Prometheus 表达式

此文档中的 PromQL 表达式可用于配置告警

在将表达式用于告警之前,必须启用监控。有关更多信息,请参阅有关在集群级别项目级别启用监控的文档。

有关查询 Prometheus 的更多信息,请参考官方的 Prometheus 文档

集群指标

集群 CPU 利用率

分类表达式
详情1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance))
汇总1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])))

集群平均负载

分类表达式
详情
load1sum(node_load1) by (instance) / count(node_cpu_seconds_total{mode="system"}) by (instance)
load5sum(node_load5) by (instance) / count(node_cpu_seconds_total{mode="system"}) by (instance)
load15sum(node_load15) by (instance) / count(node_cpu_seconds_total{mode="system"}) by (instance)
汇总
load1sum(node_load1) by (instance) / count(node_cpu_seconds_total{mode="system"})
load5sum(node_load5) by (instance) / count(node_cpu_seconds_total{mode="system"})
load15sum(node_load15) by (instance) / count(node_cpu_seconds_total{mode="system"})

集群内存利用率

分类表达式
详情1 - sum(node_memory_MemAvailable_bytes) by (instance) / sum(node_memory_MemTotal_bytes) by (instance)
汇总1 - sum(node_memory_MemAvailable_bytes) / sum(node_memory_MemTotal_bytes)

集群磁盘利用率

分类表达式
详情(sum(node_filesystem_size_bytes{device!="rootfs"}) by (instance) - sum(node_filesystem_free_bytes{device!="rootfs"}) by (instance)) / sum(node_filesystem_size_bytes{device!="rootfs"}) by (instance)
汇总(sum(node_filesystem_size_bytes{device!="rootfs"}) - sum(node_filesystem_free_bytes{device!="rootfs"})) / sum(node_filesystem_size_bytes{device!="rootfs"})

集群磁盘 I/O

分类表达式
详情
readsum(rate(node_disk_read_bytes_total[5m])) by (instance)
writtensum(rate(node_disk_written_bytes_total[5m])) by (instance)
汇总
readsum(rate(node_disk_read_bytes_total[5m]))
writtensum(rate(node_disk_written_bytes_total[5m]))

集群网络收发包

分类表达式
详情
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
receive-errssum(rate(node_network_receive_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
receive-packets sum(rate(node_network_receive_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
transmit-dropped sum(rate(node_network_transmit_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
transmit-errs sum(rate(node_network_transmit_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
transmit-packets sum(rate(node_network_transmit_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
汇总
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
receive-errs sum(rate(node_network_receive_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
receive-packets sum(rate(node_network_receive_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
transmit-dropped sum(rate(node_network_transmit_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
transmit-errs sum(rate(node_network_transmit_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
transmit-packets sum(rate(node_network_transmit_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))

集群网络 I/O

分类表达式
详情
receive sum(rate(node_network_receive_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
transmit sum(rate(node_network_transmit_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m])) by (instance)
汇总
receive sum(rate(node_network_receive_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))
transmit sum(rate(node_network_transmit_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*"}[5m]))

节点指标

节点 CPU 利用率

分类表达式
详情avg(irate(node_cpu_seconds_total{mode!="idle", instance=~"$instance"}[5m])) by (mode)
汇总1 - (avg(irate(node_cpu_seconds_total{mode="idle", instance=~"$instance"}[5m])))

节点平均负载

分类表达式
详情
load1sum(node_load1{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
load5sum(node_load5{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
load15sum(node_load15{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
汇总
load1sum(node_load1{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
load5sum(node_load5{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
load15sum(node_load15{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})

节点内存负载

分类表达式
详情1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"}) / sum(node_memory_MemTotal_bytes{instance=~"$instance"})
汇总1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"}) / sum(node_memory_MemTotal_bytes{instance=~"$instance"})

节点磁盘负载

分类表达式
详情(sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"}) by (device) - sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"}) by (device)) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"}) by (device)
汇总(sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"}) - sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"})) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})

节点磁盘 I/O

分类表达式
详情
readsum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m]))
writtensum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))
汇总
readsum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m]))
writtensum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))

