blob: 3dd1dbe28407e53116f44d769939f5ce94a189e4 [file] [log] [blame]
Namhyung Kim14cbfbe2016-01-07 20:41:53 +09001For a higher level overview, try: perf report --sort comm,dso
2Sample related events with: perf record -e '{cycles,instructions}:S'
3Compare performance results with: perf diff [<old file> <new file>]
4Boolean options have negative forms, e.g.: perf report --no-children
5Customize output of perf script with: perf script -F event,ip,sym
6Generate a script for your data: perf script -g <lang>
7Save output of perf stat using: perf stat record <target workload>
8Create an archive with symtabs to analyse on other machine: perf archive
9Search options using a keyword: perf report -h <keyword>
10Use parent filter to see specific call path: perf report -p <regex>
11List events using substring match: perf list <keyword>
12To see list of saved events and attributes: perf evlist -v
13Use --symfs <dir> if your symbol files are in non-standard locations
14To see callchains in a more compact form: perf report -g folded
Namhyung Kim09f19852016-01-11 19:35:10 +090015Show individual samples with: perf script
16Limit to show entries above 5% only: perf report --percent-limit 5
17Profiling branch (mis)predictions with: perf record -b / perf report
18Treat branches as callchains: perf report --branch-history
19To count events in every 1000 msec: perf stat -I 1000
20Print event counts in CSV format with: perf stat -x,
21If you have debuginfo enabled, try: perf report -s sym,srcline
22For memory address profiling, try: perf mem record / perf mem report
23For tracepoint events, try: perf report -s trace_fields
24To record callchains for each sample: perf record -g
Masahiro Yamada9332ef92017-02-27 14:28:47 -080025To record every process run by a user: perf record -u <user>
Kim Phillips12919272017-05-03 13:13:50 +010026Skip collecting build-id when recording: perf record -B
Namhyung Kim09f19852016-01-11 19:35:10 +090027To change sampling frequency to 100 Hz: perf record -F 100
28See assembly instructions with percentage: perf annotate <symbol>
29If you prefer Intel style assembly, try: perf annotate -M intel
Namhyung Kim42514462016-02-25 00:13:48 +090030For hierarchical output, try: perf report --hierarchy
Kim SeonYoung8649b642016-09-29 17:16:42 -070031Order by the overhead of source file name and line number: perf report -s srcline
Donghyun Kim49343232016-09-30 07:15:57 +090032System-wide collection from all CPUs: perf record -a
Nambong Ha2ad83272016-09-30 08:26:02 +090033Show current config key-value pairs: perf config --list
34Show user configuration overrides: perf config --user --list
Hansuk Hong2e38e662017-11-24 01:05:46 +090035To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`