Messages in this thread | | | Date | Thu, 2 Apr 2009 20:16:29 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH 5/6] perf_counter: add more context information |
| |
* Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:
> On Thu, 2009-04-02 at 13:36 +0200, Ingo Molnar wrote: > > * Peter Zijlstra <a.p.zijlstra@chello.nl> wrote: > > > > > Put in counts to tell which ips belong to what context. > > > > > > ----- > > > | | hv > > > | -- > > > nr | | kernel > > > | -- > > > | | user > > > ----- > > > > btw., i have an observation about the format: > > > > > -#define MAX_STACK_DEPTH 255 > > > +#define MAX_STACK_DEPTH 254 > > > > > > struct perf_callchain_entry { > > > - u64 nr; > > > + u32 nr, hv, kernel, user; > > > u64 ip[MAX_STACK_DEPTH]; > > > }; > > > > For the special case of signal notifications, if the signal is > > delivered immediately to the same task that raised it (pid=0), the > > call chain is actually a still meaningful one: it is the stack that > > is below the currently executing signal handler context. > > > > Wouldnt it make sense to record the full stack frame for that > > case, to allow walking/unwinding of the stack? Or can user-space > > do that just fine, based on its own signal context? > > I think it can do that just fine or even better than we can -- > userspace having access to a full dwarf2 unwinder and such.
eventually we'll have one in the kernel too, but yeah, user-space can do this better. It will have precise details about the runtime environment.
And any async mechanism has no chance to do anything useful with stack frame info anyway - that stack frame might be long gone.
> > We are going to hard-code the "call-chain is a series of IPs, > > nothing else" model, and i'd like to make sure it's future-proof > > :) > > I think it should be, function return addresses are the primary > piece of information here.
ok - good - just wanted to make sure :)
Ingo
| |