1perf-top(1) 2=========== 3 4NAME 5---- 6perf-top - System profiling tool. 7 8SYNOPSIS 9-------- 10[verse] 11'perf top' [-e <EVENT> | --event=EVENT] [<options>] 12 13DESCRIPTION 14----------- 15This command generates and displays a performance counter profile in real time. 16 17 18OPTIONS 19------- 20-a:: 21--all-cpus:: 22 System-wide collection. (default) 23 24-c <count>:: 25--count=<count>:: 26 Event period to sample. 27 28-C <cpu-list>:: 29--cpu=<cpu>:: 30Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a 31comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. 32Default is to monitor all CPUS. 33 34-d <seconds>:: 35--delay=<seconds>:: 36 Number of seconds to delay between refreshes. 37 38-e <event>:: 39--event=<event>:: 40 Select the PMU event. Selection can be a symbolic event name 41 (use 'perf list' to list all events) or a raw PMU event in the form 42 of rN where N is a hexadecimal value that represents the raw register 43 encoding with the layout of the event control registers as described 44 by entries in /sys/bus/event_source/devices/cpu/format/*. 45 46-E <entries>:: 47--entries=<entries>:: 48 Display this many functions. 49 50-f <count>:: 51--count-filter=<count>:: 52 Only display functions with more events than this. 53 54--group-sort-idx:: 55 Sort the output by the event at the index n in group. If n is invalid, 56 sort by the first event. It can support multiple groups with different 57 amount of events. WARNING: This should be used on grouped events. 58 59-F <freq>:: 60--freq=<freq>:: 61 Profile at this frequency. Use 'max' to use the currently maximum 62 allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate 63 sysctl. 64 65-i:: 66--inherit:: 67 Child tasks do not inherit counters. 68 69-k <path>:: 70--vmlinux=<path>:: 71 Path to vmlinux. Required for annotation functionality. 72 73--ignore-vmlinux:: 74 Ignore vmlinux files. 75 76--kallsyms=<file>:: 77 kallsyms pathname 78 79-m <pages>:: 80--mmap-pages=<pages>:: 81 Number of mmap data pages (must be a power of two) or size 82 specification with appended unit character - B/K/M/G. The 83 size is rounded up to have nearest pages power of two value. 84 85-p <pid>:: 86--pid=<pid>:: 87 Profile events on existing Process ID (comma separated list). 88 89-t <tid>:: 90--tid=<tid>:: 91 Profile events on existing thread ID (comma separated list). 92 93-u:: 94--uid=:: 95 Record events in threads owned by uid. Name or number. 96 97-r <priority>:: 98--realtime=<priority>:: 99 Collect data with this RT SCHED_FIFO priority. 100 101--sym-annotate=<symbol>:: 102 Annotate this symbol. 103 104-K:: 105--hide_kernel_symbols:: 106 Hide kernel symbols. 107 108-U:: 109--hide_user_symbols:: 110 Hide user symbols. 111 112--demangle-kernel:: 113 Demangle kernel symbols. 114 115-D:: 116--dump-symtab:: 117 Dump the symbol table used for profiling. 118 119-v:: 120--verbose:: 121 Be more verbose (show counter open errors, etc). 122 123-z:: 124--zero:: 125 Zero history across display updates. 126 127-s:: 128--sort:: 129 Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, 130 local_weight, abort, in_tx, transaction, overhead, sample, period. 131 Please see description of --sort in the perf-report man page. 132 133--fields=:: 134 Specify output field - multiple keys can be specified in CSV format. 135 Following fields are available: 136 overhead, overhead_sys, overhead_us, overhead_children, sample and period. 137 Also it can contain any sort key(s). 138 139 By default, every sort keys not specified in --field will be appended 140 automatically. 141 142-n:: 143--show-nr-samples:: 144 Show a column with the number of samples. 145 146--show-total-period:: 147 Show a column with the sum of periods. 148 149--dsos:: 150 Only consider symbols in these dsos. This option will affect the 151 percentage of the overhead column. See --percentage for more info. 152 153--comms:: 154 Only consider symbols in these comms. This option will affect the 155 percentage of the overhead column. See --percentage for more info. 156 157--symbols:: 158 Only consider these symbols. This option will affect the 159 percentage of the overhead column. See --percentage for more info. 160 161-M:: 162--disassembler-style=:: Set disassembler style for objdump. 163 164--addr2line=<path>:: 165 Path to addr2line binary. 166 167--objdump=<path>:: 168 Path to objdump binary. 169 170--prefix=PREFIX:: 171--prefix-strip=N:: 172 Remove first N entries from source file path names in executables 173 and add PREFIX. This allows to display source code compiled on systems 174 with different file system layout. 