DocsICP FilingConsole
Documentation
Home Page Alibaba Cloud Linux Operating System Console System diagnostics Node diagnostics Scheduling diagnostics System load diagnosis

System load diagnosis

Updated at:
Copy as MD
Product
My Favorites

System load diagnosis helps you analyze the cause of an abnormal one-minute average load (the load1 metric), providing detailed information and suggesting solutions.

Limitations

  • Region restrictions

  • Operating system restrictions

    Architecture

    Operating system

    x86 architecture

    • Rocky Linux 9.5

    • Rocky Linux 9.1

    • Ubuntu 20.04

    • Alibaba Cloud Linux 3 Container Optimized Edition

    • Rocky Linux 8.8

    • Ubuntu 22.04

    • Alibaba Cloud Linux 3 Pro

    • Alibaba Cloud Linux 2/3

    • CentOS 7.6 or later, or CentOS 8

    • Anolis OS 7/8

    • Ubuntu 24.04

    ARM architecture

    • Alibaba Cloud Linux 3 Pro

    • Alibaba Cloud Linux 3

Use cases

This topic describes common scenarios where you can use this feature to run diagnostics and resolve issues based on the provided suggestions.

  • Your monitoring system indicates that the system load metric is high.

  • Your system experiences short-term anomalies related to network or I/O operations.

Prerequisites

  • If you use a RAM user, make sure that the Alibaba Cloud account (primary account) has granted the RAM user the AliyunECSReadOnlyAccess and AliyunSysomFullAccess system policies.

  • The console permissions are activated.

    The first time you log on to the Operating System Console, click Activate Service to activate the console service.

Procedure

  1. Go to Operating System Console.

  2. In the left-side navigation pane, click System Diagnosis.

  3. In the upper part of the left-side navigation pane, select the region in which the target instance resides.

  4. In the Diagnosis Type list, select Scheduling Diagnosis. In the Diagnosis Item list, select System Load Diagnosis. Select an Instance ID and click Run Diagnosis.

    Note

    If SysOM is not installed, the system automatically installs SysOM on the target ECS instance and then starts the diagnosis after you click Run Diagnosis.

  5. In the Diagnosis Records section, click View Report.

Diagnostic report

  • Basic Information

    The Basic Information section summarizes the diagnosis with key details, including the instance ID (which serves as the resource ID), diagnosis item, diagnostic report ID, and diagnosis start time.

  • Diagnosis conclusion

    If a load anomaly is found, this section summarizes the results and provides the detailed root cause.

  • Suggestions

    This section provides recommended actions based on the diagnostic findings.

  • Diagnosis details

    If a load anomaly is found, this section provides detailed information about the anomaly.

Example

This example demonstrates how to use the system load diagnosis feature to troubleshoot a load anomaly caused by an improper core binding configuration.

Symptoms

The container monitoring system detects a high system load.

Diagnostic analysis

To diagnose the target ECS instance in this scenario, use the system load diagnosis feature in the Operating System Console. The diagnosis results are as follows.

  • Conclusion and suggestions

    • Diagnosis conclusion: The primary cause of the high system load is pressure on CPU resources.

    • Suggestions: The analysis indicates that an improper core binding configuration is causing an uneven CPU load, leading to task accumulation on a few CPUs.

  • Diagnosis details

    This section provides more information about the system load.

    In this example, Event overview shows that System LoadAvg is 16.00, and Sys Influences, Hardirq Influences, Softirq Influences, and IO Influences are all normal. In Load details, the total number of processes in the R and D states is 17, and all of them are in the Running state (running_tasks=17, uninterrupt_tasks=0). Among the processes that contribute to the load in the R state, stress accounts for 16 and taskstate accounts for 1.

    • Event overview: This section displays the overall system load value and provides an analysis of kernel-side pressure from system calls, hard interrupts, soft interrupts, and I/O.

    • Load details: This section shows the distribution of processes in runnable (R) and uninterruptible sleep (D) states. In this example, it reveals a large number of stress processes in the R state.

Solution

Add idle CPUs to the core binding scope or remove the core binding configuration to distribute the load across more CPUs.

Previous：Scheduling jitter diagnosisNext：Crash diagnosis