| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- Errors --- |
| 4 | |
| 5 | template: am_event_hubs_server_errors |
| 6 | on: azure_monitor.event_hubs.errors |
| 7 | class: Errors |
| 8 | type: Messaging |
| 9 | component: Azure Event Hubs |
| 10 | lookup: average -5m unaligned of server |
| 11 | units: errors/s |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 14 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: Event Hubs server errors on ${label:resource_name} |
| 17 | info: Server-side errors on Event Hubs namespace ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}) |
| 19 | to: sysadmin |
| 20 | |
| 21 | template: am_event_hubs_throttled_requests |
| 22 | on: azure_monitor.event_hubs.errors |
| 23 | class: Errors |
| 24 | type: Messaging |
| 25 | component: Azure Event Hubs |
| 26 | lookup: average -5m unaligned of throttled |
| 27 | units: errors/s |
| 28 | every: 1m |
| 29 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 30 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 31 | delay: down 5m multiplier 1.5 max 1h |
| 32 | summary: Event Hubs throttled requests on ${label:resource_name} |
| 33 | info: Requests being throttled on Event Hubs namespace ${label:resource_name} \ |
| 34 | in ${label:resource_group} (${label:region}) |
| 35 | to: sysadmin |
| 36 | |
| 37 | template: am_event_hubs_quota_exceeded |
| 38 | on: azure_monitor.event_hubs.errors |
| 39 | class: Errors |
| 40 | type: Messaging |
| 41 | component: Azure Event Hubs |
| 42 | lookup: average -5m unaligned of quota_exceeded |
| 43 | units: errors/s |
| 44 | every: 1m |
| 45 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 46 | crit: $this > (($status == $CRITICAL) ? (1) : (5)) |
| 47 | delay: down 5m multiplier 1.5 max 1h |
| 48 | summary: Event Hubs quota exceeded on ${label:resource_name} |
| 49 | info: Quota exceeded errors on Event Hubs namespace ${label:resource_name} \ |
| 50 | in ${label:resource_group} (${label:region}). \ |
| 51 | Quota errors indicate the namespace has exceeded its throughput unit limits |
| 52 | to: sysadmin |
| 53 | |
| 54 | # User errors (400-class) at sustained high rate may indicate |
| 55 | # client misconfiguration or malformed messages. |
| 56 | |
| 57 | template: am_event_hubs_user_errors |
| 58 | on: azure_monitor.event_hubs.errors |
| 59 | class: Errors |
| 60 | type: Messaging |
| 61 | component: Azure Event Hubs |
| 62 | lookup: average -5m unaligned of user |
| 63 | units: errors/s |
| 64 | every: 1m |
| 65 | warn: $this > (($status >= $WARNING) ? (10) : (25)) |
| 66 | delay: down 5m multiplier 1.5 max 1h |
| 67 | summary: Event Hubs user errors on ${label:resource_name} |
| 68 | info: Rate of user (client-side) errors on Event Hubs namespace ${label:resource_name} \ |
| 69 | in ${label:resource_group} (${label:region}) |
| 70 | to: sysadmin |
| 71 | |
| 72 | # --- Request Success Rate --- |
| 73 | |
| 74 | template: am_event_hubs_incoming_requests |
| 75 | on: azure_monitor.event_hubs.requests |
| 76 | class: Workload |
| 77 | type: Messaging |
| 78 | component: Azure Event Hubs |
| 79 | lookup: sum -5m unaligned of incoming |
| 80 | units: requests/s |
| 81 | every: 1m |
| 82 | info: Total incoming requests to Event Hubs namespace ${label:resource_name} |
| 83 | |
| 84 | template: am_event_hubs_success_rate |
| 85 | on: azure_monitor.event_hubs.requests |
| 86 | class: Errors |
| 87 | type: Messaging |
| 88 | component: Azure Event Hubs |
| 89 | lookup: sum -5m unaligned of successful |
| 90 | calc: ($am_event_hubs_incoming_requests > 0) ? ($this * 100 / $am_event_hubs_incoming_requests) : (100) |
| 91 | units: % |
| 92 | every: 1m |
| 93 | warn: ($am_event_hubs_incoming_requests > 120) ? ($this < (($status >= $WARNING) ? (99) : (95))) : (0) |
| 94 | crit: ($am_event_hubs_incoming_requests > 120) ? ($this < (($status == $CRITICAL) ? (95) : (85))) : (0) |
| 95 | delay: down 5m multiplier 1.5 max 1h |
| 96 | summary: Event Hubs request success rate on ${label:resource_name} |