175 176--source:: 177 Interleave source code with assembly code. Enabled by default, 178 disable with --no-source. 179 180--asm-raw:: 181 Show raw instruction encoding of assembly instructions. 182 183-g:: 184 Enables call-graph (stack chain/backtrace) recording. 185 186--call-graph [mode,type,min[,limit],order[,key][,branch]]:: 187 Setup and enable call-graph (stack chain/backtrace) recording, 188 implies -g. See `--call-graph` section in perf-record and 189 perf-report man pages for details. 190 191--children:: 192 Accumulate callchain of children to parent entry so that then can 193 show up in the output. The output will have a new "Children" column 194 and will be sorted on the data. It requires -g/--call-graph option 195 enabled. See the `overhead calculation' section for more details. 196 Enabled by default, disable with --no-children. 197 198--max-stack:: 199 Set the stack depth limit when parsing the callchain, anything 200 beyond the specified depth will be ignored. This is a trade-off 201 between information loss and faster processing especially for 202 workloads that can have a very long callchain stack. 203 204 Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. 205 206--ignore-callees=<regex>:: 207 Ignore callees of the function(s) matching the given regex. 208 This has the effect of collecting the callers of each such 209 function into one place in the call-graph tree. 210 211--percent-limit:: 212 Do not show entries which have an overhead under that percent. 213 (Default: 0). 214 215--percentage:: 216 Determine how to display the overhead percentage of filtered entries. 217 Filters can be applied by --comms, --dsos and/or --symbols options and 218 Zoom operations on the TUI (thread, dso, etc). 219 220 "relative" means it's relative to filtered entries only so that the 221 sum of shown entries will be always 100%. "absolute" means it retains 222 the original value before and after the filter is applied. 223 224-w:: 225--column-widths=<width[,width...]>:: 226 Force each column width to the provided list, for large terminal 227 readability. 0 means no limit (default behavior). 228 229--proc-map-timeout:: 230 When processing pre-existing threads /proc/XXX/mmap, it may take 231 a long time, because the file may be huge. A time out is needed 232 in such cases. 233 This option sets the time out limit. The default value is 500 ms. 234 235 236-b:: 237--branch-any:: 238 Enable taken branch stack sampling. Any type of taken branch may be sampled. 239 This is a shortcut for --branch-filter any. See --branch-filter for more infos. 240 241-j:: 242--branch-filter:: 243 Enable taken branch stack sampling. Each sample captures a series of consecutive 244 taken branches. The number of branches captured with each sample depends on the 245 underlying hardware, the type of branches of interest, and the executed code. 246 It is possible to select the types of branches captured by enabling filters. 247 For a full list of modifiers please see the perf record manpage. 248 249 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. 250 The privilege levels may be omitted, in which case, the privilege levels of the associated 251 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege 252 levels are subject to permissions. When sampling on multiple events, branch stack sampling 253 is enabled for all the sampling events. The sampled branch type is the same for all events. 254 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k 255 Note that this feature may not be available on all processors. 256 257--raw-trace:: 258 When displaying traceevent output, do not use print fmt or plugins. 259 260--hierarchy:: 261 Enable hierarchy output. 262 263--overwrite:: 264 Enable this to use just the most recent records, which helps in high core count 265 machines such as Knights Landing/Mill, but right now is disabled by default as 266 the pausing used in this technique is leading to loss of metadata events such 267 as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading 268 to lots of unknown samples appearing on the UI. Enable this if you are in such 269 machines and profiling a workload that doesn't creates short lived threads and/or 270 doesn't uses many executable mmap operations. Work is being planed to solve 271 this situation, till then, this will remain disabled by default. 272 273--force:: 274 Don't do ownership validation. 