fix probe memory and add heartbeat probe

claranet · Sep 11, 2024 · 39a6355 · 39a6355
1 parent a3e0305
commit 39a6355
Show file tree

Hide file tree

Showing 8 changed files with 104 additions and 89 deletions.
diff --git a/docs/severity.md b/docs/severity.md
@@ -742,6 +742,7 @@
 
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
+|GCP Cloud Run heartbeat|X|-|-|-|-|
 |GCP Cloud Run cpu utilizations|X|X|-|-|-|
 |GCP Cloud Run memory utilizations|X|X|-|-|-|
 

diff --git a/modules/integration_gcp-cloud-run/README.md b/modules/integration_gcp-cloud-run/README.md
@@ -12,8 +12,6 @@
   - [Metadata configuration for default filtering](#metadata-configuration-for-default-filtering)
   - [CPU utilizations](#cpu-utilizations)
   - [Memory utilizations](#memory-utilizations)
-  - [Connection refused to cloud sql](#connection-refused-to-cloud-sql)
-  - [Error 5xx](#error-5xx)
 - [Related documentation](#related-documentation)
 
 <!-- END doctoc generated TOC please keep comment here to allow auto update -->
@@ -82,6 +80,7 @@ This module creates the following SignalFx detectors which could contain one or
 
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
+|GCP Cloud Run heartbeat|X|-|-|-|-|
 |GCP Cloud Run cpu utilizations|X|X|-|-|-|
 |GCP Cloud Run memory utilizations|X|X|-|-|-|
 
@@ -101,7 +100,9 @@ Check the [Related documentation](#related-documentation) section for more detai
 
 Here is the list of required metrics for detectors in this module.
 
+* `container/containers`
 * `container/cpu/utilizations`
+* `container/memory/utilizations`
 
 
 ## Notes
@@ -218,49 +219,6 @@ module "signalfx-detectors-integration_gcp-cloud-run" {
 }                                                                                                                                                                                                                                                                                                                   
 ```
 
-### Connection refused to cloud sql
-
-Keeping track of this ratio is crucial in ensuring smooth and maintained service.
-
-```hcl                                                                                                                                                                                                                                                                                                               
-module "signalfx-detectors-integration_gcp-cloud-run" {                                                                                                                                                                                                                                                             
-  source = "github.com/claranet/terraform-signalfx-detectors.git//modules/integration_gcp-cloud-run"                                                                                                                                                                                                                
-                                                                                                                                                                                                                                                                                                                    
-  environment    = var.environment                                                                                                                                                                                                                                                                                  
-  gcp_project_id = var.project_id                                                                                                                                                                                                                                                                                   
-  notifications  = local.notifications                                                                                                                                                                                                                                                                              
-                                                                                                                                                                                                                                                                                                                    
-  # We keep default filtering policy here, we just want to append additional filter to it                                                                                                                                                                                                                           
-  filtering_append = true                                                                                                                                                                                                                                                                                           
-  # We define the additional filter
-  filtering_custom = "filter('service_name', '*service-name*')"                                                                                                                                                                                                                                                     
-  # We can configure the thresholds of the probes
-  connection_refused_to_sql_ratio_threshold_critical = 85                                                                                                                                                                                                                                                                              
-  connection_refused_to_sql_ratio_threshold_major    = 80                                                                                                                                                                                                                                                                              
-}                                                                                                                                                                                                                                                                                                                   
-```
-### Error 5xx
-
-Monitoring server-side errors to track and rectify system issues.
-
-```hcl                                                                                                                                                                                                                                                                                                              
-module "signalfx-detectors-integration_gcp-cloud-run" {                                                                                                                                                                                                                                                             
-  source = "github.com/claranet/terraform-signalfx-detectors.git//modules/integration_gcp-cloud-run"                                                                                                                                                                                                                
-                                                                                                                                                                                                                                                                                                                    
-  environment    = var.environment                                                                                                                                                                                                                                                                                  
-  gcp_project_id = var.project_id                                                                                                                                                                                                                                                                                   
-  notifications  = local.notifications                                                                                                                                                                                                                                                                              
-                                                                                                                                                                                                                                                                                                                    
-  # We keep default filtering policy here, we just want to append additional filter to it                                                                                                                                                                                                                           
-  filtering_append = true                                                                                                                                                                                                                                                                                           
-  # We define the additional filter
-  filtering_custom = "filter('service_name', '*service-name*')"                                                                                                                                                                                                                                                     
-  # We can configure the thresholds of the probes                                                                                                                                                                                                                                      
-  error_rate_5xx_threshold_critical = 10                                                                                                                                                                                                                                                           
-  error_rate_5xx_threshold_major    = 80                                                                                                                                                                                                                                                           
-}                                                                                                                                                                                                                                                                                                                   
-```
-
 
 ## Related documentation
 

diff --git a/modules/integration_gcp-cloud-run/conf/00-heartbeat.yaml b/modules/integration_gcp-cloud-run/conf/00-heartbeat.yaml
@@ -0,0 +1,15 @@
+module: "GCP Cloud Run"
+name: "heartbeat"
+
+transformation: true
+aggregation: true
+
+signals:
+  signal:
+    metric: "container/containers"
+
+rules:
+  critical:
+    threshold: 0
+    comparator: "=="
+
diff --git a/modules/integration_gcp-cloud-run/conf/02-memory_utilizations.yaml b/modules/integration_gcp-cloud-run/conf/02-memory_utilizations.yaml
@@ -6,7 +6,7 @@ transformation: ".min(over='30m')"
 
 signals:
   signal:
-    metric: "container/cpu/utilizations"
+    metric: "container/memory/utilizations"
 
 rules:
   critical: