Jitendra Sasmal wrote: > Hi , > I am getting the following error while downloading: > > bash-3.2# hg clone ssh://js150784 at hg.opensolaris.org/hg/tesla/powertop > remote: ssh: hg.opensolaris.org: node name or service name not known > abort: no suitable response from remote hg! > > Anything I am missing ?
Try hg clone ssh://anon at hg.opensolaris.org/hg/tesla/powertop > Thanks > Jitendra > Li, Aubrey wrote: >> tesla-dev-bounces at opensolaris.org wrote: >> >> >>> Hi All, >>> Please tell me the steps to download and build powertop on sparc >>> systems. >>> >>> >> See instruction on this website: >> http://www.opensolaris.org/os/project/tesla/Work/Powertop/ >> >> SPARC is not supported yet. You may have a try to add makefile to build >> it >> and see what you get. >> >> Thanks, >> -Aubrey >> >> >> >> >>> Thanks >>> Jitendra >>> Eric Saxe wrote: >>> >>>> Alexander Kolbasov wrote: >>>> >>>> >>>>>> The PowerTop prototype is getting to be in pretty good shape. It's >>>>>> tracking wake-ups from all the relevant events: >>>>>> >>>>>> - timeouts / callouts >>>>>> - cyclic firings (including clock) >>>>>> - Interrupts >>>>>> >>>>>> >>>>>> >>>>> That's really cool! >>>>> >>>>> A couple of comments: >>>>> >>>>> usr/src/uts/common/io/cpudrv.c: >>>>> >>>>> >>>>> 540 DTRACE_PROBE3(cpu_change_speed, >>>>> 541 processorid_t, cpudsp->cpu_id, >>>>> 542 uint_t, cpupm->cur_spd ? cpupm->cur_spd->speed : 0, >>>>> 543 uint_t, new_spd->speed); >>>>> >>>>> I suggest rewriting this probe as >>>>> >>>>> DTRACE_PROBE3(cpu_change_speed, >>>>> cpudrv_devstate_t *, cpudsp, >>>>> cpudrv_pm_t *, cpupm, >>>>> cpudrv_pm_spd_t *, new_spd) >>>>> >>>>> This should reduce disabled probe effect because all these >>>>> dereferences and conditionals are actually executed even when the >>>>> probe is disabled. >>>>> >>>>> >>>>> >>>> Agreed. Thanks. This will require additional dereferencing on behalf >>>> of the client, but eventually that would be hidden behind >>>> translators anyway. >>>> >>>> >>>> >>>>> usr/src/uts/i86pc/os/mp_pc.c: >>>>> >>>>> 246 void >>>>> 247 mach_cpu_idle(void) >>>>> 248 { >>>>> 249 DTRACE_PROBE1(cstate_transition, uint_t, 1); 250 >>>>> 251 tlb_going_idle(); >>>>> 252 i86_halt(); >>>>> 253 tlb_service(); >>>>> 254 >>>>> 255 DTRACE_PROBE1(cstate_transition, uint_t, 0); 256 } >>>>> >>>>> This is a bit odd - why do you need to pass extra 1/0 argument >>>>> instead of using different names for in/out transitions? >>>>> >>>>> >>>>> >>>> The 1/0 is the c-state that we are transitioning to, since we only >>>> support C1 currently, it's a bit hard coded...but that will probably >>>> change when we have support for deeper c-states. >>>> >>>> Thanks >>>> -Eric >>>> >>>> >>>> >>>>> - akolb >>>>> >>>>> >>>>> >>>>> >>>> _______________________________________________ >>>> tesla-dev mailing list >>>> tesla-dev at opensolaris.org >>>> http://mail.opensolaris.org/mailman/listinfo/tesla-dev >>>> >>>> >>> _______________________________________________ >>> tesla-dev mailing list >>> tesla-dev at opensolaris.org >>> http://mail.opensolaris.org/mailman/listinfo/tesla-dev >>> >> _______________________________________________ >> tesla-dev mailing list >> tesla-dev at opensolaris.org >> http://mail.opensolaris.org/mailman/listinfo/tesla-dev >> > > _______________________________________________ > tesla-dev mailing list > tesla-dev at opensolaris.org > http://mail.opensolaris.org/mailman/listinfo/tesla-dev
