Delay accounting: an underrated feature of the Linux kernel

Are you certain your application is getting the CPU time it needs? This session explores delay accounting, a built-in Linux kernel feature that most engineers overlook, and what it can reveal about CPU time shortages and application latency that traditional metrics simply cannot.

Understanding whether a process is truly starved of CPU resources is not as straightforward as checking CPU usage or load average. The Linux kernel has built-in mechanisms that precisely measure how long each task waits for kernel resources, and this talk shows you how to use them.

We dive into delay accounting, how it works, and how to leverage these kernel-level metrics for more accurate performance analysis and system optimization. If you work on infrastructure performance and want deeper visibility into what's actually happening at the kernel level, this session offers a practical look at an underused but powerful observability tool.