Scheduler latency analysis perf

Record context switches then show per-task wakeup latency; find runqueue starvation

perf sched record -- sleep 10 && perf sched latency --sort max

#perf #performance #kernel #troubleshooting

more perf all 17 commands →

Syscall trace via perf perf trace -s -p <pid> Dynamic probe on function perf probe --add 'tcp_sendmsg size' && perf record -e probe:tcp_sendmsg -a -- sleep 5 Record CPU cycles perf record -g ./my_app Show perf report perf report List available events perf list