[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"me":3,"catalog:en:devops-cloud\u002Freliability-incident-sre":4,"config":256},null,{"field_key":5,"field_name":6,"seniority":7,"topic_key":8,"topic_name":9,"spec_key":7,"spec_name":7,"locale":10,"cell_total":11,"field_total":12,"seniorities":13,"topics":17,"specs":151,"samples":171},"devops-cloud","DevOps \u002F Cloud","","reliability-incident-sre","Reliability Incident Sre","en",75,3375,[14,15,16],"junior","mid","senior",[18,21,24,27,30,33,36,39,42,45,48,51,54,57,60,63,66,69,72,75,78,81,84,87,90,93,96,99,102,105,108,111,114,117,120,123,126,129,130,133,136,139,142,145,148],{"key":19,"name":20,"count":11},"aws-compute-ec2-lambda","Aws Compute Ec2 Lambda",{"key":22,"name":23,"count":11},"aws-databases-rds-dynamodb","Aws Databases Rds Dynamodb",{"key":25,"name":26,"count":11},"aws-iam-security","Aws Iam Security",{"key":28,"name":29,"count":11},"aws-messaging-eventing","Aws Messaging Eventing",{"key":31,"name":32,"count":11},"aws-networking-vpc","Aws Networking Vpc",{"key":34,"name":35,"count":11},"aws-storage-s3-ebs","Aws Storage S3 Ebs",{"key":37,"name":38,"count":11},"azure-compute-vm-appservice","Azure Compute Vm Appservice",{"key":40,"name":41,"count":11},"azure-databases-sql-cosmosdb","Azure Databases Sql Cosmosdb",{"key":43,"name":44,"count":11},"azure-iam-security","Azure Iam Security",{"key":46,"name":47,"count":11},"azure-messaging-eventing","Azure Messaging Eventing",{"key":49,"name":50,"count":11},"azure-networking-vnet","Azure Networking Vnet",{"key":52,"name":53,"count":11},"azure-storage-blob-managed-disk","Azure Storage Blob Managed Disk",{"key":55,"name":56,"count":11},"ci-cd-pipelines","Ci Cd Pipelines",{"key":58,"name":59,"count":11},"cloud-architecture-scaling","Cloud Architecture Scaling",{"key":61,"name":62,"count":11},"containers-orchestration","Containers Orchestration",{"key":64,"name":65,"count":11},"deployment-release-strategies","Deployment Release Strategies",{"key":67,"name":68,"count":11},"gcp-compute-gce-cloudrun","Gcp Compute Gce Cloudrun",{"key":70,"name":71,"count":11},"gcp-databases-cloudsql-spanner-firestore","Gcp Databases Cloudsql Spanner Firestore",{"key":73,"name":74,"count":11},"gcp-iam-security","Gcp Iam Security",{"key":76,"name":77,"count":11},"gcp-messaging-eventing","Gcp Messaging Eventing",{"key":79,"name":80,"count":11},"gcp-networking-vpc","Gcp Networking Vpc",{"key":82,"name":83,"count":11},"gcp-storage-gcs-persistent-disk","Gcp Storage Gcs Persistent Disk",{"key":85,"name":86,"count":11},"infrastructure-as-code","Infrastructure As Code",{"key":88,"name":89,"count":11},"k8s-config-secrets","K8s Config Secrets",{"key":91,"name":92,"count":11},"k8s-observability-troubleshooting","K8s Observability Troubleshooting",{"key":94,"name":95,"count":11},"k8s-scheduling-resources","K8s Scheduling Resources",{"key":97,"name":98,"count":11},"k8s-services-networking","K8s Services Networking",{"key":100,"name":101,"count":11},"k8s-storage","K8s Storage",{"key":103,"name":104,"count":11},"k8s-workloads","K8s Workloads",{"key":106,"name":107,"count":11},"linux-filesystem-permissions-links","Linux Filesystem Permissions Links",{"key":109,"name":110,"count":11},"linux-networking-tools-troubleshooting","Linux Networking Tools Troubleshooting",{"key":112,"name":113,"count":11},"linux-performance-monitoring-resource-limits","Linux Performance Monitoring Resource Limits",{"key":115,"name":116,"count":11},"linux-process-management-signals","Linux Process Management Signals",{"key":118,"name":119,"count":11},"linux-shell-scripting-ops-automation","Linux Shell Scripting Ops Automation",{"key":121,"name":122,"count":11},"linux-systemd-service-management","Linux Systemd Service Management",{"key":124,"name":125,"count":11},"networking-dns-loadbalancing","Networking Dns Loadbalancing",{"key":127,"name":128,"count":11},"observability-monitoring","Observability Monitoring",{"key":8,"name":9,"count":11},{"key":131,"name":132,"count":11},"security-iam-secrets","Security