MON-191 - Space aggregator hard coded for Azure monitors
This commit is contained in:
Alexandre Gaillet
parent
437e230514
commit
6300ed87e8
@ -32,294 +32,271 @@ Inputs
|
||||
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| apimanagement_failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| apimanagement_failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no |
|
||||
| apimanagement_failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `<map>` | no |
|
||||
| apimanagement_failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no |
|
||||
| apimanagement_failed_requests_threshold_warning | Warning regarding acceptable percent of failed requests | string | `50` | no |
|
||||
| apimanagement_failed_requests_timeframe | Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| apimanagement_other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| apimanagement_other_requests_message | Custom message for API Management other requests monitor | string | `` | no |
|
||||
| apimanagement_other_requests_silenced | Groups to mute for API Management other requests monitor | map | `<map>` | no |
|
||||
| apimanagement_other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no |
|
||||
| apimanagement_other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no |
|
||||
| apimanagement_other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| apimanagement_status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| apimanagement_status_message | Custom message for API Management status monitor | string | `` | no |
|
||||
| apimanagement_status_silenced | Groups to mute for API Management status monitor | map | `<map>` | no |
|
||||
| apimanagement_status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `avg` | no |
|
||||
| apimanagement_status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| apimanagement_successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| apimanagement_successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no |
|
||||
| apimanagement_successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `<map>` | no |
|
||||
| apimanagement_successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no |
|
||||
| apimanagement_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no |
|
||||
| apimanagement_successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| apimanagement_unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| apimanagement_unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no |
|
||||
| apimanagement_unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `<map>` | no |
|
||||
| apimanagement_unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no |
|
||||
| apimanagement_unauthorized_requests_threshold_warning | Warning regarding acceptable percent of unauthorized requests | string | `50` | no |
|
||||
| apimanagement_unauthorized_requests_timeframe | Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| appservices_http_4xx_requests_aggregator | Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| appservices_http_4xx_requests_message | Custom message for App Services 4xx requests monitor | string | `` | no |
|
||||
| appservices_http_4xx_requests_silenced | Groups to mute for App Services 4xx requests monitor | map | `<map>` | no |
|
||||
| appservices_http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no |
|
||||
| appservices_http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no |
|
||||
| appservices_http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| appservices_http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| appservices_http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no |
|
||||
| appservices_http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `<map>` | no |
|
||||
| appservices_http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no |
|
||||
| appservices_http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no |
|
||||
| appservices_http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| appservices_http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| appservices_http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no |
|
||||
| appservices_http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `<map>` | no |
|
||||
| appservices_http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no |
|
||||
| appservices_http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no |
|
||||
| appservices_http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| appservices_memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| appservices_memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no |
|
||||
| appservices_memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `<map>` | no |
|
||||
| appservices_memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no |
|
||||
| appservices_memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no |
|
||||
| appservices_memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `avg` | no |
|
||||
| appservices_memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| appservices_response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| appservices_response_time_message | Custom message for App Services response time monitor | string | `` | no |
|
||||
| appservices_response_time_silenced | Groups to mute for App Services response time monitor | map | `<map>` | no |
|
||||
| appservices_response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no |
|
||||
| appservices_response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no |
|
||||
| appservices_response_time_time_aggregator | Monitor aggregator for App Services response time [available values: min, max or avg] | string | `min` | no |
|
||||
| appservices_response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| eventhub_errors_rate_aggregator | Monitor aggregator for Event Hub errors [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| eventhub_errors_rate_message | Custom message for Event Hub errors monitor | string | `` | no |
|
||||
| eventhub_errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `<map>` | no |
|
||||
| eventhub_errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no |
|
||||
| eventhub_errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no |
|
||||
| eventhub_errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| eventhub_failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| eventhub_failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no |
|
||||
| eventhub_failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `<map>` | no |
|
||||
| eventhub_failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no |
|
||||
| eventhub_failed_requests_rate_thresold_warning | Failed requests ratio (percentage) to trigger a warning alert | string | `50` | no |
|
||||
| eventhub_failed_requests_rate_timeframe | Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| eventhub_status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| eventhub_status_message | Custom message for Event Hub status monitor | string | `` | no |
|
||||
| eventhub_status_silenced | Groups to mute for Event Hub status monitor | map | `<map>` | no |
|
||||
| eventhub_status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `avg` | no |
|
||||
| eventhub_status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `<map>` | no |
|
||||
| iothub_dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no |
|
||||
| iothub_failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `<map>` | no |
|
||||
| iothub_failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `<map>` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `<map>` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `<map>` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `<map>` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no |
|
||||
| iothub_failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `<map>` | no |
|
||||
| iothub_failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no |
|
||||
| iothub_failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `<map>` | no |
|
||||
| iothub_failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no |
|
||||
| iothub_failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `<map>` | no |
|
||||
| iothub_failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| iothub_failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| iothub_failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `<map>` | no |
|
||||
| iothub_invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `<map>` | no |
|
||||
| iothub_orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| iothub_status_message | Custom message for IoT Hub status monitor | string | `` | no |
|
||||
| iothub_status_silenced | Groups to mute for IoT Hub status monitor | map | `<map>` | no |
|
||||
| iothub_status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max or avg] | string | `avg` | no |
|
||||
| iothub_status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| iothub_too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no |
|
||||
| iothub_too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `<map>` | no |
|
||||
| iothub_too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| iothub_total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| iothub_total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no |
|
||||
| iothub_total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `<map>` | no |
|
||||
| iothub_total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max or avg] | string | `avg` | no |
|
||||
| iothub_total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| message | Message sent when a monitor is triggered | string | - | yes |
|
||||
| non_taggable_filter_tags | Tags used for filtering for components without tag support | string | `*` | no |
|
||||
| redis_evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| redis_evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no |
|
||||
| redis_evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `<map>` | no |
|
||||
| redis_evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no |
|
||||
| redis_evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no |
|
||||
| redis_evictedkeys_limit_time_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max or avg] | string | `avg` | no |
|
||||
| redis_evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| redis_percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| redis_percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no |
|
||||
| redis_percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `<map>` | no |
|
||||
| redis_percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no |
|
||||
| redis_percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no |
|
||||
| redis_percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `avg` | no |
|
||||
| redis_percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| redis_server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| redis_server_load_rate_message | Custom message for Redis server load monitor | string | `` | no |
|
||||
| redis_server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `<map>` | no |
|
||||
| redis_server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no |
|
||||
| redis_server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no |
|
||||
| redis_server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `avg` | no |
|
||||
| redis_server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| redis_status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| redis_status_message | Custom message for Redis status monitor | string | `` | no |
|
||||
| redis_status_silenced | Groups to mute for Redis status monitor | map | `<map>` | no |
|
||||
| redis_status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `avg` | no |
|
||||
| redis_status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| servicebus_status_aggregator | Monitor timeframe aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| servicebus_status_message | Custom message for Service Bus status monitor | string | `` | no |
|
||||
| servicebus_status_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
|
||||
| servicebus_status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `min` | no |
|
||||
| servicebus_status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| sqldatabase_cpu_aggregator | Monitor aggregator for SQL CPU [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no |
|
||||
| sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `<map>` | no |
|
||||
| sqldatabase_cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
|
||||
| sqldatabase_cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
|
||||
| sqldatabase_cpu_time_aggregator | Monitor aggregator for SQL CPU [available values: min, max or avg] | string | `avg` | no |
|
||||
| sqldatabase_cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| sqldatabase_deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| sqldatabase_deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no |
|
||||
| sqldatabase_deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `<map>` | no |
|
||||
| sqldatabase_deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no |
|
||||
| sqldatabase_deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| sqldatabase_diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| sqldatabase_diskspace_message | Custom message for SQL disk space monitor | string | `` | no |
|
||||
| sqldatabase_diskspace_silenced | Groups to mute for SQL disk space monitor | map | `<map>` | no |
|
||||
| sqldatabase_diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no |
|
||||
| sqldatabase_diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no |
|
||||
| sqldatabase_diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `avg` | no |
|
||||
| sqldatabase_diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| sqldatabase_dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| sqldatabase_dtu_message | Custom message for SQL DTU monitor | string | `` | no |
|
||||
| sqldatabase_dtu_silenced | Groups to mute for SQL DTU monitor | map | `<map>` | no |
|
||||
| sqldatabase_dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no |
|
||||
| sqldatabase_dtu_threshold_warning | Amount of DTU used (warning threshold) | string | `85` | no |
|
||||
| sqldatabase_dtu_time_aggregator | Monitor aggregator for SQL DTU [available values: min, max or avg] | string | `avg` | no |
|
||||
| sqldatabase_dtu_timeframe | Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| storage_authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no |
|
||||
| storage_authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `<map>` | no |
|
||||
| storage_authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no |
|
||||
| storage_authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no |
|
||||
| storage_authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_availability_message | Custom message for Storage availability monitor | string | `` | no |
|
||||
| storage_availability_silenced | Groups to mute for Storage availability monitor | map | `<map>` | no |
|
||||
| storage_availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no |
|
||||
| storage_availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no |
|
||||
| storage_availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no |
|
||||
| storage_client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `<map>` | no |
|
||||
| storage_client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no |
|
||||
| storage_client_other_error_requests_threshold_warning | Warning regarding acceptable percent of client other error requests for a storage | string | `50` | no |
|
||||
| storage_client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_client_other_error_requests_timeframe | Monitor timeframe for Storage other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| storage_latency_message | Custom message for Storage latency monitor | string | `` | no |
|
||||
| storage_latency_silenced | Groups to mute for Storage latency monitor | map | `<map>` | no |
|
||||
| storage_latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no |
|
||||
| storage_latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no |
|
||||
| storage_latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no |
|
||||
| storage_latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no |
|
||||
| storage_network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `<map>` | no |
|
||||
| storage_network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no |
|
||||
| storage_network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no |
|
||||
| storage_network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no |
|
||||
| storage_server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `<map>` | no |
|
||||
| storage_server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no |
|
||||
| storage_server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no |
|
||||
| storage_server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no |
|
||||
| storage_successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `<map>` | no |
|
||||
| storage_successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no |
|
||||
| storage_successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no |
|
||||
| storage_successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no |
|
||||
| storage_throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `<map>` | no |
