tools/perf/Documentation/perf-report.txt

   1 perf-report(1)
   2 ==============
   3
   4 NAME
   5 ----
   6 perf-report - Read perf.data (created by perf record) and display the profile
   7
   8 SYNOPSIS
   9 --------
  10 [verse]
  11 'perf report' [-i <file> | --input=file]
  12
  13 DESCRIPTION
  14 -----------
  15 This command displays the performance counter profile information recorded
  16 via perf record.
  17
  18 OPTIONS
  19 -------
  20 -i::
  21 --input=::
  22         Input file name. (default: perf.data unless stdin is a fifo)
  23
  24 -v::
  25 --verbose::
  26         Be more verbose. (show symbol address, etc)
  27
  28 -n::
  29 --show-nr-samples::
  30         Show the number of samples for each symbol
  31
  32 --show-cpu-utilization::
  33         Show sample percentage for different cpu modes.
  34
  35 -T::
  36 --threads::
  37         Show per-thread event counters.  The input data file should be recorded
  38         with -s option.
  39 -c::
  40 --comms=::
  41         Only consider symbols in these comms. CSV that understands
  42         file://filename entries.  This option will affect the percentage of
  43         the overhead column.  See --percentage for more info.
  44 --pid=::
  45         Only show events for given process ID (comma separated list).
  46
  47 --tid=::
  48         Only show events for given thread ID (comma separated list).
  49 -d::
  50 --dsos=::
  51         Only consider symbols in these dsos. CSV that understands
  52         file://filename entries.  This option will affect the percentage of
  53         the overhead column.  See --percentage for more info.
  54 -S::
  55 --symbols=::
  56         Only consider these symbols. CSV that understands
  57         file://filename entries.  This option will affect the percentage of
  58         the overhead column.  See --percentage for more info.
  59
  60 --symbol-filter=::
  61         Only show symbols that match (partially) with this filter.
  62
  63 -U::
  64 --hide-unresolved::
  65         Only display entries resolved to a symbol.
  66
  67 -s::
  68 --sort=::
  69         Sort histogram entries by given key(s) - multiple keys can be specified
  70         in CSV format.  Following sort keys are available:
  71         pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
  72
  73         Each key has following meaning:
  74
  75         - comm: command (name) of the task which can be read via /proc/<pid>/comm
  76         - pid: command and tid of the task
  77         - dso: name of library or module executed at the time of sample
  78         - symbol: name of function executed at the time of sample
  79         - parent: name of function matched to the parent regex filter. Unmatched
  80         entries are displayed as "[other]".
  81         - cpu: cpu number the task ran at the time of sample
  82         - socket: processor socket number the task ran at the time of sample
  83         - srcline: filename and line number executed at the time of sample.  The
  84         DWARF debugging info must be provided.
  85         - srcfile: file name of the source file of the same. Requires dwarf
  86         information.
  87         - weight: Event specific weight, e.g. memory latency or transaction
  88         abort cost. This is the global weight.
  89         - local_weight: Local weight version of the weight above.
  90         - transaction: Transaction abort flags.
  91         - overhead: Overhead percentage of sample
  92         - overhead_sys: Overhead percentage of sample running in system mode
  93         - overhead_us: Overhead percentage of sample running in user mode
  94         - overhead_guest_sys: Overhead percentage of sample running in system mode
  95         on guest machine
  96         - overhead_guest_us: Overhead percentage of sample running in user mode on
  97         guest machine
  98         - sample: Number of sample
  99         - period: Raw number of event count of sample
 100
 101         By default, comm, dso and symbol keys are used.
 102         (i.e. --sort comm,dso,symbol)
 103
 104         If --branch-stack option is used, following sort keys are also
 105         available:
 106         dso_from, dso_to, symbol_from, symbol_to, mispredict.
 107
 108         - dso_from: name of library or module branched from
 109         - dso_to: name of library or module branched to
 110         - symbol_from: name of function branched from
 111         - symbol_to: name of function branched to
 112         - mispredict: "N" for predicted branch, "Y" for mispredicted branch
 113         - in_tx: branch in TSX transaction
 114         - abort: TSX transaction abort.
 115         - cycles: Cycles in basic block
 116
 117         And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 118         and symbol_to, see '--branch-stack'.
 119
 120 -F::
 121 --fields=::
 122         Specify output field - multiple keys can be specified in CSV format.
 123         Following fields are available:
 124         overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 125         Also it can contain any sort key(s).
