diff --git a/caas/kubernetes/ingress/vts/README.md b/caas/kubernetes/ingress/vts/README.md index ffc144d..27df14b 100644 --- a/caas/kubernetes/ingress/vts/README.md +++ b/caas/kubernetes/ingress/vts/README.md @@ -16,8 +16,8 @@ module "datadog-monitors-caas-kubernetes-ingress-vts" { Creates DataDog monitors with the following checks: -- Nginx Ingress 5xx errors - Nginx Ingress 4xx errors +- Nginx Ingress 5xx errors ## Inputs diff --git a/caas/kubernetes/node/README.md b/caas/kubernetes/node/README.md index 99bdb20..d310f53 100644 --- a/caas/kubernetes/node/README.md +++ b/caas/kubernetes/node/README.md @@ -17,11 +17,15 @@ module "datadog-monitors-caas-kubernetes-node" { Creates DataDog monitors with the following checks: - Kubernetes Node Disk pressure +- Kubernetes Node Frequent unregister net device - Kubernetes Node Kubelet API does not respond -- Kubernetes Node volume space usage - Kubernetes Node Kubelet sync loop that updates containers does not work +- Kubernetes Node Memory pressure +- Kubernetes Node not ready - Kubernetes Node Out of disk +- Kubernetes Node unschedulable - Kubernetes Node volume inodes usage +- Kubernetes Node volume space usage ## Inputs diff --git a/caas/kubernetes/workload/README.md b/caas/kubernetes/workload/README.md index 658cf2a..09c8b0a 100644 --- a/caas/kubernetes/workload/README.md +++ b/caas/kubernetes/workload/README.md @@ -16,9 +16,11 @@ module "datadog-monitors-caas-kubernetes-workload" { Creates DataDog monitors with the following checks: +- Kubernetes Available replicas +- Kubernetes cronjob scheduling failed - Kubernetes Current replicas - Kubernetes job failed -- Kubernetes cronjob scheduling failed +- Kubernetes Ready replicas ## Inputs diff --git a/cloud/aws/alb/README.md b/cloud/aws/alb/README.md index cffe389..0fc721d 100644 --- a/cloud/aws/alb/README.md +++ b/cloud/aws/alb/README.md @@ -17,9 +17,11 @@ module "datadog-monitors-cloud-aws-alb" { Creates DataDog monitors with the following checks: - ALB healthy instances -- ALB target HTTP code 5xx +- ALB HTTP code 4xx +- ALB HTTP code 5xx - ALB latency - ALB target HTTP code 4xx +- ALB target HTTP code 5xx ## Inputs diff --git a/cloud/aws/apigateway/README.md b/cloud/aws/apigateway/README.md index dcf77da..9da0102 100644 --- a/cloud/aws/apigateway/README.md +++ b/cloud/aws/apigateway/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-cloud-aws-apigateway" { Creates DataDog monitors with the following checks: -- API Gateway latency +- API Gateway HTTP 4xx errors - API Gateway HTTP 5xx errors +- API Gateway latency ## Inputs diff --git a/cloud/aws/elasticache/common/README.md b/cloud/aws/elasticache/common/README.md index 5eec859..4cacdd6 100644 --- a/cloud/aws/elasticache/common/README.md +++ b/cloud/aws/elasticache/common/README.md @@ -16,10 +16,12 @@ module "datadog-monitors-cloud-aws-elasticache-common" { Creates DataDog monitors with the following checks: +- Elasticache connections - Elasticache eviction -- Elasticache free memory - Elasticache evictions is growing +- Elasticache free memory - Elasticache max connections reached +- Elasticache swap ## Inputs diff --git a/cloud/aws/elasticache/redis/README.md b/cloud/aws/elasticache/redis/README.md index 2ee8c4a..e3d6d8b 100644 --- a/cloud/aws/elasticache/redis/README.md +++ b/cloud/aws/elasticache/redis/README.md @@ -18,6 +18,8 @@ Creates DataDog monitors with the following checks: - Elasticache redis cache hit ratio - Elasticache redis CPU +- Elasticache redis is receiving no commands +- Elasticache redis replication lag ## Inputs diff --git