See Workbooks in Container insights for a description of the workbooks available for Container insights. Number of GPUs in a node that can be used by Kubernetes.Ĭontainer insights includes pre-configured charts for the metrics listed earlier in the table as a GPU workbook for every cluster. It is not possible to request or limit a fraction of a GPU.Īmount of GPU Memory in bytes available to use for a specific container.Īmount of GPU Memory in bytes used by a specific container.Ĭ/clusterId, /clusterName, gpuVendor It is not possible to request or limit a fraction of a GPU.Įach container can request one or more GPUs. Duty cycle is a number between 1 and 100.Ĭ/clusterId, /clusterName, containerNameĮach container can specify limits as one or more GPUs. Percentage of time over the past sample period (60 seconds) during which GPU was busy/actively processing for a container. Metric nameĬ/clusterId, /clusterName, containerName, gpuId, gpuModel, gpuVendor Container insights collect GPU metrics through GPU driver pods running in the node. After provisioning cluster with GPU nodes, ensure that GPU driver is installed as required by AKS to run GPU workloads.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |