RE: Query: is it possible to trace at exactly start and end time of tracing

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Thank you.

It turned out I did not understand snapshot, the new feature.

Yes, I simply want a write to the buffer when the "tracing" begins and ends. John was right in this respect too.

I think this makes sense (at least) for some cases. The traced is some states, and the delta of states matter.

Yuyang

-----Original Message-----
From: Steven Rostedt [mailto:rostedt@xxxxxxxxxxx] 
Sent: Thursday, September 12, 2013 10:01 PM
To: John Kacur
Cc: Du, Yuyang; linux-trace-users@xxxxxxxxxxxxxxx
Subject: Re: Query: is it possible to trace at exactly start and end time of tracing

Top posting now, are we?

On Thu, 12 Sep 2013 13:40:38 +0200
John Kacur <jkacur@xxxxxxxxxx> wrote:

> and when I say, I don't know whether that makes sense or not, it's 
> because I don't know whether all the snapshot info is in the trace 
> anyway. (I need to play with the new snapshot feature first)
> 
> On Thu, Sep 12, 2013 at 1:39 PM, John Kacur <jkacur@xxxxxxxxxx> wrote:
> > I don't know whether this makes sense or not, but I believe he is 
> > asking to have trace_on and snapshot on simultaneously. He wants to 
> > do a trace, but also have the snapshot information that coincides 
> > with the start and end of the trace.
> >

I don't think this makes sense. A snapshot "saves" the current trace buffer with a simple swap. Once the swap happens, you have the start and stop of the trace. Unless he simply wants a write to the buffer when the "tracing_on == 0" happens.

-- Steve
--
To unsubscribe from this list: send the line "unsubscribe linux-trace-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux USB Development]     [Linux USB Development]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux