tigertoolbox/Troubleshooting-Notebooks/Big-Data-Clusters/CU4/Public/_data/toc.yml

- title: Welcome
  url: /readme
  not_numbered: true
- title: Search
  search: true

- title: Troubleshooters
  url: /troubleshooters/readme
  not_numbered: true
  expand_sections: true
  sections:
  - title: TSG100 - The Big Data Cluster troubleshooter
    url: troubleshooters/tsg100-troubleshoot-bdc
  - title: TSG101 - SQL Server troubleshooter
    url: troubleshooters/tsg101-troubleshoot-sql-server
  - title: TSG102 - HDFS troubleshooter
    url: troubleshooters/tsg102-troubleshoot-hdfs
  - title: TSG103 - Spark troubleshooter
    url: troubleshooters/tsg103-troubleshoot-spark
  - title: TSG104 - Control troubleshooter
    url: troubleshooters/tsg104-troubleshoot-control
  - title: TSG105 - Gateway troubleshooter
    url: troubleshooters/tsg105-troubleshoot-gateway
  - title: TSG106 - App troubleshooter
    url: troubleshooters/tsg106-troubleshoot-app
- title: Log Analyzers
  url: /log-analyzers/readme
  not_numbered: true
  expand_sections: true
  sections:
  - title: TSG046 - Knox gateway logs
    url: log-analyzers/tsg046-get-knox-logs
  - title: TSG036 - Controller logs
    url: log-analyzers/tsg036-get-controller-logs
  - title: TSG034 - Livy logs
    url: log-analyzers/tsg034-get-livy-logs
  - title: TSG035 - Spark History logs
    url: log-analyzers/tsg035-get-sparkhistory-logs
  - title: TSG030 - SQL Server errorlog files
    url: log-analyzers/tsg030-get-errorlog-from-all-pods
  - title: TSG031 - SQL Server PolyBase logs
    url: log-analyzers/tsg031-get-polybase-logs-for-all-pods
  - title: TSG095 - Hadoop namenode logs
    url: log-analyzers/tsg095-get-namenode-logs
  - title: TSG090 - Yarn nodemanager logs
    url: log-analyzers/tsg090-get-nodemanager-logs
  - title: TSG088 - Hadoop datanode logs
    url: log-analyzers/tsg088-get-datanode-logs
  - title: TSG096 - Zookeeper logs
    url: log-analyzers/tsg096-get-zookeeper-logs
  - title: TSG073 - InfluxDB logs
    url: log-analyzers/tsg073-get-influxdb-logs
  - title: TSG076 - Elastic Search logs
    url: log-analyzers/tsg076-get-elastic-search-logs
  - title: TSG077 - Kibana logs
    url: log-analyzers/tsg077-get-kibana-logs
  - title: TSG092 - Supervisord log tail for all containers in BDC
    url: log-analyzers/tsg092-get-all-supervisord-log-tails
  - title: TSG093 - Agent log tail for all containers in BDC
    url: log-analyzers/tsg093-get-all-agent-log-tails
  - title: TSG094 - Grafana logs
    url: log-analyzers/tsg094-get-grafana-logs
- title: Diagnose
  url: /diagnose/readme
  not_numbered: true
  expand_sections: true
  sections:
  - title: TSG027 - Observe cluster deployment
    url: diagnose/tsg027-observe-bdc-create
  - title: TSG078 - Is cluster healthy
    url: diagnose/tsg078-is-cluster-healthy
  - title: TSG029 - Find dumps in the cluster
    url: diagnose/tsg029-find-dumps-in-the-cluster
  - title: TSG032 - CPU and Memory usage for all containers
    url: diagnose/tsg032-get-cpu-and-memory-for-all-containers
  - title: TSG060 - Persistent Volume disk space for all BDC PVCs
    url: diagnose/tsg060-get-disk-space-for-all-pvcs
  - title: TSG087 - Use hadoop fs CLI on nmnode pod
    url: diagnose/tsg087-use-hadoop-fs
  - title: TSG037 - Determine master pool pod hosting primary replica
    url: diagnose/tsg037-determine-primary-master-replica
  - title: TSG055 - Time Curl to Sparkhead
    url: diagnose/tsg055-time-curl-to-sparkhead
  - title: TSG079 - Generate `controller` core dump
