On Nov 3, 2009, at 3:52 PM, Jim Walker wrote: > Garrett D'Amore wrote: >> Jim Walker wrote: >>> Garrett D'Amore wrote: >>>> Can you add *which* kstats are being used? Individual kstats are >>>> normally not documented, and some of them are more volatile than >>>> others. If this case is going to use kstats, then I think we >>>> need to document which ones are used in case someone decides to >>>> change them in the future. >>> >>> Appendix A. in the proposal file has been updated to include the >>> individual kstat information. >>> >>> Cheers, >>> Jim >> Thanks. The stats you're using look reasonable to me, but I'd like >> to hear from someone more familiar with the VM subsystem -- the >> anoninfo and cpu_vminfo stats might be unreliable... > > Here are the anoninfo and cpu_vminfo stats being used. > > anoninfo.ani_max; > anoninfo.ani_resv; > cpu_vminfo.pgpgin; > cpu_vminfo.pgpgout; > > Can someone knowledgeable give an idea of their reliability?
I ran these by a few VM people and we all agree that these should be relatively stable. --Mike > > Currently, we are assuming they are as reliable as any > other stat. > > I would like to wrap up this case. > > Here's the full proposal: > http://arc.opensolaris.org/caselog/PSARC/2009/583/proposal.txt > > Cheers, > Jim > _______________________________________________ > opensolaris-arc mailing list > opensolaris-arc at opensolaris.org
