From 3f8829eb146a5f281c47e0509270b4ee18d7afad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E2=80=9Cnico-shishkin=E2=80=9D?= <“nicoshishkinatlogz@outlook.com”> Date: Sun, 29 Jan 2023 16:58:26 +0100 Subject: [PATCH 1/4] AKS dashboards --- _source/_data/toc.yml | 8 ++++ .../aks -kubernetes-cluster-components.md | 39 +++++++++++++++++ .../aks-kubernetes-cluster-summary.md | 42 +++++++++++++++++++ .../aks-kubernetes-nodes.md | 31 ++++++++++++++ .../aks-kubernetes_pods.md | 25 +++++++++++ 5 files changed, 145 insertions(+) create mode 100644 _source/user-guide/infrastructure-monitoring/aks -kubernetes-cluster-components.md create mode 100644 _source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md create mode 100644 _source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md create mode 100644 _source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md diff --git a/_source/_data/toc.yml b/_source/_data/toc.yml index 2b7b8a4f8..28322071a 100644 --- a/_source/_data/toc.yml +++ b/_source/_data/toc.yml @@ -152,6 +152,14 @@ firstLevel: url: /user-guide/infrastructure-monitoring/explore-in-kibana-drilldown-links.html - title: Pre-built metrics dashboards thirdLevel: + - title: AKS - Kubernetes Cluster Components + url: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-cluster-components.html + - title: AKS - Kubernetes Cluster Summary + url: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-cluster-summary.html + - title: AKS - Kubernetes Nodes + url: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-nodes.html + - title: AKS - Kubernetes Pods + url: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-pods.html - title: AWS Cloudwatch - Amazon MQ url: /user-guide/infrastructure-monitoring/metrics-dashboards/amazon-mq.html - title: AWS Cloudwatch - API Gateway diff --git a/_source/user-guide/infrastructure-monitoring/aks -kubernetes-cluster-components.md b/_source/user-guide/infrastructure-monitoring/aks -kubernetes-cluster-components.md new file mode 100644 index 000000000..2c82cc32b --- /dev/null +++ b/_source/user-guide/infrastructure-monitoring/aks -kubernetes-cluster-components.md @@ -0,0 +1,39 @@ +--- +layout: article +title: AKS - Kubernetes Cluster Components +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-cluster-components.html +image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg +description: View and analyze metrics with AKS - Kubernetes Cluster Components +flags: + logzio-plan: pro +tags: + - metrics integrations +contributors: + - nshishkin +--- + +This dashboard provides an interface to view and analyze metrics from your AKS Kubernetes Cluster Components. + +| Metric Visualization | Metric Name | Description | +|----------------------|-------------|-------------| +| Cluster Nodes | kube_node_info | Sum of cluster nodes (stats) | +| Cluster Nodes | kube_node_info | Sum of cluster nodes (text) | +| Cluster Active Namespaces | kube_pod_info | Sum of active namespace (stata) | +| Cluster Active Namespaces | kube_namespace_labels | Sum of active namespace (text) | +| Nodes Condition | kube_node_status_condition | Nodes condition (timeseries) | +| Total Deployment Utilization | kube_deployment_status_replicas_available, kube_deployment_status_replicas | Total deployment utilization (gauge) | +| Total Deployments Replicas | kube_deployment_status_replicas | Total deployments replicas (stats) | +| Total Deployments Replicas Available | kube_deployment_status_replicas_available | Total deployments replicas available (stats) | +| Total Deployments Replicas Unavailable | kube_deployment_status_replicas_unavailable | Total deployments replicas unavailable (stats) | +| Running Containers | kube_pod_container_status_running | Running containers (stats) | +| Ready Containers | kube_pod_container_status_ready | Ready containers (stats) | +| Waiting Containers | kube_pod_container_status_waiting | Waiting containers (stats) | +| Terminated Containers | kube_pod_container_status_terminated | Terminated containers (stats) | +| Running Containers | kube_pod_container_status_running | Graphic representation of running containers | +| Non-Running Containers | kube_pod_container_status_waiting, kube_pod_container_status_terminated | Graphic representation of waiting and terminated containers | +| Running Pods | kube_pod_status_phase | Running pods (stats) | +| Pending Pods | kube_pod_status_phase | Pending pods (stats) | +| Failed Pods | kube_pod_status_phase | Failed pods (stats) | +| Unknown Pods | kube_pod_status_phase | Unknown pods (stats) | +| Running pods | kube_pod_status_phase | Graphic representation of running pods | +| Non-running pods | kube_pod_status_phase | Graphic representation of non-running pods | diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md new file mode 100644 index 000000000..7d5506555 --- /dev/null +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md @@ -0,0 +1,42 @@ +--- +layout: article +title: AKS - Kubernetes Cluster Summary +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_cluster_summary.html +image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg +description: View and analyze metrics with AKS Kubernetes Cluster Summary +flags: + logzio-plan: pro +tags: + - metrics integrations +contributors: + - nshishkin +--- + +This dashboard provides an interface to view and analyze metrics from your AKS Kubernetes Cluster Summary. + +| Metric Visualization | Metric Name | Description | +| ---------- | -------------------------------------- | ---------------------------------- | +| Cluster Pod Usage | kube_pod_info, kube_node_status_allocatable | Allocatable pods versus all pods (gauge) | +| Cluster CPU Usage | kube_pod_container_resource_requests, kube_node_status_allocatable | CPU usage derived from allocatable pods versus all resource requests (gauge) | +| Cluster Memory Usage | kube_pod_container_resource_requests, kube_node_status_allocatable | Memory usage derived from allocatable pods versus all resource requests (gauge)| +| Cluster Disk Usage | node_filesystem_size_bytes, node_filesystem_free_bytes, windows_logical_disk_size_bytes, windows_cs_hostname, windows_logical_disk_free_bytes / node_filesystem_size_bytes, node_filesystem_free_bytes, node_filesystem_size_bytes | Cluster disk usage (gauge) | +| Cluster Pod Capacity | kube_node_status_allocatable, kube_node_status_capacity, kube_pod_info | Cluster pod capacity (timeseries) | +| Cluster CPU Capacity | kube_node_status_capacity, kube_node_status_allocatable, kube_pod_container_resource_requests | Cluster CPU capacity (tmeseries) | +| Cluster Mem Capacity | kube_node_status_allocatable, kube_node_status_capacity, kube_pod_container_resource_requests | Cluster memory capacity (tmeseries) | +| Cluster Disk Capacity | node_filesystem_size_bytes, windows_logical_disk_size_bytes, windows_cs_hostname / node_filesystem_size_bytes | Cluster disk capacity (tmeseries) | +| Number Of Nodes | kube_node_info | Number of nodes (stats) | +| Nodes Out of Disk | kube_node_status_condition | Nodes out of disk (stats) | +| Nodes Unavailable | kube_node_spec_unschedulable | Nodes unavailable (stats) | +| Deployment Replicas - Up To Date | kube_deployment_status_replicas_updated | Deployment replicas - up to date (table) | +| Deployment Replicas | kube_deployment_status_replicas | Deployment replicas (stats) | +| Deployment Replicas - Updated | kube_deployment_status_replicas_updated | Deployment replicas - updated (stats) | +| Deployment Replicas - Unavailable | kube_deployment_status_replicas_unavailable | Deployment replicas - unavailable (stats) | +| Pods Running | kube_pod_status_phase | Pods running (stats) | +| Pods Pending | kube_pod_status_phase | Pods pending (stats) | +| Pods Failed | kube_pod_status_phase | Pods failed (stats) | +| Pods Succeeded | kube_pod_status_phase | Pods succeeded (stats) | +| Pods Unknown | kube_pod_status_phase | Pods unknown (stats) | +| Containers Running | kube_pod_container_status_running | Containers running (stats) | +| Containers Waiting | kube_pod_container_status_waiting | Containers waiting (stats) | +| Containers Terminated | kube_pod_container_status_terminated | Containers terminated (stats) | +| Containers Restarts (Per Namespace) | kube_pod_container_status_restarts_total | Containers restarts per namespace (stats) | \ No newline at end of file diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md new file mode 100644 index 000000000..b8dc7639d --- /dev/null +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md @@ -0,0 +1,31 @@ +--- +layout: article +title: AKS - Kubernetes nodes +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_nodes.html +image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg +description: View and analyze metrics with Amazon Auto Scaling +flags: + logzio-plan: pro +tags: + - metrics integrations +contributors: + - nshishkin +--- + +This dashboard provides an interface to view and analyze metrics from your AKS Kubernetes nodes. + +| Metric visualization | Metric name | Description | +| ----------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------- | +| Uptime | node_time_seconds | Node uptime in seconds (stats) | +| Cores | machine_cpu_cores | Machine CPU cores per node (stats) | +| CPU Usage | node_cpu_seconds_total, kubernetes_node, windows_cpu_time_total, windows_cs_hostname | CPU usage gauge | +| Memory Usage | node_memory_MemTotal_bytes, node_memory_MemFree_bytes, nnode_memory_MemTotal_bytes, windows_os_physical_memory_free_bytes, windows_cs_hostname, nwindows_cs_physical_memory_bytes, windows_cs_hostname | Memory usage gauge | +| Total Memory | node_memory_MemTotal_bytes, kubernetes_node, nwindows_cs_physical_memory_bytes, windows_cs_hostname | Total memory (stats) | +| Total Disk Space | node_filesystem_size_bytes, kubernetes_node, windows_logical_disk_size_bytes, windows_cs_hostname | Total Disk Space (stats) | +| CPU Usage (Stacked) | node_cpu_seconds_total, node_cpu_seconds_total, node_cpu_seconds_total, node_cpu_seconds_total, node_cpu_seconds_total, node_cpu_seconds_total, node_cpu_seconds_total, windows_cpu_time_total, windows_cs_hostname, windows_cpu_time_total, windows_cs_hostname | CPU usage stacked (stats) | +| Memory Usage (Stacked) | node_memory_MemTotal_bytes, kubernetes_node, node_memory_MemFree_bytes, windows_cs_physical_memory_bytes, windows_cs_hostname, windows_os_physical_memory_free_bytes, windows_cs_hostname | Stacked memory usage (timeseries) | +| Network Rx/Tx | node_network_receive_bytes_total, kubernetes_node, node_network_transmit_bytes_total, windows_net_bytes_received_total, windows_cs_hostname, windows_net_bytes_sent_total | Network bytes received and transmitted (time series) | +| Disk IO Time | node_disk_io_time_seconds_total, kubernetes_node, windows_logical_disk_read_seconds_total, windows_cs_hostname, windows_logical_disk_write_seconds_total, windows_cs_hostname | Disk IO Time (timeseries) | +| Filesystem Usage (Stacked) | node_filesystem_size_bytes, kubernetes_node, node_filesystem_free_bytes, node_filesystem_avail_bytes, windows_logical_disk_size_bytes, windows_cs_hostname, windows_logical_disk_free_bytes, windows_logical_disk_free_bytes | Filesystem usage stacked (timeseries) | +| Top Pods CPU Usage By Node | container_cpu_usage_seconds_total, kubernetes_io_hostname, kube_pod_container_resource_requests | Top pods CPU usage by node (gauge) | +| Top Pods Memory Usage By Node | container_memory_working_set_bytes, kube_pod_container_resource_requests | Top pods memory usage by node (gauge) | \ No newline at end of file diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md new file mode 100644 index 000000000..00a4b7c3d --- /dev/null +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md @@ -0,0 +1,25 @@ +--- +layout: article +title: AKS - Kubernetes pods +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_pods.html +image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg +description: View and analyze metrics with Amazon Auto Scaling +flags: + logzio-plan: pro +tags: + - metrics integrations +contributors: + - nshishkin +--- + +This dashboard provides an interface to view and analyze metrics from your AKS Kubernetes pods. + +| Metric visualization | Metric name | Description | +| ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------- | +| Number Of Pods Per Namespace | kube_pod_info | Number of pods per namespace (timeseries) | +| Number Of Pods Per Namespace | kube_pod_info | Number of pods per namespace (stats) | +| Pods Status Per Namespace | kube_pod_status_phase{p8s_logzio_name | Pods status per namespace (timeseries) | +| Container Restarts By Pod Per Container | kube_pod_container_status_restarts_total | Container Restarts by Pod per container (timeseries) | +| Top Pods Memory Usage Per Container | kube_pod_container_info, windows_container_memory_usage_commit_bytes, container_memory_working_set_bytes | Top pods memory usage per container (timeseries) | +| Top Pods CPU Usage Per Container | container_cpu_usage_seconds_total, kube_pod_container_info, windows_container_cpu_usage_seconds_total | Top pods CPU usage per container (time series) | +| Top Pods Network I/O Pressure Per Container | container_network_receive_bytes_total, container_network_transmit_bytes_total, kube_pod_container_info, windows_container_network_receive_bytes_total, kube_pod_container_info, windows_container_network_transmit_bytes_total | Top pods network I/O pressure per container (timeseries) | \ No newline at end of file From ab3166649174011a7428bca4bc704b9c803120a9 Mon Sep 17 00:00:00 2001 From: Nico <86240618+nico-shishkin@users.noreply.github.com> Date: Sun, 29 Jan 2023 17:03:16 +0100 Subject: [PATCH 2/4] Update aks-kubernetes-cluster-summary.md --- .../aks-kubernetes-cluster-summary.