    url: diagnose/tsg079-generate-controller-core-dump
  - title: TSG086 - Run `top` in all containers
    url: diagnose/tsg086-run-top-for-all-containers
  - title: TSG108 - View the controller upgrade config map
    url: diagnose/tsg108-controller-failed-to-upgrade
- title: Repair 
  url: /repair/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: TSG024 - Namenode is in safe mode
    url: repair/tsg024-name-node-is-in-safe-mode
  - title: TSG041 - Unable to create a new asynchronous I/O context (increase sysctl fs.aio-max-nr)
    url: repair/tsg041-increase-fs-aio-max-nr
  - title: TSG048 - Deployment stuck at "Waiting for controller pod to be up"
    url: repair/tsg048-create-stuck-waiting-for-controller
  - title: TSG038 - BDC create failures due to - doc is missing key
    url: repair/tsg038-doc-is-missing-key-error
  - title: TSG047 - ConfigException - Expected only one object with name
    url: repair/tsg047-expected-only-one-object-with-name
  - title: TSG050 - Cluster create hangs with "timeout expired waiting for volumes to attach or mount for pod"
    url: repair/tsg050-timeout-expired-waiting-for-volumes
  - title: TSG057 - Failed when starting controller service. System.TimeoutException
    url: repair/tsg057-failed-when-starting-controller
  - title: TSG067 - Failed to complete kube config setup
    url: repair/tsg067-failed-to-complete-kube-config-setup
  - title: TSG075 - FailedCreatePodSandBox due to NetworkPlugin cni failed to set up pod
    url: repair/tsg075-networkplugin-cni-failed-to-setup-pod
  - title: TSG110 - Azdata returns ApiError
    url: repair/tsg110-azdata-returns-apierror
  - title: TSG028 - Restart node manager on all storage pool nodes
    url: repair/tsg028-restart-nodemanager-in-storage-pool
  - title: TSG045 - The maximum number of data disks allowed to be attached to a VM of this size (AKS)
    url: repair/tsg045-max-number-data-disks-allowed
  - title: TSG109 - Set upgrade timeouts
    url: repair/tsg109-upgrade-stalled
- title: Notebook Runner
  url: /notebook-runner/readme
  not_numbered: true
  expand_sections: false
  sections:

  - title: RUN000 - Setup Master Pool runner infrastructure
    url: notebook-runner/run000-setup-infrastructure
  - title: RUN001 - Run a notebook
    url: notebook-runner/run001-run-notebook
  - title: RUN002 - Save result in Big Data Cluster
    url: notebook-runner/run002-save-result-in-bdc
  - title: RUN003 - Run expert rules
    url: notebook-runner/run003-run-expert-rules
  - title: RUN505a - Sample - Demo expert rules
    url: notebook-runner/run505a-sample-notebook
  - title: RUN505b - Sample - Expert rule (called by 505a)
    url: notebook-runner/run505b-expert-rule
  - title: RUN505c - Sample - Expert rule (called by 505b)
    url: notebook-runner/run505c-expert-rule
  - title: RUN600 - Monitor infrastructure (SQL)
    url: notebook-runner/run600-monitor-infrastructure-sql
  - title: RUN999 - Cleanup Master Pool runner infrastructure
    url: notebook-runner/run999-cleanup-infrastructure
- title: Notebook Operationalization 
  url: /notebook-o16n/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: OPR001 - Create app-deploy
    url: notebook-o16n/opr001-create-app-deploy
  - title: OPR002 - Run app-deploy
    url: notebook-o16n/opr002-run-app-deploy
  - title: OPR003 - Create cronjob
    url: notebook-o16n/opr003-create-cronjob
  - title: OPR004 - Suspend cronjob
    url: notebook-o16n/opr004-suspend-cronjob
  - title: OPR005 - Resume cronjob
    url: notebook-o16n/opr005-resume-cronjob
