The page has been translated by Gen AI.

Installing the ServiceWatch Agent

Users can install the ServiceWatch Agent on GPU Nodes in a Multi-node GPU Cluster to collect custom metrics and logs.

Notice

When collecting custom metrics or logs using the ServiceWatch Agent, contact us separately for the kr-south3 region by referring to Support Center > Inquiries.

Warning

Metric collection through the ServiceWatch Agent is billed separately from default metrics because it is categorized as custom metrics. We recommend removing or disabling any unnecessary metric collection settings.

ServiceWatch Agent

The agents that must be installed on GPU nodes in a multi-node GPU cluster to collect ServiceWatch custom metrics and logs can be broadly divided into two types. They are the Prometheus Exporter and the Open Telemetry Collector.

Category	Detailed Description
Prometheus Exporter	Provides metrics for specific applications or services in a format that Prometheus can scrape. To collect OS metrics from GPU Nodes, you can use Node Exporter for Linux servers and Windows Exporter for Windows servers, depending on the OS type. To collect OS metrics from GPU Nodes, you can use Node Exporter, similar to Virtual Servers. For details, see Virtual Server > ServiceWatch Agent. You can use the DCGM (NVIDIA Data Center GPU Manager) Exporter for GPU Nodes. For instructions on using the DCGM Exporter, see GPU Server > Installing the ServiceWatch Agent.
Open Telemetry Collector	Acts as a centralized collector that gathers telemetry data such as metrics and logs from distributed systems, processes it (filtering, sampling, etc.), and exports it to multiple backends (e.g., Prometheus, Jaeger, Elasticsearch, etc.) Exports data to the ServiceWatch Gateway, enabling ServiceWatch to collect metrics and log data. For information on how to use the Open Telemetry Collector provided by ServiceWatch, refer to ServiceWatch > Using the ServiceWatch Agent

Category

Detailed Description

Prometheus Exporter

Provides metrics for specific applications or services in a format that Prometheus can scrape.

To collect OS metrics from GPU Nodes, you can use Node Exporter for Linux servers and Windows Exporter for Windows servers, depending on the OS type.
- To collect OS metrics from GPU Nodes, you can use Node Exporter, similar to Virtual Servers. For details, see Virtual Server > ServiceWatch Agent.

You can use the DCGM (NVIDIA Data Center GPU Manager) Exporter for GPU Nodes.
- For instructions on using the DCGM Exporter, see GPU Server > Installing the ServiceWatch Agent.

Open Telemetry Collector

Acts as a centralized collector that gathers telemetry data such as metrics and logs from distributed systems, processes it (filtering, sampling, etc.), and exports it to multiple backends (e.g., Prometheus, Jaeger, Elasticsearch, etc.)

Exports data to the ServiceWatch Gateway, enabling ServiceWatch to collect metrics and log data.

For information on how to use the Open Telemetry Collector provided by ServiceWatch, refer to ServiceWatch > Using the ServiceWatch Agent

Table. Description of Prometheus Exporter and Open Telemetry Collector

Notice

If you have configured Kubernetes Engine on a GPU node, you can check GPU metrics using the metrics provided by Kubernetes Engine.

If you install the DCGM Exporter on a GPU node in a configured Kubernetes Engine, it may not function properly.

Reference

You can use the ServiceWatch Agent guide for collecting GPU metrics on GPU Nodes in the same way as on GPU Servers. For details, see GPU Server > ServiceWatch Agent.

Preconfiguration for Using the ServiceWatch Agent

To use the ServiceWatch Agent, prepare the prerequisites by referring to Prerequisites for the ServiceWatch Agent.

Cluster Fabric Management

Multi-node GPU Cluster Service Scope and Inspection Guide