724 lines
30 KiB
HTML
724 lines
30 KiB
HTML
<!DOCTYPE HTML>
|
|
<html lang="en" class="light sidebar-visible" dir="ltr">
|
|
<head>
|
|
<!-- Book generated using mdBook -->
|
|
<meta charset="UTF-8">
|
|
<title>Pre-Deployment Checklist - VAPORA Platform Documentation</title>
|
|
|
|
|
|
<!-- Custom HTML head -->
|
|
|
|
<meta name="description" content="Comprehensive documentation for VAPORA, an intelligent development orchestration platform built entirely in Rust.">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<meta name="theme-color" content="#ffffff">
|
|
|
|
<link rel="icon" href="../favicon.svg">
|
|
<link rel="shortcut icon" href="../favicon.png">
|
|
<link rel="stylesheet" href="../css/variables.css">
|
|
<link rel="stylesheet" href="../css/general.css">
|
|
<link rel="stylesheet" href="../css/chrome.css">
|
|
<link rel="stylesheet" href="../css/print.css" media="print">
|
|
|
|
<!-- Fonts -->
|
|
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
|
|
<link rel="stylesheet" href="../fonts/fonts.css">
|
|
|
|
<!-- Highlight.js Stylesheets -->
|
|
<link rel="stylesheet" id="highlight-css" href="../highlight.css">
|
|
<link rel="stylesheet" id="tomorrow-night-css" href="../tomorrow-night.css">
|
|
<link rel="stylesheet" id="ayu-highlight-css" href="../ayu-highlight.css">
|
|
|
|
<!-- Custom theme stylesheets -->
|
|
|
|
|
|
<!-- Provide site root and default themes to javascript -->
|
|
<script>
|
|
const path_to_root = "../";
|
|
const default_light_theme = "light";
|
|
const default_dark_theme = "dark";
|
|
</script>
|
|
<!-- Start loading toc.js asap -->
|
|
<script src="../toc.js"></script>
|
|
</head>
|
|
<body>
|
|
<div id="mdbook-help-container">
|
|
<div id="mdbook-help-popup">
|
|
<h2 class="mdbook-help-title">Keyboard shortcuts</h2>
|
|
<div>
|
|
<p>Press <kbd>←</kbd> or <kbd>→</kbd> to navigate between chapters</p>
|
|
<p>Press <kbd>S</kbd> or <kbd>/</kbd> to search in the book</p>
|
|
<p>Press <kbd>?</kbd> to show this help</p>
|
|
<p>Press <kbd>Esc</kbd> to hide this help</p>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="body-container">
|
|
<!-- Work around some values being stored in localStorage wrapped in quotes -->
|
|
<script>
|
|
try {
|
|
let theme = localStorage.getItem('mdbook-theme');
|
|
let sidebar = localStorage.getItem('mdbook-sidebar');
|
|
|
|
if (theme.startsWith('"') && theme.endsWith('"')) {
|
|
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
|
|
}
|
|
|
|
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
|
|
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
|
|
}
|
|
} catch (e) { }
|
|
</script>
|
|
|
|
<!-- Set the theme before any content is loaded, prevents flash -->
|
|
<script>
|
|
const default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? default_dark_theme : default_light_theme;
|
|
let theme;
|
|
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
|
|
if (theme === null || theme === undefined) { theme = default_theme; }
|
|
const html = document.documentElement;
|
|
html.classList.remove('light')
|
|
html.classList.add(theme);
|
|
html.classList.add("js");
|
|
</script>
|
|
|
|
<input type="checkbox" id="sidebar-toggle-anchor" class="hidden">
|
|
|
|
<!-- Hide / unhide sidebar before it is displayed -->
|
|
<script>
|
|
let sidebar = null;
|
|
const sidebar_toggle = document.getElementById("sidebar-toggle-anchor");
|
|
if (document.body.clientWidth >= 1080) {
|
|
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
|
|
sidebar = sidebar || 'visible';
|
|
} else {
|
|
sidebar = 'hidden';
|
|
}
|
|
sidebar_toggle.checked = sidebar === 'visible';
|
|
html.classList.remove('sidebar-visible');
|
|
html.classList.add("sidebar-" + sidebar);
|
|
</script>
|
|
|
|
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
|
|
<!-- populated by js -->
|
|
<mdbook-sidebar-scrollbox class="sidebar-scrollbox"></mdbook-sidebar-scrollbox>
|
|
<noscript>
|
|
<iframe class="sidebar-iframe-outer" src="../toc.html"></iframe>
|
|
</noscript>
|
|
<div id="sidebar-resize-handle" class="sidebar-resize-handle">
|
|
<div class="sidebar-resize-indicator"></div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div id="page-wrapper" class="page-wrapper">
|
|
|
|
<div class="page">
|
|
<div id="menu-bar-hover-placeholder"></div>
|
|
<div id="menu-bar" class="menu-bar sticky">
|
|
<div class="left-buttons">
|
|
<label id="sidebar-toggle" class="icon-button" for="sidebar-toggle-anchor" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
|
|
<i class="fa fa-bars"></i>
|
|
</label>
|
|
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
|
|
<i class="fa fa-paint-brush"></i>
|
|
</button>
|
|