  - title: OPR006 - Delete cronjob
    url: notebook-o16n/opr006-delete-cronjob
  - title: OPR007 - Delete app-deploy
    url: notebook-o16n/opr007-delete-app-deploy
  - title: OPR100 - Deploy and Schedule notebook(s)
    url: notebook-o16n/opr100-deploy-and-schedule-notebook
  - title: OPR600 - Monitor infrastructure (Kubernetes)
    url: notebook-o16n/opr600-monitor-infrastructure-k8s
  - title: OPR700 - Create Grafana Dashboard for App-Deploy Applications
    url: notebook-o16n/opr700-create-app-dashboard
  - title: OPR900 - Troubleshoot run app-deploy
    url: notebook-o16n/opr900-troubleshoot-run-app-deploy
  - title: OPR901 - Troubleshoot cronjob
    url: notebook-o16n/opr901-troubleshoot-cronjob-run
- title: Monitor - Big Data Cluster
  url: /monitor-bdc/readme
  not_numbered: true
  expand_sections: true
  sections:
  - title: TSG014 - Show BDC endpoints
    url: monitor-bdc/tsg014-azdata-bdc-endpoint-list
  - title: TSG012 - Show BDC Status
    url: monitor-bdc/tsg012-azdata-bdc-status
  - title: TSG069 - Show Big Data Cluster Gateway status
    url: monitor-bdc/tsg069-azdata-bdc-gateway-status
  - title: TSG049 - Show BDC Controller status
    url: monitor-bdc/tsg049-azdata-bdc-control-status
  - title: TSG033 - Show BDC SQL status
    url: monitor-bdc/tsg033-azdata-bdc-sql-status
  - title: TSG068 - Show BDC HDFS status
    url: monitor-bdc/tsg068-azdata-bdc-hdfs-status
  - title: TSG017 - Show BDC Configuration
    url: monitor-bdc/tsg017-azdata-bdc-config-show
  - title: TSG004 - Show BDC Apps
    url: monitor-bdc/tsg004-show-app-list
  - title: TSG003 - Show BDC Spark sessions
    url: monitor-bdc/tsg003-show-spark-sessions
  - title: TSG013 - Show file list in Storage Pool (HDFS)
    url: monitor-bdc/tsg013-azdata-bdc-hdfs-ls
  - title: TSG070 - Query SQL master pool
    url: monitor-bdc/tsg070-use-azdata-sql-query
- title: Monitor - Kubernetes
  url: /monitor-k8s/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: TSG021 - Get cluster info (Kubernetes)
    url: monitor-k8s/tsg021-get-k8s-cluster-info
  - title: TSG008 - Get version information (Kubernetes)
    url: monitor-k8s/tsg008-get-k8s-version-info
  - title: TSG081 - Get namespaces (Kubernetes)
    url: monitor-k8s/tsg081-get-kubernetes-namespaces
  - title: TSG009 - Get nodes (Kubernetes)
    url: monitor-k8s/tsg009-get-nodes
  - title: TSG006 - Get system pod status
    url: monitor-k8s/tsg006-view-system-pod-status
  - title: TSG007 - Get BDC pod status
    url: monitor-k8s/tsg007-view-bdc-pod-status
  - title: TSG015 - View BDC services (Kubernetes)
    url: monitor-k8s/tsg015-view-k8s-services-for-bdc
  - title: TSG097 - Get BDC stateful sets (Kubernetes)
    url: monitor-k8s/tsg097-get-statefulsets
  - title: TSG098 - Get BDC replicasets (Kubernetes)
    url: monitor-k8s/tsg098-get-replicasets
  - title: TSG099 - Get BDC daemonsets (Kubernetes)
    url: monitor-k8s/tsg099-get-daemonsets
  - title: TSG023 - Get all BDC objects (Kubernetes)
    url: monitor-k8s/tsg023-run-kubectl-get-all
  - title: TSG063 - Get storage classes (Kubernetes)
    url: monitor-k8s/tsg063-get-storage-classes
  - title: TSG072 - Get Persistent Volumes (Kubernetes)
    url: monitor-k8s/tsg072-get-persistent-volumes
  - title: TSG064 - Get BDC Persistent Volume Claims
    url: monitor-k8s/tsg064-get-persistent-volume-claims
  - title: TSG065 - Get BDC secrets (Kubernetes)
    url: monitor-k8s/tsg065-get-secrets-for-bdc-namespace
  - title: TSG066 - Get BDC event (Kubernetes)
    url: monitor-k8s/tsg066-get-kubernetes-events
