Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Peter Zijlstra]

On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> OK.  We will try to improve on this side.  But it is not an easy task
> for us to provided easy to use simple binaries.  Do you think something
> like Docker image is easy to use?

Docker muck would just make me turn around and run.

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Peter Zijlstra]

On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> OK.  We will try to improve on this side.  But it is not an easy task
> for us to provided easy to use simple binaries.  Do you think something
> like Docker image is easy to use?

Docker muck would just make me turn around and run.

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Darren Hart  writes:

> On Tue, Mar 29, 2016 at 09:12:56AM +0800, Huang, Ying wrote:
>> Darren Hart  writes:
>> 
>> > On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
>> >> Thomas Gleixner  writes:
>> >> 
>> >> > On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >> >> >  FYI, we noticed 25.6% performance improvement due to commit
>> >> >> >
>> >> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> >> >> > get_futex_key()"
>> >> >> >
>> >> >> >  in the will-it-scale.per_process_ops test.
>> >> >> >
>> >> >> >  will-it-scale.per_process_ops tests the futex operations for 
>> >> >> > process shared
>> >> >> >  futexes (Or whatever that test really does).
>> >> >> 
>> >> >> There is a futex sub test case for will-it-scale test suite.  But I 
>> >> >> got your
>> >> >> point, we need some description for the test case.  If email is not too
>> >> >> limited for the full description, we will put it in some web site and
>> >> >> include short description and link to the full description in email.
>> >> >
>> >> > Ok. Just make sure the short description gives enough information for 
>> >> > the
>> >> > casual reader.
>> >> >  
>> >> >> >  The commit has no significant impact on any other test in the test 
>> >> >> > suite.
>> >> >> 
>> >> >> Sorry, we have no enough machine power to test all test cases for each
>> >> >> bisect result.  So we will have no such information until we find a way
>> >> >> to do that.
>> >> >
>> >> > Well, then I really have to ask how I should interpret the data here:
>> >> >
>> >> >5076304 .  0% +25.6%6374220 .  0%  
>> >> > will-it-scale.per_process_ops
>> >> >
>> >> >^^^ That's the reason why you sent the mail in the first place
>> >> >
>> >> >1194117 .  0% +14.4%1366153 .  1%  
>> >> > will-it-scale.per_thread_ops
>> >> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>> >> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>> >> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>> >> >   2848 . 32%+141.2%   6870 . 65%  
>> >> > numa-meminfo.node1.Active(anon)
>> >> >   2832 . 31% +57.6%   4465 . 27%  
>> >> > numa-meminfo.node1.AnonPages
>> >> >  15018 . 12% -23.3%  11515 . 15%  
>> >> > numa-meminfo.node2.AnonPages
>> >> >   1214 . 14% -22.8% 936.75 . 20%  
>> >> > numa-meminfo.node3.PageTables
>> >> > 712.25 . 32%+141.2%   1718 . 65%  
>> >> > numa-vmstat.node1.nr_active_anon
>> >> > 708.25 . 31% +57.7%   1116 . 27%  
>> >> > numa-vmstat.node1.nr_anon_pages
>> >> >
>> >> > How is this related and what should I do about this information? 
>> >> 
>> >> For each will-it-scale sub test case, it will be run in both process
>> >> mode and thread mode, and task number will change from 1 to CPU number.
>> >> will-it-scale.per_thread_ops shows thread mode main result.
>> >> will-it-scale.scalability is calculated to measure how per_process_ops
>> >> and per_thread_ops scaled along with the task number.  These are default
>> >> behavior of will-it-scale test suite.
>> >> 
>> >> Others are monitors output.  That is, other information collected during
>> >> test.  For example, meminfo is a monitor to sampling /proc/meminfo
>> >> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
>> >> the average value of AnonHugePages line of /proc/meminfo.  Similarly
>> >> vmstat.system.cs is the average value of cs column of system column
>> >> group of /usr/bin/vmstat.
>> >> 
>> >> We hope these information are helpful for root causing the regression.
>> >> 
>> >> >  If it's important then I have to admit, that I fail to understand why.
>> >> >
>> >> >  If it's not important then I have to ask why is this included.
>> >> >
>> >> >> > So that allows me to reproduce that test more or less with no 
>> >> >> > effort. And
>> >> >> > that's the really important part.
>> >> >> 
>> >> >> For reproducing, now we use lkp-tests tool, which includes scripts to
>> >> >> build the test case, run the test, collect various information, compare
>> >> >> the test result, with the job file attached with the report email.  
>> >> >> That
>> >> >> is not the easiest way, we will continuously improve it.
>> >> >
>> >> > I know and lkp-tests is a pain to work with. So please look into a way 
>> >> > to
>> >> > extract the relevant binaries, so it's simple for developers to 
>> >> > reproduce.
>> >> 
>> >> OK.  We will try to improve on this side.  But it is not an easy task
>> >> for us to provided easy to use simple binaries.  Do you think something
>> >> like Docker image is easy to use?
>> >
>> > Thomas, I presume you are interested in binaries to be positive we're
>> > reproducing with exactly the same bits? I agree that's good to have. I'd 
>> > also
>> > want to have or be pointed to the sources with a straight forward way to
>> > rebuild and to inspect 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Darren Hart  writes:

> On Tue, Mar 29, 2016 at 09:12:56AM +0800, Huang, Ying wrote:
>> Darren Hart  writes:
>> 
>> > On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
>> >> Thomas Gleixner  writes:
>> >> 
>> >> > On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >> >> >  FYI, we noticed 25.6% performance improvement due to commit
>> >> >> >
>> >> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> >> >> > get_futex_key()"
>> >> >> >
>> >> >> >  in the will-it-scale.per_process_ops test.
>> >> >> >
>> >> >> >  will-it-scale.per_process_ops tests the futex operations for 
>> >> >> > process shared
>> >> >> >  futexes (Or whatever that test really does).
>> >> >> 
>> >> >> There is a futex sub test case for will-it-scale test suite.  But I 
>> >> >> got your
>> >> >> point, we need some description for the test case.  If email is not too
>> >> >> limited for the full description, we will put it in some web site and
>> >> >> include short description and link to the full description in email.
>> >> >
>> >> > Ok. Just make sure the short description gives enough information for 
>> >> > the
>> >> > casual reader.
>> >> >  
>> >> >> >  The commit has no significant impact on any other test in the test 
>> >> >> > suite.
>> >> >> 
>> >> >> Sorry, we have no enough machine power to test all test cases for each
>> >> >> bisect result.  So we will have no such information until we find a way
>> >> >> to do that.
>> >> >
>> >> > Well, then I really have to ask how I should interpret the data here:
>> >> >
>> >> >5076304 .  0% +25.6%6374220 .  0%  
>> >> > will-it-scale.per_process_ops
>> >> >
>> >> >^^^ That's the reason why you sent the mail in the first place
>> >> >
>> >> >1194117 .  0% +14.4%1366153 .  1%  
>> >> > will-it-scale.per_thread_ops
>> >> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>> >> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>> >> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>> >> >   2848 . 32%+141.2%   6870 . 65%  
>> >> > numa-meminfo.node1.Active(anon)
>> >> >   2832 . 31% +57.6%   4465 . 27%  
>> >> > numa-meminfo.node1.AnonPages
>> >> >  15018 . 12% -23.3%  11515 . 15%  
>> >> > numa-meminfo.node2.AnonPages
>> >> >   1214 . 14% -22.8% 936.75 . 20%  
>> >> > numa-meminfo.node3.PageTables
>> >> > 712.25 . 32%+141.2%   1718 . 65%  
>> >> > numa-vmstat.node1.nr_active_anon
>> >> > 708.25 . 31% +57.7%   1116 . 27%  
>> >> > numa-vmstat.node1.nr_anon_pages
>> >> >
>> >> > How is this related and what should I do about this information? 
>> >> 
>> >> For each will-it-scale sub test case, it will be run in both process
>> >> mode and thread mode, and task number will change from 1 to CPU number.
>> >> will-it-scale.per_thread_ops shows thread mode main result.
>> >> will-it-scale.scalability is calculated to measure how per_process_ops
>> >> and per_thread_ops scaled along with the task number.  These are default
>> >> behavior of will-it-scale test suite.
>> >> 
>> >> Others are monitors output.  That is, other information collected during
>> >> test.  For example, meminfo is a monitor to sampling /proc/meminfo
>> >> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
>> >> the average value of AnonHugePages line of /proc/meminfo.  Similarly
>> >> vmstat.system.cs is the average value of cs column of system column
>> >> group of /usr/bin/vmstat.
>> >> 
>> >> We hope these information are helpful for root causing the regression.
>> >> 
>> >> >  If it's important then I have to admit, that I fail to understand why.
>> >> >
>> >> >  If it's not important then I have to ask why is this included.
>> >> >
>> >> >> > So that allows me to reproduce that test more or less with no 
>> >> >> > effort. And
>> >> >> > that's the really important part.
>> >> >> 
>> >> >> For reproducing, now we use lkp-tests tool, which includes scripts to
>> >> >> build the test case, run the test, collect various information, compare
>> >> >> the test result, with the job file attached with the report email.  
>> >> >> That
>> >> >> is not the easiest way, we will continuously improve it.
>> >> >
>> >> > I know and lkp-tests is a pain to work with. So please look into a way 
>> >> > to
>> >> > extract the relevant binaries, so it's simple for developers to 
>> >> > reproduce.
>> >> 
>> >> OK.  We will try to improve on this side.  But it is not an easy task
>> >> for us to provided easy to use simple binaries.  Do you think something
>> >> like Docker image is easy to use?
>> >
>> > Thomas, I presume you are interested in binaries to be positive we're
>> > reproducing with exactly the same bits? I agree that's good to have. I'd 
>> > also
>> > want to have or be pointed to the sources with a straight forward way to
>> > rebuild and to inspect what exactly the test is doing. (I assume this is
>> > implied, but 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Darren Hart]

