9a29547e5b
In lowlatency mode (option --lowlatency) tasks are ordered using a deadline that is evaluated as the vruntime minus a certain "bonus", determined in function of the max time slice and the average amount of voluntary context switches, to amplify the priority boost of the tasks that are voluntarily releasing the CPU (which are typically interactive). However, this method can be extremely unfair in some cases: tasks with short bursts of voluntary context switches may receive a huge priority boost, making the rest of the system almost unresponsive (see massive hackbench stress tests for example). To prevent this rework the task's deadline logic to use the vruntime and a "deadline component" that is a function of the average used time slice, scaled using a dynamic task priority (evaluated as the static task priority and the its average amount of voluntary context switches). This logic seems to prevent excessive prioritization of tasks performing short intensive bursts of voluntary context switches. It also makes lowlatency mode in scx_bpfland (somehow) more similar to the deadline logic used by scx_rusty. Signed-off-by: Andrea Righi <andrea.righi@linux.dev> |
||
|---|---|---|
| .. | ||
| src | ||
| build.rs | ||
| Cargo.toml | ||
| LICENSE | ||
| README.md | ||
| rustfmt.toml | ||
scx_bpfland
This is a single user-defined scheduler used within sched_ext, which is a Linux kernel feature which enables implementing kernel thread schedulers in BPF and dynamically loading them. Read more about sched_ext.
Overview
scx_bpfland: a vruntime-based sched_ext scheduler that prioritizes interactive workloads.
This scheduler is derived from scx_rustland, but it is fully implemented in BPF. It has a minimal user-space Rust part to process command line options, collect metrics and log out scheduling statistics. The BPF part makes all the scheduling decisions.
Tasks are categorized as either interactive or regular based on their average rate of voluntary context switches per second. Tasks that exceed a specific voluntary context switch threshold are classified as interactive. Interactive tasks are prioritized in a higher-priority queue, while regular tasks are placed in a lower-priority queue. Within each queue, tasks are sorted based on their weighted runtime: tasks that have higher weight (priority) or use the CPU for less time (smaller runtime) are scheduled sooner, due to their a higher position in the queue.
Moreover, each task gets a time slice budget. When a task is dispatched, it receives a time slice equivalent to the remaining unused portion of its previously allocated time slice (with a minimum threshold applied). This gives latency-sensitive workloads more chances to exceed their time slice when needed to perform short bursts of CPU activity without being interrupted (i.e., real-time audio encoding / decoding workloads).
Typical Use Case
Interactive workloads, such as gaming, live streaming, multimedia, real-time audio encoding/decoding, especially when these workloads are running alongside CPU-intensive background tasks.
In this scenario scx_bpfland ensures that interactive workloads maintain a high level of responsiveness.
Production Ready?
The scheduler is based on scx_rustland, implementing nearly the same scheduling algorithm with minor changes and optimizations to be fully implemented in BPF.
Given that the scx_rustland scheduling algorithm has been extensively tested, this scheduler can be considered ready for production use.