@hiiretail/gcp-infra-cli 0.101.0 → 0.102.1

package/generators/common-resources/monitoring/templates/alerts/generic-infra.yaml

@@ -430,16 +430,16 @@ cloud_function:
       subject: 'Function: `$${resource.label.function_name}`'
 cloud_run:
   error_count:
-    display_name: "[P3] <%-clan%> - Cloud Run | Error Count"
+    display_name: "[P3] <%-clan%> - Cloud Run | Error rate"
     conditions:
-      - display_name: Error count above threshold for more than 5 minutes
+      - display_name: Error rate above threshold for more than 5 minutes
         condition_threshold:
           filter: |
             resource.type="cloud_run_revision"
             metric.type="run.googleapis.com/request_count"
             metric.label.response_code_class="5xx"
             resource.labels.project_id="<%-projectId%>"
-          threshold_value: 50
+          threshold_value: 0.05
           duration: 300s
           aggregations:
             - alignment_period: 60s
@@ -527,57 +527,61 @@ cloud_run:
       subject: 'Service: `$${resource.label.service_name}`'
 spanner:
   cpu_utilization_by_priority:
-    display_name: "[P1] <%-clan%> - Spanner | CPU Utilization by Priority"
+    display_name: "[P2] <%-clan%> - Spanner | CPU Utilization"
     conditions:
-      - display_name: Spanner - CPU Utilization by Priority
+      - display_name: Cloud Spanner Database - CPU Utilization
         condition_threshold:
           filter: |
-            resource.type="spanner_instance"
-            metric.type="spanner.googleapis.com/instance/cpu/utilization_by_priority"
+            resource.type = "spanner_instance"
+            metric.type = "spanner.googleapis.com/instance/cpu/utilization"
             resource.labels.project_id="<%-projectId%>"
-          threshold_value: 0.9
+          threshold_Value: 0.8
           duration: 300s
           aggregations:
             - alignment_period: 60s
-              per_series_aligner: ALIGN_MAX
-              cross_series_reducer: REDUCE_SUM
+              cross_series_reducer: REDUCE_MEAN
+              per_series_aligner: ALIGN_MEAN
               group_by_fields:
-                - resource.label.instance_id
+                - metric.label.database
     documentation:
-      subject: 'Instance: `$${resource.label.instance_id}`'
-  api_request_count:
-    display_name: "[P2] <%-clan%> - Spanner | API Request Count"
+      subject: 'Instance: `$${resource.label.instance_id}`, Database: `$${resource.label.database}`'
+  api_request_error_rate:
+    display_name: "[P2] <%-clan%> - Spanner | API request error rate"
     conditions:
-      - display_name: Spanner - API Request Count
+      - display_name: Cloud Spanner Database - API request error rate
         condition_threshold:
           filter: |
-            resource.type="spanner_instance"
-            metric.type="spanner.googleapis.com/api/api_request_count"
-            resource.labels.project_id="<%-projectId%>"
-          threshold_value: 1000
+            resource.type = "spanner_instance"
+            metric.type = "spanner.googleapis.com/api/api_request_count"
+            metric.labels.status != "OK"
+          threshold_value: 1
           duration: 300s
           aggregations:
             - alignment_period: 60s
-              per_series_aligner: ALIGN_SUM
+              cross_series_reducer: REDUCE_MEAN
+              per_series_aligner: ALIGN_RATE
               group_by_fields:
-                - resource.label.instance_id
+                - metric.label.status
+                - resource.label.database
     documentation:
-      subject: 'Instance: `$${resource.label.instance_id}`'
+      subject: 'Instance: `$${resource.label.instance_id}`, Database: `$${resource.label.database}}`'
   request_latencies:
-    display_name: "[P3] <%-clan%> - Spanner | Request Latencies"
+    display_name: '[P3] <%-clan%> - Spanner | API transaction latency'
     conditions:
-      - display_name: Spanner - Request Latencies
+      - display_name: Cloud Spanner Instance - Request latencies by transaction type
         condition_threshold:
           filter: |
-            resource.type="spanner_instance"
-            metric.type="spanner.googleapis.com/api/request_latencies"
-            resource.labels.project_id="<%-projectId%>"
-          threshold_value: 500
+            resource.type = "spanner_instance"
+            metric.type = "spanner.googleapis.com/api/request_latencies_by_transaction_type"
+            metric.labels.transaction_type = "READ_WRITE"
           duration: 300s
+          threshold_value: 100
           aggregations:
             - alignment_period: 60s
-              per_series_aligner: ALIGN_MEAN
+              cross_series_reducer: REDUCE_PERCENTILE_95
               group_by_fields:
-                - resource.label.instance_id
+                - metric.label.database
+                - metric.label.transaction_type
+              per_series_aligner: ALIGN_PERCENTILE_95
     documentation:
-      subject: 'Instance: `$${resource.label.instance_id}`'
+      subject: 'Instance: `$${resource.label.instance_id}`, Database: `$${resource.label.database}}`'

package/generators/docs/rca/templates/docs/rca_external.md

@@ -3,19 +3,41 @@
 ## Summary
 
 <!--
-This section should be written last, when all of the other bullets in the RCA has been written. The purpose of this section is to have a section that can be
-shared with external customers as well as internal stakeholders. Some guidelines and pointers:
+Briefly summarize what happened, who was impacted (e.g., end-users, stores), and the business consequences (e.g., data loss, incorrect pricing, downtime).
+  * Incident Description: Brief overview of what happened (2-3 sentences)
+  * Root Cause: One-sentence explanation of the fundamental issue
+  * Resolution: Brief description of how the issue was resolved
+  * Resolution Time: When the issue was fully resolved
+-->
+
+## Technical Details
+
+<!--
+Provide a clear explanation of the technical root cause. Include:
+  * What change or event triggered the incident
+  * How the system behaved unexpectedly
+  * Details about any configuration changes, bugs, or missing logic
+
+Any dependencies or services involved.
+-->
 
-* Think of it as the back cover of a book, a short but descriptive story
-* The people who will read this will most likeley not have the technical know-how that we do, keep it simple
-* Include what the problem was and how the customer(s) was affected
-* Do NOT include any customer names
-* Do NOT include any Hii Retail service names or underlying technologies that we are using
-* Include some general action points, such as if additional alerts needs to be added. Do not add details
-* Don't make promises, if there are any actions that we will look at, just mention them. Don't include target dates
+## Impact
 
-Example:
-On January 25 2023 from 14:31 CET to 15:59 CET some customers may have experienced delays with card payments. The issue was traced back to a misconfiguration of a recent deployment. At 15:31 CET a fix was deployed and monitored. At 15:59 CET the issue was resolved for all affected customers.
+<!--
+Describe the direct and indirect consequences of the incident.
+  * Customer Impact: How customers/end-users were affected
+  * Business Impact: Financial or operational consequences
+  * Duration: Total time the issue persisted
+  * Scope: Which systems/users were affected
+-->
+
+## Lessons Learned
+
+<!--
+Highlight what could have prevented the incident:
 
-We will look into the process of how we update our configuration in production to mitigate these issues going forward.
+  * Gaps in testing
+  * Gaps in monitoring
+  * Gaps in requirements
+  * etc.
 -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hiiretail/gcp-infra-cli",
-  "version": "0.101.0",
+  "version": "0.102.1",
   "description": "Infrastructure as code generator for GCP.",
   "main": "src/cli.js",
   "bin": {