Get the latest tech news
Red Hat Proposes Queue PerCPU Work "QPW" For Better Handling Per-CPU Work On RT Linux
Red Hat engineer Leonardo Bras has laid out a proposal for QPWs, or 'Queue PerCPU Work', as a better means of handling per-CPU operations within the Linux kernel especially for real-time (RT) workloads.
Red Hat engineer Leonardo Bras has laid out a proposal for QPWs, or "Queue PerCPU Work", as a better means of handling per-CPU operations within the Linux kernel especially for real-time (RT) workloads. The problem: Some places in the kernel implement a parallel programming strategy consisting on local_locks() for most of the work, and some rare remote operations are scheduled on target cpu. This keeps cache bouncing low since cacheline tends to be mostly local, and avoids the cost of locks in non-RT kernels, even though the very few remote operations will be expensive due to scheduling overhead.
Or read this on Phoronix
