This is the mail archive of the systemtap@sourceware.org mailing list for the systemtap project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[Bug kprobes/2183] kretprobe on schedule() leaks kretprobe_instances


------- Additional Comments From jkenisto at us dot ibm dot com  2006-01-20 00:14 -------
Created an attachment (id=844)
 --> (http://sourceware.org/bugzilla/attachment.cgi?id=844&action=view)
kretprobes test program

Attached is a module that sets return probes on all the functions named in the
probes[] array, and on exit, reports the number of calls, returns, and
kretprobe misses for each function.

On i386, I do indeed see a lot of misses for schedule() with maxactive set to
5, as in rp.c, but when I crank maxactive up to 5000, I see no misses for
schedule().  We would expect a lot of tasks to be stopped in schedule() at any
one time.  If that number exceeds maxactive, we start seeing misses.

-- 


http://sourceware.org/bugzilla/show_bug.cgi?id=2183

------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]