPGs 4 }
 202
 203 promPGsRecoveryFull NOTIFICATION-TYPE
 204     STATUS      current
 205     DESCRIPTION "PG recovery is impaired due to full OSDs."
 206 ::= { promPGs 5 }
 207
 208 promPGsBackfillFull NOTIFICATION-TYPE
 209     STATUS      current
 210     DESCRIPTION "PG backfill is impaired due to full OSDs."
 211 ::= { promPGs 6 }
 212
 213 promNodeRootVolumeFull NOTIFICATION-TYPE
 214     STATUS      current
 215     DESCRIPTION "Root volume (OSD and MON store) is dangerously full (< 5% free)."
 216 ::= { promNode 1 }
 217
 218 promNodeNetworkPacketDrops NOTIFICATION-TYPE
 219     STATUS      current
 220     DESCRIPTION "A node experiences packet drop > 1 packet/s on an interface."
 221 ::= { promNode 2 }
 222
 223 promNodeNetworkPacketErrors NOTIFICATION-TYPE
 224     STATUS      current
 225     DESCRIPTION "A node experiences packet errors > 1 packet/s on an interface."
 226 ::= { promNode 3 }
 227
 228 promNodeStorageFilling NOTIFICATION-TYPE
 229     STATUS      current
 230     DESCRIPTION "A mountpoint will be full in less then 5 days assuming the average fillup rate of the past 48 hours."
 231 ::= { promNode 4 }
 232
 233 promPoolFull NOTIFICATION-TYPE
 234     STATUS      current
 235     DESCRIPTION "A pool is at 90% capacity or over."
 236 ::= { promPool 1 }
 237
 238 promPoolFilling NOTIFICATION-TYPE
 239     STATUS      current
 240     DESCRIPTION "A pool will be full in less then 5 days assuming the average fillup rate of the past 48 hours."
 241 ::= { promPool 2 }
 242
 243 promRadosUnfound NOTIFICATION-TYPE
 244     STATUS      current
 245     DESCRIPTION "A RADOS object can not be found, even though all OSDs are online."
 246 ::= { promRados 1 }
 247
 248 promCephadmDaemonDown NOTIFICATION-TYPE
 249     STATUS      current
 250     DESCRIPTION "Cephadm has determined that a daemon is down."
 251 ::= { promCephadm 1 }
 252
 253 promCephadmUpgradeFailure NOTIFICATION-TYPE
 254     STATUS      current
 255     DESCRIPTION "Cephadm attempted to upgrade the cluster and encountered a problem."
 256 ::= { promCephadm 2 }
 257
 258 promPrometheusJobMissing NOTIFICATION-TYPE
 259     STATUS      current
 260     DESCRIPTION "The prometheus scrape job is not defined."
 261 ::= { promPrometheus 1 }
 262 -- ---------------------------------------------------------- --
 263 -- IEEE 802.1D MIB - Conformance Information
 264 -- ---------------------------------------------------------- --
 265
 266 cephAlertGroups   OBJECT IDENTIFIER ::= { cephConformance 1 }
 267 cephCompliances   OBJECT IDENTIFIER ::= { cephConformance 2 }
 268
 269 -- ---------------------------------------------------------- --
 270 -- units of conformance
 271 -- ---------------------------------------------------------- --
 272
 273 -- ---------------------------------------------------------- --
 274 -- The Trap Notification Group
 275 -- ---------------------------------------------------------- --
 276
 277 cephNotificationGroup NOTIFICATION-GROUP
 278     NOTIFICATIONS {
 279         promGenericNotification,
 280         promGenericDaemonCrash,
 281         promHealthStatusError,
 282         promHealthStatusWarning,
 283         promMonLowQuorum,
 284         promMonDiskSpaceCritical,
 285         promOsdDownHigh,
 286         promOsdDown,
 287         promOsdNearFull,
 288         promOsdFlapping,
 289         promOsdHighPgDeviation,
 290         promOsdFull,
 291         promOsdHighPredictedFailures,
 292         promOsdHostDown,
 293         promMdsDamaged,
 294         promMdsReadOnly,
 295         promMdsOffline,
 296         promMdsDegraded,
 297         promMdsNoStandby,
 298         promMgrModuleCrash,
 299         promMgrPrometheusInactive,
 300         promPGsInactive,
 301         promPGsUnclean,
 302         promPGsUnavailable,
 303         promPGsDamaged,
 304         promPGsRecoveryFull,
 305         promPGsBackfillFull,
 306         promNodeRootVolumeFull,
 307         promNodeNetworkPacketDrops,
 308         promNodeNetworkPacketErrors,
 309         promNodeStorageFilling,
 310         promPoolFull,
 311         promPoolFilling,
 312         promRadosUnfound,
 313         promCephadmDaemonDown,
 314         promCephadmUpgradeFailure,
 315         promPrometheusJobMissing
 316     }
 317     STATUS current
 318     DESCRIPTION
 319         "A collection of notifications triggered by the Prometheus
 320         rules to convey Ceph cluster state"
 321     ::= { cephAlertGroups 2 }
 322
 323 -- ---------------------------------------------------------- --
 324 -- compliance statements
 325 -- ---------------------------------------------------------- --
 326
 327 cephCompliance MODULE-COMPLIANCE
 328     STATUS current
 329     DESCRIPTION
 330         "The Compliance statement for the Ceph MIB"
 331     MODULE
 332         MANDATORY-GROUPS {
 333             cephNotificationGroup
 334         }
 335     ::= { cephCompliances 1 }
 336
 337 END