On Tue, Mar 29, 2016 at 09:12:56AM +0800, Huang, Ying wrote:
> Darren Hart  writes:
> 
> > On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> >> Thomas Gleixner  writes:
> >> 
> >> > On Mon, 21 Mar 2016, Huang, Ying wrote:
> >> >> >  FYI, we noticed 25.6% performance improvement due to commit
> >> >> >
> >> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> >> >> > get_futex_key()"
> >> >> >
> >> >> >  in the will-it-scale.per_process_ops test.
> >> >> >
> >> >> >  will-it-scale.per_process_ops tests the futex operations for process 
> >> >> > shared
> >> >> >  futexes (Or whatever that test really does).
> >> >> 
> >> >> There is a futex sub test case for will-it-scale test suite.  But I got 
> >> >> your
> >> >> point, we need some description for the test case.  If email is not too
> >> >> limited for the full description, we will put it in some web site and
> >> >> include short description and link to the full description in email.
> >> >
> >> > Ok. Just make sure the short description gives enough information for the
> >> > casual reader.
> >> >  
> >> >> >  The commit has no significant impact on any other test in the test 
> >> >> > suite.
> >> >> 
> >> >> Sorry, we have no enough machine power to test all test cases for each
> >> >> bisect result.  So we will have no such information until we find a way
> >> >> to do that.
> >> >
> >> > Well, then I really have to ask how I should interpret the data here:
> >> >
> >> >5076304 .  0% +25.6%6374220 .  0%  
> >> > will-it-scale.per_process_ops
> >> >
> >> >^^^ That's the reason why you sent the mail in the first place
> >> >
> >> >1194117 .  0% +14.4%1366153 .  1%  
> >> > will-it-scale.per_thread_ops
> >> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
> >> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
> >> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
> >> >   2848 . 32%+141.2%   6870 . 65%  
> >> > numa-meminfo.node1.Active(anon)
> >> >   2832 . 31% +57.6%   4465 . 27%  
> >> > numa-meminfo.node1.AnonPages
> >> >  15018 . 12% -23.3%  11515 . 15%  
> >> > numa-meminfo.node2.AnonPages
> >> >   1214 . 14% -22.8% 936.75 . 20%  
> >> > numa-meminfo.node3.PageTables
> >> > 712.25 . 32%+141.2%   1718 . 65%  
> >> > numa-vmstat.node1.nr_active_anon
> >> > 708.25 . 31% +57.7%   1116 . 27%  
> >> > numa-vmstat.node1.nr_anon_pages
> >> >
> >> > How is this related and what should I do about this information? 
> >> 
> >> For each will-it-scale sub test case, it will be run in both process
> >> mode and thread mode, and task number will change from 1 to CPU number.
> >> will-it-scale.per_thread_ops shows thread mode main result.
> >> will-it-scale.scalability is calculated to measure how per_process_ops
> >> and per_thread_ops scaled along with the task number.  These are default
> >> behavior of will-it-scale test suite.
> >> 
> >> Others are monitors output.  That is, other information collected during
> >> test.  For example, meminfo is a monitor to sampling /proc/meminfo
> >> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
> >> the average value of AnonHugePages line of /proc/meminfo.  Similarly
> >> vmstat.system.cs is the average value of cs column of system column
> >> group of /usr/bin/vmstat.
> >> 
> >> We hope these information are helpful for root causing the regression.
> >> 
> >> >  If it's important then I have to admit, that I fail to understand why.
> >> >
> >> >  If it's not important then I have to ask why is this included.
> >> >
> >> >> > So that allows me to reproduce that test more or less with no effort. 
> >> >> > And
> >> >> > that's the really important part.
> >> >> 
> >> >> For reproducing, now we use lkp-tests tool, which includes scripts to
> >> >> build the test case, run the test, collect various information, compare
> >> >> the test result, with the job file attached with the report email.  That
> >> >> is not the easiest way, we will continuously improve it.
> >> >
> >> > I know and lkp-tests is a pain to work with. So please look into a way to
> >> > extract the relevant binaries, so it's simple for developers to 
> >> > reproduce.
> >> 
> >> OK.  We will try to improve on this side.  But it is not an easy task
> >> for us to provided easy to use simple binaries.  Do you think something
> >> like Docker image is easy to use?
> >
> > Thomas, I presume you are interested in binaries to be positive we're
> > reproducing with exactly the same bits? I agree that's good to have. I'd 
> > also
> > want to have or be pointed to the sources with a straight forward way to
> > rebuild and to inspect what exactly the test is doing. (I assume this is
> > implied, but just to make sure it's stated).
> 
> lkp-tests has the scripts to download the source, apply some patch, and
> 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Darren Hart]

On Tue, Mar 29, 2016 at 09:12:56AM +0800, Huang, Ying wrote:
> Darren Hart  writes:
> 
> > On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> >> Thomas Gleixner  writes:
> >> 
> >> > On Mon, 21 Mar 2016, Huang, Ying wrote:
> >> >> >  FYI, we noticed 25.6% performance improvement due to commit
> >> >> >
> >> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> >> >> > get_futex_key()"
> >> >> >
> >> >> >  in the will-it-scale.per_process_ops test.
> >> >> >
> >> >> >  will-it-scale.per_process_ops tests the futex operations for process 
> >> >> > shared
> >> >> >  futexes (Or whatever that test really does).
> >> >> 
> >> >> There is a futex sub test case for will-it-scale test suite.  But I got 
> >> >> your
> >> >> point, we need some description for the test case.  If email is not too
> >> >> limited for the full description, we will put it in some web site and
> >> >> include short description and link to the full description in email.
> >> >
> >> > Ok. Just make sure the short description gives enough information for the
> >> > casual reader.
> >> >  
> >> >> >  The commit has no significant impact on any other test in the test 
> >> >> > suite.
> >> >> 
> >> >> Sorry, we have no enough machine power to test all test cases for each
> >> >> bisect result.  So we will have no such information until we find a way
> >> >> to do that.
> >> >
> >> > Well, then I really have to ask how I should interpret the data here:
> >> >
> >> >5076304 .  0% +25.6%6374220 .  0%  
> >> > will-it-scale.per_process_ops
> >> >
> >> >^^^ That's the reason why you sent the mail in the first place
> >> >
> >> >1194117 .  0% +14.4%1366153 .  1%  
> >> > will-it-scale.per_thread_ops
> >> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
> >> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
> >> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
> >> >   2848 . 32%+141.2%   6870 . 65%  
> >> > numa-meminfo.node1.Active(anon)
> >> >   2832 . 31% +57.6%   4465 . 27%  
> >> > numa-meminfo.node1.AnonPages
> >> >  15018 . 12% -23.3%  11515 . 15%  
> >> > numa-meminfo.node2.AnonPages
> >> >   1214 . 14% -22.8% 936.75 . 20%  
> >> > numa-meminfo.node3.PageTables
> >> > 712.25 . 32%+141.2%   1718 . 65%  
> >> > numa-vmstat.node1.nr_active_anon
> >> > 708.25 . 31% +57.7%   1116 . 27%  
> >> > numa-vmstat.node1.nr_anon_pages
> >> >
> >> > How is this related and what should I do about this information? 
> >> 
> >> For each will-it-scale sub test case, it will be run in both process
> >> mode and thread mode, and task number will change from 1 to CPU number.
> >> will-it-scale.per_thread_ops shows thread mode main result.
> >> will-it-scale.scalability is calculated to measure how per_process_ops
> >> and per_thread_ops scaled along with the task number.  These are default
> >> behavior of will-it-scale test suite.
> >> 
> >> Others are monitors output.  That is, other information collected during
> >> test.  For example, meminfo is a monitor to sampling /proc/meminfo
> >> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
> >> the average value of AnonHugePages line of /proc/meminfo.  Similarly
> >> vmstat.system.cs is the average value of cs column of system column
> >> group of /usr/bin/vmstat.
> >> 
> >> We hope these information are helpful for root causing the regression.
> >> 
> >> >  If it's important then I have to admit, that I fail to understand why.
> >> >
> >> >  If it's not important then I have to ask why is this included.
> >> >
> >> >> > So that allows me to reproduce that test more or less with no effort. 
> >> >> > And
> >> >> > that's the really important part.
> >> >> 
> >> >> For reproducing, now we use lkp-tests tool, which includes scripts to
> >> >> build the test case, run the test, collect various information, compare
> >> >> the test result, with the job file attached with the report email.  That
> >> >> is not the easiest way, we will continuously improve it.
> >> >
> >> > I know and lkp-tests is a pain to work with. So please look into a way to
> >> > extract the relevant binaries, so it's simple for developers to 
> >> > reproduce.
> >> 
> >> OK.  We will try to improve on this side.  But it is not an easy task
> >> for us to provided easy to use simple binaries.  Do you think something
> >> like Docker image is easy to use?
> >
> > Thomas, I presume you are interested in binaries to be positive we're
> > reproducing with exactly the same bits? I agree that's good to have. I'd 
> > also
> > want to have or be pointed to the sources with a straight forward way to
> > rebuild and to inspect what exactly the test is doing. (I assume this is
> > implied, but just to make sure it's stated).
> 
> lkp-tests has the scripts to download the source, apply some patch, and
> build the binary.  It is not a very 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Darren Hart  writes:

