Search Our Database

Introduction

This guide explains how to view the server usage metrics for your GPU instances through the IPServerOne Customer Portal. By accessing these graphs, you can monitor key performance metrics such as CPU utilization, memory consumption, disk throughput, bandwidth usage and data transfer. This information is crucial for maintaining optimal performance and troubleshooting issues with your GPU instance.

Prerequisites

• Access to the IPServerOne portal.
• A GPU instance that you are actively managing.

Step-by-Step Guide

Step 1: Log in to the IPServerOne Portal

• Login to the [IPServerOne Customer Portal].

Step 2: Navigate to the GPU Instance Management Section

• Go to the NovaCloud and select NovaGPU Instances to view your GPU instance management page.
  

• Select the specific GPU instance for which you want to view the performance metrics.
  

Step 3: Access the Monitoring Tab

• Scroll down within the selected GPU instance’s overview page.
• This will display several performance graphs showing usage statistics such as CPU, memory, disk throughput, bandwidth and data transfer.
• You can adjust the time range of the displayed data by clicking on the Select Time Range dropdown menu
• Review the Performance Metrics:
  • CPU % (Average per core)
    • Description: This metric displays the average CPU utilization across all cores of the GPU instance.
    • Graph Interpretation: Spikes or sustained high CPU usage may indicate that the instance is under heavy load or processing-intensive tasks.
  • Memory (MiB)
    • Description: This graph shows the total memory consumption of the instance in megabytes (MiB).
    • Graph Interpretation: A consistently high memory usage might indicate that the instance is running memory-intensive applications or processes.
  • Disk Throughput (KB/s)
    • Description: This graph monitors the read and write operations on the disk, measured in kilobytes per second (KB/s).
    • Graph Interpretation: High read or write throughput could suggest data-heavy applications such as database operations.
  • Bandwidth (KiB/s)
    • Description: The bandwidth graph displays the incoming (Rx_bytes) and outgoing (Tx_bytes) network traffic in kibibytes per second (KiB/s).
    • Graph Interpretation: Significant outgoing traffic may indicate data transfers or web hosting activity, while low incoming traffic suggests fewer data requests being made to the instance.
  • Data Transfer
    • Description: This graph displays the total accumulated incoming (Incoming (GiB)) and outgoing (Outgoing (GiB)) network data volume over time, measured in gigabytes (GiB).
    • Graph Interpretation: A steady increase in data transfer volume indicates ongoing network usage and data exchange, helping you monitor total bandwidth consumption against your plan limits.
• Use these graphs to identify trends and resource usage patterns. If a specific resource is overused, consider scaling your instance up or optimizing the running processes.
  

Conclusion

By regularly monitoring the CPU, memory, disk throughput, bandwidth and data transfer of your GPU instance, you can ensure the system runs efficiently and proactively address any performance issues. Adjust the time ranges as needed to get a more detailed view of the instance’s performance over various periods.

For additional assistance or if you encounter any issues, please contact our support team at support@ipserverone.com.

Article updated on 21 October 2026 by Johnny