|
||||
| storage_throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no |
|
||||
| storage_throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no |
|
||||
| storage_throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| storage_timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| storage_timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no |
|
||||
| storage_timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `<map>` | no |
|
||||
| storage_timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no |
|
||||
| storage_timeout_error_requests_threshold_warning | Warning regarding acceptable percent of timeout error requests for a storage | string | `50` | no |
|
||||
| storage_timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no |
|
||||
| storage_timeout_error_requests_timeframe | Monitor timeframe for Storage timeout [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| streamanalytics_conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| streamanalytics_conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no |
|
||||
| streamanalytics_conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `<map>` | no |
|
||||
| streamanalytics_conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no |
|
||||
| streamanalytics_conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no |
|
||||
| streamanalytics_conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| streamanalytics_conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| streamanalytics_failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| streamanalytics_failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no |
|
||||
| streamanalytics_failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `<map>` | no |
|
||||
| streamanalytics_failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no |
|
||||
| streamanalytics_failed_function_requests_threshold_warning | Failed Function Request rate limit (warning threshold) | string | `0` | no |
|
||||
| streamanalytics_failed_function_requests_timeframe | Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| streamanalytics_runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| streamanalytics_runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no |
|
||||
| streamanalytics_runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `<map>` | no |
|
||||
| streamanalytics_runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no |
|
||||
| streamanalytics_runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no |
|
||||
| streamanalytics_runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| streamanalytics_runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| streamanalytics_status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| streamanalytics_status_message | Custom message for Stream Analytics status monitor | string | `` | no |
|
||||
| streamanalytics_status_silenced | Groups to mute for Stream Analytics status monitor | map | `<map>` | no |
|
||||
| streamanalytics_status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `avg` | no |
|
||||
| streamanalytics_status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| streamanalytics_su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| streamanalytics_su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no |
|
||||
| streamanalytics_su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `<map>` | no |
|
||||
| streamanalytics_su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no |
|
||||
| streamanalytics_su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no |
|
||||
| streamanalytics_su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `avg` | no |
|
||||
| streamanalytics_su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -29,7 +29,6 @@ Inputs
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| failed_requests_aggregator | Monitor aggregator for API Management failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_requests_message | Custom message for API Management failed requests monitor | string | `` | no |
|
||||
| failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `<map>` | no |
|
||||
| failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no |
|
||||
@ -38,23 +37,20 @@ Inputs
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| message | Message sent when a Redis monitor is triggered | string | - | yes |
|
||||
| other_requests_aggregator | Monitor aggregator for API Management other requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| other_requests_message | Custom message for API Management other requests monitor | string | `` | no |
|
||||
| other_requests_silenced | Groups to mute for API Management other requests monitor | map | `<map>` | no |
|
||||
| other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no |
|
||||
| other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no |
|
||||
| other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| status_aggregator | Monitor aggregator for API Management status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_message | Custom message for API Management status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for API Management status monitor | map | `<map>` | no |
|
||||
| status_time_aggregator | Monitor aggregator for API Management status [available values: min, max or avg] | string | `avg` | no |
|
||||
| status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| successful_requests_aggregator | Monitor aggregator for API Management successful requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no |
|
||||
| successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `<map>` | no |
|
||||
| successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no |
|
||||
| successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no |
|
||||
| successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| unauthorized_requests_aggregator | Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no |
|
||||
| unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `<map>` | no |
|
||||
| unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no |
|
||||
|
||||
@ -37,8 +37,8 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]"
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for API Management status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -61,12 +61,6 @@ variable "failed_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -95,12 +89,6 @@ variable "other_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "other_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "other_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -129,12 +117,6 @@ variable "unauthorized_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "unauthorized_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "unauthorized_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -163,12 +145,6 @@ variable "successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "successful_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
|
||||
@ -13,7 +13,7 @@ resource "datadog_monitor" "apimgt_status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
|
||||
${var.status_time_aggregator}(${var.status_timeframe}):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -42,9 +42,9 @@ resource "datadog_monitor" "apimgt_failed_requests" {
|
||||
message = "${coalesce(var.failed_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_requests_aggregator}(${var.failed_requests_timeframe}): (
|
||||
${var.failed_requests_aggregator}:azure.apimanagement_service.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.failed_requests_aggregator}:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
sum(${var.failed_requests_timeframe}): (
|
||||
avg:azure.apimanagement_service.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
) > ${var.failed_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -74,9 +74,9 @@ resource "datadog_monitor" "apimgt_other_requests" {
|
||||
message = "${coalesce(var.other_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.other_requests_aggregator}(${var.other_requests_timeframe}): (
|
||||
${var.other_requests_aggregator}:azure.apimanagement_service.other_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.other_requests_aggregator}:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
sum(${var.other_requests_timeframe}): (
|
||||
avg:azure.apimanagement_service.other_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
) > ${var.other_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -106,9 +106,9 @@ resource "datadog_monitor" "apimgt_unauthorized_requests" {
|
||||
message = "${coalesce(var.unauthorized_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.unauthorized_requests_aggregator}(${var.unauthorized_requests_timeframe}): (
|
||||
${var.unauthorized_requests_aggregator}:azure.apimanagement_service.unauthorized_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.unauthorized_requests_aggregator}:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
sum(${var.unauthorized_requests_timeframe}): (
|
||||
avg:azure.apimanagement_service.unauthorized_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
) > ${var.unauthorized_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -138,9 +138,9 @@ resource "datadog_monitor" "apimgt_successful_requests" {
|
||||
message = "${coalesce(var.successful_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.successful_requests_aggregator}(${var.successful_requests_timeframe}): (
|
||||
${var.successful_requests_aggregator}:azure.apimanagement_service.successful_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.successful_requests_aggregator}:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
sum(${var.successful_requests_timeframe}): (
|
||||
avg:azure.apimanagement_service.successful_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
|
||||
) < ${var.successful_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
@ -32,36 +32,33 @@ Inputs
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| http_4xx_requests_aggregator | Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| http_4xx_requests_message | Custom message for App Services 4xx requests monitor | string | `` | no |
|
||||
| http_4xx_requests_silenced | Groups to mute for App Services 4xx requests monitor | map | `<map>` | no |
|
||||
| http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no |
|
||||
| http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no |
|
||||
| http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| http_5xx_requests_aggregator | Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no |
|
||||
| http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `<map>` | no |
|
||||
| http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no |
|
||||
| http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no |
|
||||
| http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| http_successful_requests_aggregator | Monitor aggregator for App Services successful requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no |
|
||||
| http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `<map>` | no |
|
||||
| http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no |
|
||||
| http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no |
|
||||
| http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| memory_usage_aggregator | Monitor aggregator for App Services memory usage [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no |
|
||||
| memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `<map>` | no |
|
||||
| memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no |
|
||||
| memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no |
|
||||
| memory_usage_time_aggregator | Monitor aggregator for App Services memory usage [available values: min, max or avg] | string | `avg` | no |
|
||||
| memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| message | Message sent when a monitor is triggered | string | - | yes |
|
||||
| response_time_aggregator | Monitor aggregator for App Services response time [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| response_time_message | Custom message for App Services response time monitor | string | `` | no |
|
||||
| response_time_silenced | Groups to mute for App Services response time monitor | map | `<map>` | no |
|
||||
| response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no |
|
||||
| response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no |
|
||||
| response_time_time_aggregator | Monitor aggregator for App Services response time [available values: min, max or avg] | string | `min` | no |
|
||||
| response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -35,8 +35,8 @@ variable "response_time_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "response_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]"
|
||||
variable "response_time_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services response time [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
@ -69,8 +69,8 @@ variable "memory_usage_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "memory_usage_aggregator" {
|
||||
description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]"
|
||||
variable "memory_usage_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -103,12 +103,6 @@ variable "http_4xx_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "http_4xx_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "http_4xx_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -137,12 +131,6 @@ variable "http_5xx_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "http_5xx_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "http_5xx_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -171,12 +159,6 @@ variable "http_successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "http_successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "http_successful_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
|
||||
@ -13,8 +13,8 @@ resource "datadog_monitor" "appservices_response_time" {
|
||||
message = "${coalesce(var.response_time_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.response_time_aggregator}(last_5m): (
|
||||
${var.response_time_aggregator}:azure.app_services.average_response_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.response_time_time_aggregator}(${var.response_time_timeframe}): (
|
||||
avg:azure.app_services.average_response_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.response_time_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -44,8 +44,8 @@ resource "datadog_monitor" "appservices_memory_usage_count" {
|
||||
message = "${coalesce(var.memory_usage_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.memory_usage_aggregator}(${var.memory_usage_timeframe}): (
|
||||
${var.memory_usage_aggregator}:azure.app_services.memory_working_set{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.memory_usage_time_aggregator}(${var.memory_usage_timeframe}): (
|
||||
avg:azure.app_services.memory_working_set{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.memory_usage_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -75,9 +75,9 @@ resource "datadog_monitor" "appservices_http_5xx_errors_count" {
|
||||
message = "${coalesce(var.http_5xx_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.http_5xx_requests_aggregator}(${var.http_5xx_requests_timeframe}): (
|
||||
${var.http_5xx_requests_aggregator}:azure.app_services.http5xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.http_5xx_requests_aggregator}:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.http_5xx_requests_timeframe}): (
|
||||
avg:azure.app_services.http5xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) * 100 > ${var.http_5xx_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -107,9 +107,9 @@ resource "datadog_monitor" "appservices_http_4xx_errors_count" {
|
||||
message = "${coalesce(var.http_4xx_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.http_4xx_requests_aggregator}(${var.http_4xx_requests_timeframe}): (
|
||||
${var.http_4xx_requests_aggregator}:azure.app_services.http4xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.http_4xx_requests_aggregator}:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.http_4xx_requests_timeframe}): (
|
||||
avg:azure.app_services.http4xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) * 100 > ${var.http_4xx_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -139,10 +139,10 @@ resource "datadog_monitor" "appservices_http_success_status_rate" {
|
||||
message = "${coalesce(var.http_successful_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.http_successful_requests_aggregator}(${var.http_successful_requests_timeframe}): (
|
||||
(${var.http_successful_requests_aggregator}:azure.app_services.http2xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
${var.http_successful_requests_aggregator}:azure.app_services.http3xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()) /
|
||||
${var.http_successful_requests_aggregator}:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.http_successful_requests_timeframe}): (
|
||||
(avg:azure.app_services.http2xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.app_services.http3xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()) /
|
||||
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) * 100 < ${var.http_successful_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
@ -28,13 +28,11 @@ Inputs
