On Tue, 27 Mar 2018 16:51:49 +0200
Matthias Schiffer wrote:
> I mentioned in my commit message was caused by the second MIPS-specific
> issue I mentioned in my last mail, so while this method may lead to
> inaccurate results [1], and it is certainly not Welford's method, it might
> be good enough
On 03/26/2018 06:51 PM, Steven Rostedt wrote:
> On Sat, 24 Mar 2018 17:26:38 +0100
> Matthias Schiffer wrote:
>
>> @@ -905,8 +898,20 @@ static void profile_graph_return(struct
>> ftrace_graph_ret *trace)
>>
>> rec = ftrace_find_profiled_func(stat, trace->func);
>> if (rec) {
>> +
On Sun, 25 Mar 2018 19:09:39 +0200
Matthias Schiffer wrote:
>
> I have two more questions/issues regarding the generic code:
>
> 1) There is a small window when enabling the profiler where rec->counter
> gets incremented, but profile_graph_return() does not record times yet. For
> functions tha
On Sat, 24 Mar 2018 17:26:38 +0100
Matthias Schiffer wrote:
> @@ -905,8 +898,20 @@ static void profile_graph_return(struct ftrace_graph_ret
> *trace)
>
> rec = ftrace_find_profiled_func(stat, trace->func);
> if (rec) {
> + unsigned long long avg, delta1, delta2;
> +
>
On 03/24/2018 11:03 PM, Matthias Schiffer wrote:
> On 03/24/2018 05:26 PM, Matthias Schiffer wrote:
>> It is well-known that it is not possible to accurately calculate variances
>> just by accumulating squared samples; in fact, such an approach can even
>> result in negative numbers. An earlier att
On 03/24/2018 05:26 PM, Matthias Schiffer wrote:
> It is well-known that it is not possible to accurately calculate variances
> just by accumulating squared samples; in fact, such an approach can even
> result in negative numbers. An earlier attempt to fix the calculation
> referred to Welford's me
It is well-known that it is not possible to accurately calculate variances
just by accumulating squared samples; in fact, such an approach can even
result in negative numbers. An earlier attempt to fix the calculation
referred to Welford's method, but did not implement it correctly, leading
to meea
7 matches
Mail list logo