> On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
>> Thomas Gleixner  writes:
>> 
>> > On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >> >  FYI, we noticed 25.6% performance improvement due to commit
>> >> >
>> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> >> > get_futex_key()"
>> >> >
>> >> >  in the will-it-scale.per_process_ops test.
>> >> >
>> >> >  will-it-scale.per_process_ops tests the futex operations for process 
>> >> > shared
>> >> >  futexes (Or whatever that test really does).
>> >> 
>> >> There is a futex sub test case for will-it-scale test suite.  But I got 
>> >> your
>> >> point, we need some description for the test case.  If email is not too
>> >> limited for the full description, we will put it in some web site and
>> >> include short description and link to the full description in email.
>> >
>> > Ok. Just make sure the short description gives enough information for the
>> > casual reader.
>> >  
>> >> >  The commit has no significant impact on any other test in the test 
>> >> > suite.
>> >> 
>> >> Sorry, we have no enough machine power to test all test cases for each
>> >> bisect result.  So we will have no such information until we find a way
>> >> to do that.
>> >
>> > Well, then I really have to ask how I should interpret the data here:
>> >
>> >5076304 .  0% +25.6%6374220 .  0%  will-it-scale.per_process_ops
>> >
>> >^^^ That's the reason why you sent the mail in the first place
>> >
>> >1194117 .  0% +14.4%1366153 .  1%  will-it-scale.per_thread_ops
>> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>> >   2848 . 32%+141.2%   6870 . 65%  
>> > numa-meminfo.node1.Active(anon)
>> >   2832 . 31% +57.6%   4465 . 27%  numa-meminfo.node1.AnonPages
>> >  15018 . 12% -23.3%  11515 . 15%  numa-meminfo.node2.AnonPages
>> >   1214 . 14% -22.8% 936.75 . 20%  numa-meminfo.node3.PageTables
>> > 712.25 . 32%+141.2%   1718 . 65%  
>> > numa-vmstat.node1.nr_active_anon
>> > 708.25 . 31% +57.7%   1116 . 27%  
>> > numa-vmstat.node1.nr_anon_pages
>> >
>> > How is this related and what should I do about this information? 
>> 
>> For each will-it-scale sub test case, it will be run in both process
>> mode and thread mode, and task number will change from 1 to CPU number.
>> will-it-scale.per_thread_ops shows thread mode main result.
>> will-it-scale.scalability is calculated to measure how per_process_ops
>> and per_thread_ops scaled along with the task number.  These are default
>> behavior of will-it-scale test suite.
>> 
>> Others are monitors output.  That is, other information collected during
>> test.  For example, meminfo is a monitor to sampling /proc/meminfo
>> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
>> the average value of AnonHugePages line of /proc/meminfo.  Similarly
>> vmstat.system.cs is the average value of cs column of system column
>> group of /usr/bin/vmstat.
>> 
>> We hope these information are helpful for root causing the regression.
>> 
>> >  If it's important then I have to admit, that I fail to understand why.
>> >
>> >  If it's not important then I have to ask why is this included.
>> >
>> >> > So that allows me to reproduce that test more or less with no effort. 
>> >> > And
>> >> > that's the really important part.
>> >> 
>> >> For reproducing, now we use lkp-tests tool, which includes scripts to
>> >> build the test case, run the test, collect various information, compare
>> >> the test result, with the job file attached with the report email.  That
>> >> is not the easiest way, we will continuously improve it.
>> >
>> > I know and lkp-tests is a pain to work with. So please look into a way to
>> > extract the relevant binaries, so it's simple for developers to reproduce.
>> 
>> OK.  We will try to improve on this side.  But it is not an easy task
>> for us to provided easy to use simple binaries.  Do you think something
>> like Docker image is easy to use?
>
> Thomas, I presume you are interested in binaries to be positive we're
> reproducing with exactly the same bits? I agree that's good to have. I'd also
> want to have or be pointed to the sources with a straight forward way to
> rebuild and to inspect what exactly the test is doing. (I assume this is
> implied, but just to make sure it's stated).

lkp-tests has the scripts to download the source, apply some patch, and
build the binary.  It is not a very straight forward way, but the script
is quite simple.

> Huang, what makes the binaries difficult to package? And how would docker make
> that any simpler?

The binaries is not difficult to package.  But the test is not only
benchmark binary.  We may do some setup for the 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Darren Hart  writes:

> On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
>> Thomas Gleixner  writes:
>> 
>> > On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >> >  FYI, we noticed 25.6% performance improvement due to commit
>> >> >
>> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> >> > get_futex_key()"
>> >> >
>> >> >  in the will-it-scale.per_process_ops test.
>> >> >
>> >> >  will-it-scale.per_process_ops tests the futex operations for process 
>> >> > shared
>> >> >  futexes (Or whatever that test really does).
>> >> 
>> >> There is a futex sub test case for will-it-scale test suite.  But I got 
>> >> your
>> >> point, we need some description for the test case.  If email is not too
>> >> limited for the full description, we will put it in some web site and
>> >> include short description and link to the full description in email.
>> >
>> > Ok. Just make sure the short description gives enough information for the
>> > casual reader.
>> >  
>> >> >  The commit has no significant impact on any other test in the test 
>> >> > suite.
>> >> 
>> >> Sorry, we have no enough machine power to test all test cases for each
>> >> bisect result.  So we will have no such information until we find a way
>> >> to do that.
>> >
>> > Well, then I really have to ask how I should interpret the data here:
>> >
>> >5076304 .  0% +25.6%6374220 .  0%  will-it-scale.per_process_ops
>> >
>> >^^^ That's the reason why you sent the mail in the first place
>> >
>> >1194117 .  0% +14.4%1366153 .  1%  will-it-scale.per_thread_ops
>> >   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>> >   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>> >   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>> >   2848 . 32%+141.2%   6870 . 65%  
>> > numa-meminfo.node1.Active(anon)
>> >   2832 . 31% +57.6%   4465 . 27%  numa-meminfo.node1.AnonPages
>> >  15018 . 12% -23.3%  11515 . 15%  numa-meminfo.node2.AnonPages
>> >   1214 . 14% -22.8% 936.75 . 20%  numa-meminfo.node3.PageTables
>> > 712.25 . 32%+141.2%   1718 . 65%  
>> > numa-vmstat.node1.nr_active_anon
>> > 708.25 . 31% +57.7%   1116 . 27%  
>> > numa-vmstat.node1.nr_anon_pages
>> >
>> > How is this related and what should I do about this information? 
>> 
>> For each will-it-scale sub test case, it will be run in both process
>> mode and thread mode, and task number will change from 1 to CPU number.
>> will-it-scale.per_thread_ops shows thread mode main result.
>> will-it-scale.scalability is calculated to measure how per_process_ops
>> and per_thread_ops scaled along with the task number.  These are default
>> behavior of will-it-scale test suite.
>> 
>> Others are monitors output.  That is, other information collected during
>> test.  For example, meminfo is a monitor to sampling /proc/meminfo
>> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
>> the average value of AnonHugePages line of /proc/meminfo.  Similarly
>> vmstat.system.cs is the average value of cs column of system column
>> group of /usr/bin/vmstat.
>> 
>> We hope these information are helpful for root causing the regression.
>> 
>> >  If it's important then I have to admit, that I fail to understand why.
>> >
>> >  If it's not important then I have to ask why is this included.
>> >
>> >> > So that allows me to reproduce that test more or less with no effort. 
>> >> > And
>> >> > that's the really important part.
>> >> 
>> >> For reproducing, now we use lkp-tests tool, which includes scripts to
>> >> build the test case, run the test, collect various information, compare
>> >> the test result, with the job file attached with the report email.  That
>> >> is not the easiest way, we will continuously improve it.
>> >
>> > I know and lkp-tests is a pain to work with. So please look into a way to
>> > extract the relevant binaries, so it's simple for developers to reproduce.
>> 
>> OK.  We will try to improve on this side.  But it is not an easy task
>> for us to provided easy to use simple binaries.  Do you think something
>> like Docker image is easy to use?
>
> Thomas, I presume you are interested in binaries to be positive we're
> reproducing with exactly the same bits? I agree that's good to have. I'd also
> want to have or be pointed to the sources with a straight forward way to
> rebuild and to inspect what exactly the test is doing. (I assume this is
> implied, but just to make sure it's stated).

lkp-tests has the scripts to download the source, apply some patch, and
build the binary.  It is not a very straight forward way, but the script
is quite simple.

> Huang, what makes the binaries difficult to package? And how would docker make
> that any simpler?