a/cloud/aws/elasticsearch/README.md b/cloud/aws/elasticsearch/README.md index 2c227fc..ae41141 100644 --- a/cloud/aws/elasticsearch/README.md +++ b/cloud/aws/elasticsearch/README.md @@ -18,8 +18,9 @@ module "datadog-monitors-cloud-aws-elasticsearch" { Creates DataDog monitors with the following checks: -- ElasticSearch cluster status is not green +- ElasticSearch cluster CPU high - ElasticSearch cluster free storage space +- ElasticSearch cluster status is not green ## Inputs diff --git a/cloud/aws/elb/README.md b/cloud/aws/elb/README.md index 746a396..430ae50 100644 --- a/cloud/aws/elb/README.md +++ b/cloud/aws/elb/README.md @@ -16,9 +16,11 @@ module "datadog-monitors-cloud-aws-elb" { Creates DataDog monitors with the following checks: +- ELB 4xx errors too high +- ELB 5xx errors too high +- ELB backend 4xx errors too high - ELB backend 5xx errors too high - ELB healthy instances -- ELB 4xx errors too high - ELB latency too high ## Inputs diff --git a/cloud/aws/rds/common/README.md b/cloud/aws/rds/common/README.md index 1a130b8..b2402be 100644 --- a/cloud/aws/rds/common/README.md +++ b/cloud/aws/rds/common/README.md @@ -18,6 +18,7 @@ Creates DataDog monitors with the following checks: - RDS instance CPU high - RDS instance free space +- RDS replica lag ## Inputs diff --git a/cloud/azure/apimanagement/README.md b/cloud/azure/apimanagement/README.md index f302ea8..2918228 100644 --- a/cloud/azure/apimanagement/README.md +++ b/cloud/azure/apimanagement/README.md @@ -19,6 +19,8 @@ Creates DataDog monitors with the following checks: - API Management is down - API Management successful requests rate too low - API Management too many failed requests +- API Management too many other requests +- API Management too many unauthorized requests ## Inputs diff --git a/cloud/azure/app-services/README.md b/cloud/azure/app-services/README.md index 5d50cb1..2f25224 100644 --- a/cloud/azure/app-services/README.md +++ b/cloud/azure/app-services/README.md @@ -16,10 +16,12 @@ module "datadog-monitors-cloud-azure-app-services" { Creates DataDog monitors with the following checks: +- App Services HTTP 4xx errors too high +- App Services HTTP 5xx errors too high - App Services HTTP successful responses too low -- App Services response time too high - App Services is down - App Services memory usage +- App Services response time too high ## Inputs diff --git a/cloud/azure/cosmosdb/README.md b/cloud/azure/cosmosdb/README.md index f145b06..e21ffd5 100644 --- a/cloud/azure/cosmosdb/README.md +++ b/cloud/azure/cosmosdb/README.md @@ -16,8 +16,10 @@ module "datadog-monitors-cloud-azure-cosmosdb" { Creates DataDog monitors with the following checks: -- Cosmos DB is down - Cosmos DB 4xx requests rate is high +- Cosmos DB 5xx requests rate is high +- Cosmos DB is down +- Cosmos DB max scaling reached for collection ## Inputs diff --git a/cloud/azure/eventgrid/README.md b/cloud/azure/eventgrid/README.md index 53319c2..03446e8 100644 --- a/cloud/azure/eventgrid/README.md +++ b/cloud/azure/eventgrid/README.md @@ -18,6 +18,7 @@ Creates DataDog monitors with the following checks: - Event Grid no successful message - Event Grid too many failed messages +- Event Grid too many unmatched events ## Inputs diff --git a/cloud/azure/eventhub/README.md b/cloud/azure/eventhub/README.md index 935998f..67d796a 100644 --- a/cloud/azure/eventhub/README.md +++ b/cloud/azure/eventhub/README.md @@ -17,6 +17,7 @@ module "datadog-monitors-cloud-azure-eventhub" { Creates DataDog monitors with the following checks: - Event Hub is down +- Event Hub too many errors - Event