节点网络收发包

分类表达式
详情
receive-dropped sum(rate(node_network_receive_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
receive-errs sum(rate(node_network_receive_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
receive-packets sum(rate(node_network_receive_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-dropped sum(rate(node_network_transmit_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-errs sum(rate(node_network_transmit_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-packets sum(rate(node_network_transmit_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
汇总
receive-dropped sum(rate(node_network_receive_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
receive-errs sum(rate(node_network_receive_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
receive-packets sum(rate(node_network_receive_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
transmit-dropped sum(rate(node_network_transmit_drop_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
transmit-errs sum(rate(node_network_transmit_errs_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
transmit-packets sum(rate(node_network_transmit_packets_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))

节点网络 I/O

分类表达式
详情
receive sum(rate(node_network_receive_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
transmit sum(rate(node_network_transmit_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m])) by (device)
汇总
receive sum(rate(node_network_receive_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))
transmit sum(rate(node_network_transmit_bytes_total{device!~"lo \| veth.* \| docker.* \| flannel.* \| cali.* \| cbr.*",instance=~"$instance"}[5m]))

etcd 指标

etcd 有领导者

max(etcd_server_has_leader)

etcd 领导者变更次数

max(etcd_server_leader_changes_seen_total)

etcd 选举提议失败次数

sum(etcd_server_proposals_failed_total)

etcd GRPC 客户端流速

分类表达式
详情
insum(rate(etcd_network_client_grpc_received_bytes_total[5m])) by (instance)
outsum(rate(etcd_network_client_grpc_sent_bytes_total[5m])) by (instance)
汇总
insum(rate(etcd_network_client_grpc_received_bytes_total[5m]))
outsum(rate(etcd_network_client_grpc_sent_bytes_total[5m]))

etcd Peer 流速

分类表达式
详情
insum(rate(etcd_network_peer_received_bytes_total[5m])) by (instance)
outsum(rate(etcd_network_peer_sent_bytes_total[5m])) by (instance)
汇总
insum(rate(etcd_network_peer_received_bytes_total[5m]))
outsum(rate(etcd_network_peer_sent_bytes_total[5m]))

etcd 数据库大小

分类表达式
详情sum(etcd_debugging_mvcc_db_total_size_in_bytes) by (instance)
汇总sum(etcd_debugging_mvcc_db_total_size_in_bytes)

etcd 活跃连接

分类表达式
详情
lease-watchsum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) by (instance)
watchsum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) by (instance)
汇总
lease-watchsum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
watchsum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})

etcd Raft 选举提议

分类表达式
详情
appliedsum(increase(etcd_server_proposals_applied_total[5m])) by (instance)
committedsum(increase(etcd_server_proposals_committed_total[5m])) by (instance)
pendingsum(increase(etcd_server_proposals_pending[5m])) by (instance)
failedsum(increase(etcd_server_proposals_failed_total[5m])) by (instance)
汇总
appliedsum(increase(etcd_server_proposals_applied_total[5m]))
committedsum(increase(etcd_server_proposals_committed_total[5m]))
pendingsum(increase(etcd_server_proposals_pending[5m]))
failedsum(increase(etcd_server_proposals_failed_total[5m]))

etcd RPC 速率

分类表达式
详情
totalsum(rate(grpc_server_started_total{grpc_type="unary"}[5m])) by (instance)
failsum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m])) by (instance)
汇总
totalsum(rate(grpc_server_started_total{grpc_type="unary"}[5m]))
failsum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m]))

etcd 磁盘操作

分类表达式
详情
commit-called-by-backendsum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m])) by (instance)
fsync-called-by-walsum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m])) by (instance)
汇总
commit-called-by-backendsum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m]))
fsync-called-by-walsum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m]))

etcd 磁盘同步持续时间

分类表达式
详情
walhistogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) by (instance, le))
dbhistogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) by (instance, le))
汇总
walsum(histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) by (instance, le)))
dbsum(histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) by (instance, le)))

Kubernetes 组件指标

Kubernetes API Server 请求延迟

分类表达式
详情avg(apiserver_request_latencies_sum / apiserver_request_latencies_count) by (instance, verb) /1e+06
汇总avg(apiserver_request_latencies_sum / apiserver_request_latencies_count) by (instance) /1e+06

Kubernetes API Server 请求速率

分类表达式
详情sum(rate(apiserver_request_count[5m])) by (instance, code)
汇总sum(rate(apiserver_request_count[5m])) by (instance)

Kubernetes Pods 调度失败次数

分类表达式
详情sum(kube_pod_status_scheduled{condition="false"})
汇总sum(kube_pod_status_scheduled{condition="false"})

