Pressure Stall Information on Netdata

Linux Cgroups V2 Memory Throttling & OOM Fix

Fri, 05 Sep 2025 00:00:00 +0000

Your critical service is lagging. Users are complaining about timeouts. You check your orchestration platform and see the dreaded OOMKilled status on a container. You dive into the node’s logs (dmesg) and confirm it: the kernel’s Out-of-Memory (OOM) killer has claimed another victim. The immediate fix is easy—restart the container, maybe give it more memory—but the real question remains unanswered: why did it happen? Was it a sudden memory leak, a traffic spike, or something more subtle?

Linux Load Average Myths and Realities

Sun, 03 Nov 2024 00:00:00 +0000

When it comes to monitoring system performance on Linux, the load average is one of the most referenced metrics. Displayed prominently in tools like top, uptime, and htop, it’s often used as a quick gauge of system load and capacity. But how reliable is it? For complex, multi-threaded applications, load average can paint a misleading picture of actual system performance.

In this article, we’ll dive into the myths and realities of Linux load average, using insights from Netdata’s high-frequency, high-concurrency monitoring setup. Through this journey, we’ll uncover why load average spikes can occur even under steady workloads, and why a single metric is rarely enough to capture the true state of a system. Whether you’re a system administrator, developer, or performance enthusiast, this exploration of load average will help you interpret it more accurately and understand when it may—or may not—reflect reality.

Linux CPU Consumption, Load & Pressure Explained

Tue, 02 May 2023 00:00:00 +0000

As a system administrator, understanding how your Linux system’s CPU is being utilized is crucial for identifying bottlenecks and optimizing performance. In this blog post, we’ll dive deep into the world of Linux CPU consumption, load, and pressure, and discuss how to use these metrics effectively to identify issues and improve your system’s performance.

CPU Consumption and Utilization

CPU consumption refers to the amount of processing power being used by applications running on your system. The system.cpu chart in Netdata represents the Total CPU utilization of your Linux system, broken down into different dimensions. Each dimension provides insight into how the CPU is being used by various tasks and processes. Here’s a brief explanation of each dimension:

Kubernetes node CPU saturation: load, throttling, and runqueue depth

Mon, 01 Jan 0001 00:00:00 +0000

Application latency climbs and pods slow down. kubectl top nodes reports 70 percent CPU, so you assume headroom exists. It does not. CPU percent is a time-average that masks micro-bursts, runqueue backlog, and CFS throttling. A container can throttle to a crawl while node utilization looks comfortable, and a node can show 50 percent utilization with every runnable thread queued behind a noisy neighbor. Distinguish node-level CPU contention from limit-induced throttling using runqueue depth, CFS bandwidth metrics, and Pressure Stall Information (PSI).