This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: why just the last stap command works?
- From: fche at redhat dot com (Frank Ch. Eigler)
- To: hit201j <hit201j at gmail dot com>
- Cc: systemtap at sourceware dot org
- Date: Tue, 16 Jul 2013 11:31:06 -0400
- Subject: Re: why just the last stap command works?
- References: <CAKK+MAd0pxvwwuCVUbi7QPf16CCUnY2ALJMH-qNmOGGU7kERag at mail dot gmail dot com>
hit201j <hit201j@gmail.com> writes:
> [...]
Those registration-error-negative-22 messages are due to the kernel
rejecting kprobes on the requested addresses. It can do this for a
variety of reasons, including placement on unfavourable instructions
(like lock/synch ones), or resource constraints (memory shortage), or
blacklisting. You might try disassembling the kernel code at the
stap-identified addresses to get a hint why the kernel might be saying
no to us.
.function probes place probes at the head of the function. .statement
probes place them within the body, and different line numbers/addresses
can lead to different rejection criteria.
- FChE