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
|
|
<li role="none"><button role="menuitem" class="theme" id="default_theme">Auto</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
|
|
</ul>
|
|
<button id="search-toggle" class="icon-button" type="button" title="Search (`/`)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="/ s" aria-controls="searchbar">
|
|
<i class="fa fa-search"></i>
|
|
</button>
|
|
</div>
|
|
|
|
<h1 class="menu-title">VAPORA Platform Documentation</h1>
|
|
|
|
<div class="right-buttons">
|
|
<a href="../print.html" title="Print this book" aria-label="Print this book">
|
|
<i id="print-button" class="fa fa-print"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora" title="Git repository" aria-label="Git repository">
|
|
<i id="git-repository-button" class="fa fa-github"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora/edit/main/docs/src/../operations/pre-deployment-checklist.md" title="Suggest an edit" aria-label="Suggest an edit">
|
|
<i id="git-edit-button" class="fa fa-edit"></i>
|
|
</a>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div id="search-wrapper" class="hidden">
|
|
<form id="searchbar-outer" class="searchbar-outer">
|
|
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
|
|
</form>
|
|
<div id="searchresults-outer" class="searchresults-outer hidden">
|
|
<div id="searchresults-header" class="searchresults-header"></div>
|
|
<ul id="searchresults">
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
|
|
<script>
|
|
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
|
|
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
|
|
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
|
|
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
|
|
});
|
|
</script>
|
|
|
|
<div id="content" class="content">
|
|
<main>
|
|
<h1 id="pre-deployment-checklist"><a class="header" href="#pre-deployment-checklist">Pre-Deployment Checklist</a></h1>
|
|
<p>Critical verification steps before any VAPORA deployment to production or staging.</p>
|
|
<hr />
|
|
<h2 id="24-hours-before-deployment"><a class="header" href="#24-hours-before-deployment">24 Hours Before Deployment</a></h2>
|
|
<h3 id="communication--scheduling"><a class="header" href="#communication--scheduling">Communication & Scheduling</a></h3>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Schedule deployment with team (record in calendar/ticket)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Post in #deployments channel: "Deployment scheduled for [DATE TIME UTC]"</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Identify on-call engineer for deployment period</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Brief on-call on deployment plan and rollback procedure</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Ensure affected teams (support, product, etc.) are notified</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify no other critical infrastructure changes scheduled same time window</li>
|
|
</ul>
|
|
<h3 id="change-documentation"><a class="header" href="#change-documentation">Change Documentation</a></h3>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Create GitHub issue or ticket tracking the deployment</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Document: what's changing (configs, manifests, versions)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Document: why (bug fix, feature, performance, security)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Document: rollback plan (revision number or previous config)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Document: success criteria (what indicates successful deployment)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Document: estimated duration (usually 5-15 minutes)</li>
|
|
</ul>
|
|
<h3 id="code-review--validation"><a class="header" href="#code-review--validation">Code Review & Validation</a></h3>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
All provisioning changes merged and code reviewed</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Confirm <code>main</code> branch has latest changes</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Run validation locally: <code>nu scripts/validate-config.nu --mode enterprise</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify all 3 modes validate without errors or critical warnings</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check git log for unexpected commits</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Review artifact generation: ensure configs are correct</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="4-hours-before-deployment"><a class="header" href="#4-hours-before-deployment">4 Hours Before Deployment</a></h2>
