plugin_name: cgroups.plugin modules: - &module meta: &meta plugin_name: cgroups.plugin module_name: /sys/fs/cgroup monitored_instance: name: Containers link: "" categories: - data-collection.containers-and-vms icon_filename: container.svg related_resources: integrations: list: [] info_provided_to_referring_integrations: description: "" keywords: - containers most_popular: true overview: &overview data_collection: &data_collection metrics_description: "Monitor Containers for performance, resource usage, and health status." method_description: "" supported_platforms: include: [] exclude: [] multi_instance: true additional_permissions: description: "" default_behavior: auto_detection: description: "" limits: description: "" performance_impact: description: "" setup: prerequisites: list: [] configuration: file: name: "" description: "" options: description: "" folding: title: "" enabled: true list: [] examples: folding: enabled: true title: "" list: [] troubleshooting: problems: list: [] alerts: - name: cgroup_10min_cpu_usage link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: cgroup.cpu_limit info: average cgroup CPU utilization over the last 10 minutes - name: cgroup_ram_in_use link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: cgroup.mem_usage info: cgroup memory utilization - name: cgroup_1m_received_packets_rate link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: cgroup.net_packets info: average number of packets received by the network interface ${label:device} over the last minute - name: cgroup_10s_received_packets_storm link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: cgroup.net_packets info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute metrics: folding: title: Metrics enabled: false description: "" availability: [] scopes: - name: cgroup description: "" labels: - name: container_name description: The container name or group path if name resolution fails. - name: image description: Docker/Podman container image name. metrics: - name: cgroup.cpu_limit description: CPU Usage within the limits unit: "percentage" chart_type: line dimensions: - name: used - name: cgroup.cpu description: CPU Usage (100% = 1 core) unit: "percentage" chart_type: stacked dimensions: - name: user - name: system - name: cgroup.cpu_per_core description: CPU Usage (100% = 1 core) Per Core unit: "percentage" chart_type: line dimensions: - name: a dimension per core - name: cgroup.throttled description: CPU Throttled Runnable Periods unit: "percentage" chart_type: line dimensions: - name: throttled - name: cgroup.throttled_duration description: CPU Throttled Time Duration unit: "ms" chart_type: line dimensions: - name: duration - name: cgroup.cpu_shares description: CPU Time Relative Share unit: "shares" chart_type: line dimensions: - name: shares - name: cgroup.mem description: Memory Usage unit: "MiB" chart_type: stacked dimensions: - name: cache - name: rss - name: swap - name: rss_huge - name: mapped_file - name: cgroup.writeback description: Writeback Memory unit: "MiB" chart_type: area dimensions: - name: dirty - name: writeback - name: cgroup.mem_activity description: Memory Activity unit: "MiB/s" chart_type: line dimensions: - name: in - name: out - name: cgroup.pgfaults description: Memory Page Faults unit: "MiB/s" chart_type: line dimensions: - name: pgfault - name: swap - name: cgroup.mem_usage description: Used Memory unit: "MiB" chart_type: stacked dimensions: - name: ram - name: swap - name: cgroup.mem_usage_limit description: Used RAM within the limits unit: "MiB" chart_type: stacked dimensions: - name: available - name: used - name: cgroup.mem_utilization description: Memory Utilization unit: "percentage" chart_type: line dimensions: - name: utilization - name: cgroup.mem_failcnt description: Memory Limit Failures unit: "count" chart_type: line dimensions: - name: failures - name: cgroup.io description: I/O Bandwidth (all disks) unit: "KiB/s" chart_type: area dimensions: - name: read - name: write - name: cgroup.serviced_ops description: Serviced I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: cgroup.throttle_io description: Throttle I/O Bandwidth (all disks) unit: "KiB/s" chart_type: area dimensions: - name: read - name: write - name: cgroup.throttle_serviced_ops description: Throttle Serviced I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: cgroup.queued_ops description: Queued I/O Operations (all disks) unit: "operations" chart_type: line dimensions: - name: read - name: write - name: cgroup.merged_ops description: Merged I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: cgroup.cpu_some_pressure description: CPU some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.cpu_some_pressure_stall_time description: CPU some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.cpu_full_pressure description: CPU full pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.cpu_full_pressure_stall_time description: CPU full pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.memory_some_pressure description: Memory some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.memory_some_pressure_stall_time description: Memory some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.memory_full_pressure description: Memory full pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.memory_full_pressure_stall_time description: Memory full pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.io_some_pressure description: I/O some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.io_some_pressure_stall_time description: I/O some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.io_full_pressure description: I/O some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: cgroup.io_full_pressure_stall_time description: I/O some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: cgroup.pids_current description: Number of processes unit: "pids" chart_type: line dimensions: - name: pids - name: cgroup network device description: "" labels: - name: container_name description: The container name or group path if name resolution fails. - name: image description: Docker/Podman container image name. - name: device description: "The name of the host network interface linked to the container's network interface." - name: container_device description: Container network interface name. - name: interface_type description: 'Network interface type. Always "virtual" for the containers.' metrics: - name: cgroup.net_net description: Bandwidth unit: "kilobits/s" chart_type: area dimensions: - name: received - name: sent - name: cgroup.net_packets description: Packets unit: "pps" chart_type: line dimensions: - name: received - name: sent - name: multicast - name: cgroup.net_errors description: Interface Errors unit: "errors/s" chart_type: line dimensions: - name: inbound - name: outbound - name: cgroup.net_drops description: Interface Drops unit: "errors/s" chart_type: line dimensions: - name: inbound - name: outbound - name: cgroup.net_fifo description: Interface FIFO Buffer Errors unit: "errors/s" chart_type: line dimensions: - name: receive - name: transmit - name: cgroup.net_compressed description: Interface FIFO Buffer Errors unit: "pps" chart_type: line dimensions: - name: receive - name: sent - name: cgroup.net_events description: Network Interface Events unit: "events/s" chart_type: line dimensions: - name: frames - name: collisions - name: carrier - name: cgroup.net_operstate description: Interface Operational State unit: "state" chart_type: line dimensions: - name: up - name: down - name: notpresent - name: lowerlayerdown - name: testing - name: dormant - name: unknown - name: cgroup.net_carrier description: Interface Physical Link State unit: "state" chart_type: line dimensions: - name: up - name: down - name: cgroup.net_mtu description: Interface MTU unit: "octets" chart_type: line dimensions: - name: mtu - <<: *module meta: <<: *meta monitored_instance: name: Kubernetes Containers link: https://kubernetes.io/ icon_filename: kubernetes.svg categories: #- data-collection.containers-and-vms - data-collection.kubernetes keywords: - k8s - kubernetes - pods - containers overview: <<: *overview data-collection: <<: *data_collection metrics_description: Monitor Kubernetes Clusters for performance, resource usage, and health status. alerts: - name: k8s_cgroup_10min_cpu_usage link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: k8s.cgroup.cpu_limit info: average cgroup CPU utilization over the last 10 minutes - name: k8s_cgroup_ram_in_use link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: k8s.cgroup.mem_usage info: cgroup memory utilization - name: k8s_cgroup_1m_received_packets_rate link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: k8s.cgroup.net_packets info: average number of packets received by the network interface ${label:device} over the last minute - name: k8s_cgroup_10s_received_packets_storm link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf metric: k8s.cgroup.net_packets info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute metrics: folding: title: Metrics enabled: false description: "" availability: [] scopes: - name: k8s cgroup description: These metrics refer to the Pod container. labels: - name: k8s_node_name description: 'Node name. The value of _pod.spec.nodeName_.' - name: k8s_namespace description: 'Namespace name. The value of _pod.metadata.namespace_.' - name: k8s_controller_kind description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' - name: k8s_controller_name description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' - name: k8s_pod_name description: 'Pod name. The value of _pod.metadata.name_.' - name: k8s_container_name description: 'Container name. The value of _pod.spec.containers.name_.' - name: k8s_kind description: 'Instance kind: "pod" or "container".' - name: k8s_qos_class description: 'QoS class (guaranteed, burstable, besteffort).' - name: k8s_cluster_id description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' metrics: - name: k8s.cgroup.cpu_limit description: CPU Usage within the limits unit: "percentage" chart_type: line dimensions: - name: used - name: k8s.cgroup.cpu description: CPU Usage (100% = 1000 mCPU) unit: "percentage" chart_type: stacked dimensions: - name: user - name: system - name: k8s.cgroup.cpu_per_core description: CPU Usage (100% = 1000 mCPU) Per Core unit: "percentage" chart_type: line dimensions: - name: a dimension per core - name: k8s.cgroup.throttled description: CPU Throttled Runnable Periods unit: "percentage" chart_type: line dimensions: - name: throttled - name: k8s.cgroup.throttled_duration description: CPU Throttled Time Duration unit: "ms" chart_type: line dimensions: - name: duration - name: k8s.cgroup.cpu_shares description: CPU Time Relative Share unit: "shares" chart_type: line dimensions: - name: shares - name: k8s.cgroup.mem description: Memory Usage unit: "MiB" chart_type: stacked dimensions: - name: cache - name: rss - name: swap - name: rss_huge - name: mapped_file - name: k8s.cgroup.writeback description: Writeback Memory unit: "MiB" chart_type: area dimensions: - name: dirty - name: writeback - name: k8s.cgroup.mem_activity description: Memory Activity unit: "MiB/s" chart_type: line dimensions: - name: in - name: out - name: k8s.cgroup.pgfaults description: Memory Page Faults unit: "MiB/s" chart_type: line dimensions: - name: pgfault - name: swap - name: k8s.cgroup.mem_usage description: Used Memory unit: "MiB" chart_type: stacked dimensions: - name: ram - name: swap - name: k8s.cgroup.mem_usage_limit description: Used RAM within the limits unit: "MiB" chart_type: stacked dimensions: - name: available - name: used - name: k8s.cgroup.mem_utilization description: Memory Utilization unit: "percentage" chart_type: line dimensions: - name: utilization - name: k8s.cgroup.mem_failcnt description: Memory Limit Failures unit: "count" chart_type: line dimensions: - name: failures - name: k8s.cgroup.io description: I/O Bandwidth (all disks) unit: "KiB/s" chart_type: area dimensions: - name: read - name: write - name: k8s.cgroup.serviced_ops description: Serviced I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: k8s.cgroup.throttle_io description: Throttle I/O Bandwidth (all disks) unit: "KiB/s" chart_type: area dimensions: - name: read - name: write - name: k8s.cgroup.throttle_serviced_ops description: Throttle Serviced I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: k8s.cgroup.queued_ops description: Queued I/O Operations (all disks) unit: "operations" chart_type: line dimensions: - name: read - name: write - name: k8s.cgroup.merged_ops description: Merged I/O Operations (all disks) unit: "operations/s" chart_type: line dimensions: - name: read - name: write - name: k8s.cgroup.cpu_some_pressure description: CPU some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.cpu_some_pressure_stall_time description: CPU some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.cpu_full_pressure description: CPU full pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.cpu_full_pressure_stall_time description: CPU full pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.memory_some_pressure description: Memory some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.memory_some_pressure_stall_time description: Memory some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.memory_full_pressure description: Memory full pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.memory_full_pressure_stall_time description: Memory full pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.io_some_pressure description: I/O some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.io_some_pressure_stall_time description: I/O some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.io_full_pressure description: I/O some pressure unit: "percentage" chart_type: line dimensions: - name: some10 - name: some60 - name: some300 - name: k8s.cgroup.io_full_pressure_stall_time description: I/O some pressure stall time unit: "ms" chart_type: line dimensions: - name: time - name: k8s.cgroup.pids_current description: Number of processes unit: "pids" chart_type: line dimensions: - name: pids - name: k8s cgroup network device description: These metrics refer to the Pod container network interface. labels: - name: device description: "The name of the host network interface linked to the container's network interface." - name: container_device description: Container network interface name. - name: interface_type description: 'Network interface type. Always "virtual" for the containers.' - name: k8s_node_name description: 'Node name. The value of _pod.spec.nodeName_.' - name: k8s_namespace description: 'Namespace name. The value of _pod.metadata.namespace_.' - name: k8s_controller_kind description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' - name: k8s_controller_name description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' - name: k8s_pod_name description: 'Pod name. The value of _pod.metadata.name_.' - name: k8s_container_name description: 'Container name. The value of _pod.spec.containers.name_.' - name: k8s_kind description: 'Instance kind: "pod" or "container".' - name: k8s_qos_class description: 'QoS class (guaranteed, burstable, besteffort).' - name: k8s_cluster_id description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' metrics: - name: k8s.cgroup.net_net description: Bandwidth unit: "kilobits/s" chart_type: area dimensions: - name: received - name: sent - name: k8s.cgroup.net_packets description: Packets unit: "pps" chart_type: line dimensions: - name: received - name: sent - name: multicast - name: k8s.cgroup.net_errors description: Interface Errors unit: "errors/s" chart_type: line dimensions: - name: inbound - name: outbound - name: k8s.cgroup.net_drops description: Interface Drops unit: "errors/s" chart_type: line dimensions: - name: inbound - name: outbound - name: k8s.cgroup.net_fifo description: Interface FIFO Buffer Errors unit: "errors/s" chart_type: line dimensions: - name: receive - name: transmit - name: k8s.cgroup.net_compressed