PERF-REPORT(1) perf Manual PERF-REPORT(1)
perf-report - Read perf.data (created by perf record) and display the profile
perf report [-i <file> | --input=file]
This command displays the performance counter profile information recorded via perf
Input file name. (default: perf.data unless stdin is a fifo)
Be more verbose. (show symbol address, etc)
Only consider symbols in these dsos. CSV that understands file://filename entries.
Show the number of samples for each symbol
Show sample percentage for different cpu modes.
Show per-thread event counters
Only consider symbols in these comms. CSV that understands file://filename entries.
Only consider these symbols. CSV that understands file://filename entries.
Only show symbols that match (partially) with this filter.
Only display entries resolved to a symbol.
Sort histogram entries by given key(s) - multiple keys can be specified in CSV format.
Following sort keys are available: pid, comm, dso, symbol, parent, cpu, srcline,
Each key has following meaning:
o comm: command (name) of the task which can be read via /proc/<pid>/comm
o pid: command and tid of the task
o dso: name of library or module executed at the time of sample
o symbol: name of function executed at the time of sample
o parent: name of function matched to the parent regex filter. Unmatched entries are
displayed as "[other]".
o cpu: cpu number the task ran at the time of sample
o srcline: filename and line number executed at the time of sample. The DWARF
debuggin info must be provided.
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
If --branch-stack option is used, following sort keys are also
dso_from, dso_to, symbol_from, symbol_to, mispredict.
o dso_from: name of library or module branched from
o dso_to: name of library or module branched to
o symbol_from: name of function branched from
o symbol_to: name of function branched to
o mispredict: "N" for predicted branch, "Y" for mispredicted branch
And default sort keys are changed to comm, dso_from, symbol_from, dso_to
and symbol_to, see '--branch-stack'.
A regex filter to identify parent. The parent is a caller of this function and
searched through the callchain, thus it requires callchain information recorded. The
pattern is in the exteneded regex format and defaults to "^sys_|^do_page_fault", see
Only display entries with parent-match.
Force each column width to the provided list, for large terminal readability.
Use a special separator character and don't pad with spaces, replacing all occurrences
of this separator in symbol names (and other output) with a . character, that thus
it's the only non valid separator.
Dump raw trace in ASCII.
-g [type,min[,limit],order[,key]], --call-graph
Display call chains using type, min percent threshold, optional print limit and order.
type can be either:
o flat: single column, linear exposure of call chains.
o graph: use a graph tree, displaying absolute overhead rates.
o fractal: like graph, but displays relative rates. Each branch of the tree is
considered as a new profiled object.
order can be either:
- callee: callee based call graph.
- caller: inverted caller based call graph.
key can be:
- function: compare on functions
- address: compare on individual code addresses
alias for inverted caller based call graph.
Ignore callees of the function(s) matching the given regex. This has the effect of
collecting the callers of each such function into one place in the call-graph tree.
Pretty printing style. key: normal, raw
Use the stdio interface.
Use the TUI interface, that is integrated with annotate and allows zooming into DSOs
or threads, among other features. Use of --tui requires a tty, if one is not present,
as when piping to other commands, the stdio interface is used.
Use the GTK2 interface.
Load module symbols. WARNING: This should only be used with -k and a LIVE kernel.
Don't complain, do it.
Look for files with symbols relative to this directory.
Only report samples for the list of CPUs provided. Multiple CPUs can be provided as a
comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
Default is to report samples on all CPUs.
Set disassembler style for objdump.
Interleave source code with assembly code. Enabled by default, disable with
Show raw instruction encoding of assembly instructions.
Show a column with the sum of periods.
Display extended information about the perf.data file. This adds information which may
be very large and thus may clutter the display. It currently includes: cpu and numa
topology of the host system.
Use the addresses of sampled taken branches instead of the instruction address to
build the histograms. To generate meaningful output, the perf.data file must have been
obtained using perf record -b or perf record --branch-filter xxx where xxx is a branch
filter option. perf report is able to auto-detect whether a perf.data file contains
branch stacks and it will automatically switch to the branch view mode, unless
--no-branch-stack is used.
Path to objdump binary.
Show event group information together.
Demangle symbol names to human readable form. It's enabled by default, disable with
Do not show entries which have an overhead under that percent. (Default: 0).
perf 06/30/2014 PERF-REPORT(1)