Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-05-05 Thread Daniel Wagner
It is possible to avoid the hackery from patch 4 completely. If the tracepoint is placed in stop_critical_timing(), lockdep doesn't complain anymore. I have changed this patch so that I don't do need to any additional work to get the latency calculated. Instead just use the values from check_criti

Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-05-04 Thread Daniel Wagner
On 05/04/2015 04:05 PM, Daniel Wagner wrote: > On 05/01/2015 11:23 AM, Daniel Wagner wrote: >> On 05/01/2015 02:54 AM, Steven Rostedt wrote: >>> On Thu, 30 Apr 2015 21:14:52 -0500 >>> Tom Zanussi wrote: >>> >>> > 'hist:key=latency.bucket:val=hitcount:sort=latency if cpu==0' > > but I h

Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-05-04 Thread Daniel Wagner
On 05/01/2015 11:23 AM, Daniel Wagner wrote: > On 05/01/2015 02:54 AM, Steven Rostedt wrote: >> On Thu, 30 Apr 2015 21:14:52 -0500 >> Tom Zanussi wrote: >> >> 'hist:key=latency.bucket:val=hitcount:sort=latency if cpu==0' but I haven't got this working. I didn't spend much time figur

Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-05-01 Thread Daniel Wagner
On 05/01/2015 02:54 AM, Steven Rostedt wrote: On Thu, 30 Apr 2015 21:14:52 -0500 Tom Zanussi wrote: 'hist:key=latency.bucket:val=hitcount:sort=latency if cpu==0' but I haven't got this working. I didn't spend much time figuring out why this doesn't work. Even if the above is working you stil

Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-04-30 Thread Steven Rostedt
On Thu, 30 Apr 2015 21:14:52 -0500 Tom Zanussi wrote: > > 'hist:key=latency.bucket:val=hitcount:sort=latency if cpu==0' > > > > but I haven't got this working. I didn't spend much time figuring out > > why this doesn't work. Even if the above is working you still > > I think it doesn't work be

Re: [RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-04-30 Thread Tom Zanussi
On Thu, 2015-04-30 at 12:06 +0200, Daniel Wagner wrote: > Finally we place a few tracepoint at the end of critical section. With > the hist trigger in place we can generate the plots. > > There are a few drawbacks compared to the latency_hist.patch [1] > > The latency plots contain the values fro

[RFD 5/5] tracing: Add trace_irqsoff tracepoints

2015-04-30 Thread Daniel Wagner
Finally we place a few tracepoint at the end of critical section. With the hist trigger in place we can generate the plots. There are a few drawbacks compared to the latency_hist.patch [1] The latency plots contain the values from all CPUs. In theory you can also filter with something like 'hist