[ltt-dev] Trace "destroy" hangs, lttd keeps running

[Mathieu Desnoyers]

* Ashwin Tanugula (ashwin.tanugula at broadcom.com) wrote:
>  
> > > Mathieu,
> > >
> > > I applied this patch on top of patch-2.6.31.6-lttng-0.177.
> > >
> > > I was able to generate the trace data.
> > >
> 
> > Great ! :)
> 
> > >However, I was only able to view two out of 10 traces generated.
> > >
> 
> > These errors seem to be caused by the fact that you run a SMP mips system with frequency scaling (either dynamic freq. scaling., or halting the clock in idle).
> 
> > You might wait to try to disable the freq. scaling and see if it works better.
> 
> Hi Mathieu,
> 
> Frequency scaling is not enabled on my kernel. 
> 
> 1) Can you think of something else that might cause this
> 
> 2) Can you please give me a list of functions to debug that would lead to this error
> 
>    ** ERROR **: Process 570 has been created at [0.000000000] and 
>    inserted at [415.432990305] before fork on cpu 0[436.945971082].
>    Probably an unsynchronized TSC problem on the traced machine.
>    aborting...

This is a state-consistency check within LTTV. A "safety net" that
detects that your TSCs are not synchronized in your trace. So there is
nothing to fix in LTTV. You are taking the correct approach by trying to
fix the TSC source on your board.

Mathieu

> 
> Thanks,
> 
> Ashwin
> 
> > Thanks,
> 
> > Mathieu
> 
> 
> 

-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68