@hiiretail/gcp-infra-cli 0.80.0 → 0.80.2

package/generators/docs/runbook/templates/docs/runbook.md

@@ -2,47 +2,88 @@
 
 ## General
 
-<!-- Describe in short what the purpose of the solution is. -->
+<!-- Describe, in short, what the system does and the interactions with external and/or third party systems.
+
+Example:
+
+Transaction Repository is a centralized product which receives transactions from many parts of Hii Retail. The intention is to store transactions long term and to expose a search API to be able to search for transactions.
+-->
 
 ## Architecture
 
-<!-- Include C4 diagrams or links to the Software Guidebook. -->
+<!-- Include the C4 diagrams and a link to the Software Guidebook. -->
 
 ## Business Continuity and Disaster Recovery Plan
 
-<!-- Link to the Business Continuity and Disaster Recovery Plan documentation. -->
+<!-- Add a link to the Business Continuity and Disaster Recovery Plan. -->
 
 ## Services
 
-<!-- A short description of what the purpose of each service is. Links to the log files of all the services that are included in the solution. -->
+<!-- List all internal services that are a part of the system with a short explanation of their purpose and a link to the logs of the service.
+-->
 
 ## Dashboard
 
-<!-- Links to one or multiple dashboards. -->
+<!-- Add link(s) to the dashboard(s) that are setup. Write a short explanation what the dashboard displays and the purpose of it.
+-->
 
 ## Service Level Objectives
 
-<!-- What are the SLOs? -->
+<!-- Add a link or include the SLOs for each service that are defined. -->
 
 ## Alerts
 
-<!-- What are the alerts that has been setup, where is alert sent to and what are the steps to mitigate the issue? -->
+<!-- List the alerts according to the format:
+
+Alert name
+  * Description
+  * Notification channels
+  * Remediation steps
+
+Example:
+
+[P1] che.checkout-engine-isrg-nl-checkout-api - Service is offline
+
+Description: Triggers when the uptime check fails
+
+Notification channels:
+  * Slack, #monitoring-channel
+  * SMS
+  * Jira
+
+Remediation steps:
+  1. Check if the memory usage (Link to where to check that) is higher than usual (Is there a threshold?)
+  2. Check if the number of requests (Link to where to check that) are higher than usual
+  3. Follow the Contact & Escalation Matrix
+-->
 
 ## Health Checks
 
-<!-- Links to the configured uptime checks that has been setup in GCP. -->
+<!-- Add links to the configured health checks in GCP -->
+
+## Accessibility (GCP)
+
+<!-- What permissions are required to access the GCP resources that are used by the system?
+
+Example:
+  * Cloud SQL - roles/cloudsql.editor (txengine-prod-1c85)
+  * Secret Manager - roles/secretmanager.admin (cardpayment-prod-d5b4)
+
+Add examples on how to use the Just-In-Time Access system (https://jit-access.retailsvc.com/)
+-->
 
 ## How do I..?
 
-<!-- Good to know things. Such as `How do I check the price for a specific item?` -->
+<!-- Good to know things, such as "How do I connect to the database?", "How do I find a specific item?"  -->
 
 ## Known Issues
 
-<!-- Are there any known issues? If yes, what is the workaround to solve them? -->
+<!-- Are there any known issues that requires manual intervention? Is there a workaround for the issue? There should be a short description of the issue and a link to the Jira where more details can be found.
+-->
 
 ## Contact & Escalation Matrix
 
-<!-- If the team is unable to resolve the issue, who is the first in line to contact?
+<!-- If the team is unable to resolve or need to escalate an incident, who is the first to contact?
 
 | #  | Name | Role | E-Mail | Phone number |
 | --- | --- | --- | --- | --- |

package/generators/resources/monitoring/index.js

@@ -7,10 +7,12 @@ const { required } = require('../../../src/validators');
 const validate = require('./validate');
 const { handleSlos, handleAlerts, handleUptimeChecks } = require('./handle-yaml');
 const { getProjectId } = require('../pubsub/get-gcp-projects');
+const getTribeAndClanName = require('../../init/clan-infra/tribe-clan-repo');
 
 const uptimeCheckTemplates = yaml.load(fs.readFileSync(`${__dirname}/templates/uptime-checks/uptime-checks.yaml`));
 const alertTemplates = yaml.load(fs.readFileSync(`${__dirname}/templates/alerts/alerts.yaml`));
 const sloTemplates = yaml.load(fs.readFileSync(`${__dirname}/templates/slos/slos.yaml`));
+const { clan: defaultClan } = getTribeAndClanName();
 const projectId = getProjectId('prod');
 
 module.exports = class extends BaseGenerator {
@@ -35,7 +37,7 @@ module.exports = class extends BaseGenerator {
         choices: (answers) => Object.keys(alertTemplates[`${answers.alertResource}`]),
       },
       {
-        when: (response) => ['alerts', 'slos', 'uptime-checks'].includes(response.monitoringResource),
+        when: (response) => ['slos', 'uptime-checks'].includes(response.monitoringResource) || response.alertResource === 'cloud_run',
         type: 'input',
         name: 'systemName',
         message: 'Please provide three-letter system name as defined in Styra (example: sre, ptf, sda, che, pnp, iam...)',
@@ -146,8 +148,10 @@ module.exports = class extends BaseGenerator {
       const yamlPath = `${resourceDir}/alerts.yaml`;
 
