대시보드

How to activate this dashboard? Welcome to the Azure Application for Container Grafana Dashboard. Learn more about dashboard. Choose your resource group and related workspace that sources AGCAccessLogs.

This dashboard monitors HPC nodes with extended GPU profiling metrics including SM activity, tensor core usage, FP16/32/64 pipeline utilization, plus InfiniBand and NVLink performance data.

This dashboard monitors HPC node performance by combining InfiniBand, GPU, and NVLink metrics for comprehensive interconnect and accelerator analysis.

This dashboard provides insights into the Layer 7 (L7) networking within a specific Kubernetes namespace.

The dashboard can be used to display the metrics for the local CSI driver and ESAN CSI driver (Will be added soon). The dashboard displays the data plane metrics of the volumes in the cluster.

Provides overview of cluster CPU, GPU, IB & NVLink metrics

This dashboard provides a heat map view of HPC (High-Performance Computing) cluster metrics in tabular format for monitoring node-level performance and resource utilization.

Provides detailed monitoring of Azure Virtual Machines using OpenTelemetry metrics collected by VM Insights. Includes an overview of uptime, CPU core count, CPU load averages, and memory limits, plus deep-dive sections for CPU (utilization, per-core, by state, top processes), memory (free, used, utilization, by state), disk I/O (throughput, operations, top processes, file system usage, paging/swap), and network (I/O, packets, connections by protocol, dropped packets, errors). Scoped by subscript

Monitors individual processes running on Azure Virtual Machines using OpenTelemetry metrics collected by VM Insights. Shows per-process thread counts, uptime, CPU utilization and time (top consumers and maximums), memory utilization and usage, and disk read/write operations. Scoped by subscription, resource group, and VM.

Monitors Azure Virtual Machines using OpenTelemetry default metrics collected by VM Insights. Displays CPU utilization (overall, per-core, and by state), memory usage and utilization, disk I/O and operations, file system consumption, and network throughput, errors, and dropped packets. Scoped by subscription, resource group, and VM.

Azure Monitor Application Insights with OpenTelemetry Metrics (RPC) This dashboard requires OpenTelemetry metrics to be ingested into an Application Insights resource with OTLP enabled.

Azure Monitor Application Insights with OpenTelemetry Metrics (RPC) on **Azure Kubernetes Service (AKS)** This dashboard requires OpenTelemetry metrics to be ingested into an Application Insights resource with OTLP enabled.

Azure Monitor Application Insights with OpenTelemetry Metrics (HTTP) on Azure Kubernetes Service (AKS) This dashboard requires OpenTelemetry metrics to be ingested into an Application Insights resource with OTLP enabled. For onboarding instructions, see [App Insights with OTel](https://aka.ms/AppInsightswithOTel) *Note: This dashboard should only be used for metrics which are ingested in cumulative temporality, the default setting for the Application Insights OpenTelemetry distro. [Learn

OpenTelemetry dashboard providing HTTP request/response delta metrics.

Azure Monitor Application Insights with OpenTelemetry Metrics (HTTP) This dashboard requires OpenTelemetry metrics to be ingested into an Application Insights resource with OTLP enabled. For onboarding instructions, see [App Insights with OTel](https://aka.ms/AppInsightswithOTel) *Note: This dashboard should only be used for metrics which are ingested in cumulative temporality, the default setting for the Application Insights OpenTelemetry distro. [Learn More](https://aka.ms/OtelMetricTem

OpenTelemetry dashboard providing RPC call delta metrics.