Detailed counter stats
Run with three -d for L1/LLC/TLB and stalled-cycle detail; reveals memory-bound vs CPU-bound
perf stat -d -d -d -- ./app
- tool
- perf17 commands
More perf commands
-
perf sched record -- sleep 10 && perf sched latency --sort maxRecord context switches then show per-task wakeup latency; find runqueue starvation
-
perf trace -s -p <pid>strace-like syscall trace with -s summary; lower overhead, no ptrace stop-the-world
-
perf probe --add 'tcp_sendmsg size' && perf record -e probe:tcp_sendmsg -a -- sleep 5Add a kprobe with an argument, then record it; inspect kernel internals without rebuilding
-
perf record -g ./my_appRecord performance data with call-graph info
-
perf reportInteractive display of recorded perf data