The binaries is not difficult to package.  But the test is not only
benchmark binary.  We may do some setup for the specific test, for
example, change the cpu 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Darren Hart]

On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> Thomas Gleixner  writes:
> 
> > On Mon, 21 Mar 2016, Huang, Ying wrote:
> >> >  FYI, we noticed 25.6% performance improvement due to commit
> >> >
> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> >> > get_futex_key()"
> >> >
> >> >  in the will-it-scale.per_process_ops test.
> >> >
> >> >  will-it-scale.per_process_ops tests the futex operations for process 
> >> > shared
> >> >  futexes (Or whatever that test really does).
> >> 
> >> There is a futex sub test case for will-it-scale test suite.  But I got 
> >> your
> >> point, we need some description for the test case.  If email is not too
> >> limited for the full description, we will put it in some web site and
> >> include short description and link to the full description in email.
> >
> > Ok. Just make sure the short description gives enough information for the
> > casual reader.
> >  
> >> >  The commit has no significant impact on any other test in the test 
> >> > suite.
> >> 
> >> Sorry, we have no enough machine power to test all test cases for each
> >> bisect result.  So we will have no such information until we find a way
> >> to do that.
> >
> > Well, then I really have to ask how I should interpret the data here:
> >
> >5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops
> >
> >^^^ That's the reason why you sent the mail in the first place
> >
> >1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
> >   0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
> >   6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
> >   2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
> >   2848 ± 32%+141.2%   6870 ± 65%  
> > numa-meminfo.node1.Active(anon)
> >   2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
> >  15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
> >   1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
> > 712.25 ± 32%+141.2%   1718 ± 65%  
> > numa-vmstat.node1.nr_active_anon
> > 708.25 ± 31% +57.7%   1116 ± 27%  
> > numa-vmstat.node1.nr_anon_pages
> >
> > How is this related and what should I do about this information? 
> 
> For each will-it-scale sub test case, it will be run in both process
> mode and thread mode, and task number will change from 1 to CPU number.
> will-it-scale.per_thread_ops shows thread mode main result.
> will-it-scale.scalability is calculated to measure how per_process_ops
> and per_thread_ops scaled along with the task number.  These are default
> behavior of will-it-scale test suite.
> 
> Others are monitors output.  That is, other information collected during
> test.  For example, meminfo is a monitor to sampling /proc/meminfo
> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
> the average value of AnonHugePages line of /proc/meminfo.  Similarly
> vmstat.system.cs is the average value of cs column of system column
> group of /usr/bin/vmstat.
> 
> We hope these information are helpful for root causing the regression.
> 
> >  If it's important then I have to admit, that I fail to understand why.
> >
> >  If it's not important then I have to ask why is this included.
> >
> >> > So that allows me to reproduce that test more or less with no effort. And
> >> > that's the really important part.
> >> 
> >> For reproducing, now we use lkp-tests tool, which includes scripts to
> >> build the test case, run the test, collect various information, compare
> >> the test result, with the job file attached with the report email.  That
> >> is not the easiest way, we will continuously improve it.
> >
> > I know and lkp-tests is a pain to work with. So please look into a way to
> > extract the relevant binaries, so it's simple for developers to reproduce.
> 
> OK.  We will try to improve on this side.  But it is not an easy task
> for us to provided easy to use simple binaries.  Do you think something
> like Docker image is easy to use?

Thomas, I presume you are interested in binaries to be positive we're
reproducing with exactly the same bits? I agree that's good to have. I'd also
want to have or be pointed to the sources with a straight forward way to
rebuild and to inspect what exactly the test is doing. (I assume this is
implied, but just to make sure it's stated).

Huang, what makes the binaries difficult to package? And how would docker make
that any simpler?

> 
> >> > You can provide nice charts and full comparison tables for all tests on 
> >> > a web
> >> > site for those who are interested in large stats and pretty charts.
> >> >
> >> > Full results: http://wherever.you.store/your/results/test-nr/results
> >> 
> >> Before we have a website for detailed information, we will still put
> >> some details into report email.
> >
> > Ok, but please make them understandable for mere mortals.

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Darren Hart]

On Mon, Mar 21, 2016 at 04:42:47PM +0800, Huang, Ying wrote:
> Thomas Gleixner  writes:
> 
> > On Mon, 21 Mar 2016, Huang, Ying wrote:
> >> >  FYI, we noticed 25.6% performance improvement due to commit
> >> >
> >> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> >> > get_futex_key()"
> >> >
> >> >  in the will-it-scale.per_process_ops test.
> >> >
> >> >  will-it-scale.per_process_ops tests the futex operations for process 
> >> > shared
> >> >  futexes (Or whatever that test really does).
> >> 
> >> There is a futex sub test case for will-it-scale test suite.  But I got 
> >> your
> >> point, we need some description for the test case.  If email is not too
> >> limited for the full description, we will put it in some web site and
> >> include short description and link to the full description in email.
> >
> > Ok. Just make sure the short description gives enough information for the
> > casual reader.
> >  
> >> >  The commit has no significant impact on any other test in the test 
> >> > suite.
> >> 
> >> Sorry, we have no enough machine power to test all test cases for each
> >> bisect result.  So we will have no such information until we find a way
> >> to do that.
> >
> > Well, then I really have to ask how I should interpret the data here:
> >
> >5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops
> >
> >^^^ That's the reason why you sent the mail in the first place
> >
> >1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
> >   0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
> >   6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
> >   2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
> >   2848 ± 32%+141.2%   6870 ± 65%  
> > numa-meminfo.node1.Active(anon)
> >   2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
> >  15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
> >   1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
> > 712.25 ± 32%+141.2%   1718 ± 65%  
> > numa-vmstat.node1.nr_active_anon
> > 708.25 ± 31% +57.7%   1116 ± 27%  
> > numa-vmstat.node1.nr_anon_pages
> >
> > How is this related and what should I do about this information? 
> 
> For each will-it-scale sub test case, it will be run in both process
> mode and thread mode, and task number will change from 1 to CPU number.
> will-it-scale.per_thread_ops shows thread mode main result.
> will-it-scale.scalability is calculated to measure how per_process_ops
> and per_thread_ops scaled along with the task number.  These are default
> behavior of will-it-scale test suite.
> 
> Others are monitors output.  That is, other information collected during
> test.  For example, meminfo is a monitor to sampling /proc/meminfo
> contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
> the average value of AnonHugePages line of /proc/meminfo.  Similarly
> vmstat.system.cs is the average value of cs column of system column
> group of /usr/bin/vmstat.
> 
> We hope these information are helpful for root causing the regression.
> 
> >  If it's important then I have to admit, that I fail to understand why.
> >
> >  If it's not important then I have to ask why is this included.
> >
> >> > So that allows me to reproduce that test more or less with no effort. And
> >> > that's the really important part.
> >> 
> >> For reproducing, now we use lkp-tests tool, which includes scripts to
> >> build the test case, run the test, collect various information, compare
> >> the test result, with the job file attached with the report email.  That
> >> is not the easiest way, we will continuously improve it.
> >
> > I know and lkp-tests is a pain to work with. So please look into a way to
> > extract the relevant binaries, so it's simple for developers to reproduce.
> 
> OK.  We will try to improve on this side.  But it is not an easy task
> for us to provided easy to use simple binaries.  Do you think something
> like Docker image is easy to use?

Thomas, I presume you are interested in binaries to be positive we're
reproducing with exactly the same bits? I agree that's good to have. I'd also
want to have or be pointed to the sources with a straight forward way to
rebuild and to inspect what exactly the test is doing. (I assume this is
implied, but just to make sure it's stated).

Huang, what makes the binaries difficult to package? And how would docker make
that any simpler?

> 
> >> > You can provide nice charts and full comparison tables for all tests on 
> >> > a web
> >> > site for those who are interested in large stats and pretty charts.
> >> >
> >> > Full results: http://wherever.you.store/your/results/test-nr/results
> >> 
> >> Before we have a website for detailed information, we will still put
> >> some details into report email.
> >
> > Ok, but please make them understandable for mere mortals.

Thanks for speaking 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Thomas Gleixner  writes:

> On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >  FYI, we noticed 25.6% performance improvement due to commit
>> >
>> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> > get_futex_key()"
>> >
>> >  in the will-it-scale.per_process_ops test.
>> >
>> >  will-it-scale.per_process_ops tests the futex operations for process 
>> > shared
>> >  futexes (Or whatever that test really does).
>> 
>> There is a futex sub test case for will-it-scale test suite.  But I got your
>> point, we need some description for the test case.  If email is not too
>> limited for the full description, we will put it in some web site and
>> include short description and link to the full description in email.
>
> Ok. Just make sure the short description gives enough information for the
> casual reader.
>  
>> >  The commit has no significant impact on any other test in the test suite.
>> 
>> Sorry, we have no enough machine power to test all test cases for each
>> bisect result.  So we will have no such information until we find a way
>> to do that.
>
> Well, then I really have to ask how I should interpret the data here:
>
>5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops
>
>^^^ That's the reason why you sent the mail in the first place
>
>1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
>   0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
>   6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
>   2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
>   2848 ± 32%+141.2%   6870 ± 65%  numa-meminfo.node1.Active(anon)
>   2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
>  15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
>   1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
> 712.25 ± 32%+141.2%   1718 ± 65%  numa-vmstat.node1.nr_active_anon
> 708.25 ± 31% +57.7%   1116 ± 27%  numa-vmstat.node1.nr_anon_pages
>
> How is this related and what should I do about this information? 

For each will-it-scale sub test case, it will be run in both process
mode and thread mode, and task number will change from 1 to CPU number.
will-it-scale.per_thread_ops shows thread mode main result.
will-it-scale.scalability is calculated to measure how per_process_ops
and per_thread_ops scaled along with the task number.  These are default
behavior of will-it-scale test suite.

Others are monitors output.  That is, other information collected during
test.  For example, meminfo is a monitor to sampling /proc/meminfo
contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
the average value of AnonHugePages line of /proc/meminfo.  Similarly
vmstat.system.cs is the average value of cs column of system column
group of /usr/bin/vmstat.

We hope these information are helpful for root causing the regression.

