O que é e como funciona o linux scheduler e sua latência

Embora a história e os testes contidos em http://www.linuxdevices.com/articles/AT8906594941.html tenham valor apenas histórico, há uma excelente explicação do mecanismo de agendamento do kernel (linux scheduler). Vale a pena conferir. Abaixo, uma "palhinha":

Conforme Clark Williams,

"Linux scheduler latency problem ... is the delay between the occurrence of an interrupt and the running of the process that services the interrupt."

"What the heck does scheduler latency mean anyway? Latency is really a shorthand term for the phrase latent period, which is defined by webster.com to be "the interval between stimulus and response". In the context of the Linux kernel, scheduler latency is the time between a wakeup (the stimulus) signaling that an event has occurred and the kernel scheduler getting an opportunity to schedule the thread that is waiting for the wakeup to occur (the response). Wakeups can be caused by hardware interrupts, or by other threads."

Se preferir, baixe o pdf aqui.