| 97 | info: Percentage of successful requests on Event Hubs namespace ${label:resource_name} \ |
| 98 | in ${label:resource_group} (${label:region}) |
| 99 | to: sysadmin |
| 100 | |
| 101 | # --- Utilization (Premium tier) --- |
| 102 | |
| 103 | template: am_event_hubs_namespace_cpu |
| 104 | on: azure_monitor.event_hubs.namespace_resources |
| 105 | class: Utilization |
| 106 | type: Messaging |
| 107 | component: Azure Event Hubs |
| 108 | lookup: average -5m unaligned of cpu |
| 109 | units: percentage |
| 110 | every: 1m |
| 111 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 112 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (80) : (90)) |
| 113 | delay: down 5m multiplier 1.5 max 1h |
| 114 | summary: Event Hubs namespace CPU on ${label:resource_name} |
| 115 | info: CPU utilization of Event Hubs Premium namespace ${label:resource_name} \ |
| 116 | in ${label:resource_group} (${label:region}) |
| 117 | to: sysadmin |
| 118 | |
| 119 | template: am_event_hubs_namespace_memory |
| 120 | on: azure_monitor.event_hubs.namespace_resources |
| 121 | class: Utilization |
| 122 | type: Messaging |
| 123 | component: Azure Event Hubs |
| 124 | lookup: average -5m unaligned of memory |
| 125 | units: percentage |
| 126 | every: 1m |
| 127 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 128 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (80) : (90)) |
| 129 | delay: down 5m multiplier 1.5 max 1h |
| 130 | summary: Event Hubs namespace memory on ${label:resource_name} |
| 131 | info: Memory utilization of Event Hubs Premium namespace ${label:resource_name} \ |
| 132 | in ${label:resource_group} (${label:region}) |
| 133 | to: sysadmin |
| 134 | |
| 135 | # --- Capture --- |
| 136 | |
| 137 | template: am_event_hubs_capture_backlog |
| 138 | on: azure_monitor.event_hubs.capture_backlog |
| 139 | class: Workload |
| 140 | type: Messaging |
| 141 | component: Azure Event Hubs |
| 142 | lookup: average -5m unaligned of backlog |
| 143 | units: messages |
| 144 | every: 1m |
| 145 | warn: $this != nan AND $this > (($status >= $WARNING) ? (500000) : (1000000)) |
| 146 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (1000000) : (5000000)) |
| 147 | delay: down 5m multiplier 1.5 max 1h |
| 148 | summary: Event Hubs capture backlog on ${label:resource_name} |
| 149 | info: Messages waiting to be captured on Event Hubs namespace ${label:resource_name} \ |
| 150 | in ${label:resource_group} (${label:region}) |
| 151 | to: sysadmin |
| 152 | |
| 153 | # --- Geo-Replication --- |
| 154 | |
| 155 | template: am_event_hubs_replication_lag |
| 156 | on: azure_monitor.event_hubs.replication_lag |
| 157 | class: Latency |
| 158 | type: Messaging |
| 159 | component: Azure Event Hubs |
| 160 | lookup: average -5m unaligned of messages |
| 161 | units: messages |
| 162 | every: 1m |
| 163 | warn: $this != nan AND $this > (($status >= $WARNING) ? (100) : (500)) |
| 164 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (500) : (1000)) |
| 165 | delay: down 5m multiplier 1.5 max 1h |
| 166 | summary: Event Hubs replication lag on ${label:resource_name} |
| 167 | info: Geo-replication message lag on Event Hubs namespace ${label:resource_name} \ |
| 168 | in ${label:resource_group} (${label:region}) |
| 169 | to: sysadmin |
| 170 | |
| 171 | template: am_event_hubs_replication_lag_duration |
| 172 | on: azure_monitor.event_hubs.replication_lag_duration |
| 173 | class: Latency |
| 174 | type: Messaging |
| 175 | component: Azure Event Hubs |
| 176 | lookup: average -5m unaligned of duration |
| 177 | units: seconds |
| 178 | every: 1m |
| 179 | warn: $this != nan AND $this > (($status >= $WARNING) ? (30) : (60)) |
| 180 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (60) : (120)) |
| 181 | delay: down 5m multiplier 1.5 max 1h |
| 182 | summary: Event Hubs replication lag duration on ${label:resource_name} |
| 183 | info: Geo-replication time lag on Event Hubs namespace ${label:resource_name} \ |
| 184 | in ${label:resource_group} (${label:region}) |
| 185 | to: sysadmin |