Ah I was reading most recent source. Yes there has been some changes around the profiling recently
On Tue, Aug 16, 2016 at 2:43 AM, Chris Swiedler <[email protected]> wrote: > Already fixed in > https://github.com/mono/mono/commit/d13d7b5bb3e7c124f670eb28f118250ad5502bc4 > looks like. > > chris > > -----Original Message----- > From: Mono-devel-list [mailto:[email protected]] On > Behalf Of Chris Swiedler > Sent: Monday, August 15, 2016 6:25 PM > To: Greg Young <[email protected]> > Cc: mono-devel-list <[email protected]> > Subject: Re: [Mono-dev] Profiling with heapshot (only) > > It looks like what's happening is that the writer_thread is spinning > constantly calling mono_lock_free_queue_dequeue(). Adding a nanosleep(100000) > in the outer loop fixes the CPU usage, with no ill effects that I can see. > How often does the writer thread need to dequeue/write out data? > > As far as I can tell this would affect any users of the log profiler. > > chris > > -----Original Message----- > From: Greg Young [mailto:[email protected]] > Sent: Monday, August 15, 2016 5:15 PM > To: Chris Swiedler <[email protected]> > Cc: mono-devel-list <[email protected]> > Subject: Re: [Mono-dev] Profiling with heapshot (only) > > +1 > +https://github.com/mono/mono/blob/master/mono/profiler/proflog.c#L4811 > > ill have to try it then > > On Tue, Aug 16, 2016 at 1:12 AM, Chris Swiedler <[email protected]> > wrote: >> The heapshot option turns both of those off automatically (and empirically, >> adding nocalls/noalloc doesn't help the CPU usage). >> >> chris >> >> -----Original Message----- >> From: Greg Young [mailto:[email protected]] >> Sent: Monday, August 15, 2016 5:07 PM >> To: Chris Swiedler <[email protected]> >> Cc: mono-devel-list <[email protected]> >> Subject: Re: [Mono-dev] Profiling with heapshot (only) >> >> Likely also noalloc. >> >> Cheers, >> >> Greg >> >> On Tue, Aug 16, 2016 at 1:04 AM, Greg Young <[email protected]> wrote: >>> https://github.com/mono/mono/blob/master/mono/profiler/proflog.c#L477 >>> 2 >>> >>> Is an option you want. Without the enter/leave hooks are registered >>> which has a significant cost. >>> >>> Not sure if this is the only option or just one of a few (have not >>> tested on your use case) >>> >>> Cheers, >>> >>> Greg >>> >>> On Tue, Aug 16, 2016 at 12:57 AM, Chris Swiedler >>> <[email protected]> wrote: >>>> I'm trying to use the heapshot=ondemand feature of the logging profiler. I >>>> want to turn off all of the other features of the logging profiler, since >>>> the allocation/method tracing stuff runs too slow to be useful in the >>>> situation that I need to test. However, even with a command line like this: >>>> >>>> mono-sgen --debug >>>> --profile=log:heapshot,heapshot=ondemand,time=fast,port=7103,output= >>>> % >>>> p.mlpd >>>> >>>> ...I still get extremely high CPU usage in my apps. From what I understand >>>> of the heapshot part of the profiler, it shouldn't need to incur any >>>> overhead except when generating the heapshot file. Is there any way to >>>> reduce the runtime overhead when it's not generating a heapshot? This link >>>> suggests that I should disable counters, but I don't see any options for >>>> that: >>>> >>>> http://mono.1490590.n4.nabble.com/Problems-with-mono-log-pofiler-td4 >>>> 6 >>>> 65572.html >>>> >>>> thanks, >>>> chris >>>> _______________________________________________ >>>> Mono-devel-list mailing list >>>> [email protected] >>>> http://lists.dot.net/mailman/listinfo/mono-devel-list >>> >>> >>> >>> -- >>> Studying for the Turing test >> >> >> >> -- >> Studying for the Turing test > > > > -- > Studying for the Turing test > _______________________________________________ > Mono-devel-list mailing list > [email protected] > http://lists.dot.net/mailman/listinfo/mono-devel-list -- Studying for the Turing test _______________________________________________ Mono-devel-list mailing list [email protected] http://lists.dot.net/mailman/listinfo/mono-devel-list