|
|
<h3 id="environment-verification"><a class="header" href="#environment-verification">Environment Verification</a></h3>
|
|
<h4 id="staging-environment"><a class="header" href="#staging-environment">Staging Environment</a></h4>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Access staging Kubernetes cluster: <code>kubectl cluster-info</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify cluster is healthy: <code>kubectl get nodes</code> (all Ready)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check namespace exists: <code>kubectl get namespace vapora</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify current deployments: <code>kubectl get deployments -n vapora</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check ConfigMap is up to date: <code>kubectl get configmap -n vapora -o yaml | head -20</code></li>
|
|
</ul>
|
|
<h4 id="production-environment-if-applicable"><a class="header" href="#production-environment-if-applicable">Production Environment (if applicable)</a></h4>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Access production Kubernetes cluster: <code>kubectl cluster-info</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify all nodes healthy: <code>kubectl get nodes</code> (all Ready)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check current resource usage: <code>kubectl top nodes</code> (not near capacity)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify current deployments: <code>kubectl get deployments -n vapora</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check pod status: <code>kubectl get pods -n vapora</code> (all Running)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify recent events: <code>kubectl get events -n vapora --sort-by='.lastTimestamp' | tail -10</code></li>
|
|
</ul>
|
|
<h3 id="health-baseline"><a class="header" href="#health-baseline">Health Baseline</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Record current metrics before deployment</p>
|
|
<ul>
|
|
<li>CPU usage per deployment</li>
|
|
<li>Memory usage per deployment</li>
|
|
<li>Request latency (p50, p95, p99)</li>
|
|
<li>Error rate (4xx, 5xx)</li>
|
|
<li>Queue depth (if applicable)</li>
|
|
</ul>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify services are responsive:</p>
|
|
<pre><code class="language-bash">curl http://localhost:8001/health -H "Authorization: Bearer $TOKEN"
|
|
curl http://localhost:8001/api/projects
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Check logs for recent errors:</p>
|
|
<pre><code class="language-bash">kubectl logs deployment/vapora-backend -n vapora --tail=50
|
|
kubectl logs deployment/vapora-agents -n vapora --tail=50
|
|
</code></pre>
|
|
</li>
|
|
</ul>
|
|
<h3 id="infrastructure-check"><a class="header" href="#infrastructure-check">Infrastructure Check</a></h3>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify storage is not near capacity: <code>df -h /var/lib/vapora</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check database health: <code>kubectl exec -n vapora <pod> -- surreal info</code></li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Verify backups are recent (within 24 hours)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Check SSL certificate expiration: <code>openssl s_client -connect api.vapora.com:443 -showcerts | grep "Validity"</code></li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="2-hours-before-deployment"><a class="header" href="#2-hours-before-deployment">2 Hours Before Deployment</a></h2>
|
|
<h3 id="artifact-preparation"><a class="header" href="#artifact-preparation">Artifact Preparation</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Trigger validation in CI/CD pipeline</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Wait for artifact generation to complete</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Download artifacts from pipeline:</p>
|
|
<pre><code class="language-bash"># From GitHub Actions or Woodpecker UI
|
|
# Download: deployment-artifacts.zip
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify artifact contents:</p>
|
|
<pre><code class="language-bash">unzip deployment-artifacts.zip
|
|
ls -la
|
|
# Should contain:
|
|
# - configmap.yaml
|
|
# - deployment.yaml
|
|
# - docker-compose.yml
|
|
# - vapora-{solo,multiuser,enterprise}.{toml,yaml,json}
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Validate manifest syntax:</p>
|
|
<pre><code class="language-bash">yq eval '.' configmap.yaml > /dev/null && echo "✓ ConfigMap valid"
|
|
yq eval '.' deployment.yaml > /dev/null && echo "✓ Deployment valid"
|
|