>  If it's important then I have to admit, that I fail to understand why.
>
>  If it's not important then I have to ask why is this included.
>
>> > So that allows me to reproduce that test more or less with no effort. And
>> > that's the really important part.
>> 
>> For reproducing, now we use lkp-tests tool, which includes scripts to
>> build the test case, run the test, collect various information, compare
>> the test result, with the job file attached with the report email.  That
>> is not the easiest way, we will continuously improve it.
>
> I know and lkp-tests is a pain to work with. So please look into a way to
> extract the relevant binaries, so it's simple for developers to reproduce.

OK.  We will try to improve on this side.  But it is not an easy task
for us to provided easy to use simple binaries.  Do you think something
like Docker image is easy to use?

>> > You can provide nice charts and full comparison tables for all tests on a 
>> > web
>> > site for those who are interested in large stats and pretty charts.
>> >
>> > Full results: http://wherever.you.store/your/results/test-nr/results
>> 
>> Before we have a website for detailed information, we will still put
>> some details into report email.
>
> Ok, but please make them understandable for mere mortals.

Sure.

Best Regards,
Huang, Ying

> Thanks,
>
>   tglx

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Thomas Gleixner  writes:

> On Mon, 21 Mar 2016, Huang, Ying wrote:
>> >  FYI, we noticed 25.6% performance improvement due to commit
>> >
>> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
>> > get_futex_key()"
>> >
>> >  in the will-it-scale.per_process_ops test.
>> >
>> >  will-it-scale.per_process_ops tests the futex operations for process 
>> > shared
>> >  futexes (Or whatever that test really does).
>> 
>> There is a futex sub test case for will-it-scale test suite.  But I got your
>> point, we need some description for the test case.  If email is not too
>> limited for the full description, we will put it in some web site and
>> include short description and link to the full description in email.
>
> Ok. Just make sure the short description gives enough information for the
> casual reader.
>  
>> >  The commit has no significant impact on any other test in the test suite.
>> 
>> Sorry, we have no enough machine power to test all test cases for each
>> bisect result.  So we will have no such information until we find a way
>> to do that.
>
> Well, then I really have to ask how I should interpret the data here:
>
>5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops
>
>^^^ That's the reason why you sent the mail in the first place
>
>1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
>   0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
>   6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
>   2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
>   2848 ± 32%+141.2%   6870 ± 65%  numa-meminfo.node1.Active(anon)
>   2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
>  15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
>   1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
> 712.25 ± 32%+141.2%   1718 ± 65%  numa-vmstat.node1.nr_active_anon
> 708.25 ± 31% +57.7%   1116 ± 27%  numa-vmstat.node1.nr_anon_pages
>
> How is this related and what should I do about this information? 

For each will-it-scale sub test case, it will be run in both process
mode and thread mode, and task number will change from 1 to CPU number.
will-it-scale.per_thread_ops shows thread mode main result.
will-it-scale.scalability is calculated to measure how per_process_ops
and per_thread_ops scaled along with the task number.  These are default
behavior of will-it-scale test suite.

Others are monitors output.  That is, other information collected during
test.  For example, meminfo is a monitor to sampling /proc/meminfo
contents,  AnonHugePages is a line in it.  meminfo.AnonHugePages is for
the average value of AnonHugePages line of /proc/meminfo.  Similarly
vmstat.system.cs is the average value of cs column of system column
group of /usr/bin/vmstat.

We hope these information are helpful for root causing the regression.

>  If it's important then I have to admit, that I fail to understand why.
>
>  If it's not important then I have to ask why is this included.
>
>> > So that allows me to reproduce that test more or less with no effort. And
>> > that's the really important part.
>> 
>> For reproducing, now we use lkp-tests tool, which includes scripts to
>> build the test case, run the test, collect various information, compare
>> the test result, with the job file attached with the report email.  That
>> is not the easiest way, we will continuously improve it.
>
> I know and lkp-tests is a pain to work with. So please look into a way to
> extract the relevant binaries, so it's simple for developers to reproduce.

OK.  We will try to improve on this side.  But it is not an easy task
for us to provided easy to use simple binaries.  Do you think something
like Docker image is easy to use?

>> > You can provide nice charts and full comparison tables for all tests on a 
>> > web
>> > site for those who are interested in large stats and pretty charts.
>> >
>> > Full results: http://wherever.you.store/your/results/test-nr/results
>> 
>> Before we have a website for detailed information, we will still put
>> some details into report email.
>
> Ok, but please make them understandable for mere mortals.

Sure.

Best Regards,
Huang, Ying

> Thanks,
>
>   tglx

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Thomas Gleixner]

On Mon, 21 Mar 2016, Huang, Ying wrote:
> >  FYI, we noticed 25.6% performance improvement due to commit
> >
> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> > get_futex_key()"
> >
> >  in the will-it-scale.per_process_ops test.
> >
> >  will-it-scale.per_process_ops tests the futex operations for process shared
> >  futexes (Or whatever that test really does).
> 
> There is a futex sub test case for will-it-scale test suite.  But I got your
> point, we need some description for the test case.  If email is not too
> limited for the full description, we will put it in some web site and
> include short description and link to the full description in email.

Ok. Just make sure the short description gives enough information for the
casual reader.
 
> >  The commit has no significant impact on any other test in the test suite.
> 
> Sorry, we have no enough machine power to test all test cases for each
> bisect result.  So we will have no such information until we find a way
> to do that.

Well, then I really have to ask how I should interpret the data here:

   5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops

   ^^^ That's the reason why you sent the mail in the first place

   1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
  0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
  6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
  2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
  2848 ± 32%+141.2%   6870 ± 65%  numa-meminfo.node1.Active(anon)
  2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
 15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
  1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
712.25 ± 32%+141.2%   1718 ± 65%  numa-vmstat.node1.nr_active_anon
708.25 ± 31% +57.7%   1116 ± 27%  numa-vmstat.node1.nr_anon_pages

How is this related and what should I do about this information? 
 
 If it's important then I have to admit, that I fail to understand why.

 If it's not important then I have to ask why is this included.

> > So that allows me to reproduce that test more or less with no effort. And
> > that's the really important part.
> 
> For reproducing, now we use lkp-tests tool, which includes scripts to
> build the test case, run the test, collect various information, compare
> the test result, with the job file attached with the report email.  That
> is not the easiest way, we will continuously improve it.

I know and lkp-tests is a pain to work with. So please look into a way to
extract the relevant binaries, so it's simple for developers to reproduce.
 
> > You can provide nice charts and full comparison tables for all tests on a 
> > web
> > site for those who are interested in large stats and pretty charts.
> >
> > Full results: http://wherever.you.store/your/results/test-nr/results
> 
> Before we have a website for detailed information, we will still put
> some details into report email.

Ok, but please make them understandable for mere mortals.
 
Thanks,

tglx

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Thomas Gleixner]

On Mon, 21 Mar 2016, Huang, Ying wrote:
> >  FYI, we noticed 25.6% performance improvement due to commit
> >
> >65d8fc777f6d "futex: Remove requirement for lock_page() in 
> > get_futex_key()"
> >
> >  in the will-it-scale.per_process_ops test.
> >
> >  will-it-scale.per_process_ops tests the futex operations for process shared
> >  futexes (Or whatever that test really does).
> 
> There is a futex sub test case for will-it-scale test suite.  But I got your
> point, we need some description for the test case.  If email is not too
> limited for the full description, we will put it in some web site and
> include short description and link to the full description in email.

Ok. Just make sure the short description gives enough information for the
casual reader.
 
> >  The commit has no significant impact on any other test in the test suite.
> 
> Sorry, we have no enough machine power to test all test cases for each
> bisect result.  So we will have no such information until we find a way
> to do that.

Well, then I really have to ask how I should interpret the data here:

   5076304 ±  0% +25.6%6374220 ±  0%  will-it-scale.per_process_ops

   ^^^ That's the reason why you sent the mail in the first place

   1194117 ±  0% +14.4%1366153 ±  1%  will-it-scale.per_thread_ops
  0.58 ±  0%  -2.0%   0.57 ±  0%  will-it-scale.scalability
  6820 ±  0% -19.6%   5483 ± 15%  meminfo.AnonHugePages
  2652 ±  5% -10.4%   2375 ±  2%  vmstat.system.cs
  2848 ± 32%+141.2%   6870 ± 65%  numa-meminfo.node1.Active(anon)
  2832 ± 31% +57.6%   4465 ± 27%  numa-meminfo.node1.AnonPages
 15018 ± 12% -23.3%  11515 ± 15%  numa-meminfo.node2.AnonPages
  1214 ± 14% -22.8% 936.75 ± 20%  numa-meminfo.node3.PageTables
712.25 ± 32%+141.2%   1718 ± 65%  numa-vmstat.node1.nr_active_anon
708.25 ± 31% +57.7%   1116 ± 27%  numa-vmstat.node1.nr_anon_pages

How is this related and what should I do about this information? 
 
 If it's important then I have to admit, that I fail to understand why.

 If it's not important then I have to ask why is this included.

> > So that allows me to reproduce that test more or less with no effort. And
> > that's the really important part.
> 
> For reproducing, now we use lkp-tests tool, which includes scripts to
> build the test case, run the test, collect various information, compare
> the test result, with the job file attached with the report email.  That
> is not the easiest way, we will continuously improve it.

I know and lkp-tests is a pain to work with. So please look into a way to
extract the relevant binaries, so it's simple for developers to reproduce.
 
