6 perf-top - System profiling tool.
11 'perf top' [-e <EVENT> | --event=EVENT] [<options>]
15 This command generates and displays a performance counter profile in real time.
22 System-wide collection. (default)
26 Event period to sample.
30 Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
31 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
32 Default is to monitor all CPUS.
36 Number of seconds to delay between refreshes.
40 Select the PMU event. Selection can be a symbolic event name
41 (use 'perf list' to list all events) or a raw PMU
42 event (eventsel+umask) in the form of rNNN where NNN is a
43 hexadecimal event descriptor.
47 Display this many functions.
50 --count-filter=<count>::
51 Only display functions with more events than this.
54 Put the counters into a counter group.
58 Profile at this frequency.
62 Child tasks do not inherit counters.
66 Path to vmlinux. Required for annotation functionality.
69 --mmap-pages=<pages>::
70 Number of mmap data pages (must be a power of two) or size
71 specification with appended unit character - B/K/M/G. The
72 size is rounded up to have nearest pages power of two value.
76 Profile events on existing Process ID (comma separated list).
80 Profile events on existing thread ID (comma separated list).
84 Record events in threads owned by uid. Name or number.
87 --realtime=<priority>::
88 Collect data with this RT SCHED_FIFO priority.
90 --sym-annotate=<symbol>::
94 --hide_kernel_symbols::
103 Dump the symbol table used for profiling.
107 Be more verbose (show counter open errors, etc).
111 Zero history across display updates.
115 Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
116 local_weight, abort, in_tx, transaction
120 Show a column with the number of samples.
122 --show-total-period::
123 Show a column with the sum of periods.
126 Only consider symbols in these dsos.
129 Only consider symbols in these comms.
132 Only consider these symbols.
135 --disassembler-style=:: Set disassembler style for objdump.
138 Interleave source code with assembly code. Enabled by default,
139 disable with --no-source.
142 Show raw instruction encoding of assembly instructions.
145 Enables call-graph (stack chain/backtrace) recording.
148 Setup and enable call-graph (stack chain/backtrace) recording,
152 Set the stack depth limit when parsing the callchain, anything
153 beyond the specified depth will be ignored. This is a trade-off
154 between information loss and faster processing especially for
155 workloads that can have a very long callchain stack.
159 --ignore-callees=<regex>::
160 Ignore callees of the function(s) matching the given regex.
161 This has the effect of collecting the callers of each such
162 function into one place in the call-graph tree.
165 Do not show entries which have an overhead under that percent.
168 INTERACTIVE PROMPTING KEYS
169 --------------------------
172 Display refresh delay.
175 Number of entries to display.
178 Event to display when multiple counters are active.
181 Profile display filter (>= hit count).
184 Annotation display filter (>= % of total).
190 Stop annotation, return to full profile display.
193 Toggle event count zeroing across display updates.
198 Pressing any unmapped key displays a menu, and prompts for input.
203 linkperf:perf-stat[1], linkperf:perf-list[1]