Re: [PATCH v2 0/4] /proc/stat: Reduce irqs counting performance overhead

[Waiman Long]

On 01/09/2019 01:52 PM, Matthew Wilcox wrote:
> On Wed, Jan 09, 2019 at 01:37:23PM -0500, Waiman Long wrote:
>> On 01/09/2019 01:24 PM, Matthew Wilcox wrote:
>>> Did you even try just using the general purpose infrastructure that's
>>> in place?  If that shows a performance problem _then_ it's time to make
>>> this special snowflake just a little more special.  Not before.
>> I have looked into the percpu counter code. There are two aspects that I
>> don't like to introduce to the interrupt handler's code path for
>> updating the counts.
>>
>> 1) There is a raw spinlock in the percpu_counter structure that may need
>> to be acquired in the update path. This can be a performance drag
>> especially if lockdep is enabled.
>>
>> 2) The percpu_counter structure is 40 bytes in size on 64-bit systems
>> compared with just 8 bytes for the percpu count pointer and an
>> additional 4 bytes that I introduced in patch 2. With thousands of irq
>> descriptors, it can consume quite a lot more memory. Memory consumption
>> was a point that you brought up in one of your previous mails.
> Then _argue that_.  Don't just go off and do something random without
> explaining to the rest of us why we're wrong.

Sorry about that. I should have included that in the cover-letter.

Cheers,
Longman