1perf-sched(1) 2============== 3 4NAME 5---- 6perf-sched - Tool to trace/measure scheduler properties (latencies) 7 8SYNOPSIS 9-------- 10[verse] 11'perf sched' {record|latency|map|replay|script|timehist} 12 13DESCRIPTION 14----------- 15There are several variants of 'perf sched': 16 17 'perf sched record <command>' to record the scheduling events 18 of an arbitrary workload. 19 20 'perf sched latency' to report the per task scheduling latencies 21 and other scheduling properties of the workload. 22 23 'perf sched script' to see a detailed trace of the workload that 24 was recorded (aliased to 'perf script' for now). 25 26 'perf sched replay' to simulate the workload that was recorded 27 via perf sched record. (this is done by starting up mockup threads 28 that mimic the workload based on the events in the trace. These 29 threads can then replay the timings (CPU runtime and sleep patterns) 30 of the workload as it occurred when it was recorded - and can repeat 31 it a number of times, measuring its performance.) 32 33 'perf sched map' to print a textual context-switching outline of 34 workload captured via perf sched record. Columns stand for 35 individual CPUs, and the two-letter shortcuts stand for tasks that 36 are running on a CPU. A '*' denotes the CPU that had the event, and 37 a dot signals an idle CPU. 38 39 'perf sched timehist' provides an analysis of scheduling events. 40 41 Example usage: 42 perf sched record -- sleep 1 43 perf sched timehist 44 45 By default it shows the individual schedule events, including the wait 46 time (time between sched-out and next sched-in events for the task), the 47 task scheduling delay (time between wakeup and actually running) and run 48 time for the task: 49 50 time cpu task name wait time sch delay run time 51 [tid/pid] (msec) (msec) (msec) 52 -------------- ------ -------------------- --------- --------- --------- 53 79371.874569 [0011] gcc[31949] 0.014 0.000 1.148 54 79371.874591 [0010] gcc[31951] 0.000 0.000 0.024 55 79371.874603 [0010] migration/10[59] 3.350 0.004 0.011 56 79371.874604 [0011] <idle> 1.148 0.000 0.035 57 79371.874723 [0005] <idle> 0.016 0.000 1.383 58 79371.874746 [0005] gcc[31949] 0.153 0.078 0.022 59 ... 60 61 Times are in msec.usec. 62 63OPTIONS 64------- 65-i:: 66--input=<file>:: 67 Input file name. (default: perf.data unless stdin is a fifo) 68 69-v:: 70--verbose:: 71 Be more verbose. (show symbol address, etc) 72 73-D:: 74--dump-raw-trace=:: 75 Display verbose dump of the sched data. 76 77OPTIONS for 'perf sched map' 78---------------------------- 79 80--compact:: 81 Show only CPUs with activity. Helps visualizing on high core 82 count systems. 83 84--cpus:: 85 Show just entries with activities for the given CPUs. 86 87--color-cpus:: 88 Highlight the given cpus. 89 90--color-pids:: 91 Highlight the given pids. 92 93OPTIONS for 'perf sched timehist' 94--------------------------------- 95-k:: 96--vmlinux=<file>:: 97 vmlinux pathname 98 99--kallsyms=<file>:: 100 kallsyms pathname 101 102-g:: 103--no-call-graph:: 104 Do not display call chains if present. 105 106--max-stack:: 107 Maximum number of functions to display in backtrace, default 5. 108 109-s:: 110--summary:: 111 Show only a summary of scheduling by thread with min, max, and average 112 run times (in sec) and relative stddev. 113 114-S:: 115--with-summary:: 116 Show all scheduling events followed by a summary by thread with min, 117 max, and average run times (in sec) and relative stddev. 118 119--symfs=<directory>:: 120 Look for files with symbols relative to this directory. 121 122-V:: 123--cpu-visual:: 124 Show visual aid for sched switches by CPU: 'i' marks idle time, 125 's' are scheduler events. 126 127-w:: 128--wakeups:: 129 Show wakeup events. 130 131-M:: 132--migrations:: 133 Show migration events. 134 135-n:: 136--next:: 137 Show next task. 138 139-I:: 140--idle-hist:: 141 Show idle-related events only. 142 143--time:: 144 Only analyze samples within given time window: <start>,<stop>. Times 145 have the format seconds.microseconds. If start is not given (i.e., time 146 string is ',x.y') then analysis starts at the beginning of the file. If 147 stop time is not given (i.e, time string is 'x.y,') then analysis goes 148 to end of file. 149 150--state:: 151 Show task state when it switched out. 152 153SEE ALSO 154-------- 155linkperf:perf-record[1] 156