Stephen, On Fri, Sep 15, 2006 at 02:38:34PM -0400, Stephen Ziemba wrote: > Stephane, > > Are you saying the removal of kapi support is temporary or possibly > permanent?
I meant it is temporary. I think there is a need. We just need to demonstrate that certain measurements cannot be done differently without incurring a huge penalty. At this point, I think it is more important to get perfmon without kapi accepted into mainline than delay the whole thing because people do not understand why kapi could be useful. During that meantime, we need to build a stronger case, and your tool may be helpful in that. I would encourage you to describe it on lkml and here. We could also use this time window to refine kapi and make sure we find and understand all the usage restrictions it has. > You stated you have pulled kapi support until a vey strong case can be made > for > it. I assume you are saying you are removing perfmon_kapi.c and the > associated > code from future perfmon kernel patches. The tool I am currently developing > utilizes the kapi interface and was hoping for clarification on the future > support of kapi. I use neither overflow nor timer based samples and instead > sample on specific kernel events. All monitoring is done within the kernel > for > the kernel. The only time any of this information is exported to user is for > debugging or further analysis. It seems without kapi any tool designed to > have > the kernel monitor specific aspects of itself will have increased overhead. > > Stephen Ziemba > Electrical and Computer Engineering > Purdue University > [EMAIL PROTECTED] > > > Quoting Stephane Eranian <[EMAIL PROTECTED]>: > > > Will, > > > > I don't think I replied to this question. > > > > On Tue, Sep 12, 2006 at 02:01:57PM -0400, William Cohen wrote: > > > Hi All, > > > > > > I have an simple-mind Systemtap interface that uses the Perfmon2 Kernel > > > API to access the counters. The user-space interface automatically loads > > > the appropriate perfmon module to get access to the performance > > > monitoring hardware when __pfm_create_context() is performed. When using > > > the kernel ABI the module does not automatically loaded. What is the > > > reasoning for this difference in behavior? > > > > > > > This is simple: there cna be a race if you call __pfm_create_context() > > from the module_init() function. In that case you would be trying to > > insert a perfmon module while you are inserting yours and you would deadlock > > on insmod. > > > > > If the Perfmon2 KAPI is not available, what are people thoughts on being > > > able to set up and read the performance counters within the kernel? What > > > about being ability for the kernel to monitor itself? > > > > For now, I have pulled the kapi support out of the new code base in an > > effort > > to ease the situation a little bit and until we can make a very strong case > > for > > it. > > > > -- > > -Stephane > > _______________________________________________ > > perfmon mailing list > > [email protected] > > http://www.hpl.hp.com/hosted/linux/mail-archives/perfmon/ > > > -- -Stephane _______________________________________________ perfmon mailing list [email protected] http://www.hpl.hp.com/hosted/linux/mail-archives/perfmon/