</code></pre>
|
|
</li>
|
|
</ul>
|
|
<h3 id="test-in-staging"><a class="header" href="#test-in-staging">Test in Staging</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Perform dry-run deployment to staging cluster:</p>
|
|
<pre><code class="language-bash">kubectl apply -f configmap.yaml --dry-run=server -n vapora
|
|
kubectl apply -f deployment.yaml --dry-run=server -n vapora
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Review dry-run output for any warnings or errors</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
If test deployment available, do actual staging deployment and verify:</p>
|
|
<pre><code class="language-bash">kubectl get deployments -n vapora
|
|
kubectl get pods -n vapora
|
|
kubectl logs deployment/vapora-backend -n vapora --tail=5
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Test health endpoints on staging</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Run smoke tests against staging (if available)</p>
|
|
</li>
|
|
</ul>
|
|
<h3 id="rollback-plan-verification"><a class="header" href="#rollback-plan-verification">Rollback Plan Verification</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Document current deployment revisions:</p>
|
|
<pre><code class="language-bash">kubectl rollout history deployment/vapora-backend -n vapora
|
|
# Record the highest revision number
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Create backup of current ConfigMap:</p>
|
|
<pre><code class="language-bash">kubectl get configmap -n vapora vapora-config -o yaml > configmap-backup.yaml
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Test rollback procedure on staging (if safe):</p>
|
|
<pre><code class="language-bash"># Record current revision
|
|
CURRENT_REV=$(kubectl rollout history deployment/vapora-backend -n vapora | tail -1 | awk '{print $1}')
|
|
|
|
# Test undo
|
|
kubectl rollout undo deployment/vapora-backend -n vapora
|
|
|
|
# Verify rollback
|
|
kubectl get deployment vapora-backend -n vapora -o yaml | grep image
|
|
|
|
# Restore to current
|
|
kubectl rollout undo deployment/vapora-backend -n vapora --to-revision=$CURRENT_REV
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Confirm rollback command is documented in ticket/issue</p>
|
|
</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="1-hour-before-deployment"><a class="header" href="#1-hour-before-deployment">1 Hour Before Deployment</a></h2>
|
|
<h3 id="final-checks"><a class="header" href="#final-checks">Final Checks</a></h3>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Confirm all prerequisites met:
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Code merged to main</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Artifacts generated and validated</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Staging deployment tested</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Rollback plan documented</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Team notified</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<h3 id="communication-setup"><a class="header" href="#communication-setup">Communication Setup</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Set status page to "Maintenance Mode" (if public)</p>
|
|
<pre><code>"VAPORA maintenance deployment starting at HH:MM UTC.
|
|
Expected duration: 10 minutes. Services may be briefly unavailable."
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Join #deployments Slack channel</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Prepare message: "🚀 Deployment starting now. Will update every 2 minutes."</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Have on-call engineer monitoring</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify monitoring/alerting dashboards are accessible</p>
|
|
</li>
|
|
</ul>
|
|
<h3 id="access-verification"><a class="header" href="#access-verification">Access Verification</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify kubeconfig is valid and up to date:</p>
|
|
<pre><code class="language-bash">kubectl cluster-info
|
|
kubectl get nodes
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify kubectl version compatibility:</p>
|
|
<pre><code class="language-bash">kubectl version
|
|
# Should match server version reasonably (within 1 minor version)
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Test write access to cluster:</p>
|
|
<pre><code class="language-bash">kubectl auth can-i create deployments --namespace=vapora
|
|
# Should return "yes"
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify docker/docker-compose access (if Docker deployment)</p>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Verify Slack webhook is working (test send message)</p>
