Re: Minutes of 8/4/05 meeting

[Ananth N Mavinakayanahalli <ananth at in dot ibm dot com>]

On Thu, Aug 04, 2005 at 12:12:08PM -0700, Jim Keniston wrote:
> Minutes of SystemTap Conference Call, August 4, 2005
> 
> >From 7/7/05:
> 39. Ananth: Summarize the status of the ppc64 runtime port for Martin.

I believe the IBM pSeries performance folks are now looking at the port.

> 40. Ananth, Will: Port the probe-all-instruction-types test to ppc64.

Checked into CVS under patches/functional_kprobe_test_ppc64
 
> Frank asked for more stress-testing of kprobes.  Will has added some
> tests, and Ananth is adding some instruction-specific tests (e.g.,
> cli/sti and pushf/popf on i386).  Prasanna is working on adding
> kprobes tests to IBM's ABAT test framework.

Prasanna is working on the push/pop testcase :)

> Ananth has posted an update to his SMP scalability patches.
> This update uses RCU instead of read locks.  He has tested it on an
> 8-way i386 system.  No solid benchmark numbers yet, but building a
> probed kernel with -j8 is noticeably faster than when the old (Big
> Kprobe Lock) implementation.

All kprobe/jprobe tests run without issues.

I'd really like more eyes on these patches. This is my first encounter
with RCU and am fairly certain that there are a few cases/codepaths that
aren't handled correctly.

Retprobe locking is something I am still not comfortable with. Reviews, 
ideas, suggestions, patches welcome.
 
...
 
> Prasanna talked about user-space probes.  A simple patch for this is
> checked into CVS.  [Where?]  Architecture-specific issues appear to be
> minimal.  Probes on shared libraries are supported.  Prasanna will
> post this work soon.

Earlier uprobe implementations are available as part of the kprobe-dprobe 
patchsets under htdocs/kprobes/releases in systemtap CVS.

Ananth