One further question... In regards to using %stick instead of a global lbolt variable, is there any guarantee that the %stick registers will be adequately synchronized across the system, such that reads of this register on two different CPUs (perhaps after a migration) would be similar enough not to cause any problems?
Thanks for the info, John Eric Saxe wrote: > Hi John, > > John Harres wrote: > >> Hi. I've just jumped on this alias to get some idea of the impact of >> these changes to the crashdump analysis tool I work on. It's nice to >> get some of this info in advance to the changes making the tool suddenly >> not work ;) >> >> > > Welcome! > > >> Will panic_lbolt and panic_lbolt64 be set on panic as normal with the >> new tickless clock? I'm concerned for the fact of getting a >> determination of "now" in a coredump. >> >> > Definitely. We'll need to cater to all existing consumers of the lbolt > time source (including panic_lbolt[64]). The implementation of that time > source will change though, but that's not something that the consumers > of the time source should have to care about. > > -Eric > _______________________________________________ > tesla-dev mailing list > tesla-dev at opensolaris.org > http://mail.opensolaris.org/mailman/listinfo/tesla-dev > >
