| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # CPU utilization |
| 4 | |
| 5 | template: am_container_apps_cpu_utilization |
| 6 | on: azure_monitor.container_apps.cpu_percentage |
| 7 | class: Utilization |
| 8 | type: Containers |
| 9 | component: Container Apps |
| 10 | lookup: average -5m unaligned of average |
| 11 | units: percentage |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (75) : (85)) |
| 14 | crit: $this > (($status == $CRITICAL) ? (85) : (95)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: Container Apps CPU on ${label:resource_name} |
| 17 | info: Average CPU utilization of Container App ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}) |
| 19 | to: sysadmin |
| 20 | |
| 21 | # Memory utilization |
| 22 | |
| 23 | template: am_container_apps_memory_utilization |
| 24 | on: azure_monitor.container_apps.memory_percentage |
| 25 | class: Utilization |
| 26 | type: Containers |
| 27 | component: Container Apps |
| 28 | lookup: average -5m unaligned of average |
| 29 | units: percentage |
| 30 | every: 1m |
| 31 | warn: $this > (($status >= $WARNING) ? (75) : (85)) |
| 32 | crit: $this > (($status == $CRITICAL) ? (85) : (95)) |
| 33 | delay: down 5m multiplier 1.5 max 1h |
| 34 | summary: Container Apps memory on ${label:resource_name} |
| 35 | info: Average memory utilization of Container App ${label:resource_name} \ |
| 36 | in ${label:resource_group} (${label:region}) |
| 37 | to: sysadmin |
| 38 | |
| 39 | # Replica restarts |
| 40 | |
| 41 | template: am_container_apps_restarts |
| 42 | on: azure_monitor.container_apps.restart_count |
| 43 | class: Errors |
| 44 | type: Containers |
| 45 | component: Container Apps |
| 46 | lookup: sum -5m unaligned of restarts |
| 47 | units: restarts |
| 48 | every: 1m |
| 49 | warn: $this > (($status >= $WARNING) ? (3) : (5)) |
| 50 | crit: $this > (($status == $CRITICAL) ? (10) : (15)) |
| 51 | delay: down 5m multiplier 1.5 max 1h |
| 52 | summary: Container Apps restarts on ${label:resource_name} |
| 53 | info: Number of replica restarts in the last 5 minutes for Container App ${label:resource_name} \ |
| 54 | in ${label:resource_group} (${label:region}) |
| 55 | to: sysadmin |
| 56 | |
| 57 | # Response time (latency) |
| 58 | |
| 59 | template: am_container_apps_response_time |
| 60 | on: azure_monitor.container_apps.response_time |
| 61 | class: Latency |
| 62 | type: Containers |
| 63 | component: Container Apps |
| 64 | lookup: average -5m unaligned of average |
| 65 | units: milliseconds |
| 66 | every: 1m |
| 67 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 68 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 69 | delay: down 5m multiplier 1.5 max 1h |
| 70 | summary: Container Apps response time on ${label:resource_name} |
| 71 | info: Average response time of Container App ${label:resource_name} \ |
| 72 | in ${label:resource_group} (${label:region}) |
| 73 | to: sysadmin |
| 74 | |
| 75 | # Resiliency - timeouts |
| 76 | |
| 77 | template: am_container_apps_resiliency_timeouts |
| 78 | on: azure_monitor.container_apps.resiliency_timeouts |
| 79 | class: Errors |
| 80 | type: Containers |
| 81 | component: Container Apps |
| 82 | lookup: sum -5m unaligned |
| 83 | units: timeouts |
| 84 | every: 1m |
| 85 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3) : (5)) |
| 86 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (10) : (20)) |
| 87 | delay: down 5m multiplier 1.5 max 1h |
| 88 | summary: Container Apps resiliency timeouts on ${label:resource_name} |
| 89 | info: Connection and request timeouts in the last 5 minutes for Container App ${label:resource_name} \ |
| 90 | in ${label:resource_group} (${label:region}) |
| 91 | to: sysadmin |
| 92 | |
| 93 | # Resiliency - retries |
| 94 | |
| 95 | template: am_container_apps_resiliency_retries |
| 96 | on: azure_monitor.container_apps.resiliency_retries |
| 97 | class: Errors |
| 98 | type: Containers |
| 99 | component: Container Apps |
| 100 | lookup: sum -5m unaligned of retries |
| 101 | units: retries |
| 102 | every: 1m |
| 103 | warn: $this != nan AND $this > (($status >= $WARNING) ? (10) : (20)) |
| 104 | delay: down 5m multiplier 1.5 max 1h |