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| errors_rate_aggregator | Monitor aggregator for Event Hub errors [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| errors_rate_message | Custom message for Event Hub errors monitor | string | `` | no |
|
||||
| errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `<map>` | no |
|
||||
| errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no |
|
||||
| errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no |
|
||||
| errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_requests_rate_aggregator | Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no |
|
||||
| failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `<map>` | no |
|
||||
| failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no |
|
||||
@ -43,9 +41,9 @@ Inputs
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| message | Message sent when an alert is triggered | string | - | yes |
|
||||
| status_aggregator | Monitor aggregator for Event Hub status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_message | Custom message for Event Hub status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for Event Hub status monitor | map | `<map>` | no |
|
||||
| status_time_aggregator | Monitor aggregator for Event Hub status [available values: min, max or avg] | string | `avg` | no |
|
||||
| status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -37,8 +37,8 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]"
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -61,12 +61,6 @@ variable "failed_requests_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_requests_rate_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_requests_rate_timeframe" {
|
||||
description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -95,12 +89,6 @@ variable "errors_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "errors_rate_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "errors_rate_timeframe" {
|
||||
description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
|
||||
@ -11,7 +11,9 @@ resource "datadog_monitor" "eventhub_status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
|
||||
${var.status_time_aggregator}(${var.status_timeframe}): (
|
||||
avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) != 1
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -36,10 +38,10 @@ resource "datadog_monitor" "eventhub_failed_requests" {
|
||||
message = "${coalesce(var.failed_requests_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_requests_rate_aggregator}(${var.failed_requests_rate_timeframe}): (
|
||||
sum(${var.failed_requests_rate_timeframe}): (
|
||||
default(
|
||||
${var.failed_requests_rate_aggregator}:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.failed_requests_rate_aggregator}:azure.eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count(),
|
||||
avg:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count(),
|
||||
0) * 100
|
||||
) > ${var.failed_requests_rate_thresold_critical}
|
||||
EOF
|
||||
@ -71,14 +73,14 @@ resource "datadog_monitor" "eventhub_errors" {
|
||||
message = "${coalesce(var.errors_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.errors_rate_aggregator}(${var.errors_rate_timeframe}): (
|
||||
sum(${var.errors_rate_timeframe}): (
|
||||
default(
|
||||
(
|
||||
${var.errors_rate_aggregator}:azure.eventhub_namespaces.internal_server_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
${var.errors_rate_aggregator}:azure.eventhub_namespaces.server_busy_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
${var.errors_rate_aggregator}:azure.eventhub_namespaces.other_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
avg:azure.eventhub_namespaces.internal_server_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.eventhub_namespaces.server_busy_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.eventhub_namespaces.other_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) / (
|
||||
${var.errors_rate_aggregator}:eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
avg:eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
),
|
||||
0) * 100
|
||||
) > ${var.errors_rate_thresold_critical}
|
||||
|
||||
@ -41,8 +41,8 @@ variable "apimanagement_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apimanagement_status_aggregator" {
|
||||
description = "Monitor aggregator for API Management status [available values: min, max, sum or avg]"
|
||||
variable "apimanagement_status_time_aggregator" {
|
||||
description = "Monitor aggregator for API Management status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -65,12 +65,6 @@ variable "apimanagement_failed_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apimanagement_failed_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "apimanagement_failed_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -99,12 +93,6 @@ variable "apimanagement_other_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apimanagement_other_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management other requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "apimanagement_other_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -133,12 +121,6 @@ variable "apimanagement_unauthorized_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apimanagement_unauthorized_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management unauthorized requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "apimanagement_unauthorized_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -167,12 +149,6 @@ variable "apimanagement_successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apimanagement_successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for API Management successful requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "apimanagement_successful_requests_timeframe" {
|
||||
description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -202,8 +178,8 @@ variable "appservices_response_time_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "appservices_response_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services response time [available values: min, max, sum or avg]"
|
||||
variable "appservices_response_time_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services response time [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
@ -236,8 +212,8 @@ variable "appservices_memory_usage_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "appservices_memory_usage_aggregator" {
|
||||
description = "Monitor aggregator for App Services memory usage [available values: min, max, sum or avg]"
|
||||
variable "appservices_memory_usage_time_aggregator" {
|
||||
description = "Monitor aggregator for App Services memory usage [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -270,12 +246,6 @@ variable "appservices_http_4xx_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "appservices_http_4xx_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services 4xx requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "appservices_http_4xx_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -304,12 +274,6 @@ variable "appservices_http_5xx_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "appservices_http_5xx_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services 5xx requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "appservices_http_5xx_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -338,12 +302,6 @@ variable "appservices_http_successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "appservices_http_successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for App Services successful requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "appservices_http_successful_requests_timeframe" {
|
||||
description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -373,8 +331,8 @@ variable "eventhub_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "eventhub_status_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub status [available values: min, max, sum or avg]"
|
||||
variable "eventhub_status_time_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -397,12 +355,6 @@ variable "eventhub_failed_requests_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "eventhub_failed_requests_rate_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "eventhub_failed_requests_rate_timeframe" {
|
||||
description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -431,12 +383,6 @@ variable "eventhub_errors_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "eventhub_errors_rate_aggregator" {
|
||||
description = "Monitor aggregator for Event Hub errors [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "eventhub_errors_rate_timeframe" {
|
||||
description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -466,8 +412,8 @@ variable "iothub_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_status_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]"
|
||||
variable "iothub_status_time_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -490,8 +436,8 @@ variable "iothub_total_devices_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_total_devices_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]"
|
||||
variable "iothub_total_devices_time_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub total devices [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -514,12 +460,6 @@ variable "iothub_too_many_d2c_telemetry_ingress_nosent_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_too_many_d2c_telemetry_ingress_nosent_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_too_many_d2c_telemetry_ingress_nosent_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -538,12 +478,6 @@ variable "iothub_failed_jobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_jobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_jobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -572,12 +506,6 @@ variable "iothub_failed_listjobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_listjobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_listjobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -606,12 +534,6 @@ variable "iothub_failed_queryjobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_queryjobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_queryjobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -640,12 +562,6 @@ variable "iothub_failed_c2d_methods_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_methods_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_methods_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -674,12 +590,6 @@ variable "iothub_failed_c2d_twin_read_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_twin_read_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_twin_read_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -708,12 +618,6 @@ variable "iothub_failed_c2d_twin_update_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_twin_update_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_c2d_twin_update_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -742,12 +646,6 @@ variable "iothub_failed_d2c_twin_read_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_d2c_twin_read_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_d2c_twin_read_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -776,12 +674,6 @@ variable "iothub_failed_d2c_twin_update_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_failed_d2c_twin_update_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_failed_d2c_twin_update_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -810,12 +702,6 @@ variable "iothub_dropped_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_dropped_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_dropped_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -844,12 +730,6 @@ variable "iothub_orphaned_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_orphaned_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_orphaned_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -878,12 +758,6 @@ variable "iothub_invalid_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "iothub_invalid_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "iothub_invalid_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -913,8 +787,8 @@ variable "redis_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "redis_status_aggregator" {
|
||||
description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]"
|
||||
variable "redis_status_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -937,8 +811,8 @@ variable "redis_evictedkeys_limit_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "redis_evictedkeys_limit_aggregator" {
|
||||
description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]"
|
||||
variable "redis_evictedkeys_limit_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis evicted keys [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -971,8 +845,8 @@ variable "redis_percent_processor_time_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "redis_percent_processor_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]"
|
||||
variable "redis_percent_processor_time_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis processor [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1005,8 +879,8 @@ variable "redis_server_load_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "redis_server_load_rate_aggregator" {
|
||||
description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]"
|
||||
variable "redis_server_load_rate_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis server load [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1040,8 +914,8 @@ variable "servicebus_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "servicebus_status_aggregator" {
|
||||
description = "Monitor aggregator for Service Bus status [available values: min, max, sum or avg]"
|
||||
variable "servicebus_status_time_aggregator" {
|
||||
description = "Monitor aggregator for Service Bus status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
@ -1064,8 +938,8 @@ variable "sqldatabase_cpu_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "sqldatabase_cpu_aggregator" {
|
||||
description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]"
|
||||
variable "sqldatabase_cpu_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL CPU [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1098,8 +972,8 @@ variable "sqldatabase_diskspace_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "sqldatabase_diskspace_aggregator" {
|
||||
description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]"
|
||||
variable "sqldatabase_diskspace_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL disk space [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1132,8 +1006,8 @@ variable "sqldatabase_dtu_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "sqldatabase_dtu_aggregator" {
|
||||
description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]"
|
||||
variable "sqldatabase_dtu_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL DTU [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1166,12 +1040,6 @@ variable "sqldatabase_deadlock_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "sqldatabase_deadlock_aggregator" {
|
||||
description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "sqldatabase_deadlock_timeframe" {
|
||||
description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -1196,8 +1064,8 @@ variable "storage_availability_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_availability_aggregator" {
|
||||
description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]"
|
||||
variable "storage_availability_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage availability [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1230,8 +1098,8 @@ variable "storage_successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]"
|
||||
variable "storage_successful_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1264,8 +1132,8 @@ variable "storage_latency_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_latency_aggregator" {
|
||||
description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]"
|
||||
variable "storage_latency_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage latency [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
@ -1298,8 +1166,8 @@ variable "storage_timeout_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_timeout_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]"
|
||||
variable "storage_timeout_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage timeout [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1332,8 +1200,8 @@ variable "storage_network_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_network_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]"
|
||||
variable "storage_network_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage network errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1366,8 +1234,8 @@ variable "storage_throttling_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_throttling_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]"
|
||||
variable "storage_throttling_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1400,8 +1268,8 @@ variable "storage_server_other_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_server_other_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]"
|
||||
variable "storage_server_other_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1434,8 +1302,8 @@ variable "storage_client_other_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_client_other_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]"