  - title: TSG020- Describe nodes (Kubernetes)
    url: monitor-k8s/tsg020-describe-all-nodes
  - title: TSG016- Describe BDC pods
    url: monitor-k8s/tsg016-describe-all-pods-in-bdc-namespace
  - title: TSG089 - Describe BDC non-running pods
    url: monitor-k8s/tsg089-describe-non-running-pods-in-bdc
  - title: TSG010 - Get configuration contexts
    url: monitor-k8s/tsg010-get-kubernetes-contexts
  - title: TSG022 - Get external IP address for kubeadm host
    url: monitor-k8s/tsg022-get-external-ip-of-kubeadm-host
  - title: TSG042 - Get `node name` and external mounts for `Data` and `Logs` `PVCs`
    url: monitor-k8s/tsg042-get-hosting-node-and-data-log-mount
- title: Logs
  url: /log-files/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: TSG001 - Run azdata copy-logs
    url: log-files/tsg001-copy-logs
  - title: TSG091 - Get the azdata CLI logs
    url: log-files/tsg091-get-azdata-logs
  - title: TSG083 - Run kubectl cluster-info dump
    url: log-files/tsg083-run-kubectl-cluster-info-dump
  - title: TSG061 - Get tail of all container logs for pods in BDC namespace
    url: log-files/tsg061-tail-bdc-container-logs
  - title: TSG062 - Get tail of all previous container logs for pods in BDC namespace
    url: log-files/tsg062-tail-bdc-previous-container-logs
  - title: TSG084 - Internal Query Processor Error
    url: log-files/tsg084-internal-query-process-error
- title: Samples 
  url: /sample/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: SAM001a - Query Storage Pool from SQL Server Master Pool (1 of 3) - Load sample data
    url: sample/sam001a-load-sample-data-into-bdc
  - title: SAM001b - Query Storage Pool from SQL Server Master Pool (2 of 3) - Convert data to parquet
    url: sample/sam001b-convert-csv-to-parquet
  - title: SAM001c - Query Storage Pool from SQL Server Master Pool (3 of 3)  - Query HDFS from SQL Server
    url: sample/sam001c-query-hdfs-in-sql-server
  - title: SAM002 - Storage Pool (2 of 2) - Query HDFS
    url: sample/sam002-query-hdfs-in-sql-server
  - title: SAM003 - Data Pool Example
    url: sample/sam003-data-pool
  - title: SAM008 - Spark using azdata
    url: sample/sam008-spark-using-azdata
  - title: SAM009 - HDFS using azdata
    url: sample/sam009-hdfs-using-azdata
  - title: SAM010 - App using azdata
    url: sample/sam010-app-using-azdata
- title: Install 
  url: /install/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: SOP036 - Install kubectl command line interface
    url: install/sop036-install-kubectl
  - title: SOP037 - Uninstall kubectl command line interface
    url: install/sop037-uninstall-kubectl
  - title: SOP059 - Install Kubernetes Python module
    url: install/sop059-install-kubernetes-module
  - title: SOP060 - Uninstall kubernetes module
    url: install/sop060-uninstall-kubernetes-module
  - title: SOP062 - Install ipython-sql and pyodbc modules
    url: install/sop062-install-ipython-sql-module
  - title: SOP063 - Install azdata CLI (using package manager)
    url: install/sop063-packman-install-azdata
  - title: SOP064 - Uninstall azdata CLI (using package manager)
    url: install/sop064-packman-uninstall-azdata
  - title: SOP054 - Install azdata CLI (using pip)
    url: install/sop054-install-azdata
  - title: SOP055 - Uninstall azdata CLI (using pip)
    url: install/sop055-uninstall-azdata
  - title: SOP038 - Install azure command line interface
    url: install/sop038-install-az
  - title: SOP039 - Uninstall azure command line interface
