diff options
Diffstat (limited to 'collectors/cgroups.plugin')
| -rw-r--r-- | collectors/cgroups.plugin/metadata.yaml (renamed from collectors/cgroups.plugin/multi_metadata.yaml) | 73 | ||||
| -rw-r--r-- | collectors/cgroups.plugin/metrics.csv | 109 | ||||
| -rw-r--r-- | collectors/cgroups.plugin/sys_fs_cgroup.c | 165 |
3 files changed, 201 insertions, 146 deletions
diff --git a/collectors/cgroups.plugin/multi_metadata.yaml b/collectors/cgroups.plugin/metadata.yaml index b2b13c2d5..b342d30a3 100644 --- a/collectors/cgroups.plugin/multi_metadata.yaml +++ b/collectors/cgroups.plugin/metadata.yaml @@ -1,4 +1,4 @@ -name: cgroups.plugin +plugin_name: cgroups.plugin modules: - &module meta: &meta @@ -9,7 +9,7 @@ modules: link: "" categories: - data-collection.containers-and-vms - icon_filename: netdata.png + icon_filename: container.svg related_resources: integrations: list: [] @@ -18,14 +18,14 @@ modules: keywords: - containers most_popular: true - overview: - data_collection: - metrics_description: "" + 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 + multi_instance: true additional_permissions: description: "" default_behavior: @@ -398,22 +398,26 @@ modules: chart_type: line dimensions: - name: mtu - - <<: *module meta: <<: *meta monitored_instance: name: Kubernetes Containers link: https://kubernetes.io/ - icon_filename: k8s.png + icon_filename: kubernetes.svg categories: - - data-collection.containers-vms + - 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/health/health.d/cgroups.conf @@ -792,16 +796,23 @@ modules: chart_type: line dimensions: - name: mtu - - <<: *module meta: <<: *meta monitored_instance: name: Systemd Services link: "" - icon_filename: systemd.png + 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: @@ -964,14 +975,18 @@ modules: monitored_instance: name: Virtual Machines link: "" - icon_filename: k8s.png + icon_filename: container.svg categories: - - data-collection.containers-vms - - data-collection.kubernetes + - 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 @@ -980,11 +995,16 @@ modules: link: "" icon_filename: lxc.png categories: - - data-collection.containers-vms + - 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 @@ -993,22 +1013,32 @@ modules: link: "" icon_filename: libvirt.png categories: - - data-collection.containers-vms + - 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.png + icon_filename: ovirt.svg categories: - - data-collection.containers-vms + - 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 @@ -1017,7 +1047,12 @@ modules: link: "" icon_filename: proxmox.png categories: - - data-collection.containers-vms + - 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." diff --git a/collectors/cgroups.plugin/metrics.csv b/collectors/cgroups.plugin/metrics.csv deleted file mode 100644 index aae057baa..000000000 --- a/collectors/cgroups.plugin/metrics.csv +++ /dev/null @@ -1,109 +0,0 @@ -metric,scope,dimensions,unit,description,chart_type,labels,plugin,module -cgroup.cpu_limit,cgroup,used,percentage,"CPU Usage within the limits",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu,cgroup,"user, system",percentage,"CPU Usage (100% = 1 core)",stacked,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_per_core,cgroup,a dimension per core,percentage,"CPU Usage (100% = 1 core) Per Core",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.throttled,cgroup,throttled,percentage,"CPU Throttled Runnable Periods",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.throttled_duration,cgroup,duration,ms,"CPU Throttled Time Duration",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_shares,cgroup,shares,shares,"CPU Time Relative Share",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem,cgroup,"cache, rss, swap, rss_huge, mapped_file",MiB,"Memory Usage",stacked,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.writeback,cgroup,"dirty, writeback",MiB,"Writeback Memory",area,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem_activity,cgroup,"in, out",MiB/s,"Memory Activity",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.pgfaults,cgroup,"pgfault, swap",MiB/s,"Memory Page