Why did control channel closes itself?

[Frank Ch. Eigler]

"Peter Teoh" <htmldeveloper@gmail.com> writes:

> [...]
> stapio:stp_main_loop:282 nb=46
> ERROR: probe overhead exceeded threshold
> stapio:stp_main_loop:282 nb=53
> WARNING: Number of errors: 1, skipped probes: 2
> stapio:stp_main_loop:282 nb=51
> WARNING: There were 45618 transport failures.
> [...]
> Notice the error "probe overhead exceeded threshold".   And
> subsequent control-C does not stop the execution, it just hanged
> without any response.

At this point, the script/module should already be unloading.  If
there are thousands of kprobes, this can unfortunately take a long
time (number-of-probes/CONFIG_HZ seconds), until we get the
bulk-unregistration kprobe support code into the kernel.  (Masami,
how is that bug #3542 going?)


> Funny thing is this - in  the stap_xxxxx.c auto-generated in the /tmp/
> directory, the following lines were observed:
> [...]
> Here c->cycles_sum is incremented.   But nowhere can I find it being
> initialized - uninitialized cycles_sum variable - could  this be a
> bug?

Yes, it certainly is, I will fix it pronto.


- FChE