命名空间
Namespace=QCE/CVM
监控指标
CPU 监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
CpuUsage | CPU 利用率 | 机器运行期间实时占用的 CPU 百分比 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max,p95] |
CpuLoadavg | CPU 一分钟平均负载 | 1分钟内正在使用和等待使用 CPU 的平均任务数(Windows 机器无此指标) | - | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
Cpuloadavg5m | CPU 五分钟平均负载 | 5分钟内正在使用和等待使用 CPU 的平均任务数(Windows 机器无此指标) | 0 | InstanceId | [60s, avg]
[300s, max] |
Cpuloadavg15m | CPU 十五分钟平均负载 | 15分钟内正在使用和等待使用 CPU 的平均任务数(Windows 机器无此指标) | 0 | InstanceId | [60s, avg]
[300s, max] |
BaseCpuUsage | 基础 CPU 使用率 | 基础 CPU 使用率通过宿主机采集上报,无须安装监控组件即可查看数据,子机高负载情况下仍可持续采集上报数据 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max, avg]
[86400s, max,p95] |
GPU 监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
GpuMemTotal | GPU 内存总量 | GPU 内存总量 | MB | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gpumemusage | GPU 内存使用率 | GPU 内存使用率 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
GpuMemUsed | GPU 内存使用量 | 评估负载对显存占用 | MB | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gpupowdraw | GPU 功耗使用量 | GPU 功耗使用量 | 0 | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gpupowlimit | GPU 功耗总量 | GPU 功耗总量 | 0 | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gpupowusage | GPU 功耗使用率 | GPU 功耗使用率 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gputemp | GPU 温度 | 评估 GPU 散热状态 | 0 | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
Gpuutil | GPU 使用率 | 评估负载所消耗的计算能力,非空闲状态百分比 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
GpuEncUtil | GPU 编码器使用率 | GPU 编码器使用率 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
GpuDecUtil | GPU 解码器使用率 | GPU 解码器使用率 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
网络监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
LanOuttraffic | 内网出带宽 | 内网网卡的平均每秒出流量 | Mbps | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
LanIntraffic | 内网入带宽 | 内网网卡的平均每秒入流量 | Mbps | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
LanOutpkg | 内网出包量 | 内网网卡的平均每秒出包量 | 个/秒 | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
LanInpkg | 内网入包量 | 内网网卡的平均每秒入包量 | 个/秒 | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
WanOuttraffic | 外网出带宽 | 外网平均每秒出流量速率,最小粒度数据为10秒总流量/10秒计算得出,该数据为 EIP+CLB+CVM 的外网出/入带宽总和 | Mbps | InstanceId | [10s, sum]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
WanIntraffic | 外网入带宽 | 外网平均每秒入流量速率,最小粒度数据为10秒总流量/10秒计算得出,该数据为 EIP+CLB+CVM 的外网出/入带宽总和 | Mbps | InstanceId | [10s, sum]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