    url: install/sop039-uninstall-az
  - title: SOP040 - Upgrade pip in ADS Python sandbox
    url: install/sop040-upgrade-pip
  - title: SOP069 - Install ODBC for SQL Server
    url: install/sop069-install-odbc-driver-for-sql-server
  - title: SOP012 - Install unixodbc for Mac
    url: install/sop012-brew-install-odbc-for-sql-server
  - title: SOP010 - Upgrade a big data cluster
    url: install/sop010-upgrade-bdc
- title: Certificate Management
  url: /cert-management/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: CER001 - Generate a Root CA certificate
    url: cert-management/cer001-create-root-ca
  - title: CER002 - Download existing Root CA certificate
    url: cert-management/cer002-download-existing-root-ca
  - title: CER003 - Upload existing Root CA certificate
    url: cert-management/cer003-upload-existing-root-ca
  - title: CER004 - Download and Upload existing Root CA certificate
    url: cert-management/cer004-download-upload-existing-root-ca
  - title: CER010 - Install generated Root CA locally
    url: cert-management/cer010-install-generated-root-ca-locally
  - title: CER020 - Create Management Proxy certificate
    url: cert-management/cer020-create-management-service-proxy-cert
  - title: CER021 - Create Knox certificate
    url: cert-management/cer021-create-knox-cert
  - title: CER022 - Create App Proxy certificate
    url: cert-management/cer022-create-app-proxy-cert
  - title: CER023 - Create Controller certificate
    url: cert-management/cer023-create-controller-cert
  - title: CER030 - Sign Management Proxy certificate with generated CA
    url: cert-management/cer030-sign-service-proxy-generated-cert
  - title: CER031 - Sign Knox certificate with generated CA
    url: cert-management/cer031-sign-knox-generated-cert
  - title: CER032 - Sign App-Proxy certificate with generated CA
    url: cert-management/cer032-sign-app-proxy-generated-cert
  - title: CER033 - Sign Controller certificate with cluster Root CA
    url: cert-management/cer033-sign-controller-generated-cert
  - title: CER040 - Install signed Management Proxy certificate
    url: cert-management/cer040-install-service-proxy-cert
  - title: CER041 - Install signed Knox certificate
    url: cert-management/cer041-install-knox-cert
  - title: CER042 - Install signed App-Proxy certificate
    url: cert-management/cer042-install-app-proxy-cert
  - title: CER043 - Install signed Controller certificate
    url: cert-management/cer043-install-controller-cert
  - title: CER050 - Wait for BDC to be Healthy
    url: cert-management/cer050-wait-cluster-healthly
  - title: CER100 - Configure Cluster with Self Signed Certificates
    url: cert-management/cer100-create-root-ca-install-certs
  - title: CER101 - Configure Cluster with Self Signed Certificates using existing Root CA
    url: cert-management/cer101-use-root-ca-install-certs
- title: Common 
  url: /common/readme
  not_numbered: true
  expand_sections: false
  sections:
  - title: SOP028 - azdata login
    url: common/sop028-azdata-login
  - title: SOP033 - azdata logout
    url: common/sop033-azdata-logout
  - title: SOP005 - az login
    url: common/sop005-az-login
  - title: SOP006 - az logout
    url: common/sop006-az-logout
  - title: SOP007 - Version information (azdata, bdc, kubernetes)
    url: common/sop007-get-key-version-information
  - title: SOP011 - Set kubernetes configuration context
    url: common/sop011-set-kubernetes-context
  - title: SOP034 - Wait for BDC to be Healthy
    url: common/sop034-wait-cluster-healthly