|
|
</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="15-minutes-before-deployment"><a class="header" href="#15-minutes-before-deployment">15 Minutes Before Deployment</a></h2>
|
|
<h3 id="final-gono-go-decision"><a class="header" href="#final-gono-go-decision">Final Go/No-Go Decision</a></h3>
|
|
<p><strong>STOP HERE</strong> and make final decision to proceed or reschedule:</p>
|
|
<p><strong>Proceed IF:</strong></p>
|
|
<ul>
|
|
<li>✅ All checklist items above completed</li>
|
|
<li>✅ No critical issues found during testing</li>
|
|
<li>✅ Staging deployment successful</li>
|
|
<li>✅ Team ready and monitoring</li>
|
|
<li>✅ Rollback plan clear and tested</li>
|
|
<li>✅ Within designated maintenance window</li>
|
|
</ul>
|
|
<p><strong>RESCHEDULE IF:</strong></p>
|
|
<ul>
|
|
<li>❌ Any critical issues discovered</li>
|
|
<li>❌ Staging tests failed</li>
|
|
<li>❌ Team member unavailable</li>
|
|
<li>❌ Production issues detected</li>
|
|
<li>❌ Unexpected changes in code/configs</li>
|
|
</ul>
|
|
<h3 id="final-notifications"><a class="header" href="#final-notifications">Final Notifications</a></h3>
|
|
<p>If proceeding:</p>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Post to #deployments: "🚀 Deployment starting in 5 minutes"</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Alert on-call engineer: "Ready to start - confirm you're monitoring"</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Have rollback plan visible and accessible</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Open monitoring dashboard showing current metrics</li>
|
|
</ul>
|
|
<h3 id="terminal-setup"><a class="header" href="#terminal-setup">Terminal Setup</a></h3>
|
|
<ul>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Open terminal with kubeconfig configured:</p>
|
|
<pre><code class="language-bash">export KUBECONFIG=/path/to/production/kubeconfig
|
|
kubectl cluster-info # Verify connected to production
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Open second terminal for tailing logs:</p>
|
|
<pre><code class="language-bash">kubectl logs -f deployment/vapora-backend -n vapora
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Have rollback commands ready:</p>
|
|
<pre><code class="language-bash"># For quick rollback if needed
|
|
kubectl rollout undo deployment/vapora-backend -n vapora
|
|
kubectl rollout undo deployment/vapora-agents -n vapora
|
|
kubectl rollout undo deployment/vapora-llm-router -n vapora
|
|
</code></pre>
|
|
</li>
|
|
<li>
|
|
<p><input disabled="" type="checkbox"/>
|
|
Prepare metrics check script:</p>
|
|
<pre><code class="language-bash">watch kubectl top pods -n vapora
|
|
watch kubectl get pods -n vapora
|
|
</code></pre>
|
|
</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="success-criteria-verification"><a class="header" href="#success-criteria-verification">Success Criteria Verification</a></h2>
|
|
<p>Document what "success" looks like for this deployment:</p>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
All three deployments have updated image IDs</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
All pods reach "Ready" state within 5 minutes</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
No pod restarts: <code>kubectl get pods -n vapora --watch</code> (no restarts column increasing)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
No error logs in first 2 minutes</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Health endpoints respond (200 OK)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
API endpoints respond to test requests</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Metrics show normal resource usage</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
No alerts triggered</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Support team reports no user impact</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="team-roles-during-deployment"><a class="header" href="#team-roles-during-deployment">Team Roles During Deployment</a></h2>
|
|
<h3 id="deployment-lead"><a class="header" href="#deployment-lead">Deployment Lead</a></h3>
|
|
<ul>
|
|
<li>Executes deployment commands</li>
|
|
<li>Monitors progress</li>
|
|
<li>Communicates status updates</li>
|
|
<li>Decides to proceed/rollback</li>
|
|
</ul>
|
|
<h3 id="on-call-engineer"><a class="header" href="#on-call-engineer">On-Call Engineer</a></h3>
|
|
<ul>
|
|
<li>Monitors dashboards and alerts</li>
|
|
<li>Watches for anomalies</li>
|
|
<li>Prepares for rollback if needed</li>
|
|
<li>Available for emergency decisions</li>
|
|
</ul>
|
|
