bcc-ppchcalls(8)

1ppchcalls(8)                System Manager's Manual               ppchcalls(8)
2
3
4

NAME

6       ppchcalls - Summarize ppc hcall counts and latencies.
7

SYNOPSIS

9       ppchcalls  [-h]  [-p PID] [-t TID] [-i INTERVAL] [-d DURATION] [-T TOP]
10       [-x] [-e ERRNO] [-L] [-m] [-P] [-l] [--hcall HCALL]
11

DESCRIPTION

13       This tool traces hcall entry and exit raw  tracepoints  and  summarizes
14       either  the  number of hcalls of each type, or the number of hcalls per
15       process. It can also collect min, max  and  average  latency  for  each
16       hcall or each process.
17
18       Since this uses BPF, only the root user can use this tool.
19

REQUIREMENTS

21       CONFIG_BPF  and bcc. Linux 4.17+ is required to attach a BPF program to
22       the raw_hcalls:hcall_{enter,exit} tracepoints, used by this tool.
23

OPTIONS

25       -h     Print usage message.
26
27       -p PID Trace only this process.
28
29       -t TID Trace only this thread.
30
31       -i INTERVAL
32              Print the summary at the specified interval (in seconds).
33
34       -d DURATION
35              Total duration of trace (in seconds).
36
37       -T TOP Print only this many entries. Default: 10.
38
39       -x     Trace only failed hcalls (i.e., the return value from the  hcall
40              was < 0).
41
42       -e ERRNO
43              Trace  only hcalls that failed with that error (e.g. -e EPERM or
44              -e 1).
45
46       -m     Display times in milliseconds. Default: microseconds.
47
48       -P     Summarize by process and not by hcall.
49
50       -l     List the hcalls recognized by the tool (hard-coded list). Hcalls
51              beyond  this  list  will still be displayed, as "[unknown: nnn]"
52              where nnn is the hcall number.
53
54       --hcall HCALL
55              Trace this hcall only (use  option  -l  to  get  all  recognized
56              hcalls).
57

EXAMPLES

59       Summarize all hcalls by hcall:
60              # ppchcalls
61
62       Summarize all hcalls by process:
63              # ppchcalls -P
64
65       Summarize only failed hcalls:
66              # ppchcalls -x
67
68       Summarize only hcalls that failed with EPERM:
69              # ppchcalls -e EPERM
70
71       Trace PID 181 only:
72              # ppchcalls -p 181
73
74       Summarize hcalls counts and latencies:
75              # ppchcalls -L
76

FIELDS

78       PID    Process ID
79
80       COMM   Process name
81
82       HCALL  Hcall  name,  or  "[unknown: nnn]" for hcalls that aren't recog‐
83              nized
84
85       COUNT  The number of events
86
87       MIN    The minimum elapsed time (in us or ms)
88
89       MAX    The maximum elapsed time (in us or ms)
90
91       AVG    The average elapsed time (in us or ms)
92

OVERHEAD

94       For most applications, the overhead should be manageable if  they  per‐
95       form  1000's  or  even 10,000's of hcalls per second. For higher rates,
96       the overhead may become considerable.
97

SOURCE

99       This is from bcc.
100
101              https://github.com/iovisor/bcc
102
103       Also look in the bcc distribution for a  companion  _examples.txt  file
104       containing example usage, output, and commentary for this tool.
105

OS

107       Linux
108

STABILITY

110       Unstable - in development.
111

AUTHOR

113       Harsh Prateek Bora
114