Faults",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem_usage,cgroup,"ram, swap",MiB,"Used Memory",stacked,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem_usage_limit,cgroup,"available, used",MiB,"Used RAM within the limits",stacked,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem_utilization,cgroup,utilization,percentage,"Memory Utilization",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.mem_failcnt,cgroup,failures,count,"Memory Limit Failures",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.io,cgroup,"read, write",KiB/s,"I/O Bandwidth (all disks)",area,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.serviced_ops,cgroup,"read, write",operations/s,"Serviced I/O Operations (all disks)",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.throttle_io,cgroup,"read, write",KiB/s,"Throttle I/O Bandwidth (all disks)",area,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.throttle_serviced_ops,cgroup,"read, write",operations/s,"Throttle Serviced I/O Operations (all disks)",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.queued_ops,cgroup,"read, write",operations,"Queued I/O Operations (all disks)",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.merged_ops,cgroup,"read, write",operations/s,"Merged I/O Operations (all disks)",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_some_pressure,cgroup,"some10, some60, some300",percentage,"CPU some pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_some_pressure_stall_time,cgroup,time,ms,"CPU some pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_full_pressure,cgroup,"some10, some60, some300",percentage,"CPU full pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.cpu_full_pressure_stall_time,cgroup,time,ms,"CPU full pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.memory_some_pressure,cgroup,"some10, some60, some300",percentage,"Memory some pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.memory_some_pressure_stall_time,cgroup,time,ms,"Memory some pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.memory_full_pressure,cgroup,"some10, some60, some300",percentage,"Memory full pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.memory_full_pressure_stall_time,cgroup,time,ms,"Memory full pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.io_some_pressure,cgroup,"some10, some60, some300",percentage,"I/O some pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.io_some_pressure_stall_time,cgroup,time,ms,"I/O some pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.io_full_pressure,cgroup,"some10, some60, some300",percentage,"I/O some pressure",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.io_full_pressure_stall_time,cgroup,time,ms,"I/O some pressure stall time",line,"container_name, image",cgroups.plugin,/sys/fs/cgroup -cgroup.net_net,"cgroup, network device","received, sent",kilobits/s,"Bandwidth",area,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_packets,"cgroup, network device","received, sent, multicast",pps,"Packets",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_errors,"cgroup, network device","inbound, outbound",errors/s,"Interface Errors",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_drops,"cgroup, network device","inbound, outbound",errors/s,"Interface Drops",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_fifo,"cgroup, network device","receive, transmit",errors/s,"Interface FIFO Buffer Errors",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_compressed,"cgroup, network device","receive, sent",pps,"Interface FIFO Buffer Errors",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_events,"cgroup, network device","frames, collisions, carrier",events/s,"Network Interface Events",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_operstate,"cgroup, network device","up, down, notpresent, lowerlayerdown, testing, dormant, unknown",state,"Interface Operational State",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_carrier,"cgroup, network device","up, down",state,"Interface Physical Link State",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -cgroup.net_mtu,"cgroup, network device",mtu,octets,"Interface MTU",line,"container_name, image, device, interface_type",cgroups.plugin,/proc/net/dev -k8s.cgroup.cpu_limit,k8s cgroup,used,percentage,"CPU Usage within the limits",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu,k8s cgroup,"user, system",percentage,"CPU Usage (100% = 1000 mCPU)",stacked,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_per_core,k8s cgroup,a dimension per core,percentage,"CPU Usage (100% = 1000 mCPU) Per Core",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.throttled,k8s cgroup,throttled,percentage,"CPU Throttled Runnable Periods",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.throttled_duration,k8s cgroup,duration,ms,"CPU Throttled Time Duration",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_shares,k8s cgroup,shares,shares,"CPU Time Relative Share",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem,k8s cgroup,"cache, rss, swap, rss_huge, mapped_file",MiB,"Memory Usage",stacked,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.writeback,k8s cgroup,"dirty, writeback",MiB,"Writeback Memory",area,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem_activity,k8s cgroup,"in, out",MiB/s,"Memory Activity",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.pgfaults,k8s cgroup,"pgfault, swap",MiB/s,"Memory Page Faults",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem_usage,k8s cgroup,"ram, swap",MiB,"Used Memory",stacked,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem_usage_limit,k8s cgroup,"available, used",MiB,"Used RAM within the limits",stacked,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem_utilization,k8s cgroup,utilization,percentage,"Memory Utilization",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.mem_failcnt,k8s cgroup,failures,count,"Memory Limit Failures",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.io,k8s cgroup,"read, write",KiB/s,"I/O Bandwidth (all disks)",area,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.serviced_ops,k8s cgroup,"read, write",operations/s,"Serviced I/O Operations (all disks)",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.throttle_io,k8s cgroup,"read, write",KiB/s,"Throttle I/O Bandwidth (all disks)",area,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.throttle_serviced_ops,k8s cgroup,"read, write",operations/s,"Throttle Serviced I/O Operations (all disks)",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.queued_ops,k8s cgroup,"read, write",operations,"Queued I/O Operations (all disks)",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.merged_ops,k8s cgroup,"read, write",operations/s,"Merged I/O Operations (all disks)",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_some_pressure,k8s cgroup,"some10, some60, some300",percentage,"CPU some pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_some_pressure_stall_time,k8s cgroup,time,ms,"CPU some pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_full_pressure,k8s cgroup,"some10, some60, some300",percentage,"CPU full pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.cpu_full_pressure_stall_time,k8s cgroup,time,ms,"CPU full pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.memory_some_pressure,k8s cgroup,"some10, some60, some300",percentage,"Memory some pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.memory_some_pressure_stall_time,k8s cgroup,time,ms,"Memory some pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.memory_full_pressure,k8s cgroup,"some10, some60, some300",percentage,"Memory full pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.memory_full_pressure_stall_time,k8s cgroup,time,ms,"Memory full pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.io_some_pressure,k8s cgroup,"some10, some60, some300",percentage,"I/O some pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.io_some_pressure_stall_time,k8s cgroup,time,ms,"I/O some pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.io_full_pressure,k8s cgroup,"some10, some60, some300",percentage,"I/O some pressure",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.io_full_pressure_stall_time,k8s cgroup,time,ms,"I/O some pressure stall time",line,"k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/sys/fs/cgroup -k8s.cgroup.net_net,"k8s cgroup, network