Hub too many failed requests ## Inputs diff --git a/cloud/azure/functions/README.md b/cloud/azure/functions/README.md index ab5a674..d74794d 100644 --- a/cloud/azure/functions/README.md +++ b/cloud/azure/functions/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-cloud-azure-functions" { Creates DataDog monitors with the following checks: -- Function App HTTP 5xx errors too high - Function App connections count too high +- Function App HTTP 5xx errors too high +- Function App threads count too high ## Inputs diff --git a/cloud/azure/iothubs/README.md b/cloud/azure/iothubs/README.md index fcc2c21..de92272 100644 --- a/cloud/azure/iothubs/README.md +++ b/cloud/azure/iothubs/README.md @@ -16,14 +16,20 @@ module "datadog-monitors-cloud-azure-iothubs" { Creates DataDog monitors with the following checks: -- IOT Hub Too many d2c telemetry egress invalid -- IOT Hub Too many d2c twin read failure -- IOT Hub Too many jobs failed -- IOT Hub Total devices is wrong +- IOT Hub is down - IOT Hub Too many c2d methods failure +- IOT Hub Too many c2d twin read failure +- IOT Hub Too many c2d twin update failure +- IOT Hub Too many d2c telemetry egress dropped +- IOT Hub Too many d2c telemetry egress invalid +- IOT Hub Too many d2c telemetry egress orphaned - IOT Hub Too many d2c telemetry ingress not sent +- IOT Hub Too many d2c twin read failure - IOT Hub Too many d2c twin update failure +- IOT Hub Too many jobs failed - IOT Hub Too many list_jobs failure +- IOT Hub Too many query_jobs failed +- IOT Hub Total devices is wrong ## Inputs diff --git a/cloud/azure/keyvault/README.md b/cloud/azure/keyvault/README.md index d9735ca..6da9e4d 100644 --- a/cloud/azure/keyvault/README.md +++ b/cloud/azure/keyvault/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-cloud-azure-keyvault" { Creates DataDog monitors with the following checks: -- Key Vault is down +- Key Vault API latency is high - Key Vault API result rate is low +- Key Vault is down ## Inputs diff --git a/cloud/azure/mysql/README.md b/cloud/azure/mysql/README.md index fecb50c..d31b2cf 100644 --- a/cloud/azure/mysql/README.md +++ b/cloud/azure/mysql/README.md @@ -17,6 +17,8 @@ module "datadog-monitors-cloud-azure-mysql" { Creates DataDog monitors with the following checks: - Mysql Server CPU usage +- Mysql Server IO consumption +- Mysql Server memory usage - Mysql Server storage ## Inputs diff --git a/cloud/azure/postgresql/README.md b/cloud/azure/postgresql/README.md index 86bbc5b..daccdee 100644 --- a/cloud/azure/postgresql/README.md +++ b/cloud/azure/postgresql/README.md @@ -17,8 +17,10 @@ module "datadog-monitors-cloud-azure-postgresql" { Creates DataDog monitors with the following checks: - Postgresql Server CPU usage -- Postgresql Server memory usage - Postgresql Server has no connection +- Postgresql Server IO consumption +- Postgresql Server memory usage +- Postgresql Server storage ## Inputs diff --git a/cloud/azure/redis/README.md b/cloud/azure/redis/README.md index 6f4d94c..b8b8ef9 100644 --- a/cloud/azure/redis/README.md +++ b/cloud/azure/redis/README.md @@ -17,6 +17,8 @@ module "datadog-monitors-cloud-azure-redis" { Creates DataDog monitors with the following checks: - Redis {{name}} is down +- Redis processor time too high +- Redis server load too high - Redis too many evictedkeys ## Inputs diff --git a/cloud/azure/serverfarms/README.md b/cloud/azure/serverfarms/README.md index 973460e..15a4e7c 100644 --- a/cloud/azure/serverfarms/README.md +++ b/cloud/azure/serverfarms/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-cloud-azure-serverfarms" { Creates