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md index 7d5506555..2e3d5b519 100644 --- a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-cluster-summary.md @@ -1,7 +1,7 @@ --- layout: article title: AKS - Kubernetes Cluster Summary -permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_cluster_summary.html +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-cluster-summary.html image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg description: View and analyze metrics with AKS Kubernetes Cluster Summary flags: @@ -39,4 +39,4 @@ This dashboard provides an interface to view and analyze metrics from your AKS K | Containers Running | kube_pod_container_status_running | Containers running (stats) | | Containers Waiting | kube_pod_container_status_waiting | Containers waiting (stats) | | Containers Terminated | kube_pod_container_status_terminated | Containers terminated (stats) | -| Containers Restarts (Per Namespace) | kube_pod_container_status_restarts_total | Containers restarts per namespace (stats) | \ No newline at end of file +| Containers Restarts (Per Namespace) | kube_pod_container_status_restarts_total | Containers restarts per namespace (stats) | From ccc8cd5297b6110fac329bf01431a7b3914707ba Mon Sep 17 00:00:00 2001 From: Nico <86240618+nico-shishkin@users.noreply.github.com> Date: Sun, 29 Jan 2023 17:03:30 +0100 Subject: [PATCH 3/4] Update aks-kubernetes-nodes.md --- .../infrastructure-monitoring/aks-kubernetes-nodes.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md index b8dc7639d..c4cc98c36 100644 --- a/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes-nodes.md @@ -1,7 +1,7 @@ --- layout: article title: AKS - Kubernetes nodes -permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_nodes.html +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-nodes.html image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg description: View and analyze metrics with Amazon Auto Scaling flags: @@ -28,4 +28,4 @@ This dashboard provides an interface to view and analyze metrics from your AKS K | Disk IO Time | node_disk_io_time_seconds_total, kubernetes_node, windows_logical_disk_read_seconds_total, windows_cs_hostname, windows_logical_disk_write_seconds_total, windows_cs_hostname | Disk IO Time (timeseries) | | Filesystem Usage (Stacked) | node_filesystem_size_bytes, kubernetes_node, node_filesystem_free_bytes, node_filesystem_avail_bytes, windows_logical_disk_size_bytes, windows_cs_hostname, windows_logical_disk_free_bytes, windows_logical_disk_free_bytes | Filesystem usage stacked (timeseries) | | Top Pods CPU Usage By Node | container_cpu_usage_seconds_total, kubernetes_io_hostname, kube_pod_container_resource_requests | Top pods CPU usage by node (gauge) | -| Top Pods Memory Usage By Node | container_memory_working_set_bytes, kube_pod_container_resource_requests | Top pods memory usage by node (gauge) | \ No newline at end of file +| Top Pods Memory Usage By Node | container_memory_working_set_bytes, kube_pod_container_resource_requests | Top pods memory usage by node (gauge) | From 70ec014c77c171bb088b571731e929c4e518f179 Mon Sep 17 00:00:00 2001 From: Nico <86240618+nico-shishkin@users.noreply.github.com> Date: Sun, 29 Jan 2023 17:03:44 +0100 Subject: [PATCH 4/4] Update aks-kubernetes_pods.md --- .../infrastructure-monitoring/aks-kubernetes_pods.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md b/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md index 00a4b7c3d..c5aeb4b8d 100644 --- a/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md +++ b/_source/user-guide/infrastructure-monitoring/aks-kubernetes_pods.md @@ -1,7 +1,7 @@ --- layout: article title: AKS - Kubernetes pods -permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes_pods.html +permalink: /user-guide/infrastructure-monitoring/metrics-dashboards/aks-kubernetes-pods.html image: https://dytvr9ot2sszz.cloudfront.net/logz-docs/social-assets/docs-social.jpg description: View and analyze metrics with Amazon Auto Scaling flags: @@ -22,4 +22,4 @@ This dashboard provides an interface to view and analyze metrics from your AKS K | Container Restarts By Pod Per Container | kube_pod_container_status_restarts_total | Container Restarts by Pod per container (timeseries) | | Top Pods Memory Usage Per Container | kube_pod_container_info, windows_container_memory_usage_commit_bytes, container_memory_working_set_bytes | Top pods memory usage per container (timeseries) | | Top Pods CPU Usage Per Container | container_cpu_usage_seconds_total, kube_pod_container_info, windows_container_cpu_usage_seconds_total | Top pods CPU usage per container (time series) | -| Top Pods Network I/O Pressure Per Container | container_network_receive_bytes_total, container_network_transmit_bytes_total, kube_pod_container_info, windows_container_network_receive_bytes_total, kube_pod_container_info, windows_container_network_transmit_bytes_total | Top pods network I/O pressure per container (timeseries) | \ No newline at end of file +| Top Pods Network I/O Pressure Per Container | container_network_receive_bytes_total, container_network_transmit_bytes_total, kube_pod_container_info, windows_container_network_receive_bytes_total, kube_pod_container_info, windows_container_network_transmit_bytes_total | Top pods network I/O pressure per container (timeseries) |