Re: [PATCH v7] io_uring: Statistics of the true utilization of sq threads.

[Jens Axboe]

On 1/29/24 12:18 AM, Xiaobing Li wrote:
> On 1/18/24 19:34, Jens Axboe wrote:
>>> diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
>>> index 8df37e8c9149..c14c00240443 100644
>>> --- a/io_uring/sqpoll.h
>>> +++ b/io_uring/sqpoll.h
>>> @@ -16,6 +16,7 @@ struct io_sq_data {
>>>  	pid_t			task_pid;
>>>  	pid_t			task_tgid;
>>>  
>>> +	long long			work_time;
>>>  	unsigned long		state;
>>>  	struct completion	exited;
>>>  };
>>
>> Probably just make that an u64.
>>
>> As Pavel mentioned, I think we really need to consider if fdinfo is the
>> appropriate API for this. It's fine if you're running stuff directly and
>> you're just curious, but it's a very cumbersome API in general as you
>> need to know the pid of the task holding the ring, the fd of the ring,
>> and then you can get it as a textual description. If this is something
>> that is deemed useful, would it not make more sense to make it
>> programatically available in addition, or even exclusively?
> 
> Hi, Jens and Pavel
> sorry for the late reply.
> 
> I've tried some other methods, but overall, I haven't found a more suitable 
> method than fdinfo.
> If you think it is troublesome to obtain the PID,  then I can provide
>  a shell script to output the total_time and work_time of all sqpoll threads 
>  to the terminal, so that we do not have to manually obtain the PID of each 
>  thread (the script can be placed in tools/ include/io_uring).
> 
> eg:
> 
> PID    WorkTime(us)   TotalTime(us)   COMMAND
> 9330   1106578        2215321         iou-sqp-9329
> 9454   1510658        1715321         iou-sqp-9453
> 9478   165785         223219          iou-sqp-9477
> 9587   106578         153217          iou-sqp-9586
> 
> What do you think of this solution?

I don't think it's a great interface, but at the same time, I don't feel
that strongly about it and perhaps bundling a script that outputs the
above in liburing would be Good Enough. I'm a bit reluctant to add a
stats API via io_uring_register() just for this.

So maybe spin a v8 with the s/long long/u64 change and include your
script as well?

-- 
Jens Axboe