| 1 |
.\" t -*- nroff -*- |
| 2 |
|
| 3 |
.TH ERROR::PASS5 7stap |
| 4 |
.SH NAME |
| 5 |
warning::pass5 \- systemtap pass-5 warnings |
| 6 |
|
| 7 |
.\" macros |
| 8 |
.de SAMPLE |
| 9 |
|
| 10 |
.nr oldin \\n(.i |
| 11 |
.br |
| 12 |
.RS |
| 13 |
.nf |
| 14 |
.nh |
| 15 |
.. |
| 16 |
.de ESAMPLE |
| 17 |
.hy |
| 18 |
.fi |
| 19 |
.RE |
| 20 |
.in \\n[oldin]u |
| 21 |
|
| 22 |
.. |
| 23 |
|
| 24 |
.SH DESCRIPTION |
| 25 |
Warnings that occur during pass 5 (execution) can have a variety of causes. |
| 26 |
|
| 27 |
|
| 28 |
.TP |
| 29 |
probe insertion errors |
| 30 |
With any of the systemtap runtimes, it may be possible that the |
| 31 |
backends are unable to insert probe points requested by the systemtap |
| 32 |
script. For example, you may see errors such as |
| 33 |
.SAMPLE |
| 34 |
WARNING: probe [...] registration error (rc -524) |
| 35 |
.ESAMPLE |
| 36 |
(524 is a kernel error code for ENOTSUPP). These situations are out |
| 37 |
of systemtap's control, and result in some probes not receiving any |
| 38 |
hits. This may be caused by temporary resource constraints or |
| 39 |
permanent problems. One common permanent problem is such a probe |
| 40 |
point being placed at instructions that the runtime (kernel kprobes, |
| 41 |
uprobes or dyninst) cannot decode or intercept. A possible workaround |
| 42 |
is to move the probe points slightly in the script, so as to target a |
| 43 |
nearby statement, or a caller, or a callee. See also |
| 44 |
.IR error::dwarf (7stap). |
| 45 |
|
| 46 |
.SH GATHERING MORE INFORMATION |
| 47 |
Increasing the verbosity of pass-5 |
| 48 |
with an option such as |
| 49 |
.IR "--vp 00001" |
| 50 |
can help pinpoint the problem. |
| 51 |
|
| 52 |
.SH SEE ALSO |
| 53 |
.nh |
| 54 |
.nf |
| 55 |
.IR stap (1), |
| 56 |
.IR http://sourceware.org/systemtap/wiki/TipExhaustedResourceErrors , |
| 57 |
.IR error::pass5 (7stap), |
| 58 |
.IR error::reporting (7stap) |
| 59 |
.IR error::dwarf (7stap) |