> > You can provide nice charts and full comparison tables for all tests on a 
> > web
> > site for those who are interested in large stats and pretty charts.
> >
> > Full results: http://wherever.you.store/your/results/test-nr/results
> 
> Before we have a website for detailed information, we will still put
> some details into report email.

Ok, but please make them understandable for mere mortals.
 
Thanks,

tglx

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Hi, Thomas,

Thanks a lot for your valuable input!

Thomas Gleixner  writes:

> On Fri, 18 Mar 2016, Huang, Ying wrote:
>> Usually we will put most important change we think in the subject of the
>> mail, for this email, it is,
>> 
>> +25.6% will-it-scale.per_process_ops
>
> That is confusing on it's own, because the reader does not know at all whether
> this is an improvement or a regression.
>
> So something like this might be useful:
>
> Subject: subsystem: 12digitsha1: 25% performance improvement
>
> or in some other case
>
> Subject: subsystem: 12digitsha1: 25% performance regression
>
> So in the latter case I will look into that mail immediately. The improvement
> one can wait until I have cared about urgent stuff.
>
> In the subject line it is pretty much irrelevant which foo-bla-ops test has
> produced that result. It really does not matter. If it's a regression, it's
> urgent. If it's an improvement it's informal and it can wait to be read.
>
> So in that case it would be:
>
> futex: 65d8fc777f6d: 25% performance improvement
>
> You can grab the subsystem prefix from the commit.

We will include regression/improvement information in subject at least.

>> and, we try to put most important changes at the top of the comparison
>> result below.  That is the will-it-scale.xxx below.
>> 
>> We are thinking about how to improve this.  You input is valuable for
>> us.  We are thinking change the "below changes" line to something like
>> below.
>> 
>> FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on
>> ...
>> 
>> Does this looks better?
>
> A bit, but it still does not tell me much. It's completely non obvious what
> 'will-it-scale.per_process_ops' means.

will-it-scale is a test suite, per_process_ops is one of its results.
That is the convention used in original report.

> Let me give you an example how a useful
> and easy to understand summary of the change could look like:
>
>
>  FYI, we noticed 25.6% performance improvement due to commit
>
>65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"
>
>  in the will-it-scale.per_process_ops test.
>
>  will-it-scale.per_process_ops tests the futex operations for process shared
>  futexes (Or whatever that test really does).

There is a futex sub test case for will-it-scale test suite.  But I got your
point, we need some description for the test case.  If email is not too
limited for the full description, we will put it in some web site and
include short description and link to the full description in email.

>  The commit has no significant impact on any other test in the test suite.

Sorry, we have no enough machine power to test all test cases for each
bisect result.  So we will have no such information until we find a way
to do that.

> So those few lines tell precisely what this is about. It's something I already
> expected, so I really can skip the rest of the mail unless I'm interested in
> reproducing the result.

We will put important information at first of the email.  And details
later.  Better to have clear mark.  So people can get important
information and ignore the details if they don't want.

> Now lets look at a performance regression.
>
> Subject: futex: 65d8fc777f6d: 25% performance regression
>
>  FYI, we noticed a 25.2% performance regression due to commit
>
>  65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"
>
>  in the will-it-scale.per_process_ops test.
>
>  will-it-scale.per_process_ops tests the futex operations for process shared
>  futexes (Or whatever that test really does).
>
>  The commit has no significant impact on any other test in the test suite.
>
> In that case I will certainly be interested how to reproduce that test. So I
> need the following information:
>
> Machine description: Intel IvyBridge 2 sockets, 32 cores, 64G RAM
> Config file: http://wherever.you.store/your/results/test-nr/config

We have some information about this before.  But not organized good
enough, will improve it.

> Test: 
> http://wherever.you.store/your/tests/will-it-scale.per_process_ops.tar.bz2
>
> That tarball should contain:
>
>  README
>  test_script.sh
>  test_binary
>
> README should tell:
>
>will-it-scale.per_process_ops
>
>Short explanation of the test
>
>Preliminaries: 
>   - perf
>   - whatever
>
> So that allows me to reproduce that test more or less with no effort. And
> that's the really important part.

For reproducing, now we use lkp-tests tool, which includes scripts to
build the test case, run the test, collect various information, compare
the test result, with the job file attached with the report email.  That
is not the easiest way, we will continuously improve it.

> You can provide nice charts and full comparison tables for all tests on a web
> site for those who are interested in large stats and pretty charts.
>
> Full results: http://wherever.you.store/your/results/test-nr/results

Before we have 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Hi, Thomas,

Thanks a lot for your valuable input!

Thomas Gleixner  writes:

> On Fri, 18 Mar 2016, Huang, Ying wrote:
>> Usually we will put most important change we think in the subject of the
>> mail, for this email, it is,
>> 
>> +25.6% will-it-scale.per_process_ops
>
> That is confusing on it's own, because the reader does not know at all whether
> this is an improvement or a regression.
>
> So something like this might be useful:
>
> Subject: subsystem: 12digitsha1: 25% performance improvement
>
> or in some other case
>
> Subject: subsystem: 12digitsha1: 25% performance regression
>
> So in the latter case I will look into that mail immediately. The improvement
> one can wait until I have cared about urgent stuff.
>
> In the subject line it is pretty much irrelevant which foo-bla-ops test has
> produced that result. It really does not matter. If it's a regression, it's
> urgent. If it's an improvement it's informal and it can wait to be read.
>
> So in that case it would be:
>
> futex: 65d8fc777f6d: 25% performance improvement
>
> You can grab the subsystem prefix from the commit.

We will include regression/improvement information in subject at least.

>> and, we try to put most important changes at the top of the comparison
>> result below.  That is the will-it-scale.xxx below.
>> 
>> We are thinking about how to improve this.  You input is valuable for
>> us.  We are thinking change the "below changes" line to something like
>> below.
>> 
>> FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on
>> ...
>> 
>> Does this looks better?
>
> A bit, but it still does not tell me much. It's completely non obvious what
> 'will-it-scale.per_process_ops' means.

will-it-scale is a test suite, per_process_ops is one of its results.
That is the convention used in original report.

> Let me give you an example how a useful
> and easy to understand summary of the change could look like:
>
>
>  FYI, we noticed 25.6% performance improvement due to commit
>
>65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"
>
>  in the will-it-scale.per_process_ops test.
>
>  will-it-scale.per_process_ops tests the futex operations for process shared
>  futexes (Or whatever that test really does).

There is a futex sub test case for will-it-scale test suite.  But I got your
point, we need some description for the test case.  If email is not too
limited for the full description, we will put it in some web site and
include short description and link to the full description in email.

>  The commit has no significant impact on any other test in the test suite.

Sorry, we have no enough machine power to test all test cases for each
bisect result.  So we will have no such information until we find a way
to do that.

> So those few lines tell precisely what this is about. It's something I already
> expected, so I really can skip the rest of the mail unless I'm interested in
> reproducing the result.

We will put important information at first of the email.  And details
later.  Better to have clear mark.  So people can get important
information and ignore the details if they don't want.

> Now lets look at a performance regression.
>
> Subject: futex: 65d8fc777f6d: 25% performance regression
>
>  FYI, we noticed a 25.2% performance regression due to commit
>
>  65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"
>
>  in the will-it-scale.per_process_ops test.
>
>  will-it-scale.per_process_ops tests the futex operations for process shared
>  futexes (Or whatever that test really does).
>
>  The commit has no significant impact on any other test in the test suite.
>
> In that case I will certainly be interested how to reproduce that test. So I
> need the following information:
>
> Machine description: Intel IvyBridge 2 sockets, 32 cores, 64G RAM
> Config file: http://wherever.you.store/your/results/test-nr/config

We have some information about this before.  But not organized good
enough, will improve it.

> Test: 
> http://wherever.you.store/your/tests/will-it-scale.per_process_ops.tar.bz2
>
> That tarball should contain:
>
>  README
>  test_script.sh
>  test_binary
>
> README should tell:
>
>will-it-scale.per_process_ops
>
>Short explanation of the test
>
>Preliminaries: 
>   - perf
>   - whatever
>
> So that allows me to reproduce that test more or less with no effort. And
> that's the really important part.

For reproducing, now we use lkp-tests tool, which includes scripts to
build the test case, run the test, collect various information, compare
the test result, with the job file attached with the report email.  That
is not the easiest way, we will continuously improve it.

> You can provide nice charts and full comparison tables for all tests on a web
> site for those who are interested in large stats and pretty charts.
>
> Full results: http://wherever.you.store/your/results/test-nr/results

Before we have a website for 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Sorry, for late.

Ingo Molnar  writes:
> * kernel test robot  wrote:
>
>> FYI, we noticed the below changes on
>> 
>> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master 
>> commit 65d8fc777f6dcfee12785c057a6b57f679641c90 ("futex: Remove requirement 
>> for 
>> lock_page() in get_futex_key()")
>
> I have asked for this before, but let me try again: could you _PLEASE_ make 
> these 
> emails more readable?
>
> For example what are the 'below changes'? Changes in the profile output? 
> Profiles 
> always change from run to run, so that alone is not informative.
>
> Also, there are a lot of changes - which ones prompted the email to be 
> generated?

Usually we will put most important change we think in the subject of the
mail, for this email, it is,

+25.6% will-it-scale.per_process_ops

and, we try to put most important changes at the top of the comparison
result below.  That is the will-it-scale.xxx below.

We are thinking about how to improve this.  You input is valuable for
us.  We are thinking change the "below changes" line to something like
below.

FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on

...

Does this looks better?

