| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # ── Streaming Job - Resource Utilization ──────────────────────────────────── |
| 4 | |
| 5 | template: am_synapse_streaming_resource_utilization |
| 6 | on: azure_monitor.synapse.streaming_resource_utilization |
| 7 | class: Utilization |
| 8 | type: Database |
| 9 | component: Azure Synapse |
| 10 | lookup: average -5m unaligned of utilization |
| 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: Synapse streaming SU utilization on ${label:resource_name} |
| 17 | info: Streaming job resource utilization on Azure Synapse workspace ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}). \ |
| 19 | High values indicate the streaming job is approaching capacity |
| 20 | to: sysadmin |
| 21 | |
| 22 | # ── Streaming Job - Errors ────────────────────────────────────────────────── |
| 23 | |
| 24 | template: am_synapse_streaming_runtime_errors |
| 25 | on: azure_monitor.synapse.streaming_errors |
| 26 | class: Errors |
| 27 | type: Database |
| 28 | component: Azure Synapse |
| 29 | lookup: average -5m unaligned of runtime |
| 30 | units: errors/s |
| 31 | every: 1m |
| 32 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 33 | crit: $this > (($status == $CRITICAL) ? (1) : (5)) |
| 34 | delay: down 5m multiplier 1.5 max 1h |
| 35 | summary: Synapse streaming runtime errors on ${label:resource_name} |
| 36 | info: Streaming job runtime errors on Azure Synapse workspace ${label:resource_name} \ |
| 37 | in ${label:resource_group} (${label:region}) |
| 38 | to: sysadmin |
| 39 | |
| 40 | template: am_synapse_streaming_data_errors |
| 41 | on: azure_monitor.synapse.streaming_errors |
| 42 | class: Errors |
| 43 | type: Database |
| 44 | component: Azure Synapse |
| 45 | lookup: average -5m unaligned of data_conversion,deserialization |
| 46 | units: errors/s |
| 47 | every: 1m |
| 48 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 49 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 50 | delay: down 5m multiplier 1.5 max 1h |
| 51 | summary: Synapse streaming data errors on ${label:resource_name} |
| 52 | info: Streaming job data conversion and deserialization errors on Azure Synapse workspace \ |
| 53 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 54 | to: sysadmin |
| 55 | |
| 56 | # ── Streaming Job - Watermark Delay ───────────────────────────────────────── |
| 57 | |
| 58 | template: am_synapse_streaming_watermark_delay |
| 59 | on: azure_monitor.synapse.streaming_watermark_delay |
| 60 | class: Latency |
| 61 | type: Database |
| 62 | component: Azure Synapse |
| 63 | lookup: average -5m unaligned of delay |
| 64 | units: seconds |
| 65 | every: 1m |
| 66 | warn: $this > (($status >= $WARNING) ? (30) : (60)) |
| 67 | crit: $this > (($status == $CRITICAL) ? (60) : (120)) |
| 68 | delay: down 5m multiplier 1.5 max 1h |
| 69 | summary: Synapse streaming watermark delay on ${label:resource_name} |
| 70 | info: Output watermark delay of the streaming job on Azure Synapse workspace ${label:resource_name} \ |
| 71 | in ${label:resource_group} (${label:region}). \ |
| 72 | High delay indicates the streaming job is falling behind real-time processing |
| 73 | to: sysadmin |
| 74 | |
| 75 | # ── Streaming Job - Event Timing Issues ───────────────────────────────────── |
| 76 | |
| 77 | template: am_synapse_streaming_late_events |
| 78 | on: azure_monitor.synapse.streaming_event_timing |
| 79 | class: Errors |
| 80 | type: Database |
| 81 | component: Azure Synapse |
| 82 | lookup: average -5m unaligned of late |
| 83 | units: events/s |
| 84 | every: 1m |
| 85 | warn: $this > (($status >= $WARNING) ? (5) : (10)) |
| 86 | crit: $this > (($status == $CRITICAL) ? (25) : (50)) |
| 87 | delay: down 5m multiplier 1.5 max 1h |
| 88 | summary: Synapse streaming late events on ${label:resource_name} |
| 89 | info: Rate of late-arriving input events in the streaming job on Azure Synapse workspace \ |
| 90 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 91 | to: sysadmin |
| 92 | |
| 93 | template: am_synapse_streaming_out_of_order_events |
| 94 | on: azure_monitor.synapse.streaming_event_timing |
| 95 | class: Errors |
| 96 | type: Database |
| 97 | component: Azure Synapse |
| 98 | lookup: average -5m unaligned of out_of_order |
| 99 | units: events/s |
| 100 | every: 1m |
| 101 | warn: $this > (($status >= $WARNING) ? (5) : (10)) |
| 102 | crit: $this > (($status == $CRITICAL) ? (25) : (50)) |
| 103 | delay: down 5m multiplier 1.5 max 1h |
| 104 | summary: Synapse streaming out-of-order events on ${label:resource_name} |
| 105 | info: Rate of out-of-order input events in the streaming job on Azure Synapse workspace \ |
| 106 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 107 | to: sysadmin |
| 108 | |
| 109 | template: am_synapse_streaming_backlogged_events |
| 110 | on: azure_monitor.synapse.streaming_event_timing |
| 111 | class: Workload |
| 112 | type: Database |
| 113 | component: Azure Synapse |
| 114 | lookup: average -5m unaligned of backlogged |
| 115 | units: events/s |
| 116 | every: 1m |
| 117 | warn: $this > (($status >= $WARNING) ? (50) : (100)) |
| 118 | crit: $this > (($status == $CRITICAL) ? (100) : (500)) |
| 119 | delay: down 5m multiplier 1.5 max 1h |
| 120 | summary: Synapse streaming backlogged events on ${label:resource_name} |
| 121 | info: Rate of backlogged input event sources in the streaming job on Azure Synapse workspace \ |
| 122 | ${label:resource_name} in ${label:resource_group} (${label:region}). \ |
| 123 | Backlog growth indicates input rate exceeds processing capacity |
| 124 | to: sysadmin |
| 125 | |
| 126 | # ── Integration - Link Processing Latency ─────────────────────────────────── |
| 127 | |
| 128 | template: am_synapse_link_processing_latency |
| 129 | on: azure_monitor.synapse.link_processing_latency |
| 130 | class: Latency |
| 131 | type: Database |
| 132 | component: Azure Synapse |
| 133 | lookup: average -5m unaligned of average |
| 134 | units: seconds |
| 135 | every: 1m |
| 136 | warn: $this != nan AND $this > (($status >= $WARNING) ? (30) : (60)) |
| 137 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (60) : (120)) |
| 138 | delay: down 5m multiplier 1.5 max 1h |
| 139 | summary: Synapse Link processing latency on ${label:resource_name} |
| 140 | info: Average Synapse Link processing latency on Azure Synapse workspace ${label:resource_name} \ |
| 141 | in ${label:resource_group} (${label:region}). \ |
| 142 | Only relevant when Synapse Link connections are configured |
| 143 | to: sysadmin |