| 105 | summary: Container Apps resiliency retries on ${label:resource_name} |
| 106 | info: Request retries in the last 5 minutes for Container App ${label:resource_name} \ |
| 107 | in ${label:resource_group} (${label:region}) |
| 108 | to: sysadmin |
| 109 | |
| 110 | # Resiliency - pending connection pool |
| 111 | |
| 112 | template: am_container_apps_pending_connections |
| 113 | on: azure_monitor.container_apps.resiliency_pending_connections |
| 114 | class: Workload |
| 115 | type: Containers |
| 116 | component: Container Apps |
| 117 | lookup: sum -5m unaligned of pending |
| 118 | units: requests |
| 119 | every: 1m |
| 120 | warn: $this != nan AND $this > (($status >= $WARNING) ? (50) : (100)) |
| 121 | delay: down 5m multiplier 1.5 max 1h |
| 122 | summary: Container Apps pending connections on ${label:resource_name} |
| 123 | info: Requests pending in the connection pool in the last 5 minutes for Container App ${label:resource_name} \ |
| 124 | in ${label:resource_group} (${label:region}) |
| 125 | to: sysadmin |
| 126 | |
| 127 | # Resiliency - host ejections |
| 128 | |
| 129 | template: am_container_apps_host_ejections |
| 130 | on: azure_monitor.container_apps.resiliency_ejections |
| 131 | class: Errors |
| 132 | type: Containers |
| 133 | component: Container Apps |
| 134 | lookup: sum -5m unaligned of ejected |
| 135 | units: ejections |
| 136 | every: 1m |
| 137 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (1)) |
| 138 | delay: down 5m multiplier 1.5 max 1h |
| 139 | summary: Container Apps host ejections on ${label:resource_name} |
| 140 | info: Upstream hosts ejected from the load balancing pool in the last 5 minutes for Container App ${label:resource_name} \ |
| 141 | in ${label:resource_group} (${label:region}) |
| 142 | to: sysadmin |
| 143 | |
| 144 | # Replica count — zero replicas means the app is scaled down or crashed |
| 145 | |
| 146 | template: am_container_apps_replica_count |
| 147 | on: azure_monitor.container_apps.replicas |
| 148 | class: Availability |
| 149 | type: Containers |
| 150 | component: Container Apps |
| 151 | lookup: average -5m unaligned of average |
| 152 | units: replicas |
| 153 | every: 1m |
| 154 | crit: $this != nan AND $this < 1 |
| 155 | delay: down 5m multiplier 1.5 max 1h |
| 156 | summary: Container Apps replicas on ${label:resource_name} |
| 157 | info: Average replica count for Container App ${label:resource_name} \ |
| 158 | in ${label:resource_group} (${label:region}). \ |
| 159 | Zero replicas means the app is either scaled to zero or all replicas have crashed |
| 160 | to: sysadmin |
| 161 | |
| 162 | # GPU utilization (optional - only present when GPU workload profiles are used) |
| 163 | |
| 164 | template: am_container_apps_gpu_utilization |
| 165 | on: azure_monitor.container_apps.gpu_utilization |
| 166 | class: Utilization |
| 167 | type: Containers |
| 168 | component: Container Apps |
| 169 | lookup: average -5m unaligned of average |
| 170 | units: percentage |
| 171 | every: 1m |
| 172 | warn: $this != nan AND $this > (($status >= $WARNING) ? (85) : (95)) |
| 173 | delay: down 5m multiplier 1.5 max 1h |
| 174 | summary: Container Apps GPU on ${label:resource_name} |
| 175 | info: Average GPU utilization of Container App ${label:resource_name} \ |
| 176 | in ${label:resource_group} (${label:region}) |
| 177 | to: sysadmin |
| 178 | |
| 179 | # JVM GC duration (optional - only present for Java workloads) |
| 180 | |
| 181 | template: am_container_apps_jvm_gc_duration |
| 182 | on: azure_monitor.container_apps.jvm_gc_duration |
| 183 | class: Latency |
| 184 | type: Containers |
| 185 | component: Container Apps |
| 186 | lookup: sum -1m unaligned of duration |
| 187 | units: milliseconds |
| 188 | every: 1m |
| 189 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 190 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 191 | delay: down 5m multiplier 1.5 max 1h |
| 192 | summary: Container Apps JVM GC duration on ${label:resource_name} |
| 193 | info: Time spent in JVM garbage collection in the last minute for Container App ${label:resource_name} \ |
| 194 | in ${label:resource_group} (${label:region}) |
| 195 | to: sysadmin |