Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1416041 > unrolled thread

about definition of iowait

Back to article view | Back to linux.kernel

Contents

  about definition of iowait Cao jin <caoj.fnst@cn.fujitsu.com> - 2016-06-07 13:20 +0200
    Re: about definition of iowait Peter Zijlstra <peterz@infradead.org> - 2016-06-07 14:10 +0200
      Re: about definition of iowait Cao jin <caoj.fnst@cn.fujitsu.com> - 2016-06-08 09:10 +0200

#1416041 — about definition of iowait

Hi,

I noticed some problems about iowait entry of /proc/stat: it seems not 
accurate, and sometimes will decrease in SMP.

For UP, we have a simple definition about iowait, which is:
The time that the processor is idle, during which there is a task 
waiting for I/O.

This definition seems don't fit well when step into SMP era, so I think 
maybe it can be extended like:
For a given CPU, the I/O wait time is the time during which that CPU was 
idle, and there is at least one outstanding disk I/O operation requested 
by a task scheduled on that CPU.

But tasks can migrate among cpus, so this definition maybe not accurate.

I also saw some suggestions that it should be a global value, not per 
cpu, but don`t see clear definition, so anyone have suggestions about 
it? (personally guessing, maybe: there is task waiting for outstanding 
I/O while all cpus are idle? But I don't think it is good...)

-- 
Yours Sincerely,

Cao jin

[toc] | [next] | [standalone]

#1416095

On Tue, Jun 07, 2016 at 07:24:46PM +0800, Cao jin wrote:
> Hi,
> 
> I noticed some problems about iowait entry of /proc/stat: it seems not
> accurate, and sometimes will decrease in SMP.
> 
> For UP, we have a simple definition about iowait, which is:
> The time that the processor is idle, during which there is a task waiting
> for I/O.
> 
> This definition seems don't fit well when step into SMP era, so I think
> maybe it can be extended like:
> For a given CPU, the I/O wait time is the time during which that CPU was
> idle, and there is at least one outstanding disk I/O operation requested by
> a task scheduled on that CPU.
> 
> But tasks can migrate among cpus, so this definition maybe not accurate.
> 
> I also saw some suggestions that it should be a global value, not per cpu,
> but don`t see clear definition, so anyone have suggestions about it?
> (personally guessing, maybe: there is task waiting for outstanding I/O while
> all cpus are idle? But I don't think it is good...)

It is possible to come up with definition for a single global number;
per-cpu iowait numbers are doomed.

But I don't see it matters one way or the other. Personally I would just
make the kernel return 0 and be done with it.

[toc] | [prev] | [next] | [standalone]

#1416947

On 06/07/2016 08:01 PM, Peter Zijlstra wrote:
> On Tue, Jun 07, 2016 at 07:24:46PM +0800, Cao jin wrote:
>> Hi,
>>
>> I noticed some problems about iowait entry of /proc/stat: it seems not
>> accurate, and sometimes will decrease in SMP.
>>
>> For UP, we have a simple definition about iowait, which is:
>> The time that the processor is idle, during which there is a task waiting
>> for I/O.
>>
>> This definition seems don't fit well when step into SMP era, so I think
>> maybe it can be extended like:
>> For a given CPU, the I/O wait time is the time during which that CPU was
>> idle, and there is at least one outstanding disk I/O operation requested by
>> a task scheduled on that CPU.
>>
>> But tasks can migrate among cpus, so this definition maybe not accurate.
>>
>> I also saw some suggestions that it should be a global value, not per cpu,
>> but don`t see clear definition, so anyone have suggestions about it?
>> (personally guessing, maybe: there is task waiting for outstanding I/O while
>> all cpus are idle? But I don't think it is good...)
>
> It is possible to come up with definition for a single global number;
> per-cpu iowait numbers are doomed.
>
> But I don't see it matters one way or the other. Personally I would just
> make the kernel return 0 and be done with it.
>

I see. Thanks peter

-- 
Yours Sincerely,

Cao jin

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web