DataDog monitors with the following checks: -- Serverfarm is down - Serverfarm CPU percentage is too high +- Serverfarm is down +- Serverfarm memory percentage is too high ## Inputs diff --git a/cloud/azure/servicebus/README.md b/cloud/azure/servicebus/README.md index 8a239e4..9021cc2 100644 --- a/cloud/azure/servicebus/README.md +++ b/cloud/azure/servicebus/README.md @@ -16,8 +16,10 @@ module "datadog-monitors-cloud-azure-servicebus" { Creates DataDog monitors with the following checks: -- Service Bus is down - Service Bus has no active connection +- Service Bus is down +- Service Bus server errors rate is high +- Service Bus user errors rate is high ## Inputs diff --git a/cloud/azure/sql-database/README.md b/cloud/azure/sql-database/README.md index 42d19c2..585628f 100644 --- a/cloud/azure/sql-database/README.md +++ b/cloud/azure/sql-database/README.md @@ -16,9 +16,11 @@ module "datadog-monitors-cloud-azure-sql-database" { Creates DataDog monitors with the following checks: -- SQL Database Deadlocks too high -- SQL Database is down - SQL Database CPU too high +- SQL Database Deadlocks too high +- SQL Database DTU Consumption too high +- SQL Database high disk usage +- SQL Database is down ## Inputs diff --git a/cloud/azure/sql-elasticpool/README.md b/cloud/azure/sql-elasticpool/README.md index a6f1ebb..7e510d8 100644 --- a/cloud/azure/sql-elasticpool/README.md +++ b/cloud/azure/sql-elasticpool/README.md @@ -17,6 +17,7 @@ module "datadog-monitors-cloud-azure-sql-elasticpool" { Creates DataDog monitors with the following checks: - SQL Elastic Pool CPU too high +- SQL Elastic Pool DTU Consumption too high - SQL Elastic Pool high disk usage ## Inputs diff --git a/cloud/azure/storage/README.md b/cloud/azure/storage/README.md index c031622..3a3993f 100644 --- a/cloud/azure/storage/README.md +++ b/cloud/azure/storage/README.md @@ -17,10 +17,14 @@ module "datadog-monitors-cloud-azure-storage" { Creates DataDog monitors with the following checks: - Azure Storage is down -- Azure Storage too many authorization errors -- Azure Storage too many network errors - Azure Storage too few successful requests +- Azure Storage too high end to end latency +- Azure Storage too many authorization errors +- Azure Storage too many client_other errors +- Azure Storage too many network errors +- Azure Storage too many server_other errors - Azure Storage too many throttling errors +- Azure Storage too many timeout errors ## Inputs diff --git a/cloud/azure/stream-analytics/README.md b/cloud/azure/stream-analytics/README.md index 3b913be..c447a24 100644 --- a/cloud/azure/stream-analytics/README.md +++ b/cloud/azure/stream-analytics/README.md @@ -17,8 +17,10 @@ module "datadog-monitors-cloud-azure-stream-analytics" { Creates DataDog monitors with the following checks: - Stream Analytics is down -- Stream Analytics too many runtime errors - Stream Analytics streaming units utilization too high +- Stream Analytics too many conversion errors +- Stream Analytics too many failed requests +- Stream Analytics too many runtime errors ## Inputs diff --git a/cloud/azure/virtual-machine/README.md b/cloud/azure/virtual-machine/README.md index 77f5b2f..1980300 100644 --- a/cloud/azure/virtual-machine/README.md +++ b/cloud/azure/virtual-machine/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-cloud-azure-virtual-machine" { Creates DataDog monitors with the following checks: -- Virtual Machine is unreachable - Virtual Machine CPU usage +- Virtual Machine credit CPU +- Virtual Machine is unreachable ## Inputs diff --git