       copyTemplate('alerts', resourceDir, yamlPath);
+
       const oldYaml = yaml.load(fs.readFileSync(yamlPath, 'utf8')) || [];
-      const newYaml = await handleAlerts(oldYaml, alertTemplates, this.answers);
+      const newYaml = await handleAlerts(oldYaml, alertTemplates,
+        { ...this.answers, clan: defaultClan });
 
       fs.writeFileSync(yamlPath, yaml.dump(newYaml));
     }

package/generators/resources/monitoring/templates/alerts/alerts.yaml

@@ -18,7 +18,7 @@ cloud_run:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
 cloud_scheduler:
   failed_job:
-    display_name: "[P4] <%-systemName%> - Cloud Scheduler | Job Failed"
+    display_name: "[P4] <%-clan%> - Cloud Scheduler | Job Failed"
     conditions:
       - display_name: Cloud Scheduler Job - Log entries with SEVERITY=Error exceed threshold
         condition_threshold:
@@ -36,7 +36,7 @@ cloud_scheduler:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
 cloud_sql:
   cpu_over_65:
-    display_name: "[P3] <%-systemName%> - CloudSQL | CPU over 65%"
+    display_name: "[P3] <%-clan%> - CloudSQL | CPU over 65%"
     conditions:
       - display_name: Cloud SQL Database - CPU utilization above 65% over 5 min
         condition_threshold:
@@ -53,7 +53,7 @@ cloud_sql:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   cpu_over_85:
-    display_name: "[P3] <%-systemName%> - CloudSQL | CPU over 85%"
+    display_name: "[P3] <%-clan%> - CloudSQL | CPU over 85%"
     conditions:
       - display_name: "Cloud SQL Database - CPU-usage above 85% over 1 min"
         condition_threshold:
@@ -70,7 +70,7 @@ cloud_sql:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   cpu_over_90:
-    display_name: "[P3] <%-systemName%> - CloudSQL | CPU over 90%"
+    display_name: "[P3] <%-clan%> - CloudSQL | CPU over 90%"
     conditions:
       - display_name: Cloud SQL Database - CPU-usage above 90%
         condition_threshold:
@@ -86,7 +86,7 @@ cloud_sql:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   query_over_1s:
-    display_name: "[P4] <%-systemName%> - CloudSQL | Query resolve time"
+    display_name: "[P4] <%-clan%> - CloudSQL | Query resolve time"
     conditions:
       - display_name: Cloud SQL Instance Database - Per query execution times above 1000 ms
         condition_threshold:
@@ -103,7 +103,7 @@ cloud_sql:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
 memorystore:
   memory_over_50:
-    display_name: "[P4] <%-systemName%> - Memorystore | Memory over 50%"
+    display_name: "[P4] <%-clan%> - Memorystore | Memory over 50%"
     conditions:
       - display_name: Memorystore Redis Instance - Memory Usage above 50% over 5 min
         condition_threshold:
@@ -120,7 +120,7 @@ memorystore:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   memory_over_75:
-    display_name: "[P4] <%-systemName%> - Memorystore | Memory over 75%"
+    display_name: "[P4] <%-clan%> - Memorystore | Memory over 75%"
     conditions:
       - display_name: Memorystore Redis Instance - Memory Usage above 75% for 5min
         condition_threshold:
@@ -137,7 +137,7 @@ memorystore:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   memory_over_90:
-    display_name: "[P2] <%-systemName%> - Memorystore | Memory over 90%"
+    display_name: "[P2] <%-clan%> - Memorystore | Memory over 90%"
     conditions:
       - display_name: Memorystore Redis Instance - Memory Usage above 90%
         condition_threshold:
@@ -155,7 +155,7 @@ memorystore:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
 pub_sub:
   unacknowledged_messages:
-    display_name: "[P3] <%-systemName%> - Pub/Sub | Undelivered message(s)"
+    display_name: "[P3] <%-clan%> - Pub/Sub | Undelivered message(s)"
     conditions:
       - display_name: Cloud Pub/Sub Subscription - Undelivered messages above 1 for 5 min
         condition_threshold:
@@ -172,7 +172,7 @@ pub_sub:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   messages_in_dlq:
-    display_name: "[P3] <%-systemName%> - Pub/Sub | Message(s) in DLQ"
+    display_name: "[P3] <%-clan%> - Pub/Sub | Message(s) in DLQ"
     conditions:
       - display_name: Cloud Pub/Sub Subscription - Number of undelivered message(s) forwarded to DLQ
         condition_threshold:
@@ -189,7 +189,7 @@ pub_sub:
     documentation:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
   latency:
-    display_name: "[P3] <%-systemName%> - Pub/Sub | Response latency distribution"
+    display_name: "[P3] <%-clan%> - Pub/Sub | Response latency distribution"
     conditions:
       - display_name: Cloud Pub/Sub Subscription - Latency above 3s
         condition_threshold:
@@ -208,7 +208,7 @@ pub_sub:
       content: <% if (runbookLink) { %>[Runbook](<%-runbookLink%>)<%} else { %> <% } %>
 cloud_function:
   failed_execution:
-    display_name: "[P2] <%-systemName%> - Cloud Function | Failed job execution"
+    display_name: "[P2] <%-clan%> - Cloud Function | Failed job execution"
     conditions:
       - display_name: Cloud Function - Execution error count
         condition_threshold:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hiiretail/gcp-infra-cli",
-  "version": "0.80.0",
+  "version": "0.80.2",
   "description": "Infrastructure as code generator for GCP.",
   "main": "src/cli.js",
   "bin": {