|
||||
variable "storage_client_other_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1468,8 +1336,8 @@ variable "storage_authorization_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "storage_authorization_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]"
|
||||
variable "storage_authorization_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1503,8 +1371,8 @@ variable "streamanalytics_status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "streamanalytics_status_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]"
|
||||
variable "streamanalytics_status_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1527,8 +1395,8 @@ variable "streamanalytics_su_utilization_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "streamanalytics_su_utilization_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]"
|
||||
variable "streamanalytics_su_utilization_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1561,12 +1429,6 @@ variable "streamanalytics_failed_function_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "streamanalytics_failed_function_requests_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "streamanalytics_failed_function_requests_timeframe" {
|
||||
description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -1595,8 +1457,8 @@ variable "streamanalytics_conversion_errors_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "streamanalytics_conversion_errors_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]"
|
||||
variable "streamanalytics_conversion_errors_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -1629,8 +1491,8 @@ variable "streamanalytics_runtime_errors_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "streamanalytics_runtime_errors_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]"
|
||||
variable "streamanalytics_runtime_errors_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
|
||||
@ -39,86 +39,74 @@ Inputs
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| dropped_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| dropped_d2c_telemetry_egress_message | Custom message for IoT Hub dropped d2c telemetry monitor | string | `` | no |
|
||||
| dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no |
|
||||
| dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no |
|
||||
| dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `<map>` | no |
|
||||
| dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| environment | Architecture Environment | string | - | yes |
|
||||
| failed_c2d_methods_rate_aggregator | Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no |
|
||||
| failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `<map>` | no |
|
||||
| failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_c2d_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no |
|
||||
| failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `<map>` | no |
|
||||
| failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_c2d_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no |
|
||||
| failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `<map>` | no |
|
||||
| failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_d2c_twin_read_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no |
|
||||
| failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `<map>` | no |
|
||||
| failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_d2c_twin_update_rate_aggregator | Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no |
|
||||
| failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `<map>` | no |
|
||||
| failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_jobs_rate_aggregator | Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no |
|
||||
| failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `<map>` | no |
|
||||
| failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_listjobs_rate_aggregator | Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no |
|
||||
| failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `<map>` | no |
|
||||
| failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| failed_queryjobs_rate_aggregator | Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no |
|
||||
| failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `<map>` | no |
|
||||
| failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no |
|
||||
| failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no |
|
||||
| failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| filter_tags | Tags used for filtering | string | `*` | no |
|
||||
| invalid_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no |
|
||||
| invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no |
|
||||
| invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no |
|
||||
| invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `<map>` | no |
|
||||
| invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| message | Message sent when an alert is triggered | string | - | yes |
|
||||
| orphaned_d2c_telemetry_egress_aggregator | Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no |
|
||||
| orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no |
|
||||
| orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no |
|
||||
| orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `<map>` | no |
|
||||
| orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| status_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_message | Custom message for IoT Hub status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for IoT Hub status monitor | map | `<map>` | no |
|
||||
| status_time_aggregator | Monitor aggregator for IoT Hub status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| too_many_d2c_telemetry_ingress_nosent_aggregator | Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no |
|
||||
| too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `<map>` | no |
|
||||
| too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| total_devices_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no |
|
||||
| total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `<map>` | no |
|
||||
| total_devices_time_aggregator | Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -32,7 +32,7 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub status [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
@ -56,7 +56,7 @@ variable "total_devices_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "total_devices_aggregator" {
|
||||
variable "total_devices_time_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub total devices [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
@ -80,12 +80,6 @@ variable "too_many_d2c_telemetry_ingress_nosent_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "too_many_d2c_telemetry_ingress_nosent_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub unsent d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "too_many_d2c_telemetry_ingress_nosent_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -104,12 +98,6 @@ variable "failed_jobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_jobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_jobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -138,12 +126,6 @@ variable "failed_listjobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_listjobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed listjobs jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_listjobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -172,12 +154,6 @@ variable "failed_queryjobs_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_queryjobs_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed query jobs [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_queryjobs_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -206,12 +182,6 @@ variable "failed_c2d_methods_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_c2d_methods_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d method [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_c2d_methods_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -240,12 +210,6 @@ variable "failed_c2d_twin_read_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_c2d_twin_read_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d twin read [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_c2d_twin_read_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -274,12 +238,6 @@ variable "failed_c2d_twin_update_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_c2d_twin_update_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed c2d twin update [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_c2d_twin_update_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -308,12 +266,6 @@ variable "failed_d2c_twin_read_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_d2c_twin_read_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c twin read [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_d2c_twin_read_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -342,12 +294,6 @@ variable "failed_d2c_twin_update_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_d2c_twin_update_rate_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c twin update [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_d2c_twin_update_rate_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -376,12 +322,6 @@ variable "dropped_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "dropped_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub failed d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "dropped_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -410,12 +350,6 @@ variable "orphaned_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "orphaned_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub orphaned d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "orphaned_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -444,12 +378,6 @@ variable "invalid_d2c_telemetry_egress_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "invalid_d2c_telemetry_egress_aggregator" {
|
||||
description = "Monitor aggregator for IoT Hub invalid d2c telemetry [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "invalid_d2c_telemetry_egress_timeframe" {
|
||||
description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
|
||||
@ -3,10 +3,10 @@ resource "datadog_monitor" "too_many_jobs_failed" {
|
||||
message = "${coalesce(var.failed_jobs_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_jobs_rate_aggregator}(${var.failed_jobs_rate_timeframe}):(
|
||||
${var.failed_jobs_rate_aggregator}:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_jobs_rate_aggregator}:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_jobs_rate_aggregator}:azure.devices_iothubs.jobs.completed{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_jobs_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.jobs.completed{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_jobs_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -37,10 +37,10 @@ resource "datadog_monitor" "too_many_list_jobs_failed" {
|
||||
message = "${coalesce(var.failed_listjobs_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_listjobs_rate_aggregator}(${var.failed_listjobs_rate_timeframe}):(
|
||||
${var.failed_listjobs_rate_aggregator}:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
|
||||
( ${var.failed_listjobs_rate_aggregator}:azure.devices_iothubs.jobs.list_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
|
||||
${var.failed_listjobs_rate_aggregator}:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
|
||||
sum(${var.failed_listjobs_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.jobs.list_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
|
||||
avg:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
|
||||
) * 100 > ${var.failed_listjobs_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -71,10 +71,10 @@ resource "datadog_monitor" "too_many_query_jobs_failed" {
|
||||
message = "${coalesce(var.failed_queryjobs_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_queryjobs_rate_aggregator}(${var.failed_queryjobs_rate_timeframe}):(
|
||||
${var.failed_queryjobs_rate_aggregator}:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
|
||||
( ${var.failed_queryjobs_rate_aggregator}:azure.devices_iothubs.jobs.query_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
|
||||
${var.failed_queryjobs_rate_aggregator}:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
|
||||
sum(${var.failed_queryjobs_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.jobs.query_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
|
||||
avg:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
|
||||
) * 100 > ${var.failed_queryjobs_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -105,7 +105,9 @@ resource "datadog_monitor" "status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}):avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name} < 1
|
||||
${var.status_time_aggregator}(${var.status_timeframe}): (
|
||||
avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name}
|
||||
) < 1
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -130,7 +132,9 @@ resource "datadog_monitor" "total_devices" {
|
||||
message = "${coalesce(var.total_devices_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.total_devices_aggregator}(${var.total_devices_timeframe}):avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name} == 0
|
||||
${var.total_devices_time_aggregator}(${var.total_devices_timeframe}): (
|
||||
avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name}
|
||||
) == 0
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -155,10 +159,10 @@ resource "datadog_monitor" "too_many_c2d_methods_failed" {
|
||||
message = "${coalesce(var.failed_c2d_methods_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_c2d_methods_rate_aggregator}(${var.failed_c2d_methods_rate_timeframe}):(
|
||||
${var.failed_c2d_methods_rate_aggregator}:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_c2d_methods_rate_aggregator}:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_c2d_methods_rate_aggregator}:azure.devices_iothubs.c2d.methods.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_c2d_methods_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.c2d.methods.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_c2d_methods_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -189,10 +193,10 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" {
|
||||
message = "${coalesce(var.failed_c2d_twin_read_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_c2d_twin_read_rate_aggregator}(${var.failed_c2d_twin_read_rate_timeframe}):(
|
||||
${var.failed_c2d_twin_read_rate_aggregator}:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_c2d_twin_read_rate_aggregator}:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_c2d_twin_read_rate_aggregator}:azure.devices_iothubs.c2d.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_c2d_twin_read_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.c2d.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_c2d_twin_read_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -223,10 +227,10 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" {
|
||||
message = "${coalesce(var.failed_c2d_twin_update_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_c2d_twin_update_rate_aggregator}(${var.failed_c2d_twin_update_rate_timeframe}):(
|
||||
${var.failed_c2d_twin_update_rate_aggregator}:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_c2d_twin_update_rate_aggregator}:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_c2d_twin_update_rate_aggregator}:azure.devices_iothubs.c2d.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_c2d_twin_update_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.c2d.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_c2d_twin_update_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -257,10 +261,10 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" {
|
||||
message = "${coalesce(var.failed_d2c_twin_read_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_d2c_twin_read_rate_aggregator}(${var.failed_d2c_twin_read_rate_timeframe}):(
|
||||
${var.failed_d2c_twin_read_rate_aggregator}:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_d2c_twin_read_rate_aggregator}:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_d2c_twin_read_rate_aggregator}:azure.devices_iothubs.d2c.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_d2c_twin_read_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_d2c_twin_read_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -291,10 +295,10 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" {
|
||||
message = "${coalesce(var.failed_d2c_twin_update_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_d2c_twin_update_rate_aggregator}(${var.failed_d2c_twin_update_rate_timeframe}):(
|
||||
${var.failed_d2c_twin_update_rate_aggregator}:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( ${var.failed_d2c_twin_update_rate_aggregator}:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.failed_d2c_twin_update_rate_aggregator}:azure.devices_iothubs.d2c.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
sum(${var.failed_d2c_twin_update_rate_timeframe}):(
|
||||
avg:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
( avg:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
|
||||
) * 100 > ${var.failed_d2c_twin_update_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -325,12 +329,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" {
|
||||
