View CES Monitor

You can view monitoring data for CES resources to understand the operating status of the CPU, memory, load, disks, and InfiniBand.

​

View Monitoring Data

1. Log in to the GPU Cloud console and go to OBSERVABILITY > Monitor.
2. Select CES under Resource Type.
3. Select a region and the target resource.
4. Select a time range.
5. View monitoring charts. CES monitoring includes the following metric groups:

   Group	Metrics	Description
   CPU/MEM/LOAD	CPU Usage(%)、Memory Usage(GB)、System Load	View CPU usage, memory usage, and system load.
   Disk Metrics	Disk Usage(B)、Inode Usage(%)、Disk I/O(Bps)、Disk I/O Count(count/s)、Infiniband Receive(B/s)、Infiniband Transmitted(B/s)	View disk capacity, inodes, disk I/O, and InfiniBand data transmission and reception.

   Memory Usage (GB) can display curves for memory used, memory buffers, memory cached, memory free, and memory total. System Load can display the 1-minute, 5-minute, and 15-minute load averages, as well as the number of logical cores. If some charts display No data, check whether the resources and time range are correct.
6. To retrieve the latest data, click Refresh.

When viewing metrics, pay close attention to trends in CPU Usage (%), Memory Usage (GB), System Load, Disk Usage (B), and InfiniBand send/receive metrics. When investigating resource anomalies, it is recommended to assess them together with instance monitoring, logs, and alarm history.