device","received, sent",kilobits/s,"Bandwidth",area,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_packets,"k8s cgroup, network device","received, sent, multicast",pps,"Packets",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_errors,"k8s cgroup, network device","inbound, outbound",errors/s,"Interface Errors",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_drops,"k8s cgroup, network device","inbound, outbound",errors/s,"Interface Drops",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_fifo,"k8s cgroup, network device","receive, transmit",errors/s,"Interface FIFO Buffer Errors",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_compressed,"k8s cgroup, network device","receive, sent",pps,"Interface FIFO Buffer Errors",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_events,"k8s cgroup, network device","frames, collisions, carrier",events/s,"Network Interface Events",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_operstate,"k8s cgroup, network device","up, down, notpresent, lowerlayerdown, testing, dormant, unknown",state,"Interface Operational State",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_carrier,"k8s cgroup, network device","up, down",state,"Interface Physical Link State",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -k8s.cgroup.net_mtu,"k8s cgroup, network device",mtu,octets,"Interface MTU",line,"device, interface_type, k8s_namespace, k8s_pod_name, k8s_pod_uid, k8s_controller_kind, k8s_controller_name, k8s_node_name, k8s_container_name, k8s_container_id, k8s_kind, k8s_qos_class, k8s_cluster_id",cgroups.plugin,/proc/net/dev -services.cpu,,a dimension per systemd service,percentage,"Systemd Services CPU utilization (100% = 1 core)",stacked,,cgroups.plugin,systemd -services.mem_usage,,a dimension per systemd service,MiB,"Systemd Services Used Memory",stacked,,cgroups.plugin,systemd -services.mem_rss,,a dimension per systemd service,MiB,"Systemd Services RSS Memory",stacked,,cgroups.plugin,systemd -services.mem_mapped,,a dimension per systemd service,MiB,"Systemd Services Mapped Memory",stacked,,cgroups.plugin,systemd -services.mem_cache,,a dimension per systemd service,MiB,"Systemd Services Cache Memory",stacked,,cgroups.plugin,systemd -services.mem_writeback,,a dimension per systemd service,MiB,"Systemd Services Writeback Memory",stacked,,cgroups.plugin,systemd -services.mem_pgfault,,a dimension per systemd service,MiB/s,"Systemd Services Memory Minor Page Faults",stacked,,cgroups.plugin,systemd -services.mem_pgmajfault,,a dimension per systemd service,MiB/s,"Systemd Services Memory Major Page Faults",stacked,,cgroups.plugin,systemd -services.mem_pgpgin,,a dimension per systemd service,MiB/s,"Systemd Services Memory Charging Activity",stacked,,cgroups.plugin,systemd -services.mem_pgpgout,,a dimension per systemd service,MiB/s,"Systemd Services Memory Uncharging Activity",stacked,,cgroups.plugin,systemd -services.mem_failcnt,,a dimension per systemd service,failures,"Systemd Services Memory Limit Failures",stacked,,cgroups.plugin,systemd -services.swap_usage,,a dimension per systemd service,MiB,"Systemd Services Swap Memory Used",stacked,,cgroups.plugin,systemd -services.io_read,,a dimension per systemd service,KiB/s,"Systemd Services Disk Read Bandwidth",stacked,,cgroups.plugin,systemd -services.io_write,,a dimension per systemd service,KiB/s,"Systemd Services Disk Write Bandwidth",stacked,,cgroups.plugin,systemd -services.io_ops_read,,a dimension per systemd service,operations/s,"Systemd Services Disk Read Operations",stacked,,cgroups.plugin,systemd -services.io_ops_write,,a dimension per systemd service,operations/s,"Systemd Services Disk Write Operations",stacked,,cgroups.plugin,systemd -services.throttle_io_read,,a dimension per systemd service,KiB/s,"Systemd Services Throttle Disk Read Bandwidth",stacked,,cgroups.plugin,systemd -services.services.throttle_io_write,,a dimension per systemd service,KiB/s,"Systemd Services Throttle Disk Write Bandwidth",stacked,,cgroups.plugin,systemd -services.throttle_io_ops_read,,a dimension per systemd service,operations/s,"Systemd Services Throttle Disk Read Operations",stacked,,cgroups.plugin,systemd -throttle_io_ops_write,,a dimension per systemd service,operations/s,"Systemd Services Throttle Disk Write Operations",stacked,,cgroups.plugin,systemd -services.queued_io_ops_read,,a dimension per systemd service,operations/s,"Systemd Services Queued Disk Read Operations",stacked,,cgroups.plugin,systemd -services.queued_io_ops_write,,a dimension per systemd service,operations/s,"Systemd Services Queued Disk Write Operations",stacked,,cgroups.plugin,systemd -services.merged_io_ops_read,,a dimension per systemd service,operations/s,"Systemd Services Merged Disk Read Operations",stacked,,cgroups.plugin,systemd -services.merged_io_ops_write,,a dimension per systemd service,operations/s,"Systemd Services Merged Disk Write Operations",stacked,,cgroups.plugin,systemd
\ No newline at end of file diff --git a/collectors/cgroups.plugin/sys_fs_cgroup.c b/collectors/cgroups.plugin/sys_fs_cgroup.c index fb805e63c..9c7488c82 100644 --- a/collectors/cgroups.plugin/sys_fs_cgroup.c +++ b/collectors/cgroups.plugin/sys_fs_cgroup.c @@ -62,6 +62,8 @@ static int cgroup_enable_pressure_io_some = CONFIG_BOOLEAN_AUTO; static int cgroup_enable_pressure_io_full = CONFIG_BOOLEAN_AUTO; static int cgroup_enable_pressure_memory_some = CONFIG_BOOLEAN_AUTO; static int cgroup_enable_pressure_memory_full = CONFIG_BOOLEAN_AUTO; +static int cgroup_enable_pressure_irq_some = CONFIG_BOOLEAN_NO; +static int cgroup_enable_pressure_irq_full = CONFIG_BOOLEAN_AUTO; static int cgroup_enable_systemd_services = CONFIG_BOOLEAN_YES; static int cgroup_enable_systemd_services_detailed_memory = CONFIG_BOOLEAN_NO; @@ -474,6 +476,7 @@ void read_cgroup_plugin_configuration() { " !*.mount " " !*.partition " " !*.service " + " !*.service/udev " " !*.socket " " !*.slice " " !*.swap " @@ -828,6 +831,7 @@ struct cgroup { struct pressure cpu_pressure; struct pressure io_pressure; struct pressure memory_pressure; + struct pressure irq_pressure; // per cgroup charts RRDSET *st_cpu; @@ -1451,28 +1455,33 @@ static inline void cgroup2_read_pressure(struct pressure *res) { return; } - res->some.share_time.value10 = strtod(procfile_lineword(ff, 0, 2), NULL); - res->some.share_time.value60 = strtod(procfile_lineword(ff, 0, 4), NULL); - res->some.share_time.value300 = strtod(procfile_lineword(ff, 0, 6), NULL); - res->some.total_time.value_total = str2ull(procfile_lineword(ff, 0, 8), NULL) / 1000; // us->ms + bool did_some = false, did_full = false; - if (lines > 2) { - res->full.share_time.value10 = strtod(procfile_lineword(ff, 1, 2), NULL); - res->full.share_time.value60 = strtod(procfile_lineword(ff, 1, 4), NULL); - res->full.share_time.value300 = strtod(procfile_lineword(ff, 1, 6), NULL); - res->full.total_time.value_total = str2ull(procfile_lineword(ff, 1, 8), NULL) / 1000; // us->ms + for(size_t l = 0; l < lines ;l++) { + const char *key = procfile_lineword(ff, l, 0); + if(strcmp(key, "some") == 0) { + res->some.share_time.value10 = strtod(procfile_lineword(ff, l, 2), NULL); + res->some.share_time.value60 = strtod(procfile_lineword(ff, l, 4), NULL); + res->some.share_time.value300 = strtod(procfile_lineword(ff, l, 6), NULL); + res->some.total_time.value_total = str2ull(procfile_lineword(ff, l, 8), NULL) / 1000; // us->ms + did_some = true; + } + else if(strcmp(key, "full") == 0) { + res->full.share_time.value10 = strtod(procfile_lineword(ff, l, 2), NULL); + res->full.share_time.value60 = strtod(procfile_lineword(ff, l, 4), NULL); + res->full.share_time.value300 = strtod(procfile_lineword(ff, l, 6), NULL); + res->full.total_time.value_total = str2ull(procfile_lineword(ff, l, 8), NULL) / 1000; // us->ms + did_full = true; + } } - res->updated = 1; + res->updated = (did_full || did_some) ? 