message = "${coalesce(var.dropped_d2c_telemetry_egress_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.dropped_d2c_telemetry_egress_aggregator}(${var.dropped_d2c_telemetry_egress_timeframe}): (
|
||||
${var.dropped_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(${var.dropped_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.dropped_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.dropped_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.dropped_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
sum(${var.dropped_d2c_telemetry_egress_timeframe}): (
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
* 100
|
||||
) > ${var.dropped_d2c_telemetry_egress_rate_threshold_critical}
|
||||
EOF
|
||||
@ -362,12 +366,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" {
|
||||
message = "${coalesce(var.orphaned_d2c_telemetry_egress_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.orphaned_d2c_telemetry_egress_aggregator}(${var.orphaned_d2c_telemetry_egress_timeframe}): (
|
||||
${var.orphaned_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(${var.orphaned_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.orphaned_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.orphaned_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.orphaned_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
sum(${var.orphaned_d2c_telemetry_egress_timeframe}): (
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
* 100
|
||||
) > ${var.orphaned_d2c_telemetry_egress_rate_threshold_critical}
|
||||
EOF
|
||||
@ -399,12 +403,12 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" {
|
||||
message = "${coalesce(var.invalid_d2c_telemetry_egress_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.invalid_d2c_telemetry_egress_aggregator}(${var.invalid_d2c_telemetry_egress_timeframe}): (
|
||||
${var.invalid_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(${var.invalid_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.invalid_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.invalid_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
${var.invalid_d2c_telemetry_egress_aggregator}:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
sum(${var.invalid_d2c_telemetry_egress_timeframe}): (
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() /
|
||||
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() +
|
||||
avg:azure.devices_iothubs.d2c.telemetry.egress.success{${var.filter_tags}} by {resource_group,region,name}.as_count())
|
||||
* 100
|
||||
) > ${var.invalid_d2c_telemetry_egress_rate_threshold_critical}
|
||||
EOF
|
||||
@ -436,9 +440,9 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" {
|
||||
message = "${coalesce(var.too_many_d2c_telemetry_ingress_nosent_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.too_many_d2c_telemetry_ingress_nosent_aggregator}(${var.too_many_d2c_telemetry_ingress_nosent_timeframe}): (
|
||||
${var.too_many_d2c_telemetry_ingress_nosent_aggregator}:azure.devices_iothubs.d2c.telemetry.ingress.all_protocol{${var.filter_tags}} by {resource_group,region,name}.as_count() -
|
||||
${var.too_many_d2c_telemetry_ingress_nosent_aggregator}:azure.devices_iothubs.d2c.telemetry.ingress.success{${var.filter_tags}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.too_many_d2c_telemetry_ingress_nosent_timeframe}): (
|
||||
avg:azure.devices_iothubs.d2c.telemetry.ingress.all_protocol{${var.filter_tags}} by {resource_group,region,name}.as_count() -
|
||||
avg:azure.devices_iothubs.d2c.telemetry.ingress.success{${var.filter_tags}} by {resource_group,region,name}.as_count()
|
||||
) > 0
|
||||
EOF
|
||||
|
||||
|
||||
@ -10,29 +10,25 @@ module "apimanagement" {
|
||||
|
||||
status_silenced = "${var.apimanagement_status_silenced}"
|
||||
status_message = "${var.apimanagement_status_message}"
|
||||
status_aggregator = "${var.apimanagement_status_aggregator}"
|
||||
status_time_aggregator = "${var.apimanagement_status_time_aggregator}"
|
||||
status_timeframe = "${var.apimanagement_status_timeframe}"
|
||||
failed_requests_silenced = "${var.apimanagement_failed_requests_silenced}"
|
||||
failed_requests_message = "${var.apimanagement_failed_requests_message}"
|
||||
failed_requests_aggregator = "${var.apimanagement_failed_requests_aggregator}"
|
||||
failed_requests_timeframe = "${var.apimanagement_failed_requests_timeframe}"
|
||||
failed_requests_threshold_critical = "${var.apimanagement_failed_requests_threshold_critical}"
|
||||
failed_requests_threshold_warning = "${var.apimanagement_failed_requests_threshold_warning}"
|
||||
other_requests_silenced = "${var.apimanagement_other_requests_silenced}"
|
||||
other_requests_message = "${var.apimanagement_other_requests_message}"
|
||||
other_requests_aggregator = "${var.apimanagement_other_requests_aggregator}"
|
||||
other_requests_timeframe = "${var.apimanagement_other_requests_timeframe}"
|
||||
other_requests_threshold_critical = "${var.apimanagement_other_requests_threshold_critical}"
|
||||
other_requests_threshold_warning = "${var.apimanagement_other_requests_threshold_warning}"
|
||||
successful_requests_silenced = "${var.apimanagement_successful_requests_silenced}"
|
||||
successful_requests_message = "${var.apimanagement_successful_requests_message}"
|
||||
successful_requests_aggregator = "${var.apimanagement_successful_requests_aggregator}"
|
||||
successful_requests_timeframe = "${var.apimanagement_successful_requests_timeframe}"
|
||||
successful_requests_threshold_critical = "${var.apimanagement_successful_requests_threshold_critical}"
|
||||
successful_requests_threshold_warning = "${var.apimanagement_successful_requests_threshold_warning}"
|
||||
unauthorized_requests_silenced = "${var.apimanagement_unauthorized_requests_silenced}"
|
||||
unauthorized_requests_message = "${var.apimanagement_unauthorized_requests_message}"
|
||||
unauthorized_requests_aggregator = "${var.apimanagement_unauthorized_requests_aggregator}"
|
||||
unauthorized_requests_timeframe = "${var.apimanagement_unauthorized_requests_timeframe}"
|
||||
unauthorized_requests_threshold_critical = "${var.apimanagement_unauthorized_requests_threshold_critical}"
|
||||
unauthorized_requests_threshold_warning = "${var.apimanagement_unauthorized_requests_threshold_warning}"
|
||||
@ -50,31 +46,28 @@ module "appservices" {
|
||||
|
||||
http_successful_requests_silenced = "${var.appservices_http_successful_requests_silenced}"
|
||||
http_successful_requests_message = "${var.appservices_http_successful_requests_message}"
|
||||
http_successful_requests_aggregator = "${var.appservices_http_successful_requests_aggregator}"
|
||||
http_successful_requests_timeframe = "${var.appservices_http_successful_requests_timeframe}"
|
||||
http_successful_requests_threshold_critical = "${var.appservices_http_successful_requests_threshold_critical}"
|
||||
http_successful_requests_threshold_warning = "${var.appservices_http_successful_requests_threshold_warning}"
|
||||
http_5xx_requests_silenced = "${var.appservices_http_5xx_requests_silenced}"
|
||||
http_5xx_requests_message = "${var.appservices_http_5xx_requests_message}"
|
||||
http_5xx_requests_aggregator = "${var.appservices_http_5xx_requests_aggregator}"
|
||||
http_5xx_requests_timeframe = "${var.appservices_http_5xx_requests_timeframe}"
|
||||
http_5xx_requests_threshold_critical = "${var.appservices_http_5xx_requests_threshold_critical}"
|
||||
http_5xx_requests_threshold_warning = "${var.appservices_http_5xx_requests_threshold_warning}"
|
||||
http_4xx_requests_silenced = "${var.appservices_http_4xx_requests_silenced}"
|
||||
http_4xx_requests_message = "${var.appservices_http_4xx_requests_message}"
|
||||
http_4xx_requests_aggregator = "${var.appservices_http_4xx_requests_aggregator}"
|
||||
http_4xx_requests_timeframe = "${var.appservices_http_4xx_requests_timeframe}"
|
||||
http_4xx_requests_threshold_critical = "${var.appservices_http_4xx_requests_threshold_critical}"
|
||||
http_4xx_requests_threshold_warning = "${var.appservices_http_4xx_requests_threshold_warning}"
|
||||
memory_usage_silenced = "${var.appservices_memory_usage_silenced}"
|
||||
memory_usage_message = "${var.appservices_memory_usage_message}"
|
||||
memory_usage_aggregator = "${var.appservices_memory_usage_aggregator}"
|
||||
memory_usage_time_aggregator = "${var.appservices_memory_usage_time_aggregator}"
|
||||
memory_usage_timeframe = "${var.appservices_memory_usage_timeframe}"
|
||||
memory_usage_threshold_critical = "${var.appservices_memory_usage_threshold_critical}"
|
||||
memory_usage_threshold_warning = "${var.appservices_memory_usage_threshold_warning}"
|
||||
response_time_silenced = "${var.appservices_response_time_silenced}"
|
||||
response_time_message = "${var.appservices_response_time_message}"
|
||||
response_time_aggregator = "${var.appservices_response_time_aggregator}"
|
||||
response_time_time_aggregator = "${var.appservices_response_time_time_aggregator}"
|
||||
response_time_timeframe = "${var.appservices_response_time_timeframe}"
|
||||
response_time_threshold_critical = "${var.appservices_response_time_threshold_critical}"
|
||||
response_time_threshold_warning = "${var.appservices_response_time_threshold_warning}"
|
||||
@ -92,17 +85,15 @@ module "eventhub" {
|
||||
|
||||
status_silenced = "${var.eventhub_status_silenced}"
|
||||
status_message = "${var.eventhub_status_message}"
|
||||
status_aggregator = "${var.eventhub_status_aggregator}"
|
||||
status_time_aggregator = "${var.eventhub_status_time_aggregator}"
|
||||
status_timeframe = "${var.eventhub_status_timeframe}"
|
||||
errors_rate_silenced = "${var.eventhub_errors_rate_silenced}"
|
||||
errors_rate_message = "${var.eventhub_errors_rate_message}"
|
||||
errors_rate_aggregator = "${var.eventhub_errors_rate_aggregator}"
|
||||
errors_rate_timeframe = "${var.eventhub_errors_rate_timeframe}"
|
||||
errors_rate_thresold_critical = "${var.eventhub_errors_rate_thresold_critical}"
|
||||
errors_rate_thresold_warning = "${var.eventhub_errors_rate_thresold_warning}"
|
||||
failed_requests_rate_silenced = "${var.eventhub_failed_requests_rate_silenced}"
|
||||
failed_requests_rate_message = "${var.eventhub_failed_requests_rate_message}"
|
||||
failed_requests_rate_aggregator = "${var.eventhub_failed_requests_rate_aggregator}"
|
||||
failed_requests_rate_timeframe = "${var.eventhub_failed_requests_rate_timeframe}"
|
||||
failed_requests_rate_thresold_critical = "${var.eventhub_failed_requests_rate_thresold_critical}"
|
||||
failed_requests_rate_thresold_warning = "${var.eventhub_failed_requests_rate_thresold_warning}"
|
||||
@ -119,79 +110,67 @@ module "iothub" {
|
||||
|
||||
status_silenced = "${var.iothub_status_silenced}"
|
||||
status_message = "${var.iothub_status_message}"
|
||||
status_aggregator = "${var.iothub_status_aggregator}"
|
||||
status_time_aggregator = "${var.iothub_status_time_aggregator}"
|
||||
status_timeframe = "${var.iothub_status_timeframe}"
|
||||
total_devices_silenced = "${var.iothub_total_devices_silenced}"
|
||||
total_devices_message = "${var.iothub_total_devices_message}"
|
||||
total_devices_aggregator = "${var.iothub_total_devices_aggregator}"
|
||||
total_devices_time_aggregator = "${var.iothub_total_devices_time_aggregator}"
|
||||
total_devices_timeframe = "${var.iothub_total_devices_timeframe}"
|
||||
too_many_d2c_telemetry_ingress_nosent_silenced = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_silenced}"
|
||||
too_many_d2c_telemetry_ingress_nosent_message = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_message}"
|
||||
too_many_d2c_telemetry_ingress_nosent_aggregator = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_aggregator}"
|
||||
too_many_d2c_telemetry_ingress_nosent_timeframe = "${var.iothub_too_many_d2c_telemetry_ingress_nosent_timeframe}"
|
||||
dropped_d2c_telemetry_egress_silenced = "${var.iothub_dropped_d2c_telemetry_egress_silenced}"
|
||||
dropped_d2c_telemetry_egress_message = "${var.iothub_dropped_d2c_telemetry_egress_message}"
|
||||
dropped_d2c_telemetry_egress_aggregator = "${var.iothub_dropped_d2c_telemetry_egress_aggregator}"
|
||||
dropped_d2c_telemetry_egress_timeframe = "${var.iothub_dropped_d2c_telemetry_egress_timeframe}"
|
||||
dropped_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_critical}"
|
||||
dropped_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_dropped_d2c_telemetry_egress_rate_threshold_warning}"
|
||||
failed_c2d_methods_rate_silenced = "${var.iothub_failed_c2d_methods_rate_silenced}"
|
||||
failed_c2d_methods_rate_message = "${var.iothub_failed_c2d_methods_rate_message}"
|
||||
failed_c2d_methods_rate_aggregator = "${var.iothub_failed_c2d_methods_rate_aggregator}"
|
||||
failed_c2d_methods_rate_timeframe = "${var.iothub_failed_c2d_methods_rate_timeframe}"
|
||||
failed_c2d_methods_rate_threshold_critical = "${var.iothub_failed_c2d_methods_rate_threshold_critical}"
|
||||
failed_c2d_methods_rate_threshold_warning = "${var.iothub_failed_c2d_methods_rate_threshold_warning}"
|
||||
failed_c2d_twin_read_rate_silenced = "${var.iothub_failed_c2d_twin_read_rate_silenced}"
|
||||
failed_c2d_twin_read_rate_message = "${var.iothub_failed_c2d_twin_read_rate_message}"
|
||||
failed_c2d_twin_read_rate_aggregator = "${var.iothub_failed_c2d_twin_read_rate_aggregator}"
|
||||
failed_c2d_twin_read_rate_timeframe = "${var.iothub_failed_c2d_twin_read_rate_timeframe}"
|
||||
failed_c2d_twin_read_rate_threshold_critical = "${var.iothub_failed_c2d_twin_read_rate_threshold_critical}"
|
||||
failed_c2d_twin_read_rate_threshold_warning = "${var.iothub_failed_c2d_twin_read_rate_threshold_warning}"
|
||||
failed_c2d_twin_update_rate_silenced = "${var.iothub_failed_c2d_twin_update_rate_silenced}"
|
||||
failed_c2d_twin_update_rate_message = "${var.iothub_failed_c2d_twin_update_rate_message}"
|
||||
failed_c2d_twin_update_rate_aggregator = "${var.iothub_failed_c2d_twin_update_rate_aggregator}"
|
||||
failed_c2d_twin_update_rate_timeframe = "${var.iothub_failed_c2d_twin_update_rate_timeframe}"
|
||||
failed_c2d_twin_update_rate_threshold_critical = "${var.iothub_failed_c2d_twin_update_rate_threshold_critical}"
|
||||
failed_c2d_twin_update_rate_threshold_warning = "${var.iothub_failed_c2d_twin_update_rate_threshold_warning}"
|
||||
failed_d2c_twin_read_rate_silenced = "${var.iothub_failed_d2c_twin_read_rate_silenced}"
|
||||
failed_d2c_twin_read_rate_message = "${var.iothub_failed_d2c_twin_read_rate_message}"
|
||||
failed_d2c_twin_read_rate_aggregator = "${var.iothub_failed_d2c_twin_read_rate_aggregator}"
|
||||
failed_d2c_twin_read_rate_timeframe = "${var.iothub_failed_d2c_twin_read_rate_timeframe}"
|
||||
failed_d2c_twin_read_rate_threshold_critical = "${var.iothub_failed_d2c_twin_read_rate_threshold_critical}"
|
||||
failed_d2c_twin_read_rate_threshold_warning = "${var.iothub_failed_d2c_twin_read_rate_threshold_warning}"
|
||||
failed_d2c_twin_update_rate_silenced = "${var.iothub_failed_d2c_twin_update_rate_silenced}"
|
||||
failed_d2c_twin_update_rate_message = "${var.iothub_failed_d2c_twin_update_rate_message}"
|
||||
failed_d2c_twin_update_rate_aggregator = "${var.iothub_failed_d2c_twin_update_rate_aggregator}"
|
||||
failed_d2c_twin_update_rate_timeframe = "${var.iothub_failed_d2c_twin_update_rate_timeframe}"
|
||||
failed_d2c_twin_update_rate_threshold_critical = "${var.iothub_failed_d2c_twin_update_rate_threshold_critical}"
|
||||
failed_d2c_twin_update_rate_threshold_warning = "${var.iothub_failed_d2c_twin_update_rate_threshold_warning}"
|
||||
failed_jobs_rate_silenced = "${var.iothub_failed_jobs_rate_silenced}"
|
||||
failed_jobs_rate_message = "${var.iothub_failed_jobs_rate_message}"
|
||||
failed_jobs_rate_aggregator = "${var.iothub_failed_jobs_rate_aggregator}"
|
||||
failed_jobs_rate_timeframe = "${var.iothub_failed_jobs_rate_timeframe}"
|
||||
failed_jobs_rate_threshold_critical = "${var.iothub_failed_jobs_rate_threshold_critical}"
|
||||
failed_jobs_rate_threshold_warning = "${var.iothub_failed_jobs_rate_threshold_warning}"
|
||||
failed_listjobs_rate_silenced = "${var.iothub_failed_listjobs_rate_silenced}"
|
||||
failed_listjobs_rate_message = "${var.iothub_failed_listjobs_rate_message}"
|
||||
failed_listjobs_rate_aggregator = "${var.iothub_failed_listjobs_rate_aggregator}"
|
||||
failed_listjobs_rate_timeframe = "${var.iothub_failed_listjobs_rate_timeframe}"
|
||||
failed_listjobs_rate_threshold_critical = "${var.iothub_failed_listjobs_rate_threshold_critical}"
|
||||
failed_listjobs_rate_threshold_warning = "${var.iothub_failed_listjobs_rate_threshold_warning}"
|
||||
failed_queryjobs_rate_silenced = "${var.iothub_failed_queryjobs_rate_silenced}"
|
||||
failed_queryjobs_rate_message = "${var.iothub_failed_queryjobs_rate_message}"
|
||||
failed_queryjobs_rate_aggregator = "${var.iothub_failed_queryjobs_rate_aggregator}"
|
||||
failed_queryjobs_rate_timeframe = "${var.iothub_failed_queryjobs_rate_timeframe}"
|
||||
failed_queryjobs_rate_threshold_critical = "${var.iothub_failed_queryjobs_rate_threshold_critical}"
|
||||
failed_queryjobs_rate_threshold_warning = "${var.iothub_failed_queryjobs_rate_threshold_warning}"
|
||||
invalid_d2c_telemetry_egress_silenced = "${var.iothub_invalid_d2c_telemetry_egress_silenced}"
|
||||
invalid_d2c_telemetry_egress_message = "${var.iothub_invalid_d2c_telemetry_egress_message}"
|
||||
invalid_d2c_telemetry_egress_aggregator = "${var.iothub_invalid_d2c_telemetry_egress_aggregator}"
|
||||
invalid_d2c_telemetry_egress_timeframe = "${var.iothub_invalid_d2c_telemetry_egress_timeframe}"
|
||||