Kubernetes Controller Manager 队列长度

分类表达式
详情
volumessum(volumes_depth) by instance
deploymentsum(deployment_depth) by instance
replicasetsum(replicaset_depth) by instance
servicesum(service_depth) by instance
serviceaccountsum(serviceaccount_depth) by instance
endpointsum(endpoint_depth) by instance
daemonsetsum(daemonset_depth) by instance
statefulsetsum(statefulset_depth) by instance
replicationmanagersum(replicationmanager_depth) by instance
汇总
volumessum(volumes_depth)
deploymentsum(deployment_depth)
replicasetsum(replicaset_depth)
servicesum(service_depth)
serviceaccountsum(serviceaccount_depth)
endpointsum(endpoint_depth)
daemonsetsum(daemonset_depth)
statefulsetsum(statefulset_depth)
replicationmanagersum(replicationmanager_depth)

Kubernetes Scheduler E2E 调度延迟

分类表达式
详情histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) by (le, instance)) / 1e+06
汇总sum(histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) by (le, instance)) / 1e+06)

Kubernetes Scheduler 抢占请求

分类表达式
详情sum(rate(scheduler_total_preemption_attempts[5m])) by (instance)
汇总sum(rate(scheduler_total_preemption_attempts[5m]))

Ingress Controller 链接数

分类表达式
详情
readingsum(nginx_ingress_controller_nginx_process_connections{state="reading"}) by (instance)
waitingsum(nginx_ingress_controller_nginx_process_connections{state="waiting"}) by (instance)
writingsum(nginx_ingress_controller_nginx_process_connections{state="writing"}) by (instance)
acceptedsum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="accepted"}[5m]))) by (instance)
activesum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="active"}[5m]))) by (instance)
handledsum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="handled"}[5m]))) by (instance)
汇总
readingsum(nginx_ingress_controller_nginx_process_connections{state="reading"})
waitingsum(nginx_ingress_controller_nginx_process_connections{state="waiting"})
writingsum(nginx_ingress_controller_nginx_process_connections{state="writing"})
acceptedsum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="accepted"}[5m])))
activesum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="active"}[5m])))
handledsum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="handled"}[5m])))

Ingress Controller 请求处理时长

分类表达式
详情topk(10, histogram_quantile(0.95,sum by (le, host, path)(rate(nginx_ingress_controller_request_duration_seconds_bucket{host!="_"}[5m]))))
汇总topk(10, histogram_quantile(0.95,sum by (le, host)(rate(nginx_ingress_controller_request_duration_seconds_bucket{host!="_"}[5m]))))

Rancher 日志组件指标

Fluentd 缓冲队列速率

分类表达式
详情sum(rate(fluentd_output_status_buffer_queue_length[5m])) by (instance)
汇总sum(rate(fluentd_output_status_buffer_queue_length[5m]))

Fluentd 输入速率

分类表达式
详情sum(rate(fluentd_input_status_num_records_total[5m])) by (instance)
汇总sum(rate(fluentd_input_status_num_records_total[5m]))

Fluentd 错误输出速率

分类表达式
详情sum(rate(fluentd_output_status_num_errors[5m])) by (type)
汇总sum(rate(fluentd_output_status_num_errors[5m]))

Fluentd 输出速率

分类表达式
详情sum(rate(fluentd_output_status_num_records_total[5m])) by (instance)
汇总sum(rate(fluentd_output_status_num_records_total[5m]))

工作负载指标

工作负载 CPU 利用率

分类表达式
详情
cfs throttled secondssum(rate(container_cpu_cfs_throttled_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
user secondssum(rate(container_cpu_user_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
system secondssum(rate(container_cpu_system_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
usage secondssum(rate(container_cpu_usage_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
汇总
cfs throttled secondssum(rate(container_cpu_cfs_throttled_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
user secondssum(rate(container_cpu_user_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
system secondssum(rate(container_cpu_system_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
usage secondssum(rate(container_cpu_usage_seconds_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))

工作负载内存利用率

分类表达式
详情sum(container_memory_working_set_bytes{namespace="$namespace",pod_name=~"$podName", container_name!=""}) by (pod_name)
汇总sum(container_memory_working_set_bytes{namespace="$namespace",pod_name=~"$podName", container_name!=""})

