Minutes of SystemTap Conference Call, Sept. 22, 2005

[Kevin Stafford <kevinrs at us dot ibm dot com>]

Minutes of SystemTap Conference Call, Sept. 22, 2005

Participants:
IBM:
       Ananth Mavinakayanahalli (mananth@in.ibm.com -- Boston)
       Jim Keniston (jkenisto@us.ibm.com -- Beaverton)
       Hien Nguyen (nguyhien@us.ibm.com -- Beaverton)
       Kevin Stafford (kevinrs@us.ibm.com -- Beaverton)
       Vara Prasad (varap@us.ibm.com -- Beaverton)
       Prasanna Panchamukhi (prasanna@in.ibm.com -- Bangalore)
       Maneesh Soni (maneesh@in.ibm.com -- Bangalore)
       Tom Zanussi (trz@us.ibm.com -- Chicago)
Red Hat:
       Will Cohen (wcohen@redhat.com -- Raleigh)
       Martin Hunt (hunt@redhat.com -- Seattle)
       Frank Eigler (fche@redhat.com -- Toronto)
Intel:
       Josh Stone (joshua.i.stone@intel.com -- Santa Clara)
       Anil KeshavaMurthy (anil.s.keshavamurthy@intel.com -- Hillsboro)

Actions Required (ARs):
>From 5/19/05:
19. Vara: Collect sample kprobes modules and post them to the
SystemTap web site. [OBSOLETE: We are now collecting ST examples]

22. Rusty: Look into x86_64 limitation re: temporary disarming of
reentrant probes.

23. Jim, Martin: Ensure that the runtime's stack-trace feature works
appropriately when there are return probes in the call stack.
[Update: Martin is working on this.  Jim will prototype an improvement
whereby the saved IP is updated before the handler is called.]

>From 6/9/05:
26. Rusty/Brad: Forward email address of Intel test person to Jay
Turner.  [Update: As of 7/7/05, Brad hasn't done this.  Did Rusty?]

>From 6/23/05:
30. Rusty: Review Will's rendition of Rusty's test that exercises
probes on a wide variety of instruction types.  [Update: As of 7/7/05,
Will still needs to hear back from Rusty.]

>From 7/7/05:
39. Ananth: Summarize the status of the ppc64 runtime port for Martin.
[Update 8/22/05: Hien now owns this project]

>From 7/28/05:
41. Anil: Post a summary of known djprobes implementation issues.

>From 8/4/05:
43. Prasanna: Post work on user-space probes. [DONE: Posted to ML 9/13/2005]

>From 8/11/05:
44. Tom: Automate relayfs tests and post them to mailing list.
[Update: In progress]

>From 8/18/05:
48. Elena, Vara: Manage planning of next face-to-face meeting.

53. Anil: Test RCU-based SMP scalability feature on ia64.
[Update: Results for 4x IA64 box posted to ML 9/19/2005.
Will continue testing on 32 way machine and post to ML]

>From 8/25/05:
54. Vara: Report on availability of tech writer(s) at IBM to help
with user documentation.

55. Elena: Investigate approaches to making the full SystemTap bug
list available to SystemTap developers outside Red Hat.

>From 9/8/05:

56. Will: Integate RH testsuite as part of std distro tests (rather
than local system testing).

57. Martin: Runtime build issues fix.

58. Ananth: Work on resolving PPC64 runtime issues.
[OBSOLETE: see AI #39]

59: Elena: Send out editable OLS slides [DONE: Posted to ML 9/8/2005]

60: Will: Check editable OLS slides into CVS - htdocs [DONE]

61: Kevin: Post FC4 SystemTap installation instructions. [DONE:
posted to ML 9/7/2005]

>From 9/15/05:

63. Will: post howto mail on running the test module from CVS to SystemTap
ML.

64. Masami Hiramatsu: post new djprobes patches to SystemTap ML for review.

70. Prasanna: post working userspace probes patches to ML. [OBSOLETE: see AI
#43]

71. Hien: test RCU patches on 4x PPC64 machine. [DONE: posted to ML 
9/19/2005]

72. Jim: post user-space return probes design document.
[Update: Jim has posted to Prasanna for internal review]

>From 9/22/05:

73. Prasanna: post user space probes paper to ML (with permission from Linux
Congress, otherwise to private CVS)

74. Ananth: post kprobes RCU patches to LKML, contingent upon resolution of
BZ# 1345 and possible others.

75. Elena: post RHEL update 3 milestone list.

76. Hien: post dumpstack routine that solves kallsyms_lookup PPC issue.

77. Frank: post prototype to do symbol lookup in the translator.

78. Vara: Correspond with Elena about the next face-2-face meeting.

79. Hien: Update install directions for SystemTap, commit to src/ in CVS.

80. Kevin: write arch agnostic return value getter routine, commit to CVS.

Prasanna has submitted his paper on user-space probes to Linux Kongress
2005.  He will make it available to us if he legally can.

Per Andrew Morton's request, Prasanna has moved CONFIG_KPROBES to a
new "Instrumentation Support" menu and updated the MAINTAINERS file
wrt Kprobes.

Hien is pursuing a kretprobes bug reported by Frank.  There may be
more than one bug there.

Ananth is ready to post his SMP scalability (AKA RCU) patches to
LKML, but is waiting to hear whether the aforementioned kretprobes
bug shows up in the RCU code as well as the pre-RCU code.

Tom Z is working on characterizing a procfs transport problem,
which he sees in his kmalloc instrumentation.

We again see a need for an interface to change configs like
MAXSTRINGLEN, MAXBUFSIZE, etc.  This enhancement request is already
in bugzilla.

Martin is doing some cleanup in the runtime.  People doing ppc64
and ia64 ports beware.

Will has been evangelizing for SystemTap among potential users at
Red Hat.  He has checked more examples into
tests/testsuite/systemtap.samples.

Frank's "next steps" email will serve as a good starting point
for an agenda for the upcoming (but as yet unplanned) face-to-face
meeting.

We need to be vigilant about monitoring LKML and Andrew Morton's
bug list for opportunities to help solve problems using SystemTap.
Should we establish a new mailing list for that?  Looks like we'll
use the SystemTap ML for that for now.

--
Kevin Stafford
DES 2 | MS 2M3
Beaverton - OR
Linux Technology Center
IBM Systems & Technology
Phone: 1-503-578-3039
Email: kevinrs@us.ibm.com