invalid_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_critical}"
|
||||
invalid_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_invalid_d2c_telemetry_egress_rate_threshold_warning}"
|
||||
orphaned_d2c_telemetry_egress_silenced = "${var.iothub_orphaned_d2c_telemetry_egress_silenced}"
|
||||
orphaned_d2c_telemetry_egress_message = "${var.iothub_orphaned_d2c_telemetry_egress_message}"
|
||||
orphaned_d2c_telemetry_egress_aggregator = "${var.iothub_orphaned_d2c_telemetry_egress_aggregator}"
|
||||
orphaned_d2c_telemetry_egress_timeframe = "${var.iothub_orphaned_d2c_telemetry_egress_timeframe}"
|
||||
orphaned_d2c_telemetry_egress_rate_threshold_critical = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_critical}"
|
||||
orphaned_d2c_telemetry_egress_rate_threshold_warning = "${var.iothub_orphaned_d2c_telemetry_egress_rate_threshold_warning}"
|
||||
@ -209,23 +188,23 @@ module "redis" {
|
||||
|
||||
status_silenced = "${var.redis_status_silenced}"
|
||||
status_message = "${var.redis_status_message}"
|
||||
status_aggregator = "${var.redis_status_aggregator}"
|
||||
status_time_aggregator = "${var.redis_status_time_aggregator}"
|
||||
status_timeframe = "${var.redis_status_timeframe}"
|
||||
evictedkeys_limit_silenced = "${var.redis_evictedkeys_limit_silenced}"
|
||||
evictedkeys_limit_message = "${var.redis_evictedkeys_limit_message}"
|
||||
evictedkeys_limit_aggregator = "${var.redis_evictedkeys_limit_aggregator}"
|
||||
evictedkeys_limit_time_aggregator = "${var.redis_evictedkeys_limit_time_aggregator}"
|
||||
evictedkeys_limit_timeframe = "${var.redis_evictedkeys_limit_timeframe}"
|
||||
evictedkeys_limit_threshold_critical = "${var.redis_evictedkeys_limit_threshold_critical}"
|
||||
evictedkeys_limit_threshold_warning = "${var.redis_evictedkeys_limit_threshold_warning}"
|
||||
percent_processor_time_silenced = "${var.redis_percent_processor_time_silenced}"
|
||||
percent_processor_time_message = "${var.redis_percent_processor_time_message}"
|
||||
percent_processor_time_aggregator = "${var.redis_percent_processor_time_aggregator}"
|
||||
percent_processor_time_time_aggregator = "${var.redis_percent_processor_time_time_aggregator}"
|
||||
percent_processor_time_timeframe = "${var.redis_percent_processor_time_timeframe}"
|
||||
percent_processor_time_threshold_critical = "${var.redis_percent_processor_time_threshold_critical}"
|
||||
percent_processor_time_threshold_warning = "${var.redis_percent_processor_time_threshold_warning}"
|
||||
server_load_rate_silenced = "${var.redis_server_load_rate_silenced}"
|
||||
server_load_rate_message = "${var.redis_server_load_rate_message}"
|
||||
server_load_rate_aggregator = "${var.redis_server_load_rate_aggregator}"
|
||||
server_load_rate_time_aggregator = "${var.redis_server_load_rate_time_aggregator}"
|
||||
server_load_rate_timeframe = "${var.redis_server_load_rate_timeframe}"
|
||||
server_load_rate_threshold_critical = "${var.redis_server_load_rate_threshold_critical}"
|
||||
server_load_rate_threshold_warning = "${var.redis_server_load_rate_threshold_warning}"
|
||||
@ -244,7 +223,7 @@ module "servicebus" {
|
||||
status_silenced = "${var.servicebus_status_silenced}"
|
||||
status_message = "${var.servicebus_status_message}"
|
||||
status_timeframe = "${var.servicebus_status_timeframe}"
|
||||
status_timeframe_aggregator = "${var.servicebus_status_aggregator}"
|
||||
status_timeframe_time_aggregator = "${var.servicebus_status_time_aggregator}"
|
||||
}
|
||||
|
||||
module "sqldatabase" {
|
||||
@ -259,24 +238,23 @@ module "sqldatabase" {
|
||||
|
||||
cpu_silenced = "${var.sqldatabase_cpu_silenced}"
|
||||
cpu_message = "${var.sqldatabase_cpu_message}"
|
||||
cpu_aggregator = "${var.sqldatabase_cpu_aggregator}"
|
||||
cpu_time_aggregator = "${var.sqldatabase_cpu_time_aggregator}"
|
||||
cpu_timeframe = "${var.sqldatabase_cpu_timeframe}"
|
||||
cpu_threshold_critical = "${var.sqldatabase_cpu_threshold_critical}"
|
||||
cpu_threshold_warning = "${var.sqldatabase_cpu_threshold_warning}"
|
||||
deadlock_silenced = "${var.sqldatabase_deadlock_silenced}"
|
||||
deadlock_message = "${var.sqldatabase_deadlock_message}"
|
||||
deadlock_aggregator = "${var.sqldatabase_deadlock_aggregator}"
|
||||
deadlock_timeframe = "${var.sqldatabase_deadlock_timeframe}"
|
||||
deadlock_threshold_critical = "${var.sqldatabase_deadlock_threshold_critical}"
|
||||
diskspace_silenced = "${var.sqldatabase_diskspace_silenced}"
|
||||
diskspace_message = "${var.sqldatabase_diskspace_message}"
|
||||
diskspace_aggregator = "${var.sqldatabase_diskspace_aggregator}"
|
||||
diskspace_time_aggregator = "${var.sqldatabase_diskspace_time_aggregator}"
|
||||
diskspace_timeframe = "${var.sqldatabase_diskspace_timeframe}"
|
||||
diskspace_threshold_critical = "${var.sqldatabase_diskspace_threshold_critical}"
|
||||
diskspace_threshold_warning = "${var.sqldatabase_diskspace_threshold_warning}"
|
||||
dtu_silenced = "${var.sqldatabase_dtu_silenced}"
|
||||
dtu_message = "${var.sqldatabase_dtu_message}"
|
||||
dtu_aggregator = "${var.sqldatabase_dtu_aggregator}"
|
||||
dtu_time_aggregator = "${var.sqldatabase_dtu_time_aggregator}"
|
||||
dtu_timeframe = "${var.sqldatabase_dtu_timeframe}"
|
||||
dtu_threshold_critical = "${var.sqldatabase_dtu_threshold_critical}"
|
||||
dtu_threshold_warning = "${var.sqldatabase_dtu_threshold_warning}"
|
||||
@ -294,55 +272,55 @@ module "storage" {
|
||||
|
||||
authorization_error_requests_silenced = "${var.storage_authorization_error_requests_silenced}"
|
||||
authorization_error_requests_message = "${var.storage_authorization_error_requests_message}"
|
||||
authorization_error_requests_aggregator = "${var.storage_authorization_error_requests_aggregator}"
|
||||
authorization_error_requests_time_aggregator = "${var.storage_authorization_error_requests_time_aggregator}"
|
||||
authorization_error_requests_timeframe = "${var.storage_authorization_error_requests_timeframe}"
|
||||
authorization_error_requests_threshold_critical = "${var.storage_authorization_error_requests_threshold_critical}"
|
||||
authorization_error_requests_threshold_warning = "${var.storage_authorization_error_requests_threshold_warning}"
|
||||
availability_silenced = "${var.storage_availability_silenced}"
|
||||
availability_message = "${var.storage_availability_message}"
|
||||
availability_aggregator = "${var.storage_availability_aggregator}"
|
||||
availability_time_aggregator = "${var.storage_availability_time_aggregator}"
|
||||
availability_timeframe = "${var.storage_availability_timeframe}"
|
||||
availability_threshold_critical = "${var.storage_availability_threshold_critical}"
|
||||
availability_threshold_warning = "${var.storage_availability_threshold_warning}"
|
||||
client_other_error_requests_silenced = "${var.storage_client_other_error_requests_silenced}"
|
||||
client_other_error_requests_message = "${var.storage_client_other_error_requests_message}"
|
||||
client_other_error_requests_aggregator = "${var.storage_client_other_error_requests_aggregator}"
|
||||
client_other_error_requests_time_aggregator = "${var.storage_client_other_error_requests_time_aggregator}"
|
||||
client_other_error_requests_timeframe = "${var.storage_client_other_error_requests_timeframe}"
|
||||
client_other_error_requests_threshold_critical = "${var.storage_client_other_error_requests_threshold_critical}"
|
||||
client_other_error_requests_threshold_warning = "${var.storage_client_other_error_requests_threshold_warning}"
|
||||
latency_silenced = "${var.storage_latency_silenced}"
|
||||
latency_message = "${var.storage_latency_message}"
|
||||
latency_aggregator = "${var.storage_latency_aggregator}"
|
||||
latency_time_aggregator = "${var.storage_latency_time_aggregator}"
|
||||
latency_timeframe = "${var.storage_latency_timeframe}"
|
||||
latency_threshold_critical = "${var.storage_latency_threshold_critical}"
|
||||
latency_threshold_warning = "${var.storage_latency_threshold_warning}"
|
||||
network_error_requests_silenced = "${var.storage_network_error_requests_silenced}"
|
||||
network_error_requests_message = "${var.storage_network_error_requests_message}"
|
||||
network_error_requests_aggregator = "${var.storage_network_error_requests_aggregator}"
|
||||
network_error_requests_time_aggregator = "${var.storage_network_error_requests_time_aggregator}"
|
||||
network_error_requests_timeframe = "${var.storage_network_error_requests_timeframe}"
|
||||
network_error_requests_threshold_critical = "${var.storage_network_error_requests_threshold_critical}"
|
||||
network_error_requests_threshold_warning = "${var.storage_network_error_requests_threshold_warning}"
|
||||
server_other_error_requests_silenced = "${var.storage_server_other_error_requests_silenced}"
|
||||
server_other_error_requests_message = "${var.storage_server_other_error_requests_message}"
|
||||
server_other_error_requests_aggregator = "${var.storage_server_other_error_requests_aggregator}"
|
||||
server_other_error_requests_time_aggregator = "${var.storage_server_other_error_requests_time_aggregator}"
|
||||
server_other_error_requests_timeframe = "${var.storage_server_other_error_requests_timeframe}"
|
||||
server_other_error_requests_threshold_critical = "${var.storage_server_other_error_requests_threshold_critical}"
|
||||
server_other_error_requests_threshold_warning = "${var.storage_server_other_error_requests_threshold_warning}"
|
||||
successful_requests_silenced = "${var.storage_successful_requests_silenced}"
|
||||
successful_requests_message = "${var.storage_successful_requests_message}"
|
||||
successful_requests_aggregator = "${var.storage_successful_requests_aggregator}"
|
||||
successful_requests_time_aggregator = "${var.storage_successful_requests_time_aggregator}"
|
||||
successful_requests_timeframe = "${var.storage_successful_requests_timeframe}"
|
||||
successful_requests_threshold_critical = "${var.storage_successful_requests_threshold_critical}"
|
||||
successful_requests_threshold_warning = "${var.storage_successful_requests_threshold_warning}"
|
||||
throttling_error_requests_silenced = "${var.storage_throttling_error_requests_silenced}"
|
||||
throttling_error_requests_message = "${var.storage_throttling_error_requests_message}"
|
||||
throttling_error_requests_aggregator = "${var.storage_throttling_error_requests_aggregator}"
|
||||
throttling_error_requests_time_aggregator = "${var.storage_throttling_error_requests_time_aggregator}"
|
||||
throttling_error_requests_timeframe = "${var.storage_throttling_error_requests_timeframe}"
|
||||
throttling_error_requests_threshold_critical = "${var.storage_throttling_error_requests_threshold_critical}"
|
||||
throttling_error_requests_threshold_warning = "${var.storage_throttling_error_requests_threshold_warning}"
|
||||
timeout_error_requests_silenced = "${var.storage_timeout_error_requests_silenced}"
|
||||
timeout_error_requests_message = "${var.storage_timeout_error_requests_message}"
|
||||
timeout_error_requests_aggregator = "${var.storage_timeout_error_requests_aggregator}"
|
||||
timeout_error_requests_time_aggregator = "${var.storage_timeout_error_requests_time_aggregator}"
|
||||
timeout_error_requests_timeframe = "${var.storage_timeout_error_requests_timeframe}"
|
||||
timeout_error_requests_threshold_critical = "${var.storage_timeout_error_requests_threshold_critical}"
|
||||
timeout_error_requests_threshold_warning = "${var.storage_timeout_error_requests_threshold_warning}"
|
||||
@ -360,25 +338,24 @@ module "streamanalytics" {
|
||||
|
||||
conversion_errors_silenced = "${var.streamanalytics_conversion_errors_silenced}"
|
||||
conversion_errors_message = "${var.streamanalytics_conversion_errors_message}"
|
||||
conversion_errors_aggregator = "${var.streamanalytics_conversion_errors_aggregator}"
|
||||
conversion_errors_time_aggregator = "${var.streamanalytics_conversion_errors_time_aggregator}"
|
||||
conversion_errors_timeframe = "${var.streamanalytics_conversion_errors_timeframe}"
|
||||
conversion_errors_threshold_critical = "${var.streamanalytics_conversion_errors_threshold_critical}"
|
||||
conversion_errors_threshold_warning = "${var.streamanalytics_conversion_errors_threshold_warning}"
|
||||
failed_function_requests_silenced = "${var.streamanalytics_failed_function_requests_silenced}"
|
||||
failed_function_requests_message = "${var.streamanalytics_failed_function_requests_message}"
|
||||
failed_function_requests_aggregator = "${var.streamanalytics_failed_function_requests_aggregator}"
|
||||
failed_function_requests_timeframe = "${var.streamanalytics_failed_function_requests_timeframe}"
|
||||
failed_function_requests_threshold_critical = "${var.streamanalytics_failed_function_requests_threshold_critical}"
|
||||
failed_function_requests_threshold_warning = "${var.streamanalytics_failed_function_requests_threshold_warning}"
|
||||
runtime_errors_silenced = "${var.streamanalytics_runtime_errors_silenced}"
|
||||
runtime_errors_message = "${var.streamanalytics_runtime_errors_message}"
|
||||
runtime_errors_aggregator = "${var.streamanalytics_runtime_errors_aggregator}"
|
||||
runtime_errors_time_aggregator = "${var.streamanalytics_runtime_errors_time_aggregator}"
|
||||
runtime_errors_timeframe = "${var.streamanalytics_runtime_errors_timeframe}"
|
||||
runtime_errors_threshold_critical = "${var.streamanalytics_runtime_errors_threshold_critical}"
|
||||
runtime_errors_threshold_warning = "${var.streamanalytics_runtime_errors_threshold_warning}"
|
||||
su_utilization_silenced = "${var.streamanalytics_su_utilization_silenced}"
|
||||
su_utilization_message = "${var.streamanalytics_su_utilization_message}"
|
||||
su_utilization_aggregator = "${var.streamanalytics_su_utilization_aggregator}"
|
||||
su_utilization_time_aggregator = "${var.streamanalytics_su_utilization_time_aggregator}"
|
||||
su_utilization_timeframe = "${var.streamanalytics_su_utilization_timeframe}"
|
||||
su_utilization_threshold_critical = "${var.streamanalytics_su_utilization_threshold_critical}"
|
||||
su_utilization_threshold_warning = "${var.streamanalytics_su_utilization_threshold_warning}"
|
||||
|
||||
@ -29,30 +29,30 @@ Inputs
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| evictedkeys_limit_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| evictedkeys_limit_message | Custom message for Redis evicted keys monitor | string | `` | no |
|
||||
| evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `<map>` | no |
|
||||
| evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no |
|
||||
| evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no |
|
||||
| evictedkeys_limit_time_aggregator | Monitor aggregator for Redis evicted keys [available values: min, max or avg] | string | `avg` | no |
|
||||
| evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| message | Message sent when a Redis monitor is triggered | string | - | yes |
|
||||
| percent_processor_time_aggregator | Monitor aggregator for Redis processor [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| percent_processor_time_message | Custom message for Redis processor monitor | string | `` | no |
|
||||
| percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `<map>` | no |
|
||||
| percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no |
|
||||
| percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no |
|
||||
| percent_processor_time_time_aggregator | Monitor aggregator for Redis processor [available values: min, max or avg] | string | `avg` | no |
|
||||
| percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| server_load_rate_aggregator | Monitor aggregator for Redis server load [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| server_load_rate_message | Custom message for Redis server load monitor | string | `` | no |
|
||||
| server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `<map>` | no |
|
||||
| server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no |
|
||||
| server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no |
|
||||
| server_load_rate_time_aggregator | Monitor aggregator for Redis server load [available values: min, max or avg] | string | `avg` | no |
|
||||
| server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| status_aggregator | Monitor aggregator for Redis status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_message | Custom message for Redis status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for Redis status monitor | map | `<map>` | no |
|
||||
| status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `avg` | no |
|
||||
| status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -37,8 +37,8 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
description = "Monitor aggregator for Redis status [available values: min, max, sum or avg]"
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -61,8 +61,8 @@ variable "evictedkeys_limit_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "evictedkeys_limit_aggregator" {
|
||||
description = "Monitor aggregator for Redis evicted keys [available values: min, max, sum or avg]"
|
||||
variable "evictedkeys_limit_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis evicted keys [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -95,8 +95,8 @@ variable "percent_processor_time_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "percent_processor_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis processor [available values: min, max, sum or avg]"
|
||||
