* [PATCH] Change the document about iowait @ 2016-10-26 2:41 Chao Fan 2016-11-09 1:33 ` Chao Fan 2016-11-13 15:47 ` Jonathan Corbet 0 siblings, 2 replies; 5+ messages in thread From: Chao Fan @ 2016-10-26 2:41 UTC (permalink / raw) To: linux-doc, linux-kernel Cc: peterz, corbet, akpm, izumi.taku, Chao Fan, Cao Jin The iowait is not reliable by reading from /proc/stat, so this method to get iowait is not suggested. And we mark it in the document. Signed-off-by: Cao Jin <caoj.fnst@cn.fujitsu.com> Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> --- Documentation/filesystems/proc.txt | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 74329fd..71f5096 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1305,7 +1305,16 @@ second). The meanings of the columns are as follows, from left to right: - nice: niced processes executing in user mode - system: processes executing in kernel mode - idle: twiddling thumbs -- iowait: waiting for I/O to complete +- iowait: In a word, iowait stands for waiting for I/O to complete. But there + are several problems: + 1. Cpu will not wait for I/O to complete, iowait is the time that a task is + waiting for I/O to complete. When cpu goes into idle state for + outstanding task io, another task will be scheduled on this CPU. + 2. In a multi-core CPU, the task waiting for I/O to complete is not running + on any CPU, so the iowait of each CPU is difficult to calculate. + 3. The value of iowait field in /proc/stat will decrease in certain + conditions. + So, the iowait is not reliable by reading from /proc/stat. - irq: servicing interrupts - softirq: servicing softirqs - steal: involuntary wait -- 2.7.4 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] Change the document about iowait 2016-10-26 2:41 [PATCH] Change the document about iowait Chao Fan @ 2016-11-09 1:33 ` Chao Fan 2016-11-13 15:47 ` Jonathan Corbet 1 sibling, 0 replies; 5+ messages in thread From: Chao Fan @ 2016-11-09 1:33 UTC (permalink / raw) To: linux-doc, linux-kernel; +Cc: peterz, corbet, akpm, izumi.taku, Cao Jin ping Thanks, Chao Fan On Wed, Oct 26, 2016 at 10:41:28AM +0800, Chao Fan wrote: >The iowait is not reliable by reading from /proc/stat, so this >method to get iowait is not suggested. And we mark it in the >document. > >Signed-off-by: Cao Jin <caoj.fnst@cn.fujitsu.com> >Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> >--- > Documentation/filesystems/proc.txt | 11 ++++++++++- > 1 file changed, 10 insertions(+), 1 deletion(-) > >diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt >index 74329fd..71f5096 100644 >--- a/Documentation/filesystems/proc.txt >+++ b/Documentation/filesystems/proc.txt >@@ -1305,7 +1305,16 @@ second). The meanings of the columns are as follows, from left to right: > - nice: niced processes executing in user mode > - system: processes executing in kernel mode > - idle: twiddling thumbs >-- iowait: waiting for I/O to complete >+- iowait: In a word, iowait stands for waiting for I/O to complete. But there >+ are several problems: >+ 1. Cpu will not wait for I/O to complete, iowait is the time that a task is >+ waiting for I/O to complete. When cpu goes into idle state for >+ outstanding task io, another task will be scheduled on this CPU. >+ 2. In a multi-core CPU, the task waiting for I/O to complete is not running >+ on any CPU, so the iowait of each CPU is difficult to calculate. >+ 3. The value of iowait field in /proc/stat will decrease in certain >+ conditions. >+ So, the iowait is not reliable by reading from /proc/stat. > - irq: servicing interrupts > - softirq: servicing softirqs > - steal: involuntary wait >-- >2.7.4 > ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] Change the document about iowait 2016-10-26 2:41 [PATCH] Change the document about iowait Chao Fan 2016-11-09 1:33 ` Chao Fan @ 2016-11-13 15:47 ` Jonathan Corbet 2016-11-14 3:42 ` Chao Fan 1 sibling, 1 reply; 5+ messages in thread From: Jonathan Corbet @ 2016-11-13 15:47 UTC (permalink / raw) To: Chao Fan; +Cc: linux-doc, linux-kernel, peterz, akpm, izumi.taku, Cao Jin On Wed, 26 Oct 2016 10:41:28 +0800 Chao Fan <fanc.fnst@cn.fujitsu.com> wrote: > The iowait is not reliable by reading from /proc/stat, so this > method to get iowait is not suggested. And we mark it in the > document. Sorry for the delay on this. Life has been...challenging... > Signed-off-by: Cao Jin <caoj.fnst@cn.fujitsu.com> > Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> What does this signoff chain mean? > --- > Documentation/filesystems/proc.txt | 11 ++++++++++- > 1 file changed, 10 insertions(+), 1 deletion(-) > > diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt > index 74329fd..71f5096 100644 > --- a/Documentation/filesystems/proc.txt > +++ b/Documentation/filesystems/proc.txt > @@ -1305,7 +1305,16 @@ second). The meanings of the columns are as follows, from left to right: > - nice: niced processes executing in user mode > - system: processes executing in kernel mode > - idle: twiddling thumbs > -- iowait: waiting for I/O to complete > +- iowait: In a word, iowait stands for waiting for I/O to complete. But there > + are several problems: > + 1. Cpu will not wait for I/O to complete, iowait is the time that a task is > + waiting for I/O to complete. When cpu goes into