@hiiretail/gcp-infra-cli 0.70.0 → 0.71.0

package/generators/docs/rca/generator.json

@@ -0,0 +1,4 @@
+{
+  "name": "Root Cause Analysis documentation",
+  "description": "Create a Root Cause Analysis template"
+}

package/generators/docs/rca/index.js

@@ -0,0 +1,44 @@
+const chalk = require('chalk');
+const BaseGenerator = require('../../../src/BaseGenerator');
+const { required } = require('../../../src/validators');
+
+module.exports = class extends BaseGenerator {
+  prompting() {
+    const prompts = [
+      {
+        type: 'input',
+        name: 'description',
+        message: 'A very short description of the problem',
+        validate: required,
+      },
+      {
+        type: 'input',
+        name: 'date',
+        message: 'Date of the incident',
+        validate: required,
+      },
+    ];
+
+    return this.prompt(prompts).then((props) => {
+      this.answers = props;
+    });
+  }
+
+  writing() {
+    const { date } = this.answers;
+    const filename = `rca_${date}`;
+
+    this.fs.copyTpl(
+      this.templatePath('docs', 'rca.md'),
+      this.destinationPath('docs', 'rca', `${filename}.md`),
+      this.answers,
+    );
+  }
+
+  end() {
+    this.log(`
+${chalk.green('Your RCA template have now been created.')}
+Next, push this change in a feature branch and open a pull request.
+`);
+  }
+};

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

@@ -0,0 +1,75 @@
+# RCA - <%-description%> - <%-date%>
+
+## Overview
+
+**Incident start**: <!-- The date and time when the incident started, for example: 2022-06-14 14.36 CET -->
+
+**Incident end**: <!-- The date and time when the incident was resolved, for example: 2022-06-14 14.53 CET -->
+
+**Problem statement**: <!-- Describe, in short, what the problem was -->
+
+**Impacted customer(s)**: <!-- What customer(s) that were affected -->
+
+**Impact to customer**: <!-- Describe how the customer, and end customers, was affected by the incident -->
+
+**Ticket information**: <!-- Add link(s) to any Jira issues -->
+
+**Services involved**: <!-- List the services that were involved in the incident -->
+
+## Sequence of Events
+
+<!--
+Describe the events that caused the incident, starting from first getting notified about the incident until the incident was resolved.
+
+Example:
+
+2022-06-14 14.36 - Alert X was triggered
+2022-06-14 14.36 - Team started working on the incident
+2022-06-14 14.49 - A fix was pushed and deployed
+2022-06-14 14.53 - Incident was resolved
+-->
+
+## Five Whys
+
+<!--
+Five whys is a technique used to explore the cause and effect underlying a particular problem. The primary goal of the technique is to determine the root cause of a problem by repeating the question "Why?". Each answer forms the basis of the next question.
+
+Example:
+
+Problem: The vehicle won't start
+
+  1. __Why?__ - The battery is dead (First why)
+  2. __Why?__ - The alternator is not functioning (Second why)
+  3. __Why?__ - The alternator belt is broken (Third why)
+  4. __Why?__ - The alternator belt was well beyond its useful service life and not replaced. (Fourth why)
+  5. __Why?__ - The vehicle was not maintained according to the recommended service schedule. (Fifth why, the root cause)
+-->
+
+  1. __Why?__
+  2. __Why?__
+  3. __Why?__
+  4. __Why?__
+  5. __Why?__
+
+## Summary
+
+<!--
+Write a short summary of what the problem was, what the root cause was and what potentially action items that were taken.
+-->
+
+## Action items
+
+<!--
+A table that describes the different actions that was the outcome of the analysis, who is the owner of the task and the status of the task.
+The status should be updated until the action is completed.
+
+Example:
+| Description | Owner | Date | Status |
+|-------------|-------|------|--------|
+| Create alert for high CPU Usage | Bob the Builder | 2022-06-14 | Not started |
+|             |       |      |        |
+-->
+
+| Description | Owner | Date | Status |
+|-------------|-------|------|--------|
+|             |       |      |        |

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

@@ -2,49 +2,50 @@
 
 ## General
 
-Describe in short what the purpose of the solution is.
+<!-- Describe in short what the purpose of the solution is. -->
 
 ## Architecture
 
-Include C4 diagrams or links to the Software Guidebook.
+<!-- Include C4 diagrams or links to the Software Guidebook. -->
 
 ## Business Continuity and Disaster Recovery Plan
 
-Link to the Business Continuity and Disaster Recovery Plan documentation.
+<!-- Link to the Business Continuity and Disaster Recovery Plan documentation. -->
 
 ## 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.
+<!-- 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. -->
 
 ## Dashboard
 
-Links to one or multiple dashboards.
+<!-- Links to one or multiple dashboards. -->
 
 ## Service Level Objectives
 
-What are the SLOs?
+<!-- What are the SLOs? -->
 
 ## Alerts
 
-What are the alerts that has been setup, where is alert sent to and what are the steps to mitigate the issue?
+<!-- What are the alerts that has been setup, where is alert sent to and what are the steps to mitigate the issue? -->
 
 ## Health Checks
 
-Links to the configured uptime checks that has been setup in GCP.
+<!-- Links to the configured uptime checks that has been setup in GCP. -->
 
 ## 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 check the price for a specific item?` -->
 
 ## Known Issues
 
-Are there any known issues? If yes, what is the workaround to solve them?
+<!-- Are there any known issues? If yes, what is the workaround to solve them? -->
 
 ## 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 the issue, who is the first in line to contact?
 
 | #  | Name | Role | E-Mail | Phone number |
 | --- | --- | --- | --- | --- |
 | 1 | Mr X | My Role | mr.x@x.com | 1234567 |
 | 2 | Mr Y | My Role | mr.y@y.com | 7654321 |
+-->

package/generators/docs/srb/templates/docs/sre.md

@@ -1,9 +1,43 @@
 # Observability and SRE
 
-## SLIs
+<!--
+Explain what metrics you will monitor and how you will monitor them. Read through the SRE Chapter documentation
+and adopt the guidelines and naming convetions that exist, https://github.com/extenda/chap-sre-docs/blob/master/README.md
 
-## SLOs
+List
 
-## Observability
+  * that the clan will use GCP Operations to monitor their service and GCP-resources
+  * that the clan will keep this documentation up-to-date through the lifecycle of the service
+  * that the clan will create and maintain a Runbook
+-->
 
-## Operations monitoring and alert
+## Service A
+
+<!--
+List the SLIs and SLOs per service, more information about SLIs and SLOs can be found here, https://github.com/extenda/chap-sre-docs/blob/master/docs/service-levels.md
+All services must list and explain how they will monitor and have SLOs set for:
+
+  * Availability
+  * Latency
+  * Throughput
+  * Error rate
+
+If the team need to monitor any additional SLOs, it must be mentioned how they plan to monitor that.
+
+If not using fully-managed services by Google, SLIs and SLOs needs to be set for those as well. When using fully-managed services, only SLIs needs to be monitored
+Example:
+
+  * A clan is using Cloud SQL
+  * Then they need to set SLIs and SLOs based on when they need to increase CPU and Memory for example
+
+-->
+
+### SLIs
+
+### SLOs
+
+## Service B
+
+### SLIs
+
+### SLOs

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hiiretail/gcp-infra-cli",
-  "version": "0.70.0",
+  "version": "0.71.0",
   "description": "Infrastructure as code generator for GCP.",
   "main": "src/cli.js",
   "bin": {