Iam Secrets",{"key":134,"name":135,"count":11},"terraform-hcl-language-expressions","Terraform Hcl Language Expressions",{"key":137,"name":138,"count":11},"terraform-modules-workspaces","Terraform Modules Workspaces",{"key":140,"name":141,"count":11},"terraform-plan-apply-drift-import","Terraform Plan Apply Drift Import",{"key":143,"name":144,"count":11},"terraform-providers-lifecycle-provisioners","Terraform Providers Lifecycle Provisioners",{"key":146,"name":147,"count":11},"terraform-state-backend-locking","Terraform State Backend Locking",{"key":149,"name":150,"count":11},"terraform-testing-policy-cicd","Terraform Testing Policy Cicd",[152,156,159,162,165,168],{"key":153,"name":154,"count":155},"aws","AWS",450,{"key":157,"name":158,"count":155},"azure","Azure",{"key":160,"name":161,"count":155},"gcp","GCP",{"key":163,"name":164,"count":155},"kubernetes","Kubernetes",{"key":166,"name":167,"count":155},"linux","Linux",{"key":169,"name":170,"count":155},"terraform","Terraform",[172,190,203,217,230,243],{"id":173,"topic":9,"difficulty":174,"body":175,"options":176,"correct_key":181,"explanation":189},"019f56bb-b971-77b3-8623-07a00749a6c3",1,"What is the primary goal of Site Reliability Engineering (SRE) as a discipline?",[177,180,183,186],{"key":178,"text":179},"a","To replace all manual operations work with a dedicated QA team that tests every release before deployment.",{"key":181,"text":182},"b","To apply software engineering approaches to operations problems, balancing reliability with the pace of change.",{"key":184,"text":185},"c","To ensure infrastructure changes are always deployed manually so operators keep full control over every step of the process.",{"key":187,"text":188},"d","To guarantee that every service reaches 100% uptime by adding redundant hardware in every data center.","SRE (as popularized by Google) treats operations as an engineering problem: automation, measurable reliability targets, and error budgets are used to balance reliability against release velocity. (a) describes a QA function, not SRE. (c) contradicts SRE's automation-first mindset. (d) is unrealistic and not the actual goal — perfect availability is neither achievable nor cost-effective.",{"id":191,"topic":9,"difficulty":174,"body":192,"options":193,"correct_key":178,"explanation":202},"019f56bb-b972-715b-ada9-0ed2c3c42a9d","In SRE terminology, what does an SLI (Service Level Indicator) measure?",[194,196,198,200],{"key":178,"text":195},"A quantitative measurement of some aspect of the service, such as request latency or error rate.",{"key":181,"text":197},"The contractual penalty a company pays to customers when a service fails to meet its agreed target.",{"key":184,"text":199},"The maximum number of incidents a team is allowed to have in a given quarter.",{"key":187,"text":201},"The internal ranking that determines which engineer is on-call for a given week.","An SLI is a concrete, measurable metric (latency, error rate, throughput, etc.) used to describe service behavior. (b) describes something closer to an SLA penalty clause, not an SLI. (c) and (d) are unrelated invented concepts, not standard SRE terminology.",{"id":204,"topic":9,"difficulty":205,"body":206,"options":207,"correct_key":184,"explanation":216},"019f56bb-b972-77fb-a0b3-58cac4b2bc83",2,"How does an SLO (Service Level Objective) typically differ from an SLA (Service Level Agreement)?",[208,210,212,214],{"key":178,"text":209},"An SLO is a legal document signed with customers, while an SLA is only used internally by the engineering team.",{"key":181,"text":211},"An SLO applies only to security incidents, while an SLA covers every other type of service disruption.",{"key":184,"text":213},"An SLO is an internal reliability target a team aims for, while an SLA is an external commitment that often includes contractual consequences.",{"key":187,"text":215},"An SLO measures cost efficiency, while an SLA