a/cloud/gcp/big-query/README.md b/cloud/gcp/big-query/README.md index 49ca366..193b766 100644 --- a/cloud/gcp/big-query/README.md +++ b/cloud/gcp/big-query/README.md @@ -18,9 +18,13 @@ Creates DataDog monitors with the following checks: - GCP Big Query Available Slots - GCP Big Query Concurrent Queries -- GCP Big Query Uploaded Bytes Billed - GCP Big Query Execution Time +- GCP Big Query Scanned Bytes Billed +- GCP Big Query Scanned Bytes - GCP Big Query Stored Bytes +- GCP Big Query Table Count +- GCP Big Query Uploaded Bytes Billed +- GCP Big Query Uploaded Bytes ## Inputs diff --git a/cloud/gcp/cloud-sql/common/README.md b/cloud/gcp/cloud-sql/common/README.md index 6916d06..96fec35 100644 --- a/cloud/gcp/cloud-sql/common/README.md +++ b/cloud/gcp/cloud-sql/common/README.md @@ -17,10 +17,11 @@ module "datadog-monitors-cloud-gcp-cloud-sql-common" { Creates DataDog monitors with the following checks: - Cloud SQL CPU Utilization -- Cloud SQL Failover Unavailable -- Cloud SQL Memory Utilization +- Cloud SQL Disk Utilization forecast - Cloud SQL Disk Utilization +- Cloud SQL Failover Unavailable - Cloud SQL Memory Utilization forecast +- Cloud SQL Memory Utilization ## Inputs diff --git a/cloud/gcp/gce/instance/README.md b/cloud/gcp/gce/instance/README.md index ad30770..619649a 100644 --- a/cloud/gcp/gce/instance/README.md +++ b/cloud/gcp/gce/instance/README.md @@ -18,6 +18,7 @@ Creates DataDog monitors with the following checks: - Compute Engine instance CPU Utilization - Compute Engine instance Disk Throttled Bps +- Compute Engine instance Disk Throttled OPS ## Inputs diff --git a/cloud/gcp/lb/README.md b/cloud/gcp/lb/README.md index 304d8eb..0501fd2 100644 --- a/cloud/gcp/lb/README.md +++ b/cloud/gcp/lb/README.md @@ -17,8 +17,10 @@ module "datadog-monitors-cloud-gcp-lb" { Creates DataDog monitors with the following checks: - GCP LB 4xx errors -- GCP LB Requests count increased abruptly - GCP LB 5xx errors +- GCP LB bucket backend latency +- GCP LB Requests count increased abruptly +- GCP LB service backend latency ## Inputs diff --git a/database/elasticsearch/README.md b/database/elasticsearch/README.md index 751100a..e92f8ee 100644 --- a/database/elasticsearch/README.md +++ b/database/elasticsearch/README.md @@ -17,16 +17,26 @@ module "datadog-monitors-database-elasticsearch" { Creates DataDog monitors with the following checks: - Elasticsearch average index flushing to disk latency -- Elasticsearch change alert on the number of currently active queries -- Elasticsearch change alert on the number of request cache evictions -- ElasticSearch Cluster has unassigned shards -- ElasticSearch does not respond -- Elasticsearch JVM memory Old usage +- Elasticsearch average indexing time by document - Elasticsearch average Old-generation garbage collections latency +- Elasticsearch average search fetch latency +- Elasticsearch average search query latency +- Elasticsearch average Young-generation garbage collections latency - Elasticsearch change alert on the average time spent by tasks in the queue +- Elasticsearch change alert on the number of currently active queries +- Elasticsearch change alert on the number of query cache evictions +- Elasticsearch change alert on the number of request cache evictions - Elasticsearch change alert on the number of search fetches currently running +- Elasticsearch change alert on the total number of evictions from the fielddata cache +- ElasticSearch Cluster has unassigned shards +- ElasticSearch Cluster is initializing shards +- ElasticSearch Cluster is relocating shards - ElasticSearch