description: Interface FIFO Buffer Errors unit: "pps" chart_type: line dimensions: - name: receive - name: sent - name: k8s.cgroup.net_events description: Network Interface Events unit: "events/s" chart_type: line dimensions: - name: frames - name: collisions - name: carrier - name: k8s.cgroup.net_operstate description: Interface Operational State unit: "state" chart_type: line dimensions: - name: up - name: down - name: notpresent - name: lowerlayerdown - name: testing - name: dormant - name: unknown - name: k8s.cgroup.net_carrier description: Interface Physical Link State unit: "state" chart_type: line dimensions: - name: up - name: down - name: k8s.cgroup.net_mtu description: Interface MTU unit: "octets" chart_type: line dimensions: - name: mtu - <<: *module meta: <<: *meta monitored_instance: name: Systemd Services link: "" icon_filename: systemd.svg categories: - data-collection.systemd keywords: - systemd - services overview: <<: *overview data-collection: <<: *data_collection metrics_desctiption: "Monitor Systemd Services for performance, resource usage, and health status." alerts: [] metrics: folding: title: Metrics enabled: false description: "" availability: [] scopes: - name: systemd service description: "" labels: - name: service_name description: Service name metrics: - name: systemd.service.cpu.utilization description: Systemd Services CPU utilization (100% = 1 core) unit: percentage chart_type: stacked dimensions: - name: user - name: system - name: systemd.service.memory.usage description: Systemd Services Used Memory unit: MiB chart_type: stacked dimensions: - name: ram - name: swap - name: systemd.service.memory.failcnt description: Systemd Services Memory Limit Failures unit: failures/s chart_type: line dimensions: - name: fail - name: systemd.service.memory.ram.usage description: Systemd Services Memory unit: MiB chart_type: stacked dimensions: - name: rss - name: cache - name: mapped_file - name: rss_huge - name: systemd.service.memory.writeback description: Systemd Services Writeback Memory unit: MiB chart_type: stacked dimensions: - name: writeback - name: dirty - name: systemd.service.memory.paging.faults description: Systemd Services Memory Minor and Major Page Faults unit: MiB/s chart_type: area dimensions: - name: minor - name: major - name: systemd.service.memory.paging.io description: Systemd Services Memory Paging IO unit: MiB/s chart_type: area dimensions: - name: in - name: out - name: systemd.service.disk.io description: Systemd Services Disk Read/Write Bandwidth unit: KiB/s chart_type: area dimensions: - name: read - name: write - name: systemd.service.disk.iops description: Systemd Services Disk Read/Write Operations unit: operations/s chart_type: line dimensions: - name: read - name: write - name: systemd.service.disk.throttle.io description: Systemd Services Throttle Disk Read/Write Bandwidth unit: KiB/s chart_type: area dimensions: - name: read - name: write - name: systemd.service.disk.throttle.iops description: Systemd Services Throttle Disk Read/Write Operations unit: operations/s chart_type: line dimensions: - name: read - name: write - name: systemd.service.disk.queued_iops description: Systemd Services Queued Disk Read/Write Operations unit: operations/s chart_type: line dimensions: - name: read - name: write - name: systemd.service.disk.merged_iops description: Systemd Services Merged Disk Read/Write Operations unit: operations/s chart_type: line dimensions: - name: read - name: write - name: systemd.service.pids.current description: Systemd Services Number of Processes unit: pids chart_type: line dimensions: - name: pids - <<: *module meta: <<: *meta monitored_instance: name: Virtual Machines link: "" icon_filename: container.svg categories: - data-collection.containers-and-vms keywords: - vms - virtualization - container overview: <<: *overview data_collection: <<: *data_collection metrics_description: "Monitor Virtual Machines for performance, resource usage, and health status." - <<: *module meta: <<: *meta monitored_instance: name: LXC Containers link: "" icon_filename: lxc.png categories: - data-collection.containers-and-vms keywords: - lxc - lxd - container overview: <<: *overview data_collection: <<: *data_collection metrics_description: "Monitor LXC Containers for performance, resource usage, and health status." - <<: *module meta: <<: *meta monitored_instance: name: Libvirt Containers link: "" icon_filename: libvirt.png categories: - data-collection.containers-and-vms keywords: - libvirt - container overview: <<: *overview data_collection: <<: *data_collection metrics_description: "Monitor Libvirt for performance, resource usage, and health status." - <<: *module meta: <<: *meta monitored_instance: name: oVirt Containers link: "" icon_filename: ovirt.svg categories: - data-collection.containers-and-vms keywords: - ovirt - container overview: <<: *overview data_collection: <<: *data_collection metrics_description: "Monitor oVirt for performance, resource usage, and health status." - <<: *module meta: <<: *meta monitored_instance: name: Proxmox Containers link: "" icon_filename: proxmox.png categories: - data-collection.containers-and-vms keywords: - proxmox - container overview: <<: *overview data_collection: <<: *data_collection metrics_description: "Monitor Proxmox for performance, resource usage, and health status."