Tenant Cloud Monitor and Operation Cloud Monitor Operation Guide TI-ONE Online Services

TI-ONE Online Services

Last Updated At: 2026-08-14 08:08:00

Metric English Name	Metric Description	Unit	Dimension	Statistical Granularity
Apicallerrortotal	Number of failed API calls	Count	ServiceGroupId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Apicalllimittotal	Total number of API calls throttled	Count	ServiceGroupId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Apicallsuccesstotal	Total number of successful API calls	Count	ServiceGroupId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Apicalltotal	Total number of API calls	Count	ServiceGroupId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Apiresponsetime	Average response time	ms	ServiceGroupId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsClientDataReadBandwidth	TuroCFS single-node server read bandwidth in the task instance dimension	KBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsClientDataWriteBandwidth	TuroCFS single-node server write bandwidth in the task instance dimension	KBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsDataReadIoBytes	CFS server read bandwidth in the task instance dimension	KBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsDataReadIoLatency	CFS read latency in the task instance dimension	ms	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsDataWriteIoBytes	CFS server write bandwidth in the task instance dimension	KBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsDataWriteIoLatency	CFS write latency in the task instance dimension	ms	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
CfsStrageUsageGb	CFS storage data capacity in the task instance dimension	GBytes	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Cpuutil	Task-dimension CPU utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskIoUtil	Disk I/O utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskIoWait	Disk I/O wait time in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskReadByte	Disk read bandwidth in the task instance dimension	MBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskReadIops	Disk read IOPS in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskUsageRadio	System disk partition utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskWriteByte	Disk write bandwidth in the task instance dimension	MBytes/s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DiskWriteIops	Disk write IOPS in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Gpumemutil	Task-dimension GPU memory utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Gpuutil	Task-dimension GPU utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancecpuutil	CPU utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancegpumemutil	GPU memory utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancegpuutil	GPU utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancehttpqps	HTTP requests per second in the task instance dimension	Count/s	InstanceId Source SubUin	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
Instancehttpqpslimit	HTTP requests per second limited in the task instance dimension	Count/s	InstanceId Source SubUin	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
Instancememutil	Memory utilization in the task instance dimension	%	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancememvalue	Memory usage in the task instance dimension	MBytes	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instancenetworkibytes	Inbound network traffic in the task instance dimension	MBytes	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Instanceready	Number of running instances in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, last ] [ 60s, last ] [ 300s, last ] [ 3600s, last ] [ 86400s, last ]
InstanceTiemsCurrentRequests	Number of concurrent requests in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
Instancetotal	Number of instances in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, last ] [ 60s, last ] [ 300s, last ] [ 3600s, last ] [ 86400s, last ]
Memutil	Task-dimension memory utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Memvalue	Task-dimension memory usage	MBytes	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Networkreceivebytes	Inbound network traffic in the task dimension	MBytes	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsClientDataReadBandwidth	Task-dimension TuroCFS single-node server read bandwidth	KBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsClientDataWriteBandwidth	Task-dimension TuroCFS single-node server write bandwidth	KBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsDataReadIoBytes	Task-dimension CFS server read bandwidth	KBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsDataReadIoLatency	Task-dimension CFS read latency	ms	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsDataWriteIoBytes	Task-dimension CFS server write bandwidth	KBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsDataWriteIoLatency	Task-dimension CFS write latency	ms	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceCfsStrageUsageGb	Task-dimension CFS storage data capacity	GBytes	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskIoUtil	Task-dimension disk I/O utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskIoWait	Task-dimension disk I/O wait time	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskReadByte	Task-dimension disk read bandwidth	MBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskReadIops	Task-dimension disk read IOPS	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskUsageRadio	Task-dimension system disk partition utilization	%	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskWriteByte	Task-dimension disk write bandwidth	MBytes/s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceDiskWriteIops	Task-dimension disk write IOPS	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Servicehttpqps	HTTP requests per second in the task dimension for the service	Count/s	AppId Source SubUin TaskId	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