 126
 127         By default, every sort keys not specified in -F will be appended
 128         automatically.
 129
 130         If --mem-mode option is used, following sort keys are also available
 131         (incompatible with --branch-stack):
 132         symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
 133
 134         - symbol_daddr: name of data symbol being executed on at the time of sample
 135         - dso_daddr: name of library or module containing the data being executed
 136         on at the time of sample
 137         - locked: whether the bus was locked at the time of sample
 138         - tlb: type of tlb access for the data at the time of sample
 139         - mem: type of memory access for the data at the time of sample
 140         - snoop: type of snoop (if any) for the data at the time of sample
 141         - dcacheline: the cacheline the data address is on at the time of sample
 142
 143         And default sort keys are changed to local_weight, mem, sym, dso,
 144         symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
 145
 146 -p::
 147 --parent=<regex>::
 148         A regex filter to identify parent. The parent is a caller of this
 149         function and searched through the callchain, thus it requires callchain
 150         information recorded. The pattern is in the exteneded regex format and
 151         defaults to "\^sys_|^do_page_fault", see '--sort parent'.
 152
 153 -x::
 154 --exclude-other::
 155         Only display entries with parent-match.
 156
 157 -w::
 158 --column-widths=<width[,width...]>::
 159         Force each column width to the provided list, for large terminal
 160         readability.  0 means no limit (default behavior).
 161
 162 -t::
 163 --field-separator=::
 164         Use a special separator character and don't pad with spaces, replacing
 165         all occurrences of this separator in symbol names (and other output)
 166         with a '.' character, that thus it's the only non valid separator.
 167
 168 -D::
 169 --dump-raw-trace::
 170         Dump raw trace in ASCII.
 171
 172 -g::
 173 --call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::
 174         Display call chains using type, min percent threshold, print limit,
 175         call order, sort key and branch.  Note that ordering of parameters is not
 176         fixed so any parement can be given in an arbitraty order.  One exception
 177         is the print_limit which should be preceded by threshold.
 178
 179         print_type can be either:
 180         - flat: single column, linear exposure of call chains.
 181         - graph: use a graph tree, displaying absolute overhead rates. (default)
 182         - fractal: like graph, but displays relative rates. Each branch of
 183                  the tree is considered as a new profiled object.
 184         - none: disable call chain display.
 185
 186         threshold is a percentage value which specifies a minimum percent to be
 187         included in the output call graph.  Default is 0.5 (%).
 188
 189         print_limit is only applied when stdio interface is used.  It's to limit
 190         number of call graph entries in a single hist entry.  Note that it needs
 191         to be given after threshold (but not necessarily consecutive).
 192         Default is 0 (unlimited).
 193
 194         order can be either:
 195         - callee: callee based call graph.
 196         - caller: inverted caller based call graph.
 197         Default is 'caller' when --children is used, otherwise 'callee'.
 198
 199         sort_key can be:
 200         - function: compare on functions (default)
 201         - address: compare on individual code addresses
 202
 203         branch can be:
 204         - branch: include last branch information in callgraph when available.
 205                   Usually more convenient to use --branch-history for this.
 206
 207 --children::
 208         Accumulate callchain of children to parent entry so that then can
 209         show up in the output.  The output will have a new "Children" column
 210         and will be sorted on the data.  It requires callchains are recorded.
 211         See the `overhead calculation' section for more details.
 212
 213 --max-stack::
 214         Set the stack depth limit when parsing the callchain, anything
 215         beyond the specified depth will be ignored. This is a trade-off
 216         between information loss and faster processing especially for
 217         workloads that can have a very long callchain stack.
 218         Note that when using the --itrace option the synthesized callchain size
 219         will override this value if the synthesized callchain size is bigger.
 220
 221         Default: 127
 222
 223 -G::
 224 --inverted::
 225         alias for inverted caller based call graph.
 226
 227 --ignore-callees=<regex>::
 228         Ignore callees of the function(s) matching the given regex.
 229         This has the effect of collecting the callers of each such
 230         function into one place in the call-graph tree.
 231
 232 --pretty=<key>::
 233         Pretty printing style.  key: normal, raw
 234
 235 --stdio:: Use the stdio interface.
 236
 237 --tui:: Use the TUI interface, that is integrated with annotate and allows
 238         zooming into DSOs or threads, among other features. Use of --tui
 239         requires a tty, if one is not present, as when piping to other
 240         commands, the stdio interface is used.
 241
 242 --gtk:: Use the GTK2 interface.