> All in one, this email is hard to parse, because it just dumps a lot of 
> information with very little explanatory structure for someone not versed in 
> their 
> format. Please try to create an easy to parse 'story' that leads the reader 
> towards what you want these emails to tell - not just a raw dump of seemingly 
> unconnected pieces of data ...

Which kind of story?  Something like, we tested some benchmark on some
machine, which triggered some regression, we do bisect, and find the
first bad commit is xxx.  In addition to benchmark result, we collected
some other information, hope they are helpful for you.

We just try to help.  Sorry for confusion.  We try to provide all
information needed to describe the change and help for root causing the
changes.  But we know, we are still far from there, so your input is
important for us to improve our test report.  Which part of the report
do you think should be changed firstly?  The overall structure?  Or the
data format?

Best Regards,
Huang, Ying

> Thanks,
>
>   Ingo
>
>> 
>> 
>> =
>> compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
>>   
>> gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-sbx04/futex1/will-it-scale
>> 
>> commit: 
>>   8ad7b378d0d016309014cae0f640434bca7b5e11
>>   65d8fc777f6dcfee12785c057a6b57f679641c90
>> 
>> 8ad7b378d0d01630 65d8fc777f6dcfee12785c057a 
>>  -- 
>>  %stddev %change %stddev
>>  \  |\  
>>5076304 .  0% +25.6%6374220 .  0%  will-it-scale.per_process_ops
>>1194117 .  0% +14.4%1366153 .  1%  will-it-scale.per_thread_ops
>>   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>>   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>>   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>>   2848 . 32%+141.2%   6870 . 65%  numa-meminfo.node1.Active(anon)
>>   2832 . 31% +57.6%   4465 . 27%  numa-meminfo.node1.AnonPages
>>  15018 . 12% -23.3%  11515 . 15%  numa-meminfo.node2.AnonPages
>>   1214 . 14% -22.8% 936.75 . 20%  numa-meminfo.node3.PageTables
>> 712.25 . 32%+141.2%   1718 . 65%  
>> numa-vmstat.node1.nr_active_anon
>> 708.25 . 31% +57.7%   1116 . 27%  numa-vmstat.node1.nr_anon_pages
>>   3754 . 12% -23.3%   2879 . 15%  numa-vmstat.node2.nr_anon_pages
>> 304.75 . 14% -23.1% 234.50 . 20%  
>> numa-vmstat.node3.nr_page_table_pages
>> 3.53 . 1% -100.0% 0.00 . -1%
> perf-profile.cycles.___might_sleep.__might_sleep.get_futex_key.futex_wake.do_futex
>> 4.34 . 1% -100.0% 0.00 . -1%
> perf-profile.cycles.__might_sleep.get_futex_key.futex_wake.do_futex.sys_futex
>> 1.27 . 3% -100.0% 0.00 . -1%
> perf-profile.cycles.__wake_up_bit.unlock_page.get_futex_key.futex_wake.do_futex
>> 4.36 . 1% +29.6% 5.65 . 1%
> perf-profile.cycles.drop_futex_key_refs.isra.12.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>>   6.69 .  1% +28.1%   8.57 .  0%  
>> perf-profile.cycles.entry_SYSCALL_64
>>   6.73 .  0% +30.6%   8.79 .  0%  
>> perf-profile.cycles.entry_SYSCALL_64_after_swapgs
>> 74.21 . 0% -11.0% 66.06 . 0%
> perf-profile.cycles.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 59.05 . 0% -21.4% 46.40 . 0%
> perf-profile.cycles.get_futex_key.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 4.12 . 0% +78.5% 7.36 . 1%
> perf-profile.cycles.get_futex_key_refs.isra.11.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 2.27 . 3% +24.1% 2.82 . 4%
> 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Sorry, for late.

Ingo Molnar  writes:
> * kernel test robot  wrote:
>
>> FYI, we noticed the below changes on
>> 
>> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master 
>> commit 65d8fc777f6dcfee12785c057a6b57f679641c90 ("futex: Remove requirement 
>> for 
>> lock_page() in get_futex_key()")
>
> I have asked for this before, but let me try again: could you _PLEASE_ make 
> these 
> emails more readable?
>
> For example what are the 'below changes'? Changes in the profile output? 
> Profiles 
> always change from run to run, so that alone is not informative.
>
> Also, there are a lot of changes - which ones prompted the email to be 
> generated?

Usually we will put most important change we think in the subject of the
mail, for this email, it is,

+25.6% will-it-scale.per_process_ops

and, we try to put most important changes at the top of the comparison
result below.  That is the will-it-scale.xxx below.

We are thinking about how to improve this.  You input is valuable for
us.  We are thinking change the "below changes" line to something like
below.

FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on

...

Does this looks better?

> All in one, this email is hard to parse, because it just dumps a lot of 
> information with very little explanatory structure for someone not versed in 
> their 
> format. Please try to create an easy to parse 'story' that leads the reader 
> towards what you want these emails to tell - not just a raw dump of seemingly 
> unconnected pieces of data ...

Which kind of story?  Something like, we tested some benchmark on some
machine, which triggered some regression, we do bisect, and find the
first bad commit is xxx.  In addition to benchmark result, we collected
some other information, hope they are helpful for you.

We just try to help.  Sorry for confusion.  We try to provide all
information needed to describe the change and help for root causing the
changes.  But we know, we are still far from there, so your input is
important for us to improve our test report.  Which part of the report
do you think should be changed firstly?  The overall structure?  Or the
data format?

Best Regards,
Huang, Ying

> Thanks,
>
>   Ingo
>
>> 
>> 
>> =
>> compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
>>   
>> gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-sbx04/futex1/will-it-scale
>> 
>> commit: 
>>   8ad7b378d0d016309014cae0f640434bca7b5e11
>>   65d8fc777f6dcfee12785c057a6b57f679641c90
>> 
>> 8ad7b378d0d01630 65d8fc777f6dcfee12785c057a 
>>  -- 
>>  %stddev %change %stddev
>>  \  |\  
>>5076304 .  0% +25.6%6374220 .  0%  will-it-scale.per_process_ops
>>1194117 .  0% +14.4%1366153 .  1%  will-it-scale.per_thread_ops
>>   0.58 .  0%  -2.0%   0.57 .  0%  will-it-scale.scalability
>>   6820 .  0% -19.6%   5483 . 15%  meminfo.AnonHugePages
>>   2652 .  5% -10.4%   2375 .  2%  vmstat.system.cs
>>   2848 . 32%+141.2%   6870 . 65%  numa-meminfo.node1.Active(anon)
>>   2832 . 31% +57.6%   4465 . 27%  numa-meminfo.node1.AnonPages
>>  15018 . 12% -23.3%  11515 . 15%  numa-meminfo.node2.AnonPages
>>   1214 . 14% -22.8% 936.75 . 20%  numa-meminfo.node3.PageTables
>> 712.25 . 32%+141.2%   1718 . 65%  
>> numa-vmstat.node1.nr_active_anon
>> 708.25 . 31% +57.7%   1116 . 27%  numa-vmstat.node1.nr_anon_pages
>>   3754 . 12% -23.3%   2879 . 15%  numa-vmstat.node2.nr_anon_pages
>> 304.75 . 14% -23.1% 234.50 . 20%  
>> numa-vmstat.node3.nr_page_table_pages
>> 3.53 . 1% -100.0% 0.00 . -1%
> perf-profile.cycles.___might_sleep.__might_sleep.get_futex_key.futex_wake.do_futex
>> 4.34 . 1% -100.0% 0.00 . -1%
> perf-profile.cycles.__might_sleep.get_futex_key.futex_wake.do_futex.sys_futex
>> 1.27 . 3% -100.0% 0.00 . -1%
> perf-profile.cycles.__wake_up_bit.unlock_page.get_futex_key.futex_wake.do_futex
>> 4.36 . 1% +29.6% 5.65 . 1%
> perf-profile.cycles.drop_futex_key_refs.isra.12.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>>   6.69 .  1% +28.1%   8.57 .  0%  
>> perf-profile.cycles.entry_SYSCALL_64
>>   6.73 .  0% +30.6%   8.79 .  0%  
>> perf-profile.cycles.entry_SYSCALL_64_after_swapgs
>> 74.21 . 0% -11.0% 66.06 . 0%
> perf-profile.cycles.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 59.05 . 0% -21.4% 46.40 . 0%
> perf-profile.cycles.get_futex_key.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 4.12 . 0% +78.5% 7.36 . 1%
> perf-profile.cycles.get_futex_key_refs.isra.11.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath
>> 2.27 . 3% +24.1% 2.82 . 4%
> 

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Thomas Gleixner]

On Fri, 18 Mar 2016, Huang, Ying wrote:
> Usually we will put most important change we think in the subject of the
> mail, for this email, it is,
> 
> +25.6% will-it-scale.per_process_ops

That is confusing on it's own, because the reader does not know at all whether
this is an improvement or a regression.

So something like this might be useful:

Subject: subsystem: 12digitsha1: 25% performance improvement

or in some other case

Subject: subsystem: 12digitsha1: 25% performance regression

So in the latter case I will look into that mail immediately. The improvement
one can wait until I have cared about urgent stuff.

In the subject line it is pretty much irrelevant which foo-bla-ops test has
produced that result. It really does not matter. If it's a regression, it's
urgent. If it's an improvement it's informal and it can wait to be read.

So in that case it would be:

futex: 65d8fc777f6d: 25% performance improvement

You can grab the subsystem prefix from the commit.