WanOutpkg | 外网出包量 | 外网网卡的平均每秒出包量 | 个/秒 | InstanceId | [10s, sum]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
WanInpkg | 外网入包量 | 外网网卡的平均每秒入包量 | 个/秒 | InstanceId | [10s, sum]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
AccOuttraffic | 外网出流量 | 外网网卡的平均每秒出流量 | MB | InstanceId | [10s, sum]
[60s, sum]
[300s, sum]
[3600s, sum]
[86400s, sum] |
TcpCurrEstab | TCP 连接数 | 处于 ESTABLISHED 状态的 TCP 连接数量 | - | InstanceId | [10s, max]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
Timeoffset | 子机 utc 时间和 ntp 时间差值 | 子机 utc 时间和 ntp 时间差值 | 秒 | InstanceId | [60s, max]
[300s, max] |
Outratio | 公网出带宽利用率 | 公网出带宽利用率 | % | InstanceId | [ 10s, sum ]
[ 60s, max ]
[ 300s, max ] |
内存监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
MemUsed | 内存使用量 | 用户实际使用的内存量,不包括缓冲区与系统缓存占用的内存,总内存 - 可用内存(包括 buffers 与 cached)得到内存使用量数值,不包含 buffers和 cached | MB | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max] |
MemUsage | 内存利用率 | 用户实际内存使用率,不包括缓冲区与系统缓存占用的内存,除去缓存、buffer 和剩余,用户实际使用内存与总内存之比 | % | InstanceId | [10s, avg]
[60s, avg]
[300s, max]
[3600s, max]
[86400s, max,p95] |
磁盘监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
CvmDiskUsage | 磁盘利用率 | 磁盘已使用容量占总容量的百分比(所有磁盘中最大值) | % | InstanceId | [60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
CVM 磁盘分区监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
DiskReadTrafficNew | 磁盘读流量 | 平均每秒从磁盘读到内存的数据量 | KB/s | disk_name、serial、vm_uuid | [10s, last]
[60s, last]
[300s, max]
[3600s, max]
[86400s, max] |
DiskSvctm | 磁盘分区平均每次 I/O 操作所花的时间 | 磁盘分区平均每次 I/O 操作所花的时间 | ms | disk_name、serial、vm_uuid | [10s, last]
[60s, last]
[300s, max]
[3600s, max]
[86400s, max] |
DiskWriteTrafficNew | 磁盘写流量 | 平均每秒从内存写到磁盘的数据量 | KB/s | disk_name、serial、vm_uuid | [10s, last]
[60s, last]
[300s, max]
[3600s, max]
[86400s, max] |
磁盘分区监控
指标英文名 | 指标中文名 | 指标说明 | 单位 | 维度 | 统计规则
[period, statType] |
DiskTotal | 磁盘总量[子机] | 磁盘分区总容量 | M | InstanceId、diskname | [10s, max]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
DiskUsage | 磁盘使用率 | 磁盘分区已使用容量和总容量的百分比 | % | InstanceId、diskname | [10s, max]
[60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
CVM 磁盘数据监控
指标英文名 | 指标中文名 | 指标说明(非必填) | 单位 | 维度 | 统计规则
[period, statType] |
VmDiskReadIops | 磁盘读 IOPS | 磁盘读 IOPS | count/s | vmUuid | [60s, max]
[300s, avg] |
VmDiskTmpio | 处理 IO 所需要的平均时间 | 磁盘 svctm | ms | vmUuid | [60s, max]
[300s, avg] |
设备监控
指标英文名 | 指标中文名 | 指标说明(非必填) | 单位 | 维度 | 统计规则
[period, statType] |
DiskIoAwait | 磁盘分区 I/O 平均每次操作的等待时间[子机] | 磁盘分区 I/O 平均每次操作的等待时间 | ms | vm_uuid | [60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