Servicehttpqpslimit	Rate-limited HTTP requests per second in the task dimension for the service	Count/s	AppId Source SubUin TaskId	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
ServiceTiemsCurrentRequests	Number of concurrent requests in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, max ] [ 60s, max ] [ 300s, max ] [ 3600s, max ] [ 86400s, max ]
ServiceGpuMemValue	Task-dimension GPU memory usage	MBytes	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsTokenThroughput	Number of tokens processed per minute in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsTokenThroughputInput	Number of input tokens processed per minute in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsTokenThroughputOutput	Number of output tokens processed per minute in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsFirstTokenLatency	Task-dimension first token latency	s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsNonFirstTokenLatency	Task-dimension non-first token latency	s	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsProcessingRequestCount	Number of requests in processing in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
ServiceEmsQueuingRequestCount	Number of queued requests in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
ServiceEmsTotalProcessedTokens	Total number of tokens processed in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
ServiceEmsTotalProcessedTokensInput	Total number of output tokens in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
ServiceEmsTotalProcessedTokensOutput	Total number of output tokens in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
ServiceEmsAverageLengthInput	Average input length in tokens in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
ServiceEmsAverageLengthOutput	Average output length in tokens in the task dimension	Count	AppId Source SubUin TaskId	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuMemValue	GPU memory usage in the task instance dimension	MBytes	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsTokenThroughput	Number of tokens processed per minute in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsTokenThroughputInput	Total number of input tokens processed per minute in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsTokenThroughputOutput	Total number of output tokens processed per minute in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsFirstTokenLatency	First token latency in the task instance dimension	s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsNonFirstTokenLatency	Non-first token latency in the task instance dimension	s	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsProcessingRequestCount	Number of requests in processing in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
EmsQueuingRequestCount	Number of queued requests in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
EmsTotalProcessedTokens	Total number of tokens processed in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
EmsTotalProcessedTokensInput	Total number of input tokens processed in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
EmsTotalProcessedTokensOutput	Total number of output tokens processed in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, sum ] [ 60s, sum ] [ 300s, sum ] [ 3600s, sum ] [ 86400s, sum ]
EmsAverageLengthInput	Average input length (tokens) in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
EmsAverageLengthOutput	Average output length (tokens) in the task instance dimension	Count	InstanceId Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Fp16EngineActivity	FP16 active time ratio in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Fp32EngineActivity	FP32 active time ratio in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
Fp64EngineActivity	FP64 active time ratio in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
NvlinkBandwidth	NVLink transmission rate in the service instance-GPU card dimension	Bytes/s	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
PcieBandwidth	PCIe bus transmission rate in the service instance-GPU card dimension	Bytes/s	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
SmActivity	SM active time ratio in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
TensorActivity	Tensor active time ratio in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DcgmFiDevFbUsed	GPU memory usage in the service instance-GPU card dimension	MBytes	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DcgmFiDevGpuUtil	GPU utilization in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
DcgmFiDevMemCopyUtil	GPU memory utilization in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuDecUtil	GPU decoder utilization in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuEncUtil	GPU encoder utilization in the service instance-GPU card dimension	%	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuMemoryClock	GPU memory frequency in the service instance-GPU card dimension	S	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuNvlinkRxMb	NVLink received data volume in the service instance-GPU card dimension	Mbps	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuNvlinkTxMb	NVLink transmitted data volume in the service instance-GPU card dimension	Mbps	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuPcieRxMb	PCIe received data volume in the service instance-GPU card dimension	Mbps	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuPcieTxMb	PCIe transmitted data volume in the service instance-GPU card dimension	Mbps	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]
GpuSmClock	SM clock frequency in the service instance-GPU card dimension	S	Appld InstanceGpuNum Source SubUin	[ 10s, avg ] [ 60s, avg ] [ 300s, avg ] [ 3600s, avg ] [ 86400s, avg ]