Re: [PATCH v3] pipe: use __pipe_{lock,unlock} instead of spinlock

[Hongchen Zhang <zhanghongchen@loongson.cn>]

Hi Luis,

On 2023/1/7 上午3:13, Luis Chamberlain wrote:
> On Fri, Jan 06, 2023 at 05:48:44PM +0800, Hongchen Zhang wrote:
>> Use spinlock in pipe_read/write cost too much time,IMO
>> pipe->{head,tail} can be protected by __pipe_{lock,unlock}.
>> On the other hand, we can use __pipe_{lock,unlock} to protect
>> the pipe->{head,tail} in pipe_resize_ring and
>> post_one_notification.
>>
>> I tested this patch using UnixBench's pipe test case on a x86_64
>> machine,and get the following data:
>> 1) before this patch
>> System Benchmarks Partial Index  BASELINE       RESULT    INDEX
>> Pipe Throughput                   12440.0     493023.3    396.3
>>                                                          ========
>> System Benchmarks Index Score (Partial Only)              396.3
>>
>> 2) after this patch
>> System Benchmarks Partial Index  BASELINE       RESULT    INDEX
>> Pipe Throughput                   12440.0     507551.4    408.0
>>                                                          ========
>> System Benchmarks Index Score (Partial Only)              408.0
>>
>> so we get ~3% speedup.
>>
>> Signed-off-by: Hongchen Zhang <zhanghongchen@loongson.cn>
>> ---
> 
> After the above "---" line you should have the changlog descrption.
> For instance:
> 
> v3:
>    - fixes bleh blah blah
> v2:
>    - fixes 0-day report by ... etc..
>    - fixes spelling or whatever
> 
> I cannot decipher what you did here differently, not do I want to go
> looking and diff'ing. So you are making the life of reviewer harder.
> 
>    Luis
> 
Matthew also reminded me to add the change log, but I don't think it is 
necessary to write the change log to fix the errors in the patch. 
Anyway, I think it is a good habit and will add these contents in the 
new v3 version.

Best Regards,
Hongchen Zhang