DiskReadTraffic | 平均每秒从磁盘读到内存的数据量[子机] | 平均每秒从磁盘读到内存的数据量 | KB/s | vm_uuid | [60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
DiskWriteTraffic | 平均每秒从内存写到硬盘的数据量子机 | 平均每秒从内存写到磁盘的数据量 | KB/s | vm_uuid | [60s, max]
[300s, max]
[3600s, max]
[86400s, max] |
RdmaInpkg | RX 报文量(pps) | rdma 网卡的平均每秒入包量 | Count/s | vm_uuid | [10s, avg]
[60s, avg]
[300s, max] |
DockerCluster 监控
指标英文名 | 指标中文名 | 指标说明(非必填) | 单位 | 维度 | 统计规则
[period, statType] |
DcCpuUsage | CPU 使用率[子机] | 运行期间实时占用的 CPU 百分比,依赖监控组件安装采集 | % | docker_clusterid | [60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
DcMemUsage | 内存使用率[子机] | 使用的内存占总内存比率,使用的内存不包括系统缓存和缓存区占用内存,依赖监控组件安装采集 | % | docker_clusterid | [60s, avg]
[300s, avg]
[3600s, avg]
[86400s, avg] |
cvm 磁盘(diskId 索引)监控
指标英文名 | 指标中文名 | 指标说明(非必填) | 单位 | 维度 | 统计规则
[period, statType] |
CbsVolumeFsUsage | 内存使用率[子机] | 硬盘文件系统使用率 | % |
diskId
| [10s, max]
[60s, max]
[300s, max] |
RDMA 监控
指标英文名 | 指标中文名 | 指标说明(非必填) | 单位 | 维度 | 统计规则
[period, statType] |
RdmaIntraffic | RDMA 网卡接收带宽 | RDMA 网卡接收带宽 | MBit/s | InstanceId | [60s, last] |
RdmaOuttraffic | RDMA 网卡发送带宽 | RDMA 网卡发送带宽 | MBit/s | InstanceId | [60s, last] |
RdmaInpkt | RDMA 网卡入包量 | RDMA 网卡入包量 | 个/秒 | InstanceId | [60s, last] |
RdmaOutpkt | RDMA 网卡出包量 | RDMA 网卡出包量 | 个/秒 | InstanceId | [60s, last] |
CnpCount | CNP 统计量 | 拥塞通知报文统计 | 个/秒 | InstanceId | [60s, last] |
EcnCount | ECN 统计量 | 显示拥塞通知统计 | 个/秒 | InstanceId | [60s, last] |
RdmaPktDiscard | 端测丢包量 | 端测丢包量 | 个/秒 | InstanceId | [60s, last] |
RdmaOutOfSequence | 接收方乱序错误量 | 接收方乱序错误量 | 个/秒 | InstanceId | [60s, last] |
RdmaTimeoutCount | 发送方超时错误量 | 发送方超时错误量 | 个/秒 | InstanceId | [60s, last] |
TxPfcCount | TX PFC 统计量 | TX PFC 统计量 | 个/秒 | InstanceId | [60s, last] |
RxPfcCount | RX PFC 统计量 | RX PFC 统计量 | 个/秒 | InstanceId | [60s, last] |
RxHpbwAvg | 毫秒级_RDMA 网卡接收平均带宽 | 毫秒级_RDMA 网卡接收平均带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
RxHpbwMax | 毫秒级_RDMA 网卡接收最大带宽 | 毫秒级_RDMA 网卡接收最大带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
RxHpbwMin | 毫秒级_RDMA 网卡接收最小带宽 | 毫秒级_RDMA 网卡接收最小带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
RxHpbwP50 | 毫秒级_RDMA 网卡接收带宽P50 | 毫秒级_RDMA 网卡接收带宽P50 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
RxHpbwP90 | 毫秒级_RDMA 网卡接收带宽P90 | 毫秒级_RDMA 网卡接收带宽P90 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
TxHpbwAvg | 毫秒级_RDMA 网卡发送平均带宽 | 毫秒级_RDMA 网卡发送平均带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
TxHpbwMax | 毫秒级_RDMA 网卡发送最大带宽 | 毫秒级_RDMA 网卡发送最大带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
