Profiling
代码语言：javascript复制# Sample on-CPU functions for the specified command, at 99 Hertz:
perf record -F 99 command
# Sample on-CPU functions for the specified PID, at 99 Hertz, until Ctrl-C:
perf record -F 99 -p PID
# Sample on-CPU functions for the specified PID, at 99 Hertz, for 10 seconds:
perf record -F 99 -p PID sleep 10
# Sample CPU stack traces (via frame pointers) for the specified PID, at 99 Hertz, for 10 seconds:
perf record -F 99 -p PID -g -- sleep 10
# Sample CPU stack traces for the PID, using dwarf (dbg info) to unwind stacks, at 99 Hertz, for 10 seconds:
perf record -F 99 -p PID --call-graph dwarf sleep 10
# Sample CPU stack traces for the entire system, at 99 Hertz, for 10 seconds (< Linux 4.11):
perf record -F 99 -ag -- sleep 10
# Sample CPU stack traces for the entire system, at 99 Hertz, for 10 seconds (>= Linux 4.11):
perf record -F 99 -g -- sleep 10
# If the previous command didn't work, try forcing perf to use the cpu-clock event:
perf record -F 99 -e cpu-clock -ag -- sleep 10
# Sample CPU stack traces for a container identified by its /sys/fs/cgroup/perf_event cgroup:
perf record -F 99 -e cpu-clock --cgroup=docker/1d567f4393190204...etc... -a -- sleep 10
# Sample CPU stack traces for the entire system, with dwarf stacks, at 99 Hertz, for 10 seconds:
perf record -F 99 -a --call-graph dwarf sleep 10
# Sample CPU stack traces for the entire system, using last branch record for stacks, ... (>= Linux 4.?):
perf record -F 99 -a --call-graph lbr sleep 10
# Sample CPU stack traces, once every 10,000 Level 1 data cache misses, for 5 seconds:
perf record -e L1-dcache-load-misses -c 10000 -ag -- sleep 5
# Sample CPU stack traces, once every 100 last level cache misses, for 5 seconds:
perf record -e LLC-load-misses -c 100 -ag -- sleep 5
# Sample on-CPU kernel instructions, for 5 seconds:
perf record -e cycles:k -a -- sleep 5
# Sample on-CPU user instructions, for 5 seconds:
perf record -e cycles:u -a -- sleep 5
# Sample on-CPU user instructions precisely (using PEBS), for 5 seconds:
perf record -e cycles:up -a -- sleep 5
# Perform branch tracing (needs HW support), for 1 second:
perf record -b -a sleep 1
# Sample CPUs at 49 Hertz, and show top addresses and symbols, live (no perf.data file):
perf top -F 49
# Sample CPUs at 49 Hertz, and show top process names and segments, live:
perf top -F 49 -ns comm,dsoStatic Tracing
代码语言：javascript复制# Trace new processes, until Ctrl-C:
perf record -e sched:sched_process_exec -a
# Sample (take a subset of) context-switches, until Ctrl-C:
perf record -e context-switches -a
# Trace all context-switches, until Ctrl-C:
perf record -e context-switches -c 1 -a
# Include raw settings used (see: man perf_event_open):
perf record -vv -e context-switches -a
# Trace all context-switches via sched tracepoint, until Ctrl-C:
perf record -e sched:sched_switch -a
# Sample context-switches with stack traces, until Ctrl-C:
perf record -e context-switches -ag
# Sample context-switches with stack traces, for 10 seconds:
perf record -e context-switches -ag -- sleep 10
# Sample CS, stack traces, and with timestamps (< Linux 3.17, -T now default):
perf record -e context-switches -ag -T
# Sample CPU migrations, for 10 seconds:
perf record -e migrations -a -- sleep 10
# Trace all connect()s with stack traces (outbound connections), until Ctrl-C:
perf record -e syscalls:sys_enter_connect -ag
# Trace all accepts()s with stack traces (inbound connections), until Ctrl-C:
perf record -e syscalls:sys_enter_accept* -ag
# Trace all block device (disk I/O) requests with stack traces, until Ctrl-C:
perf record -e block:block_rq_insert -ag
# Sample at most 100 block device requests per second, until Ctrl-C:
perf record -F 100 -e block:block_rq_insert -a
# Trace all block device issues and completions (has timestamps), until Ctrl-C:
perf record -e block:block_rq_issue -e block:block_rq_complete -a
# Trace all block completions, of size at least 100 Kbytes, until Ctrl-C:
perf record -e block:block_rq_complete --filter 'nr_sector > 200'
# Trace all block completions, synchronous writes only, until Ctrl-C:
perf record -e block:block_rq_complete --filter 'rwbs == "WS"'
# Trace all block completions, all types of writes, until Ctrl-C:
perf record -e block:block_rq_complete --filter 'rwbs ~ "*W*"'
# Sample minor faults (RSS growth) with stack traces, until Ctrl-C:
perf record -e minor-faults -ag
# Trace all minor faults with stack traces, until Ctrl-C:
perf record -e minor-faults -c 1 -ag
# Sample page faults with stack traces, until Ctrl-C:
perf record -e page-faults -ag
# Trace all ext4 calls, and write to a non-ext4 location, until Ctrl-C:
perf record -e 'ext4:*' -o /tmp/perf.data -a
# Trace kswapd wakeup events, until Ctrl-C:
perf record -e vmscan:mm_vmscan_wakeup_kswapd -ag
# Add Node.js USDT probes (Linux 4.10 ):
perf buildid-cache --add `which node`
# Trace the node http__server__request USDT event (Linux 4.10 ):
perf record -e sdt_node:http__server__request -a
