svn commit: r304436 - in head: . sys/netinet

[Adrian Chadd]

On 26 August 2016 at 17:46, Slawa Olhovchenkov <slw at zxy.spb.ru> wrote:
> On Fri, Aug 26, 2016 at 04:55:34PM -0700, Adrian Chadd wrote:
>
>> Hi,
>>
>> I use the kernel lock profiling debugging,
>
> I am already have 100% utilise all CPU cores, I think this is drop
> performance?
>
>> but you can use dtrace to
>> get an idea:
>>
>> dtrace -n 'lockstat:::adaptive-block { @[stack()] = sum(arg1); }'
>
> How to interpret results (how to distinct lock contention from lock
> cost/overhead (LOCK CMPXCGQ is very expensive))?

well, paste the results? :)

the lock is expensive because it's contended. :)


-a

>> (https://wiki.freebsd.org/DTrace/One-Liners)
>>
>>
>>
>> -adrian