What processor metrics should be monitored during load diagnosis?

When diagnosing CPU load, it is important to look at the following indicators:

• CPU Utilization — the percentage of time the CPU is busy executing tasks. High utilization (close to 100%) may indicate overload.
• Load Average — the average number of processes waiting to run over the last 1, 5, and 15 minutes. If the load average significantly exceeds the number of cores, it is a sign of overload.
• CPU Steal Time — the time when a virtual machine is waiting for the CPU from the hypervisor, important in virtualized environments.
• User vs System CPU Time — how much time the CPU spends on user processes and system (kernel) processes. This helps understand where the load is coming from.
• Interrupts and Context Switches — a high number of interrupts and context switches can reduce performance.

These indicators can be obtained using utilities like top, htop, vmstat, mpstat, and sar.