measures how quickly a team can deploy new features.","SLOs are internal targets (often stricter than the SLA) used to guide engineering decisions; SLAs are external, customer-facing commitments that can carry financial or contractual consequences if missed. (a) reverses the roles. (b) and (d) invent scopes that don't match either concept.",{"id":218,"topic":9,"difficulty":205,"body":219,"options":220,"correct_key":187,"explanation":229},"019f56bb-b973-7529-9264-599e5aeddbe6","A team's SLO allows a 0.1% monthly error budget, and they have already consumed 90% of it just two weeks into the month after a rocky rollout. What is the most reasonable SRE-aligned response?",[221,223,225,227],{"key":178,"text":222},"Ignore the budget consumption, since SLOs are typically only reviewed at the end of the quarter regardless of trend.",{"key":181,"text":224},"Immediately roll back to a version from a year ago, regardless of what has changed in the system since then.",{"key":184,"text":226},"Raise the SLO target for next month so the team appears to be meeting its goal again.",{"key":187,"text":228},"Slow down further risky releases and prioritize reliability work until the error budget recovers.","The whole point of an error budget is to inform release-pace decisions: when it's nearly exhausted, the team should shift focus toward stability rather than shipping more risk. (a) ignores the signal the budget is meant to provide. (b) is an overreaction unrelated to the actual cause. (c) games the metric instead of addressing the underlying reliability problem.",{"id":231,"topic":9,"difficulty":174,"body":232,"options":233,"correct_key":181,"explanation":242},"019f56bb-b973-7f0a-87c5-9fa83e752802","A service advertises 99.9% (\"three nines\") availability. Roughly how much downtime per year does this correspond to?",[234,236,238,240],{"key":178,"text":235},"About 5 minutes per year.",{"key":181,"text":237},"About 8-9 hours per year.",{"key":184,"text":239},"About 3-4 days per year.",{"key":187,"text":241},"About 36 days per year.","99.9% availability allows 0.1% downtime per year, which is roughly 8.76 hours (365 days x 0.001). (a) corresponds instead to 99.999% (\"five nines\"). (c) and (d) are far too much downtime for three nines and would correspond to much lower availability percentages.",{"id":244,"topic":9,"difficulty":205,"body":245,"options":246,"correct_key":178,"explanation":255},"019f56bb-b974-7785-b7fe-8bb961a95a98","Team A resolves incidents in an average of 20 minutes after detection. Team B resolves incidents in an average of 2 hours, but rarely has incidents in the first place. Which metric specifically captures Team A's strength here?",[247,249,251,253],{"key":178,"text":248},"MTTR (Mean Time To Recovery), which measures how quickly service is restored once an incident starts.",{"key":181,"text":250},"MTBF (Mean Time Between Failures), which measures how often incidents occur in the first place.",{"key":184,"text":252},"SLA compliance rate, which measures whether a contractual agreement was honored in that period.",{"key":187,"text":254},"Error budget burn rate, which measures how fast allowed unreliability is being consumed over a period.","Team A's advantage is speed of recovery once something breaks, which is exactly what MTTR captures. (b) would instead describe Team B's strength (fewer failures). (c) and (d) are real metrics too, but neither is the one that specifically isolates recovery speed.",{"fields":257,"seniorities":429,"interview_shapes":430,"locales":435,"oauth":437,"question_count":440,"coach_enabled":441,"jd_match_enabled":441},[258,283,303,320,330,343,362,381,403,410,416,423],{"key":259,"name_tr":260,"name_en":260,"sort":174,"specializations":261},"backend","Backend",[262,265,268,271,274,277,280],{"key":263,"name":264,"field":259},"general","Genel",{"key":266,"name":267,"field":259},"go","Go",{"key":269,"name":270,"field":259},"python","Python",{"key":272,"name":273,"field":259},"java","Java",{"key":275,"name":276,"field":259},"csharp","C#\u002F.NET",{"key":278,"name":279,"field":259},"nodejs","Node.js",{"key":281,"name":282,"field":259},"php","PHP",{"key":284,"name_tr":285,"name_en":285,"sort":205,"specializations":286},"frontend","Frontend",[287,288,291,294,297,300],{"key":263,"name":264,"field":284},{"key":289,"name":290,"field":284},"javascript","JavaScript",{"key":292,"name":293,"field":284},"typescript","TypeScript",{"key":295,"name":296,"field":284},"react","React",{"key":298,"name":299,"field":284},"vue","Vue",{"key":301,"name":302,"field":284},"angular","Angular",{"key":304,"name_tr":305,"name_en":305,"sort":306,"specializations":307},"fullstack","Fullstack",3,[308,309,310,311,312,313,314,315,316,317,318,319],{"key":263,"name":264,"field":304},{"key":266,"name":267,"field":259},{"key":269,"name":270,"field":259},{"key":272,"name":273,"field":259},{"key":275,"name":276,"field":259},{"key":278,"name":279,"field":259},{"key":281,"name":282,"field":259},{"key":289,"name":290,"field":284},{"key":292,"name":293,"field":284},{"key":295,"name":296,"field":284},{"key":298,"name":299,"field":284},{"key":301,"name":302,"field":284},{"key":5,"name_tr":6,"name_en":6,"sort":321,"specializations":322},4,[323,324,325,326,327,328,329],{"key":263,"name":264,"field":5},{"key":153,"name":154,"field":5},{"key":160,"name":161,"field":5},{"key":157,"name":158,"field":5},{"key":163,"name":164,"field":5},{"key":169,"name":170,"field":5},{"key":166,"name":167,"field":5},{"key":331,"name_tr":332,"name_en":332,"sort":333,"specializations":334},"ai-engineer","AI Engineer",5,[335,336,337,340],{"key":263,"name":264,"field":331},{"key":269,"name":270,"field":331},{"key":338,"name":339,"field":331},"llm-rag","LLM\u002FRAG",{"key":341,"name":342,"field":331},"mlops","MLOps",{"key":344,"name_tr":345,"name_en":346,"sort":347,"specializations":348},"database","Veritabanı","Database",6,[349,350,353,356,359],{"key":263,"name":264,"field":344},{"key":351,"name":352,"field":344},"postgresql","PostgreSQL",{"key":354,"name":355,"field":344},"mysql","MySQL",{"key":357,"name":358,"field":344},"mongodb","MongoDB",{"key":360,"name":361,"field":344},"redis","Redis",{"key":363,"name_tr":364,"name_en":365,"sort":366,"specializations":367},"mobile","Mobil","Mobile",7,[368,369,372,375,378],{"key":263,"name":264,"field":363},{"key":370,"name":371,"field":363},"ios-swift","iOS (Swift)",{"key":373,"name":374,"field":363},"android-kotlin","Android (Kotlin)",{"key":376,"name":377,"field":363},"flutter","Flutter",{"key":379,"name":380,"field":363},"react-native","React Native",{"key":382,"name_tr":383,"name_en":384,"sort":385,"specializations":386},"security","Güvenlik","Security",8,[387,388,391,394,397,400],{"key":263,"name":264,"field":382},{"key":389,"name":390,"field":382},"appsec","AppSec",{"key":392,"name":393,"field":382},"offensive-pentest","Offensive \u002F Pentest",{"key":395,"name":396,"field":382},"cloud-security","Cloud Security",{"key":398,"name":399,"field":382},"devsecops","DevSecOps",{"key":401,"name":402,"field":382},"blue-team-incident","Blue Team \u002F Incident",{"key":404,"name_tr":405,"name_en":406,"sort":407,"specializations":408},"qa-test-automation","QA \u002F Test Otomasyonu","QA \u002F Test Automation",9,[409],{"key":263,"name":264,"field":404},{"key":411,"name_tr":412,"name_en":412,"sort":413,"specializations":414},"data-engineer","Data Engineer",10,[415],{"key":263,"name":264,"field":411},{"key":417,"name_tr":418,"name_en":419,"sort":420,"specializations":421},"game-dev","Oyun Geliştirme","Game Development",11,[422],{"key":263,"name":264,"field":417},{"key":424,"name_tr":425,"name_en":425,"sort":426,"specializations":427},"ml-engineer","ML Engineer",12,[428],{"key":263,"name":264,"field":424},[14,15,16],{"junior":431,"mid":433,"senior":434},{"questions":432,"median_sec":3},20,{"questions":432,"median_sec":3},{"questions":432,"median_sec":3},[436,10],"tr",[438,439],"google","github",21750,true]