On 8.09.17 г. 21:13, Steven Rostedt wrote:
> On Fri, 8 Sep 2017 20:18:29 +0300
> Georgi Djakov <georgi.djakov@xxxxxxxxxx> wrote:
>
>> diff --git a/include/trace/events/interconnect.h b/include/trace/events/interconnect.h
>> new file mode 100644
>> index 000000000000..c4a72163873c
>> --- /dev/null
>> +++ b/include/trace/events/interconnect.h
>> @@ -0,0 +1,45 @@
>> +#undef TRACE_SYSTEM
>> +#define TRACE_SYSTEM interconnect
>> +
>> +#if !defined(_TRACE_INTERCONNECT_H) || defined(TRACE_HEADER_MULTI_READ)
>> +#define _TRACE_INTERCONNECT_H
>> +
>> +#include <linux/tracepoint.h>
>> +
>> +struct interconnect_path;
>> +
>> +DECLARE_EVENT_CLASS(interconnect_path,
>> +
>> + TP_PROTO(struct interconnect_path *path),
>> +
>> + TP_ARGS(path),
>> +
>> + TP_STRUCT__entry(
>> + __field(struct interconnect_path *, path)
>> + ),
>> +
>> + TP_fast_assign(
>> + __entry->path = path;
>> + ),
>> +
>> + TP_printk("INTERCONNECT: %p", __entry->path)
>
> You're passing in an interconnect_path and only recording the pointer
> to it? Wouldn't it be useful to record other aspects? Like the number
> of nodes, the avg and peak bw of each node?
>
My goal was to get just the path with some timestamps, but your suggestion
sounds good. Will do it. Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-arm-msm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