idle state for > + outstanding task io, another task will be scheduled on this CPU. > + 2. In a multi-core CPU, the task waiting for I/O to complete is not running > + on any CPU, so the iowait of each CPU is difficult to calculate. > + 3. The value of iowait field in /proc/stat will decrease in certain > + conditions. > + So, the iowait is not reliable by reading from /proc/stat. > - irq: servicing interrupts So I suppose I can apply this. But is there any chance of making it say what iowait actually measures, rather than just saying that it's unreliable? Thanks, jon ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] Change the document about iowait 2016-11-13 15:47 ` Jonathan Corbet @ 2016-11-14 3:42 ` Chao Fan 2016-11-19 17:39 ` Jonathan Corbet 0 siblings, 1 reply; 5+ messages in thread From: Chao Fan @ 2016-11-14 3:42 UTC (permalink / raw) To: Jonathan Corbet Cc: linux-doc, linux-kernel, peterz, akpm, izumi.taku, Cao Jin On Sun, Nov 13, 2016 at 08:47:55AM -0700, Jonathan Corbet wrote: >On Wed, 26 Oct 2016 10:41:28 +0800 >Chao Fan <fanc.fnst@cn.fujitsu.com> wrote: > >> The iowait is not reliable by reading from /proc/stat, so this >> method to get iowait is not suggested. And we mark it in the >> document. > >Sorry for the delay on this. Life has been...challenging... > >> Signed-off-by: Cao Jin <caoj.fnst@cn.fujitsu.com> >> Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> > >What does this signoff chain mean? Hi jon, I made this patch. He is my colleague who helped me a lot on investigating why this value decrease, so I added his s-o-b. I didn't know how to put the position, but both of us are responsible for this patch. Should I change and resend it? > >> --- >> Documentation/filesystems/proc.txt | 11 ++++++++++- >> 1 file changed, 10 insertions(+), 1 deletion(-) >> >> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt >> index 74329fd..71f5096 100644 >> --- a/Documentation/filesystems/proc.txt >> +++ b/Documentation/filesystems/proc.txt >> @@ -1305,7 +1305,16 @@ second). The meanings of the columns are as follows, from left to right: >> - nice: niced processes executing in user mode >> - system: processes executing in kernel mode >> - idle: twiddling thumbs >> -- iowait: waiting for I/O to complete >> +- iowait: In a word, iowait stands for waiting for I/O to complete. But there >> + are several problems: >> + 1. Cpu will not wait for I/O to complete, iowait is the time that a task is >> + waiting for I/O to complete. When cpu goes into idle state for >> + outstanding task io, another task will be scheduled on this CPU. >> + 2. In a multi-core CPU, the task waiting for I/O to complete is not running >> + on any CPU, so the iowait of each CPU is difficult to calculate. >> + 3. The value of iowait field in /proc/stat will decrease in certain >> + conditions. >> + So, the iowait is not reliable by reading from /proc/stat. >> - irq: servicing interrupts > >So I suppose I can apply this. But is there any chance of making it say >what iowait actually measures, rather than just saying that it's >unreliable? Current iowait definition and way of accounting is legacy from UP era, it works well in UP era, but when step into SMP era, both definition and accounting way are not suitable, one example is when task migrating between CPUs. In SMP era, this value should be a global one, not per-cpu. So, it is hard to say what iowait actually measures, the current problem is: a appropriate definition (iowait in SMP) is not clear. Quote someone's words, its accounting is "a steaming pile of crap". Whether the explanation is OK? Thanks, Chao Fan > >Thanks, > >jon > > ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] Change the document about iowait 2016-11-14 3:42 ` Chao Fan @ 2016-11-19 17:39 ` Jonathan Corbet 0 siblings, 0 replies; 5+ messages in thread From: Jonathan Corbet @ 2016-11-19 17:39 UTC (permalink / raw) To: Chao Fan; +Cc: linux-doc, linux-kernel, peterz, akpm, izumi.taku, Cao Jin On Mon, 14 Nov 2016 11:42:41 +0800 Chao Fan <fanc.fnst@cn.fujitsu.com> wrote: > >Sorry for the delay on this. Life has been...challenging... > > > >> Signed-off-by: Cao Jin <caoj.fnst@cn.fujitsu.com> > >> Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> > > > >What does this signoff chain mean? > > Hi jon, > > I made this patch. He is my colleague who helped me a lot on > investigating why this value decrease, so I added his s-o-b. > I didn't know how to put the position, but both of us are > responsible for this patch. Should I change and resend it? The meaning of Signed-off-by is defined in the DOC, as seen in Documentation/submitting-patches.rst. In this case, the better approach would have been to credit Cao Jin in the changelog, since he didn't write the patch. For a little documentation tweak like this it's not that big a deal, though, so I simply gone ahead and applied it. Thanks, jon ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2016-11-19 17:39 UTC | newest] Thread overview: 5+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2016-10-26 2:41 [PATCH] Change the document about iowait Chao Fan 2016-11-09 1:33 ` Chao Fan 2016-11-13 15:47 ` Jonathan Corbet 2016-11-14 3:42 ` Chao Fan 2016-11-19 17:39 ` Jonathan Corbet
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).