275 276--num-thread-synthesize:: 277 The number of threads to run when synthesizing events for existing processes. 278 By default, the number of threads equals to the number of online CPUs. 279 280--namespaces:: 281 Record events of type PERF_RECORD_NAMESPACES and display it with the 282 'cgroup_id' sort key. 283 284-G name:: 285--cgroup name:: 286monitor only in the container (cgroup) called "name". This option is available only 287in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to 288container "name" are monitored when they run on the monitored CPUs. Multiple cgroups 289can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup 290to first event, second cgroup to second event and so on. It is possible to provide 291an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have 292corresponding events, i.e., they always refer to events defined earlier on the command 293line. If the user wants to track multiple events for a specific cgroup, the user can 294use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'. 295 296--all-cgroups:: 297 Record events of type PERF_RECORD_CGROUP and display it with the 298 'cgroup' sort key. 299 300--switch-on EVENT_NAME:: 301 Only consider events after this event is found. 302 303 E.g.: 304 305 Find out where broadcast packets are handled 306 307 perf probe -L icmp_rcv 308 309 Insert a probe there: 310 311 perf probe icmp_rcv:59 312 313 Start perf top and ask it to only consider the cycles events when a 314 broadcast packet arrives This will show a menu with two entries and 315 will start counting when a broadcast packet arrives: 316 317 perf top -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv 318 319 Alternatively one can ask for a group and then two overhead columns 320 will appear, the first for cycles and the second for the switch-on event. 321 322 perf top -e '{cycles,probe:icmp_rcv}' --switch-on=probe:icmp_rcv 323 324 This may be interesting to measure a workload only after some initialization 325 phase is over, i.e. insert a perf probe at that point and use the above 326 examples replacing probe:icmp_rcv with the just-after-init probe. 327 328--switch-off EVENT_NAME:: 329 Stop considering events after this event is found. 330 331--show-on-off-events:: 332 Show the --switch-on/off events too. This has no effect in 'perf top' now 333 but probably we'll make the default not to show the switch-on/off events 334 on the --group mode and if there is only one event besides the off/on ones, 335 go straight to the histogram browser, just like 'perf top' with no events 336 explicitly specified does. 337 338--stitch-lbr:: 339 Show callgraph with stitched LBRs, which may have more complete 340 callgraph. The option must be used with --call-graph lbr recording. 341 Disabled by default. In common cases with call stack overflows, 342 it can recreate better call stacks than the default lbr call stack 343 output. But this approach is not foolproof. There can be cases 344 where it creates incorrect call stacks from incorrect matches. 345 The known limitations include exception handing such as 346 setjmp/longjmp will have calls/returns not match. 347 348ifdef::HAVE_LIBPFM[] 349--pfm-events events:: 350Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) 351including support for event filters. For example '--pfm-events 352inst_retired:any_p:u:c=1:i'. More than one event can be passed to the 353option using the comma separator. Hardware events and generic hardware 354events cannot be mixed together. The latter must be used with the -e 355option. The -e option and this one can be mixed and matched. Events 356can be grouped using the {} notation. 357endif::HAVE_LIBPFM[] 358 359INTERACTIVE PROMPTING KEYS 360-------------------------- 361 362[d]:: 363 Display refresh delay. 364 365[e]:: 366 Number of entries to display. 367 368[E]:: 369 Event to display when multiple counters are active. 370 371[f]:: 372 Profile display filter (>= hit count). 373 374[F]:: 375 Annotation display filter (>= % of total). 376 377[s]:: 378 Annotate symbol. 379 380[S]:: 381 Stop annotation, return to full profile display. 382 383[K]:: 384 Hide kernel symbols. 385 386[U]:: 387 Hide user symbols. 388 389[z]:: 390 Toggle event count zeroing across display updates. 391 392[qQ]:: 393 Quit. 394 395Pressing any unmapped key displays a menu, and prompts for input. 396 397include::callchain-overhead-calculation.txt[] 398 399SEE ALSO 400-------- 401linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-report[1] 402