Home | History | Annotate | Download | only in Documentation
      1 perf-trace(1)
      2 =============
      3 
      4 NAME
      5 ----
      6 perf-trace - strace inspired tool
      7 
      8 SYNOPSIS
      9 --------
     10 [verse]
     11 'perf trace'
     12 
     13 DESCRIPTION
     14 -----------
     15 This command will show the events associated with the target, initially
     16 syscalls, but other system events like pagefaults, task lifetime events,
     17 scheduling events, etc.
     18 
     19 Initially this is a live mode only tool, but eventually will work with
     20 perf.data files like the other tools, allowing a detached 'record' from
     21 analysis phases.
     22 
     23 OPTIONS
     24 -------
     25 
     26 -a::
     27 --all-cpus::
     28         System-wide collection from all CPUs.
     29 
     30 -e::
     31 --expr::
     32 	List of events to show, currently only syscall names.
     33 	Prefixing with ! shows all syscalls but the ones specified.  You may
     34 	need to escape it.
     35 
     36 -o::
     37 --output=::
     38 	Output file name.
     39 
     40 -p::
     41 --pid=::
     42 	Record events on existing process ID (comma separated list).
     43 
     44 -t::
     45 --tid=::
     46         Record events on existing thread ID (comma separated list).
     47 
     48 -u::
     49 --uid=::
     50         Record events in threads owned by uid. Name or number.
     51 
     52 -v::
     53 --verbose=::
     54         Verbosity level.
     55 
     56 -i::
     57 --no-inherit::
     58 	Child tasks do not inherit counters.
     59 
     60 -m::
     61 --mmap-pages=::
     62 	Number of mmap data pages. Must be a power of two.
     63 
     64 -C::
     65 --cpu::
     66 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
     67 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
     68 In per-thread mode with inheritance mode on (default), Events are captured only when
     69 the thread executes on the designated CPUs. Default is to monitor all CPUs.
     70 
     71 --duration:
     72 	Show only events that had a duration greater than N.M ms.
     73 
     74 --sched:
     75 	Accrue thread runtime and provide a summary at the end of the session.
     76 
     77 -i
     78 --input
     79 	Process events from a given perf data file.
     80 
     81 SEE ALSO
     82 --------
     83 linkperf:perf-record[1], linkperf:perf-script[1]
     84