variable "percent_processor_time_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis processor [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -129,8 +129,8 @@ variable "server_load_rate_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "server_load_rate_aggregator" {
|
||||
description = "Monitor aggregator for Redis server load [available values: min, max, sum or avg]"
|
||||
variable "server_load_rate_time_aggregator" {
|
||||
description = "Monitor aggregator for Redis server load [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
|
||||
@ -11,7 +11,9 @@ resource "datadog_monitor" "status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}):avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
|
||||
${var.status_time_aggregator}(${var.status_timeframe}): (
|
||||
avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) != 1
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -36,8 +38,8 @@ resource "datadog_monitor" "evictedkeys" {
|
||||
message = "${coalesce(var.evictedkeys_limit_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.evictedkeys_limit_aggregator}(${var.evictedkeys_limit_timeframe}): (
|
||||
${var.evictedkeys_limit_aggregator}:azure.cache_redis.evictedkeys{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.evictedkeys_limit_time_aggregator}(${var.evictedkeys_limit_timeframe}): (
|
||||
avg:azure.cache_redis.evictedkeys{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.evictedkeys_limit_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -68,8 +70,8 @@ resource "datadog_monitor" "percent_processor_time" {
|
||||
message = "${coalesce(var.percent_processor_time_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.percent_processor_time_aggregator}(${var.percent_processor_time_timeframe}): (
|
||||
${var.percent_processor_time_aggregator}:azure.cache_redis.percent_processor_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.percent_processor_time_time_aggregator}(${var.percent_processor_time_timeframe}): (
|
||||
avg:azure.cache_redis.percent_processor_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.percent_processor_time_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -100,8 +102,8 @@ resource "datadog_monitor" "server_load" {
|
||||
message = "${coalesce(var.server_load_rate_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.server_load_rate_aggregator}(${var.server_load_rate_timeframe}): (
|
||||
${var.server_load_rate_aggregator}:azure.cache_redis.server_load{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.server_load_rate_time_aggregator}(${var.server_load_rate_timeframe}): (
|
||||
avg:azure.cache_redis.server_load{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.server_load_rate_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
@ -32,7 +32,7 @@ Inputs
|
||||
| status_message | Custom message for Service Bus status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
|
||||
| status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| status_aggregator | Monitor aggregator for Service Bus status [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `min` | no |
|
||||
|
||||
Related documentation
|
||||
---------------------
|
||||
|
||||
@ -37,8 +37,8 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
description = "Monitor aggregator for Service Bus status [available values: min, max, sum or avg]"
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for Service Bus status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
|
||||
@ -11,8 +11,8 @@ resource "datadog_monitor" "servicebus_status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}): (
|
||||
${var.status_aggregator}:azure.servicebus_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.status_time_aggregator}(${var.status_timeframe}): (
|
||||
avg:azure.servicebus_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) != 1
|
||||
EOF
|
||||
|
||||
|
||||
@ -27,25 +27,24 @@ Inputs
|
||||
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| cpu_aggregator | Monitor aggregator for SQL CPU [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| cpu_time_aggregator | Monitor aggregator for SQL CPU [available values: min, max or avg] | string | `avg` | no |
|
||||
| cpu_message | Custom message for SQL CPU monitor | string | `` | no |
|
||||
| cpu_silenced | Groups to mute for SQL CPU monitor | map | `<map>` | no |
|
||||
| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
|
||||
| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
|
||||
| cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| deadlock_aggregator | Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no |
|
||||
| deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `<map>` | no |
|
||||
| deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no |
|
||||
| deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| diskspace_aggregator | Monitor aggregator for SQL disk space [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| diskspace_time_aggregator | Monitor aggregator for SQL disk space [available values: min, max or avg] | string | `avg` | no |
|
||||
| diskspace_message | Custom message for SQL disk space monitor | string | `` | no |
|
||||
| diskspace_silenced | Groups to mute for SQL disk space monitor | map | `<map>` | no |
|
||||
| diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no |
|
||||
| diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no |
|
||||
| diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
|
||||
| dtu_aggregator | Monitor aggregator for SQL DTU [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| dtu_time_aggregator | Monitor aggregator for SQL DTU [available values: min, max or avg] | string | `avg` | no |
|
||||
| dtu_message | Custom message for SQL DTU monitor | string | `` | no |
|
||||
| dtu_silenced | Groups to mute for SQL DTU monitor | map | `<map>` | no |
|
||||
| dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no |
|
||||
|
||||
@ -37,8 +37,8 @@ variable "cpu_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "cpu_aggregator" {
|
||||
description = "Monitor aggregator for SQL CPU [available values: min, max, sum or avg]"
|
||||
variable "cpu_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL CPU [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -71,8 +71,8 @@ variable "diskspace_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "diskspace_aggregator" {
|
||||
description = "Monitor aggregator for SQL disk space [available values: min, max, sum or avg]"
|
||||
variable "diskspace_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL disk space [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -105,8 +105,8 @@ variable "dtu_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "dtu_aggregator" {
|
||||
description = "Monitor aggregator for SQL DTU [available values: min, max, sum or avg]"
|
||||
variable "dtu_time_aggregator" {
|
||||
description = "Monitor aggregator for SQL DTU [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -139,12 +139,6 @@ variable "deadlock_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "deadlock_aggregator" {
|
||||
description = "Monitor aggregator for SQL Deadlock [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "deadlock_timeframe" {
|
||||
description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
|
||||
@ -11,8 +11,8 @@ resource "datadog_monitor" "sql-database_cpu_90_15min" {
|
||||
message = "${coalesce(var.cpu_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.cpu_aggregator}(${var.cpu_timeframe}): (
|
||||
${var.cpu_aggregator}:azure.sql_servers_databases.cpu_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.cpu_time_aggregator}(${var.cpu_timeframe}): (
|
||||
avg:azure.sql_servers_databases.cpu_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.cpu_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -44,8 +44,8 @@ resource "datadog_monitor" "sql-database_free_space_low" {
|
||||
type = "metric alert"
|
||||
|
||||
query = <<EOF
|
||||
${var.diskspace_aggregator}(${var.diskspace_timeframe}): (
|
||||
${var.diskspace_aggregator}:azure.sql_servers_databases.storage_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.diskspace_time_aggregator}(${var.diskspace_timeframe}): (
|
||||
avg:azure.sql_servers_databases.storage_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.diskspace_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -76,7 +76,7 @@ resource "datadog_monitor" "sql-database_dtu_consumption_high" {
|
||||
type = "metric alert"
|
||||
|
||||
query = <<EOF
|
||||
${var.dtu_aggregator}(${var.dtu_timeframe}): (
|
||||
${var.dtu_time_aggregator}(${var.dtu_timeframe}): (
|
||||
azure.sql_servers_databases.dtu_consumption_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.dtu_threshold_critical}
|
||||
EOF
|
||||
@ -108,8 +108,8 @@ resource "datadog_monitor" "sql-database_deadlocks_count" {
|
||||
type = "metric alert"
|
||||
|
||||
query = <<EOF
|
||||
${var.deadlock_aggregator}(${var.deadlock_timeframe}): (
|
||||
${var.deadlock_aggregator}:azure.sql_servers_databases.deadlock{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.deadlock_timeframe}): (
|
||||
avg:azure.sql_servers_databases.deadlock{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) > ${var.deadlock_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
@ -32,19 +32,19 @@ Inputs
|
||||
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| authorization_error_requests_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| authorization_error_requests_time_aggregator | Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| authorization_error_requests_message | Custom message for Storage authorization errors monitor | string | `` | no |
|
||||
| authorization_error_requests_silenced | Groups to mute for Storage authorization errors monitor | map | `<map>` | no |
|
||||
| authorization_error_requests_threshold_critical | Maximum acceptable percent of authorization error requests for a storage | string | `90` | no |
|
||||
| authorization_error_requests_threshold_warning | Warning regarding acceptable percent of authorization error requests for a storage | string | `50` | no |
|
||||
| authorization_error_requests_timeframe | Monitor timeframe for Storage authorization errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| availability_aggregator | Monitor aggregator for Storage availability [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| availability_time_aggregator | Monitor aggregator for Storage availability [available values: min, max or avg] | string | `avg` | no |
|
||||
| availability_message | Custom message for Storage availability monitor | string | `` | no |
|
||||
| availability_silenced | Groups to mute for Storage availability monitor | map | `<map>` | no |
|
||||
| availability_threshold_critical | Minimum acceptable percent of availability for a storage | string | `50` | no |
|
||||
| availability_threshold_warning | Warning regarding acceptable percent of availability for a storage | string | `90` | no |
|
||||
| availability_timeframe | Monitor timeframe for Storage availability [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| client_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| client_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| client_other_error_requests_message | Custom message for Storage other errors monitor | string | `` | no |
|
||||
| client_other_error_requests_silenced | Groups to mute for Storage other errors monitor | map | `<map>` | no |
|
||||
| client_other_error_requests_threshold_critical | Maximum acceptable percent of client other error requests for a storage | string | `90` | no |
|
||||
@ -54,38 +54,38 @@ Inputs
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| latency_aggregator | Monitor aggregator for Storage latency [available values: min, max, sum or avg] | string | `min` | no |
|
||||
| latency_time_aggregator | Monitor aggregator for Storage latency [available values: min, max or avg] | string | `min` | no |
|
||||
| latency_message | Custom message for Storage latency monitor | string | `` | no |
|
||||
| latency_silenced | Groups to mute for Storage latency monitor | map | `<map>` | no |
|
||||
| latency_threshold_critical | Maximum acceptable end to end latency (ms) for a storage | string | `2000` | no |
|
||||
| latency_threshold_warning | Warning regarding acceptable end to end latency (ms) for a storage | string | `1000` | no |
|
||||
| latency_timeframe | Monitor timeframe for Storage latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| message | Message sent when a Redis monitor is triggered | string | - | yes |
|
||||
| network_error_requests_aggregator | Monitor aggregator for Storage network errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| network_error_requests_time_aggregator | Monitor aggregator for Storage network errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| network_error_requests_message | Custom message for Storage network errors monitor | string | `` | no |
|
||||
| network_error_requests_silenced | Groups to mute for Storage network errors monitor | map | `<map>` | no |
|
||||
| network_error_requests_threshold_critical | Maximum acceptable percent of network error requests for a storage | string | `90` | no |
|
||||
| network_error_requests_threshold_warning | Warning regarding acceptable percent of network error requests for a storage | string | `50` | no |
|
||||
| network_error_requests_timeframe | Monitor timeframe for Storage network errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| server_other_error_requests_aggregator | Monitor aggregator for Storage other errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| server_other_error_requests_time_aggregator | Monitor aggregator for Storage other errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| server_other_error_requests_message | Custom message for Storage server other errors monitor | string | `` | no |
|
||||
| server_other_error_requests_silenced | Groups to mute for Storage server other errors monitor | map | `<map>` | no |
|
||||
| server_other_error_requests_threshold_critical | Maximum acceptable percent of server other error requests for a storage | string | `90` | no |
|
||||
| server_other_error_requests_threshold_warning | Warning regarding acceptable percent of server other error requests for a storage | string | `50` | no |
|
||||
| server_other_error_requests_timeframe | Monitor timeframe for Storage server other errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| successful_requests_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| successful_requests_time_aggregator | Monitor aggregator for Storage sucessful requests [available values: min, max or avg] | string | `avg` | no |
|
||||
| successful_requests_message | Custom message for Storage sucessful requests monitor | string | `` | no |
|
||||
| successful_requests_silenced | Groups to mute for Storage sucessful requests monitor | map | `<map>` | no |
|
||||
| successful_requests_threshold_critical | Minimum acceptable percent of successful requests for a storage | string | `10` | no |
|
||||
| successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests for a storage | string | `30` | no |
|
||||
| successful_requests_timeframe | Monitor timeframe for Storage sucessful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| throttling_error_requests_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| throttling_error_requests_time_aggregator | Monitor aggregator for Storage throttling errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| throttling_error_requests_message | Custom message for Storage throttling error monitor | string | `` | no |
|
||||
| throttling_error_requests_silenced | Groups to mute for Storage throttling error monitor | map | `<map>` | no |
|
||||
| throttling_error_requests_threshold_critical | Maximum acceptable percent of throttling error requests for a storage | string | `90` | no |
|
||||
| throttling_error_requests_threshold_warning | Warning regarding acceptable percent of throttling error requests for a storage | string | `50` | no |
|
||||
| throttling_error_requests_timeframe | Monitor timeframe for Storage throttling errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| timeout_error_requests_aggregator | Monitor aggregator for Storage timeout [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| timeout_error_requests_time_aggregator | Monitor aggregator for Storage timeout [available values: min, max or avg] | string | `avg` | no |
|
||||
| timeout_error_requests_message | Custom message for Storage timeout monitor | string | `` | no |
|
||||
| timeout_error_requests_silenced | Groups to mute for Storage timeout monitor | map | `<map>` | no |
|
||||
| timeout_error_requests_threshold_critical | Maximum acceptable percent of timeout error requests for a storage | string | `90` | no |
|
||||
|
||||
@ -37,8 +37,8 @@ variable "availability_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "availability_aggregator" {
|
||||
description = "Monitor aggregator for Storage availability [available values: min, max, sum or avg]"
|
||||
variable "availability_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage availability [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -71,8 +71,8 @@ variable "successful_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "successful_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage sucessful requests [available values: min, max, sum or avg]"
|
||||