 243
 244 -k::
 245 --vmlinux=<file>::
 246         vmlinux pathname
 247
 248 --kallsyms=<file>::
 249         kallsyms pathname
 250
 251 -m::
 252 --modules::
 253         Load module symbols. WARNING: This should only be used with -k and
 254         a LIVE kernel.
 255
 256 -f::
 257 --force::
 258         Don't complain, do it.
 259
 260 --symfs=<directory>::
 261         Look for files with symbols relative to this directory.
 262
 263 -C::
 264 --cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
 265         be provided as a comma-separated list with no space: 0,1. Ranges of
 266         CPUs are specified with -: 0-2. Default is to report samples on all
 267         CPUs.
 268
 269 -M::
 270 --disassembler-style=:: Set disassembler style for objdump.
 271
 272 --source::
 273         Interleave source code with assembly code. Enabled by default,
 274         disable with --no-source.
 275
 276 --asm-raw::
 277         Show raw instruction encoding of assembly instructions.
 278
 279 --show-total-period:: Show a column with the sum of periods.
 280
 281 -I::
 282 --show-info::
 283         Display extended information about the perf.data file. This adds
 284         information which may be very large and thus may clutter the display.
 285         It currently includes: cpu and numa topology of the host system.
 286
 287 -b::
 288 --branch-stack::
 289         Use the addresses of sampled taken branches instead of the instruction
 290         address to build the histograms. To generate meaningful output, the
 291         perf.data file must have been obtained using perf record -b or
 292         perf record --branch-filter xxx where xxx is a branch filter option.
 293         perf report is able to auto-detect whether a perf.data file contains
 294         branch stacks and it will automatically switch to the branch view mode,
 295         unless --no-branch-stack is used.
 296
 297 --branch-history::
 298         Add the addresses of sampled taken branches to the callstack.
 299         This allows to examine the path the program took to each sample.
 300         The data collection must have used -b (or -j) and -g.
 301
 302 --objdump=<path>::
 303         Path to objdump binary.
 304
 305 --group::
 306         Show event group information together.
 307
 308 --demangle::
 309         Demangle symbol names to human readable form. It's enabled by default,
 310         disable with --no-demangle.
 311
 312 --demangle-kernel::
 313         Demangle kernel symbol names to human readable form (for C++ kernels).
 314
 315 --mem-mode::
 316         Use the data addresses of samples in addition to instruction addresses
 317         to build the histograms.  To generate meaningful output, the perf.data
 318         file must have been obtained using perf record -d -W and using a
 319         special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
 320         'perf mem' for simpler access.
 321
 322 --percent-limit::
 323         Do not show entries which have an overhead under that percent.
 324         (Default: 0).
 325
 326 --percentage::
 327         Determine how to display the overhead percentage of filtered entries.
 328         Filters can be applied by --comms, --dsos and/or --symbols options and
 329         Zoom operations on the TUI (thread, dso, etc).
 330
 331         "relative" means it's relative to filtered entries only so that the
 332         sum of shown entries will be always 100%.  "absolute" means it retains
 333         the original value before and after the filter is applied.
 334
 335 --header::
 336         Show header information in the perf.data file.  This includes
 337         various information like hostname, OS and perf version, cpu/mem
 338         info, perf command line, event list and so on.  Currently only
 339         --stdio output supports this feature.
 340
 341 --header-only::
 342         Show only perf.data header (forces --stdio).
 343
 344 --itrace::
 345         Options for decoding instruction tracing data. The options are:
 346
 347 include::itrace.txt[]
 348
 349         To disable decoding entirely, use --no-itrace.
 350
 351 --full-source-path::
 352         Show the full path for source files for srcline output.
 353
 354 --show-ref-call-graph::
 355         When multiple events are sampled, it may not be needed to collect
 356         callgraphs for all of them. The sample sites are usually nearby,
 357         and it's enough to collect the callgraphs on a reference event.
 358         So user can use "call-graph=no" event modifier to disable callgraph
 359         for other events to reduce the overhead.
 360         However, perf report cannot show callgraphs for the event which
 361         disable the callgraph.
 362         This option extends the perf report to show reference callgraphs,
 363         which collected by reference event, in no callgraph event.
 364
 365 --socket-filter::
 366         Only report the samples on the processor socket that match with this filter
 367
 368 include::callchain-overhead-calculation.txt[]
 369
 370 SEE ALSO
 371 --------
 372 linkperf:perf-stat[1], linkperf:perf-annotate[1]