Robert, I have undone the patch for now because I want to release an updated pfmon-3.7 quickly. We can revisit this for 3.8, this is not critical.
Thanks. On Tue, Feb 17, 2009 at 11:30 AM, stephane eranian <eran...@googlemail.com> wrote: > Robert, > > This patch causes pfmon to crash when using sampling: > > pfmon -ecpu_clk_unhalted --long-smpl-periods=2400000 date > > I think this needs to be done slightly differently. There are things in > pfmon_initialize() that absolutely need to be done before you start > parsing the cmdline options. And others which can be deferred. > > It may be the case that the library needs to be initialized BEFORE > you parse the options, I need to check on that. Libpfm already has > a mechanism to enable verbose and debug output using environment > variables. would that be enough for you? > > > On Mon, Feb 16, 2009 at 12:44 PM, Robert Richter <robert.rich...@amd.com> > wrote: >> On 16.02.09 11:58:05, stephane eranian wrote: >>> I am not sure I understand the motivation for this change. >>> pfmon_initialize() is done early before options are parsed. >>> Can you elaborate a bit? >> >> Hi Stephane, >> >> in the follow on patches there are changes to pass debug and verbose >> options to libpfm early. To use this settings also during >> initialization, options must be parsed before. >> >> -Robert >> >> -- >> Advanced Micro Devices, Inc. >> Operating System Research Center >> email: robert.rich...@amd.com >> >> > ------------------------------------------------------------------------------ Open Source Business Conference (OSBC), March 24-25, 2009, San Francisco, CA -OSBC tackles the biggest issue in open source: Open Sourcing the Enterprise -Strategies to boost innovation and cut costs with open source participation -Receive a $600 discount off the registration fee with the source code: SFAD http://p.sf.net/sfu/XcvMzF8H _______________________________________________ perfmon2-devel mailing list perfmon2-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/perfmon2-devel