variable "successful_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage sucessful requests [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -105,8 +105,8 @@ variable "latency_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "latency_aggregator" {
|
||||
description = "Monitor aggregator for Storage latency [available values: min, max, sum or avg]"
|
||||
variable "latency_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage latency [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "min"
|
||||
}
|
||||
@ -139,8 +139,8 @@ variable "timeout_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "timeout_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage timeout [available values: min, max, sum or avg]"
|
||||
variable "timeout_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage timeout [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -173,8 +173,8 @@ variable "network_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "network_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage network errors [available values: min, max, sum or avg]"
|
||||
variable "network_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage network errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -207,8 +207,8 @@ variable "throttling_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "throttling_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage throttling errors [available values: min, max, sum or avg]"
|
||||
variable "throttling_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage throttling errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -241,8 +241,8 @@ variable "server_other_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "server_other_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]"
|
||||
variable "server_other_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -275,8 +275,8 @@ variable "client_other_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "client_other_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max, sum or avg]"
|
||||
variable "client_other_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage other errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -309,8 +309,8 @@ variable "authorization_error_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "authorization_error_requests_aggregator" {
|
||||
description = "Monitor aggregator for Storage authorization errors [available values: min, max, sum or avg]"
|
||||
variable "authorization_error_requests_time_aggregator" {
|
||||
description = "Monitor aggregator for Storage authorization errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
|
||||
@ -11,8 +11,8 @@ resource "datadog_monitor" "availability" {
|
||||
message = "${coalesce(var.availability_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.availability_aggregator}(${var.availability_timeframe}): (default(
|
||||
${var.availability_aggregator}:azure.storage.availability{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.availability_time_aggregator}(${var.availability_timeframe}): (default(
|
||||
avg:azure.storage.availability{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
100)) < ${var.availability_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -42,8 +42,8 @@ resource "datadog_monitor" "successful_requests" {
|
||||
message = "${coalesce(var.successful_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.successful_requests_aggregator}(${var.successful_requests_timeframe}): (default(
|
||||
${var.successful_requests_aggregator}:azure.storage.percent_success{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.successful_requests_time_aggregator}(${var.successful_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_success{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
100)) < ${var.successful_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -73,8 +73,8 @@ resource "datadog_monitor" "latency" {
|
||||
message = "${coalesce(var.latency_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.latency_aggregator}(${var.latency_timeframe}): (default(
|
||||
${var.latency_aggregator}:azure.storage.average_e2_e_latency{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.latency_time_aggregator}(${var.latency_timeframe}): (default(
|
||||
avg:azure.storage.average_e2_e_latency{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.latency_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -104,8 +104,8 @@ resource "datadog_monitor" "timeout_error_requests" {
|
||||
message = "${coalesce(var.timeout_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.timeout_error_requests_aggregator}(${var.timeout_error_requests_timeframe}): (default(
|
||||
${var.timeout_error_requests_aggregator}:azure.storage.percent_timeout_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.timeout_error_requests_time_aggregator}(${var.timeout_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_timeout_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.timeout_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -135,8 +135,8 @@ resource "datadog_monitor" "network_error_requests" {
|
||||
message = "${coalesce(var.network_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.network_error_requests_aggregator}(${var.network_error_requests_timeframe}): (default(
|
||||
${var.network_error_requests_aggregator}:azure.storage.percent_network_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.network_error_requests_time_aggregator}(${var.network_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_network_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.network_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -166,8 +166,8 @@ resource "datadog_monitor" "throttling_error_requests" {
|
||||
message = "${coalesce(var.throttling_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.throttling_error_requests_aggregator}(${var.throttling_error_requests_timeframe}): (default(
|
||||
${var.throttling_error_requests_aggregator}:azure.storage.percent_throttling_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.throttling_error_requests_time_aggregator}(${var.throttling_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_throttling_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.throttling_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -197,8 +197,8 @@ resource "datadog_monitor" "server_other_error_requests" {
|
||||
message = "${coalesce(var.server_other_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.server_other_error_requests_aggregator}(${var.server_other_error_requests_timeframe}): (default(
|
||||
${var.server_other_error_requests_aggregator}:azure.storage.percent_server_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.server_other_error_requests_time_aggregator}(${var.server_other_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_server_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.server_other_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -228,8 +228,8 @@ resource "datadog_monitor" "client_other_error_requests" {
|
||||
message = "${coalesce(var.client_other_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.client_other_error_requests_aggregator}(${var.client_other_error_requests_timeframe}): (default(
|
||||
${var.client_other_error_requests_aggregator}:azure.storage.percent_client_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.client_other_error_requests_time_aggregator}(${var.client_other_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_client_other_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.client_other_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -259,8 +259,8 @@ resource "datadog_monitor" "authorization_error_requests" {
|
||||
message = "${coalesce(var.authorization_error_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.authorization_error_requests_aggregator}(${var.authorization_error_requests_timeframe}): (default(
|
||||
${var.authorization_error_requests_aggregator}:azure.storage.percent_authorization_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
${var.authorization_error_requests_time_aggregator}(${var.authorization_error_requests_timeframe}): (default(
|
||||
avg:azure.storage.percent_authorization_error{${data.template_file.filter.rendered},transaction_type:all} by {resource_group,storage_type,name},
|
||||
0)) > ${var.authorization_error_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
@ -18,15 +18,14 @@ Inputs
|
||||
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| conversion_errors_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| conversion_errors_message | Custom message for Stream Analytics conversion errors monitor | string | `` | no |
|
||||
| conversion_errors_silenced | Groups to mute for Stream Analytics conversion errors monitor | map | `<map>` | no |
|
||||
| conversion_errors_threshold_critical | Conversion errors limit (critical threshold) | string | `10` | no |
|
||||
| conversion_errors_threshold_warning | Conversion errors limit (warning threshold) | string | `0` | no |
|
||||
| conversion_errors_time_aggregator | Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| conversion_errors_timeframe | Monitor timeframe for Stream Analytics conversion errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
|
||||
| environment | Architecture environment | string | - | yes |
|
||||
| failed_function_requests_aggregator | Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg] | string | `sum` | no |
|
||||
| failed_function_requests_message | Custom message for Stream Analytics failed requests monitor | string | `` | no |
|
||||
| failed_function_requests_silenced | Groups to mute for Stream Analytics failed requests monitor | map | `<map>` | no |
|
||||
| failed_function_requests_threshold_critical | Failed Function Request rate limit (critical threshold) | string | `10` | no |
|
||||
@ -35,21 +34,21 @@ Inputs
|
||||
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
|
||||
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
|
||||
| message | Message sent when a Redis monitor is triggered | string | - | yes |
|
||||
| runtime_errors_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| runtime_errors_message | Custom message for Stream Analytics runtime errors monitor | string | `` | no |
|
||||
| runtime_errors_silenced | Groups to mute for Stream Analytics runtime errors monitor | map | `<map>` | no |
|
||||
| runtime_errors_threshold_critical | Runtime errors limit (critical threshold) | string | `10` | no |
|
||||
| runtime_errors_threshold_warning | Runtime errors limit (warning threshold) | string | `0` | no |
|
||||
| runtime_errors_time_aggregator | Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg] | string | `avg` | no |
|
||||
| runtime_errors_timeframe | Monitor timeframe for Stream Analytics runtime errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| status_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| status_message | Custom message for Stream Analytics status monitor | string | `` | no |
|
||||
| status_silenced | Groups to mute for Stream Analytics status monitor | map | `<map>` | no |
|
||||
| status_time_aggregator | Monitor aggregator for Stream Analytics status [available values: min, max or avg] | string | `avg` | no |
|
||||
| status_timeframe | Monitor timeframe for Stream Analytics status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
| su_utilization_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg] | string | `avg` | no |
|
||||
| su_utilization_message | Custom message for Stream Analytics utilization monitor | string | `` | no |
|
||||
| su_utilization_silenced | Groups to mute for Stream Analytics utilization monitor | map | `<map>` | no |
|
||||
| su_utilization_threshold_critical | Streaming Unit utilization rate limit (critical threshold) | string | `80` | no |
|
||||
| su_utilization_threshold_warning | Streaming Unit utilization rate limit (warning threshold) | string | `60` | no |
|
||||
| su_utilization_time_aggregator | Monitor aggregator for Stream Analytics utilization [available values: min, max or avg] | string | `avg` | no |
|
||||
| su_utilization_timeframe | Monitor timeframe for Stream Analytics utilization [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
|
||||
|
||||
Related documentation
|
||||
|
||||
@ -37,8 +37,8 @@ variable "status_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "status_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics status [available values: min, max, sum or avg]"
|
||||
variable "status_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics status [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -61,8 +61,8 @@ variable "su_utilization_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "su_utilization_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max, sum or avg]"
|
||||
variable "su_utilization_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics utilization [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -95,12 +95,6 @@ variable "failed_function_requests_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "failed_function_requests_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics failed requests [available values: min, max, sum or avg]"
|
||||
type = "string"
|
||||
default = "sum"
|
||||
}
|
||||
|
||||
variable "failed_function_requests_timeframe" {
|
||||
description = "Monitor timeframe for Stream Analytics failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
|
||||
type = "string"
|
||||
@ -129,8 +123,8 @@ variable "conversion_errors_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "conversion_errors_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max, sum or avg]"
|
||||
variable "conversion_errors_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics conversion errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
@ -163,8 +157,8 @@ variable "runtime_errors_message" {
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "runtime_errors_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max, sum or avg]"
|
||||
variable "runtime_errors_time_aggregator" {
|
||||
description = "Monitor aggregator for Stream Analytics runtime errors [available values: min, max or avg]"
|
||||
type = "string"
|
||||
default = "avg"
|
||||
}
|
||||
|
||||
@ -11,7 +11,9 @@ resource "datadog_monitor" "status" {
|
||||
message = "${coalesce(var.status_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.status_aggregator}(${var.status_timeframe}):avg:azure.streamanalytics_streamingjobs.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
|
||||
${var.status_time_aggregator}(${var.status_timeframe}): (
|
||||
avg:azure.streamanalytics_streamingjobs.status{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) < 1
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
@ -36,8 +38,8 @@ resource "datadog_monitor" "su_utilization" {
|
||||
message = "${coalesce(var.su_utilization_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.su_utilization_aggregator}(${var.su_utilization_timeframe}): (
|
||||
${var.su_utilization_aggregator}:azure.streamanalytics_streamingjobs.resource_utilization{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.su_utilization_time_aggregator}(${var.su_utilization_timeframe}): (
|
||||
avg:azure.streamanalytics_streamingjobs.resource_utilization{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.su_utilization_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -68,9 +70,9 @@ resource "datadog_monitor" "failed_function_requests" {
|
||||
message = "${coalesce(var.failed_function_requests_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.failed_function_requests_aggregator}(${var.failed_function_requests_timeframe}): (
|
||||
${var.failed_function_requests_aggregator}:azure.streamanalytics_streamingjobs.aml_callout_failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
${var.failed_function_requests_aggregator}:azure.streamanalytics_streamingjobs.aml_callout_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
sum(${var.failed_function_requests_timeframe}): (
|
||||
avg:azure.streamanalytics_streamingjobs.aml_callout_failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
|
||||
avg:azure.streamanalytics_streamingjobs.aml_callout_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
|
||||
) * 100 > ${var.failed_function_requests_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -101,8 +103,8 @@ resource "datadog_monitor" "conversion_errors" {
|
||||
message = "${coalesce(var.conversion_errors_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.conversion_errors_aggregator}(${var.conversion_errors_timeframe}): (
|
||||
${var.conversion_errors_aggregator}:azure.streamanalytics_streamingjobs.conversion_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.conversion_errors_time_aggregator}(${var.conversion_errors_timeframe}): (
|
||||
avg:azure.streamanalytics_streamingjobs.conversion_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.conversion_errors_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -133,8 +135,8 @@ resource "datadog_monitor" "runtime_errors" {
|
||||
message = "${coalesce(var.runtime_errors_message, var.message)}"
|
||||
|
||||
query = <<EOF
|
||||
${var.runtime_errors_aggregator}(${var.runtime_errors_timeframe}): (
|
||||
${var.runtime_errors_aggregator}:azure.streamanalytics_streamingjobs.errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
${var.runtime_errors_time_aggregator}(${var.runtime_errors_timeframe}): (
|
||||
avg:azure.streamanalytics_streamingjobs.errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
|
||||
) > ${var.runtime_errors_threshold_critical}
|
||||
EOF
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user