[{"data":1,"prerenderedAt":222},["ShallowReactive",2],{"term-a\u002Falerting":3,"related-a\u002Falerting":202},{"id":4,"title":5,"acronym":6,"body":7,"category":181,"description":182,"difficulty":183,"extension":184,"letter":185,"meta":186,"navigation":187,"path":188,"related":189,"seo":196,"sitemap":197,"stem":200,"subcategory":6,"__hash__":201},"terms\u002Fterms\u002Fa\u002Falerting.md","Alerting",null,{"type":8,"value":9,"toc":175},"minimark",[10,15,19,23,26,30,164,168,171],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 — The Vibe Check",[16,17,18],"p",{},"Alerting is the part of monitoring that actually wakes people up when something goes wrong. You define rules: 'If error rate > 1% for 5 minutes, send a PagerDuty alert.' Without alerting, monitoring is like a smoke detector with no alarm — useless when the house is on fire.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"Alerting is a monitoring subsystem that evaluates rules against collected metrics and sends notifications when thresholds are breached. Alert rules define conditions, severities, and notification channels (Slack, PagerDuty, email). Good alerting is actionable — alerts should require a human response.",[11,27,29],{"id":28},"show-me-the-code","Show Me The Code",[31,32,37],"pre",{"className":33,"code":34,"language":35,"meta":36,"style":36},"language-yaml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Prometheus alert rule\ngroups:\n  - name: app.rules\n    rules:\n      - alert: HighErrorRate\n        expr: rate(http_errors_total[5m]) > 0.01\n        for: 5m\n        labels:\n          severity: critical\n        annotations:\n          summary: \"Error rate above 1%\"\n","yaml","",[38,39,40,49,60,76,84,98,109,120,128,139,147],"code",{"__ignoreMap":36},[41,42,45],"span",{"class":43,"line":44},"line",1,[41,46,48],{"class":47},"sHwdD","# Prometheus alert rule\n",[41,50,52,56],{"class":43,"line":51},2,[41,53,55],{"class":54},"swJcz","groups",[41,57,59],{"class":58},"sMK4o",":\n",[41,61,63,66,69,72],{"class":43,"line":62},3,[41,64,65],{"class":58},"  -",[41,67,68],{"class":54}," name",[41,70,71],{"class":58},":",[41,73,75],{"class":74},"sfazB"," app.rules\n",[41,77,79,82],{"class":43,"line":78},4,[41,80,81],{"class":54},"    rules",[41,83,59],{"class":58},[41,85,87,90,93,95],{"class":43,"line":86},5,[41,88,89],{"class":58},"      -",[41,91,92],{"class":54}," alert",[41,94,71],{"class":58},[41,96,97],{"class":74}," HighErrorRate\n",[41,99,101,104,106],{"class":43,"line":100},6,[41,102,103],{"class":54},"        expr",[41,105,71],{"class":58},[41,107,108],{"class":74}," rate(http_errors_total[5m]) > 0.01\n",[41,110,112,115,117],{"class":43,"line":111},7,[41,113,114],{"class":54},"        for",[41,116,71],{"class":58},[41,118,119],{"class":74}," 5m\n",[41,121,123,126],{"class":43,"line":122},8,[41,124,125],{"class":54},"        labels",[41,127,59],{"class":58},[41,129,131,134,136],{"class":43,"line":130},9,[41,132,133],{"class":54},"          severity",[41,135,71],{"class":58},[41,137,138],{"class":74}," critical\n",[41,140,142,145],{"class":43,"line":141},10,[41,143,144],{"class":54},"        annotations",[41,146,59],{"class":58},[41,148,150,153,155,158,161],{"class":43,"line":149},11,[41,151,152],{"class":54},"          summary",[41,154,71],{"class":58},[41,156,157],{"class":58}," \"",[41,159,160],{"class":74},"Error rate above 1%",[41,162,163],{"class":58},"\"\n",[11,165,167],{"id":166},"when-youll-hear-this","When You'll Hear This",[16,169,170],{},"\"Set up alerting so the on-call engineer gets paged if the service is down.\" \u002F \"Too many false-positive alerts cause alert fatigue — tune them carefully.\"",[172,173,174],"style",{},"html pre.shiki code .sHwdD, html code.shiki .sHwdD{--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic}html pre.shiki code .swJcz, html code.shiki .swJcz{--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178}html pre.shiki code .sMK4o, html code.shiki .sMK4o{--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF}html pre.shiki code .sfazB, html code.shiki .sfazB{--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D}html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":36,"searchDepth":51,"depth":51,"links":176},[177,178,179,180],{"id":13,"depth":51,"text":14},{"id":21,"depth":51,"text":22},{"id":28,"depth":51,"text":29},{"id":166,"depth":51,"text":167},"cicd","Alerting is the part of monitoring that actually wakes people up when something goes wrong.","beginner","md","a",{},true,"\u002Fterms\u002Fa\u002Falerting",[190,191,192,193,194,195],"Monitoring","On-call","Pager","Incident","Metrics","Prometheus",{"title":5,"description":182},{"changefreq":198,"priority":199},"weekly",0.7,"terms\u002Fa\u002Falerting","KsHhlel8K3-GK4dB4_5_JDmmQFLfKq3AqFAHjv-vW6E",[203,206,209,212,215,218],{"title":193,"path":204,"acronym":6,"category":181,"difficulty":183,"description":205},"\u002Fterms\u002Fi\u002Fincident","An incident is when something has gone wrong in production and users are affected.",{"title":194,"path":207,"acronym":6,"category":181,"difficulty":183,"description":208},"\u002Fterms\u002Fm\u002Fmetrics","Metrics are the numbers your app tracks about itself over time — requests per second, error rate, CPU usage, response time, active users.",{"title":190,"path":210,"acronym":6,"category":181,"difficulty":183,"description":211},"\u002Fterms\u002Fm\u002Fmonitoring","Monitoring is keeping a constant eye on your app while it runs — tracking whether it's up, how fast it responds, how many errors it throws, and how much me...",{"title":191,"path":213,"acronym":6,"category":181,"difficulty":183,"description":214},"\u002Fterms\u002Fo\u002Fon-call","On-call means it's your turn to be the person who gets woken up at 3am if production breaks.",{"title":192,"path":216,"acronym":6,"category":181,"difficulty":183,"description":217},"\u002Fterms\u002Fp\u002Fpager","A pager (or more likely PagerDuty\u002FOpsGenie today) is the alert that goes off on the on-call engineer's phone when something breaks in production.",{"title":195,"path":219,"acronym":6,"category":181,"difficulty":220,"description":221},"\u002Fterms\u002Fp\u002Fprometheus","intermediate","Prometheus scrapes your services every 15 seconds asking 'how are you?' and stores the answers (metrics) as time series.",1776518254851]