> and, we try to put most important changes at the top of the comparison
> result below.  That is the will-it-scale.xxx below.
> 
> We are thinking about how to improve this.  You input is valuable for
> us.  We are thinking change the "below changes" line to something like
> below.
> 
> FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on
> ...
> 
> Does this looks better?

A bit, but it still does not tell me much. It's completely non obvious what
'will-it-scale.per_process_ops' means. Let me give you an example how a useful
and easy to understand summary of the change could look like:


 FYI, we noticed 25.6% performance improvement due to commit

   65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_process_ops test.

 will-it-scale.per_process_ops tests the futex operations for process shared
 futexes (Or whatever that test really does).

 The commit has no significant impact on any other test in the test suite.

So those few lines tell precisely what this is about. It's something I already
expected, so I really can skip the rest of the mail unless I'm interested in
reproducing the result.

Now lets look at a performance regression.

Subject: futex: 65d8fc777f6d: 25% performance regression

 FYI, we noticed a 25.2% performance regression due to commit

 65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_process_ops test.

 will-it-scale.per_process_ops tests the futex operations for process shared
 futexes (Or whatever that test really does).

 The commit has no significant impact on any other test in the test suite.

In that case I will certainly be interested how to reproduce that test. So I
need the following information:

Machine description: Intel IvyBridge 2 sockets, 32 cores, 64G RAM
Config file: http://wherever.you.store/your/results/test-nr/config
Test: http://wherever.you.store/your/tests/will-it-scale.per_process_ops.tar.bz2

That tarball should contain:

 README
 test_script.sh
 test_binary

README should tell:

   will-it-scale.per_process_ops

   Short explanation of the test

   Preliminaries: 
- perf
- whatever

So that allows me to reproduce that test more or less with no effort. And
that's the really important part.

You can provide nice charts and full comparison tables for all tests on a web
site for those who are interested in large stats and pretty charts.

Full results: http://wherever.you.store/your/results/test-nr/results

So now lets look at a scenario where that commit results in a performance
improvement on will-it-scale.per_process_ops and a regression on
will-it-scale.per_task.

Subject: futex: 65d8fc777f6d: 25% performance regression

 FYI, we noticed a 25.2% performance regression due to commit

 65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_task test.

 will-it-scale.per_tasks tests the futex operations for process private
 futexes (Or whatever that test really does).

 The commit has significant impact on the following tests in the test suite:
 
will-it-scale.per_process_ops: 25% improvement

The 25% improvement is really not interesting. What's interesting is the
regression. That's what people need to look at. You still can provide the
information about all the tests including the 25% improvement data on 

Full results: http://wherever.you.store/your/results/test-nr/results

Now, if you have commits which have mixed impact on various tests, then it's
important to point out the most relevant issue clearly in the
summary. I.e. you need to filter the tests for the maximum
regression/improvement and use that as the main information. You still can
provide the information about the impact on other tests in a very condensed
form.

 The commit has significant impact on the following tests in the test suite:

 test1: 0.5% Regression
 test2: 2.0% Improvement
 
 testN:

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Thomas Gleixner]

On Fri, 18 Mar 2016, Huang, Ying wrote:
> Usually we will put most important change we think in the subject of the
> mail, for this email, it is,
> 
> +25.6% will-it-scale.per_process_ops

That is confusing on it's own, because the reader does not know at all whether
this is an improvement or a regression.

So something like this might be useful:

Subject: subsystem: 12digitsha1: 25% performance improvement

or in some other case

Subject: subsystem: 12digitsha1: 25% performance regression

So in the latter case I will look into that mail immediately. The improvement
one can wait until I have cared about urgent stuff.

In the subject line it is pretty much irrelevant which foo-bla-ops test has
produced that result. It really does not matter. If it's a regression, it's
urgent. If it's an improvement it's informal and it can wait to be read.

So in that case it would be:

futex: 65d8fc777f6d: 25% performance improvement

You can grab the subsystem prefix from the commit.

> and, we try to put most important changes at the top of the comparison
> result below.  That is the will-it-scale.xxx below.
> 
> We are thinking about how to improve this.  You input is valuable for
> us.  We are thinking change the "below changes" line to something like
> below.
> 
> FYI, we noticed the +25.6% will-it-scale.per_process_ops improvement on
> ...
> 
> Does this looks better?

A bit, but it still does not tell me much. It's completely non obvious what
'will-it-scale.per_process_ops' means. Let me give you an example how a useful
and easy to understand summary of the change could look like:


 FYI, we noticed 25.6% performance improvement due to commit

   65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_process_ops test.

 will-it-scale.per_process_ops tests the futex operations for process shared
 futexes (Or whatever that test really does).

 The commit has no significant impact on any other test in the test suite.

So those few lines tell precisely what this is about. It's something I already
expected, so I really can skip the rest of the mail unless I'm interested in
reproducing the result.

Now lets look at a performance regression.

Subject: futex: 65d8fc777f6d: 25% performance regression

 FYI, we noticed a 25.2% performance regression due to commit

 65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_process_ops test.

 will-it-scale.per_process_ops tests the futex operations for process shared
 futexes (Or whatever that test really does).

 The commit has no significant impact on any other test in the test suite.

In that case I will certainly be interested how to reproduce that test. So I
need the following information:

Machine description: Intel IvyBridge 2 sockets, 32 cores, 64G RAM
Config file: http://wherever.you.store/your/results/test-nr/config
Test: http://wherever.you.store/your/tests/will-it-scale.per_process_ops.tar.bz2

That tarball should contain:

 README
 test_script.sh
 test_binary

README should tell:

   will-it-scale.per_process_ops

   Short explanation of the test

   Preliminaries: 
- perf
- whatever

So that allows me to reproduce that test more or less with no effort. And
that's the really important part.

You can provide nice charts and full comparison tables for all tests on a web
site for those who are interested in large stats and pretty charts.

Full results: http://wherever.you.store/your/results/test-nr/results

So now lets look at a scenario where that commit results in a performance
improvement on will-it-scale.per_process_ops and a regression on
will-it-scale.per_task.

Subject: futex: 65d8fc777f6d: 25% performance regression

 FYI, we noticed a 25.2% performance regression due to commit

 65d8fc777f6d "futex: Remove requirement for lock_page() in get_futex_key()"

 in the will-it-scale.per_task test.

 will-it-scale.per_tasks tests the futex operations for process private
 futexes (Or whatever that test really does).

 The commit has significant impact on the following tests in the test suite:
 
will-it-scale.per_process_ops: 25% improvement

The 25% improvement is really not interesting. What's interesting is the
regression. That's what people need to look at. You still can provide the
information about all the tests including the 25% improvement data on 

Full results: http://wherever.you.store/your/results/test-nr/results

Now, if you have commits which have mixed impact on various tests, then it's
important to point out the most relevant issue clearly in the
summary. I.e. you need to filter the tests for the maximum
regression/improvement and use that as the main information. You still can
provide the information about the impact on other tests in a very condensed
form.

 The commit has significant impact on the following tests in the test suite:

 test1: 0.5% Regression
 test2: 2.0% Improvement
 
 testN:

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Hi, Ingo,

Ingo Molnar  writes:

> * kernel test robot  wrote:
>
>> FYI, we noticed the below changes on
>> 
>> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master 
>> commit 65d8fc777f6dcfee12785c057a6b57f679641c90 ("futex: Remove requirement 
>> for 
>> lock_page() in get_futex_key()")
>
> I have asked for this before, but let me try again: could you _PLEASE_ make 
> these 
> emails more readable?
>
> For example what are the 'below changes'? Changes in the profile output? 
> Profiles 
> always change from run to run, so that alone is not informative.
>
> Also, there are a lot of changes - which ones prompted the email to be 
> generated?
>
> All in one, this email is hard to parse, because it just dumps a lot of 
> information with very little explanatory structure for someone not versed in 
> their 
> format. Please try to create an easy to parse 'story' that leads the reader 
> towards what you want these emails to tell - not just a raw dump of seemingly 
> unconnected pieces of data ...

Your input are valuable for us.  We are discussing how to improve our
reporting to be helpful for kernel developers.  Will go back to you soon
on this.

Best Regards,
Huang, Ying

> Thanks,
>
>   Ingo
>

Re: [LKP] [lkp] [futex] 65d8fc777f: +25.6% will-it-scale.per_process_ops

[Huang, Ying]

Hi, Ingo,

Ingo Molnar  writes:

> * kernel test robot  wrote:
>
>> FYI, we noticed the below changes on
>> 
>> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master 
>> commit 65d8fc777f6dcfee12785c057a6b57f679641c90 ("futex: Remove requirement 
>> for 
>> lock_page() in get_futex_key()")
>
> I have asked for this before, but let me try again: could you _PLEASE_ make 
> these 
> emails more readable?
>
> For example what are the 'below changes'? Changes in the profile output? 
> Profiles 
> always change from run to run, so that alone is not informative.
>
> Also, there are a lot of changes - which ones prompted the email to be 
> generated?
>
> All in one, this email is hard to parse, because it just dumps a lot of 
> information with very little explanatory structure for someone not versed in 
> their 
> format. Please try to create an easy to parse 'story' that leads the reader 
> towards what you want these emails to tell - not just a raw dump of seemingly 
> unconnected pieces of data ...

Your input are valuable for us.  We are discussing how to improve our
reporting to be helpful for kernel developers.  Will go back to you soon
on this.

Best Regards,
Huang, Ying

> Thanks,
>
>   Ingo
>