工作负载网络收发包

分类表达式
详情
receive-packetssum(rate(container_network_receive_packets_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
receive-droppedsum(rate(container_network_receive_packets_dropped_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
receive-errorssum(rate(container_network_receive_errors_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
transmit-packetssum(rate(container_network_transmit_packets_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
transmit-droppedsum(rate(container_network_transmit_packets_dropped_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
transmit-errorssum(rate(container_network_transmit_errors_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
汇总
receive-packetssum(rate(container_network_receive_packets_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
receive-droppedsum(rate(container_network_receive_packets_dropped_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
receive-errorssum(rate(container_network_receive_errors_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
transmit-packetssum(rate(container_network_transmit_packets_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
transmit-droppedsum(rate(container_network_transmit_packets_dropped_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
transmit-errorssum(rate(container_network_transmit_errors_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))

工作负载网络 I/O

分类表达式
详情
receivesum(rate(container_network_receive_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
transmitsum(rate(container_network_transmit_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
汇总
receivesum(rate(container_network_receive_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
transmitsum(rate(container_network_transmit_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))

工作负载磁盘 I/O

分类表达式
详情
readsum(rate(container_fs_reads_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
writesum(rate(container_fs_writes_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m])) by (pod_name)
汇总
readsum(rate(container_fs_reads_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))
writesum(rate(container_fs_writes_bytes_total{namespace="$namespace",pod_name=~"$podName",container_name!=""}[5m]))

Pod 指标

Pod CPU 利用率

分类表达式
详情
cfs throttled secondssum(rate(container_cpu_cfs_throttled_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m])) by (container_name)
usage secondssum(rate(container_cpu_usage_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m])) by (container_name)
system secondssum(rate(container_cpu_system_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m])) by (container_name)
user secondssum(rate(container_cpu_user_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m])) by (container_name)
汇总
cfs throttled secondssum(rate(container_cpu_cfs_throttled_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m]))
usage secondssum(rate(container_cpu_usage_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m]))
system secondssum(rate(container_cpu_system_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m]))
user secondssum(rate(container_cpu_user_seconds_total{container_name!="POD",namespace="$namespace",pod_name="$podName", container_name!=""}[5m]))

Pod 内存利用率

分类表达式
详情sum(container_memory_working_set_bytes{container_name!="POD",namespace="$namespace",pod_name="$podName",container_name!=""}) by (container_name)
汇总sum(container_memory_working_set_bytes{container_name!="POD",namespace="$namespace",pod_name="$podName",container_name!=""})

Pod 网络收发包

分类表达式
详情
receive-packetssum(rate(container_network_receive_packets_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
receive-droppedsum(rate(container_network_receive_packets_dropped_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
receive-errorssum(rate(container_network_receive_errors_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-packetssum(rate(container_network_transmit_packets_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-droppedsum(rate(container_network_transmit_packets_dropped_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-errorssum(rate(container_network_transmit_errors_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
汇总
receive-packetssum(rate(container_network_receive_packets_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
receive-droppedsum(rate(container_network_receive_packets_dropped_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
receive-errorssum(rate(container_network_receive_errors_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-packetssum(rate(container_network_transmit_packets_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-droppedsum(rate(container_network_transmit_packets_dropped_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmit-errorssum(rate(container_network_transmit_errors_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))

Pod 网络 I/O

分类表达式
详情
receivesum(rate(container_network_receive_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmitsum(rate(container_network_transmit_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
汇总
receivesum(rate(container_network_receive_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
transmitsum(rate(container_network_transmit_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))

Pod 磁盘 I/O

分类表达式
详情
readsum(rate(container_fs_reads_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m])) by (container_name)
writesum(rate(container_fs_writes_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m])) by (container_name)
汇总
readsum(rate(container_fs_reads_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))
writesum(rate(container_fs_writes_bytes_total{namespace="$namespace",pod_name="$podName",container_name!=""}[5m]))

容器指标

容器 CPU 利用率

分类表达式
cfs throttled secondssum(rate(container_cpu_cfs_throttled_seconds_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))
usage secondssum(rate(container_cpu_usage_seconds_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))
system secondssum(rate(container_cpu_system_seconds_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))
user secondssum(rate(container_cpu_user_seconds_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))

容器内存利用率

sum(container_memory_working_set_bytes{namespace="$namespace",pod_name="$podName",container_name="$containerName"})

容器磁盘 IO

分类表达式
readsum(rate(container_fs_reads_bytes_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))
writesum(rate(container_fs_writes_bytes_total{namespace="$namespace",pod_name="$podName",container_name="$containerName"}[5m]))
最后由 yzeng25更新 于