Cluster status not green +- ElasticSearch does not respond - ElasticSearch free space < 10% +- Elasticsearch JVM HEAP memory usage +- Elasticsearch JVM memory Old usage +- Elasticsearch JVM memory Young usage - Elasticsearch number of current open HTTP connections anomaly detected ## Inputs diff --git a/database/mongodb/README.md b/database/mongodb/README.md index 8d526f4..0fd1cae 100644 --- a/database/mongodb/README.md +++ b/database/mongodb/README.md @@ -17,7 +17,9 @@ module "datadog-monitors-database-mongodb" { Creates DataDog monitors with the following checks: - MongoDB primary state +- MongoDB replication lag - MongoDB secondary missing +- MongoDB too much servers or wrong monitoring config ## Inputs diff --git a/database/mysql/README.md b/database/mysql/README.md index f894048..122f1ce 100644 --- a/database/mysql/README.md +++ b/database/mysql/README.md @@ -16,10 +16,14 @@ module "datadog-monitors-database-mysql" { Creates DataDog monitors with the following checks: -- Mysql Innodb buffer pool efficiency -- Mysql server does not respond +- Mysql Aborted connects - Mysql Connections limit +- Mysql Innodb buffer pool efficiency - Mysql Innodb buffer pool utilization +- Mysql queries changed abnormally +- Mysql server does not respond +- Mysql Slow queries +- Mysql threads changed abnormally ## Inputs diff --git a/database/postgresql/README.md b/database/postgresql/README.md index 729525b..784e152 100644 --- a/database/postgresql/README.md +++ b/database/postgresql/README.md @@ -16,8 +16,9 @@ module "datadog-monitors-database-postgresql" { Creates DataDog monitors with the following checks: -- PostgreSQL server does not respond - PostgreSQL Connections +- PostgreSQL server does not respond +- PostgreSQL too many locks ## Inputs diff --git a/database/redis/README.md b/database/redis/README.md index 7e41f80..ecfdbb7 100644 --- a/database/redis/README.md +++ b/database/redis/README.md @@ -16,12 +16,16 @@ module "datadog-monitors-database-redis" { Creates DataDog monitors with the following checks: +- Redis blocked clients - Redis does not respond +- Redis evicted keys +- Redis expired keys +- Redis hitrate - Redis keyspace seems full (no changes since ${var.keyspace_timeframe}) - Redis latency -- Redis evicted keys -- Redis hitrate +- Redis memory fragmented - Redis memory used +- Redis rejected connections ## Inputs diff --git a/middleware/nginx/README.md b/middleware/nginx/README.md index 2f0e475..8166536 100644 --- a/middleware/nginx/README.md +++ b/middleware/nginx/README.md @@ -16,8 +16,8 @@ module "datadog-monitors-middleware-nginx" { Creates DataDog monitors with the following checks: -- Nginx vhost status does not respond - Nginx dropped connections +- Nginx vhost status does not respond ## Inputs diff --git a/middleware/php-fpm/README.md b/middleware/php-fpm/README.md index f5d7423..f0d05a0 100644 --- a/middleware/php-fpm/README.md +++ b/middleware/php-fpm/README.md @@ -16,8 +16,8 @@ module "datadog-monitors-middleware-php-fpm" { Creates DataDog monitors with the following checks: -- Php-fpm ping url does not respond - Php-fpm busy worker +- Php-fpm ping url does not respond ## Inputs diff --git a/system/generic/README.md b/system/generic/README.md index af09057..bbb65ab 100644 --- a/system/generic/README.md +++ b/system/generic/README.md @@ -18,9 +18,11 @@ module "datadog-monitors-system-generic" { Creates DataDog monitors with the following checks: +- CPU load 5 ratio - CPU usage - Disk inodes usage -- CPU load 5 ratio +- Disk Space usage forecast +- Disk space usage - Usable Memory ## Inputs