1 : 0; - if (unlikely(res->some.enabled == CONFIG_BOOLEAN_AUTO)) { - res->some.enabled = CONFIG_BOOLEAN_YES; - if (lines > 2) { - res->full.enabled = CONFIG_BOOLEAN_YES; - } else { - res->full.enabled = CONFIG_BOOLEAN_NO; - } - } + if(unlikely(res->some.enabled == CONFIG_BOOLEAN_AUTO)) + res->some.enabled = (did_some) ? CONFIG_BOOLEAN_YES : CONFIG_BOOLEAN_NO; + + if(unlikely(res->full.enabled == CONFIG_BOOLEAN_AUTO)) + res->full.enabled = (did_full) ? CONFIG_BOOLEAN_YES : CONFIG_BOOLEAN_NO; } } @@ -1637,6 +1646,7 @@ static inline void read_cgroup(struct cgroup *cg) { cgroup2_read_pressure(&cg->cpu_pressure); cgroup2_read_pressure(&cg->io_pressure); cgroup2_read_pressure(&cg->memory_pressure); + cgroup2_read_pressure(&cg->irq_pressure); cgroup_read_memory(&cg->memory, 1); } } @@ -1851,6 +1861,7 @@ static inline void cgroup_free(struct cgroup *cg) { free_pressure(&cg->cpu_pressure); free_pressure(&cg->io_pressure); free_pressure(&cg->memory_pressure); + free_pressure(&cg->irq_pressure); freez(cg->id); freez(cg->intermediate_id); @@ -2465,6 +2476,18 @@ static inline void discovery_update_filenames() { netdata_log_debug(D_CGROUP, "memory.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); } } + + if (unlikely((cgroup_enable_pressure_irq_some || cgroup_enable_pressure_irq_full) && !cg->irq_pressure.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/irq.pressure", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->irq_pressure.filename = strdupz(filename); + cg->irq_pressure.some.enabled = cgroup_enable_pressure_irq_some; + cg->irq_pressure.full.enabled = cgroup_enable_pressure_irq_full; + netdata_log_debug(D_CGROUP, "irq.pressure filename for cgroup '%s': '%s'", cg->id, cg->irq_pressure.filename); + } else { + netdata_log_debug(D_CGROUP, "irq.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); + } + } } } } @@ -4643,6 +4666,112 @@ void update_cgroup_charts(int update_every) { update_pressure_charts(pcs); } + res = &cg->irq_pressure; + + if (likely(res->updated && res->some.enabled)) { + struct pressure_charts *pcs; + pcs = &res->some; + + if (unlikely(!pcs->share_time.st)) { + RRDSET *chart; + snprintfz(title, CHART_TITLE_MAX, "IRQ some pressure"); + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) + , "irq_some_pressure" + , NULL + , "interrupts" + , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure" : "cgroup.irq_some_pressure" + , title + , "percentage" + , PLUGIN_CGROUPS_NAME + , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME + , cgroup_containers_chart_priority + 2310 + , update_every + , RRDSET_TYPE_LINE + ); + rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + if (unlikely(!pcs->total_time.st)) { + RRDSET *chart; + snprintfz(title, CHART_TITLE_MAX, "IRQ some pressure stall time"); + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) + , "irq_some_pressure_stall_time" + , NULL + , "interrupts" + , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure_stall_time" : "cgroup.irq_some_pressure_stall_time" + , title + , "ms" + , PLUGIN_CGROUPS_NAME + , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME + , cgroup_containers_chart_priority + 2330 + , update_every + , RRDSET_TYPE_LINE + ); + rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + update_pressure_charts(pcs); + } + + if (likely(res->updated && res->full.enabled)) { + struct pressure_charts *pcs; + pcs = &res->full; + + if (unlikely(!pcs->share_time.st)) { + RRDSET *chart; + snprintfz(title, CHART_TITLE_MAX, "IRQ full pressure"); + + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) + , "irq_full_pressure" + , NULL + , "interrupts" + , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure" : "cgroup.irq_full_pressure" + , title + , "percentage" + , PLUGIN_CGROUPS_NAME + , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME + , cgroup_containers_chart_priority + 2350 + , update_every + , RRDSET_TYPE_LINE + ); + + rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + if (unlikely(!pcs->total_time.st)) { + RRDSET *chart; + snprintfz(title, CHART_TITLE_MAX, "IRQ full pressure stall time"); + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) + , "irq_full_pressure_stall_time" + , NULL + , "interrupts" + , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure_stall_time" : "cgroup.irq_full_pressure_stall_time" + , title + , "ms" + , PLUGIN_CGROUPS_NAME + , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME + , cgroup_containers_chart_priority + 2370 + , update_every + , RRDSET_TYPE_LINE + ); + rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + update_pressure_charts(pcs); + } + res = &cg->io_pressure; if (likely(res->updated && res->some.enabled)) { |