<h3 id="communications-lead-optional"><a class="header" href="#communications-lead-optional">Communications Lead (optional)</a></h3>
|
|
<ul>
|
|
<li>Updates #deployments channel</li>
|
|
<li>Notifies support/product teams</li>
|
|
<li>Updates status page if public</li>
|
|
<li>Handles external communication</li>
|
|
</ul>
|
|
<h3 id="backup-person"><a class="header" href="#backup-person">Backup Person</a></h3>
|
|
<ul>
|
|
<li>Monitors for issues</li>
|
|
<li>Ready to assist with troubleshooting</li>
|
|
<li>Prepares rollback procedures</li>
|
|
<li>Escalates if needed</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="common-issues-to-watch-for"><a class="header" href="#common-issues-to-watch-for">Common Issues to Watch For</a></h2>
|
|
<p>⚠️ <strong>Pod CrashLoopBackOff</strong></p>
|
|
<ul>
|
|
<li>Indicates config or image issue</li>
|
|
<li>Check pod logs: <code>kubectl logs <pod></code></li>
|
|
<li>Check events: <code>kubectl describe pod <pod></code></li>
|
|
<li><strong>Action</strong>: Rollback immediately</li>
|
|
</ul>
|
|
<p>⚠️ <strong>Pending Pods (not starting)</strong></p>
|
|
<ul>
|
|
<li>Check resource availability: <code>kubectl describe pod <pod></code></li>
|
|
<li>Check node capacity</li>
|
|
<li><strong>Action</strong>: Investigate or rollback if resource exhausted</li>
|
|
</ul>
|
|
<p>⚠️ <strong>High Error Rate</strong></p>
|
|
<ul>
|
|
<li>Check application logs</li>
|
|
<li>Compare with baseline errors</li>
|
|
<li><strong>Action</strong>: If >10% error increase, rollback</li>
|
|
</ul>
|
|
<p>⚠️ <strong>Database Connection Errors</strong></p>
|
|
<ul>
|
|
<li>Check ConfigMap has correct database URL</li>
|
|
<li>Verify network connectivity to database</li>
|
|
<li><strong>Action</strong>: Check ConfigMap, fix and reapply if needed</li>
|
|
</ul>
|
|
<p>⚠️ <strong>Memory or CPU Spike</strong></p>
|
|
<ul>
|
|
<li>Monitor trends (sudden spike vs gradual)</li>
|
|
<li>Check if within expected range for new code</li>
|
|
<li><strong>Action</strong>: Rollback if resource limits exceeded</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="post-deployment-documentation"><a class="header" href="#post-deployment-documentation">Post-Deployment Documentation</a></h2>
|
|
<p>After deployment completes, record:</p>
|
|
<ul>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Deployment start time (UTC)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Deployment end time (UTC)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Total duration</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Any issues encountered and resolution</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Rollback performed (Y/N)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Metrics before/after (CPU, memory, latency, errors)</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Team members involved</li>
|
|
<li><input disabled="" type="checkbox"/>
|
|
Blockers or lessons learned</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="sign-off"><a class="header" href="#sign-off">Sign-Off</a></h2>
|
|
<p>Use this template for deployment issue/ticket:</p>
|
|
<pre><code>DEPLOYMENT COMPLETED
|
|
|
|
✓ All checks passed
|
|
✓ Deployment successful
|
|
✓ All pods running
|
|
✓ Health checks passing
|
|
✓ No user impact
|
|
|
|
Deployed by: [Name]
|
|
Start time: [UTC]
|
|
Duration: [X minutes]
|
|
Rollback needed: No
|
|
|
|
Metrics:
|
|
- Latency (p99): [X]ms
|
|
- Error rate: [X]%
|
|
- Pod restarts: 0
|
|
|
|
Next deployment: [Date/Time]
|
|
</code></pre>
|
|
|
|
</main>
|
|
|
|
<nav class="nav-wrapper" aria-label="Page navigation">
|
|
<!-- Mobile navigation buttons -->
|
|
<a rel="prev" href="../../operations/deployment-runbook.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../operations/monitoring-operations.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
|
|
<div style="clear: both"></div>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
|
|
<nav class="nav-wide-wrapper" aria-label="Page navigation">
|
|
<a rel="prev" href="../../operations/deployment-runbook.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../operations/monitoring-operations.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
</nav>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<script>
|
|
window.playground_copyable = true;
|
|
</script>
|
|
|
|
|
|
<script src="../elasticlunr.min.js"></script>
|
|
<script src="../mark.min.js"></script>
|
|
<script src="../searcher.js"></script>
|
|
|
|
<script src="../clipboard.min.js"></script>
|
|
<script src="../highlight.js"></script>
|
|
<script src="../book.js"></script>
|
|
|
|
<!-- Custom JS scripts -->
|
|
|
|
|
|
</div>
|
|
</body>
|
|
</html>
|