TxHpbwMin | 毫秒级_RDMA 网卡发送最小带宽 | 毫秒级_RDMA 网卡发送最小带宽 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
TxHpbwP50 | 毫秒级_RDMA 网卡发送带宽P50 | 毫秒级_RDMA 网卡发送带宽P50 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
TxHpbwP90 | 毫秒级_RDMA 网卡发送带宽P90 | 毫秒级_RDMA 网卡发送带宽P90 | Mbps | InstanceId | [ 10s, last ]
[ 60s, avg ]
[ 300s, avg ] |
说明:
1. 安装 云服务器监控组件 Agent 才能获取基础指标数据(CPU、内存等)和告警时间(为客户云服务器的本地时间)。若客户云服务器本地时间非东八区时间,将导致该云服务器的监控数据的时间为非东八区的子机本地时间。
2. 安装监控组件两种方式:
用户可通过购买机器时勾选云监控按钮自动安装监控组件。
通过 安装云服务器监控组件 手动安装监控组件。
3. 每个指标的统计粒度(Period)可取值不一定相同,可通过 DescribeBaseMetrics 接口获取每个指标支持的统计粒度。
各维度对应参数总览
参数名称 | 维度名称 | 维度解释 | 格式 |
Instances.N.Dimensions.0.Name | InstanceId | 云服务器实例 ID 的维度名称 | 输入 String 类型维度名称:InstanceId |
Instances.N.Dimensions.0.Value | InstanceId | 云服务器实例的具体 ID | 输入具体实例 ID,例如:ins-mm8bs222 |
Instances.N.Dimensions.1.Name | disk_name | 云硬盘在系统中的设备名称维度 | 输入 String 类型维度名称:disk_name |
Instances.N.Dimensions.1.Value | disk_name | 云硬盘在系统中的具体设备名称 | 输入具体设备名,例如:/dev/vdb |
Instances.N.Dimensions.2.Name | serial | 云硬盘在系统中的设备序列号 | 输入 String 类型维度名称:serial |
Instances.N.Dimensions.2.Value | serial | 云硬盘在系统中的具体序列号 | 输入具体序列号,例如:d489ca1c-5057-4536-81cb-ceb2847f9954 |
Instances.N.Dimensions.3.Name | vm_uuid | 云服务器实例 uuid 的维度名称 | 输入 String 类型维度名称:vm_uuid |
Instances.N.Dimensions.3.Value | vm_uuid | 云服务器实例 uuid 的维度名称 | 输入具体 uuid,例如:54e5c0ec-af7d-4264-a205-16a31091e07f |
Instances.N.Dimensions.4.Name | docker_clusterid | 云硬盘磁盘使用率 ID 的维度 | 输入 String 类型维度名称:docker_clusterid |
Instances.N.Dimensions.4.Value | docker_clusterid | 云硬盘磁盘使用率 ID | 输入具体 docker_clusterid,例如:00b7cfff-c61f-4247-8-vda1 |
Instances.N.Dimensions.5.Name | diskId | 云硬盘 ID 的维度名称 | 输入String类型维度名称:diskId |
Instances.N.Dimensions.5.Value | diskId | 云硬盘的具体 ID | 输入具体的云硬盘 ID,例如:disk-niel84nf |
Instances.N.Dimensions.6.Name | diskname | 云硬盘在系统中的设备名称维度 | 输入 String 类型维度名称:diskname |
Instances.N.Dimensions.6.Value | diskname | 云硬盘在系统中的具体设备名称 | 输入具体设备名,例如:vdb |
入参说明
查询云服务器监控数据,入参取值如下:
&Namespace=QCE/CVM
&Instances.N.Dimensions.0.Name=InstanceId
&Instances.N.Dimensions.0.Value=云服务器的具体 ID
&Instances.N.Dimensions.1.Name=disk_name
&Instances.N.Dimensions.1.Value=云硬盘在系统中的具体设备名称
&Instances.N.Dimensions.2.Name=serial
&Instances.N.Dimensions.2.Value=云硬盘在系统中的具体序列号
&Instances.N.Dimensions.3.Name=vm_uuid
&Instances.N.Dimensions.3.Value=云服务器实例 uuid 的维度名称
&Instances.N.Dimensions.4.Name=docker_clusterid
&Instances.N.Dimensions.4.Value=云硬盘磁盘使用率 ID
&Instances.N.Dimensions.5.Name=diskId
&Instances.N.Dimensions.5.Value=云硬盘的具体 ID
&Instances.N.Dimensions.6.Name=diskname
&Instances.N.Dimensions.6.Value=云硬盘在系统中的具体设备名称