| Message ID | 20211209004442.999696-1-ying.huang@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [-V2] numa balancing: move some document to make it consistent with the code | expand |
On Thu, Dec 09, 2021 at 08:44:42AM +0800, Huang Ying wrote: > After commit 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to > debugfs"), some NUMA balancing sysctls enclosed with SCHED_DEBUG has > been moved to debugfs. This patch move the document for these > sysctls from > > Documentation/admin-guide/sysctl/kernel.rst > > to > > Documentation/scheduler/debug.txt > > to make the document consistent with the code. > Acked-by: Mel Gorman <mgorman@suse.de>
On 09/12/21 08:44, Huang Ying wrote: > After commit 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to > debugfs"), some NUMA balancing sysctls enclosed with SCHED_DEBUG has > been moved to debugfs. This patch move the document for these > sysctls from > > Documentation/admin-guide/sysctl/kernel.rst > > to > > Documentation/scheduler/debug.txt > AFAIA new documentation files should be written in reST, and the "source" file is .rst so the new one should be too (as much as Peter hates it). Also, most files in there are named sched-*.rst, does that want to be sched-debug.rst ? > to make the document consistent with the code. > > Signed-off-by: "Huang, Ying" <ying.huang@intel.com> > Fixes: 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to debugfs") > Cc: Mel Gorman <mgorman@techsingularity.net> > Cc: Peter Zijlstra (Intel) <peterz@infradead.org> > Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > Cc: Valentin Schneider <valentin.schneider@arm.com> > Cc: stable@vger.kernel.org # since v5.13 > diff --git a/Documentation/scheduler/debug.txt b/Documentation/scheduler/debug.txt > new file mode 100644 > index 000000000000..848d83c3123c > --- /dev/null > +++ b/Documentation/scheduler/debug.txt > @@ -0,0 +1,48 @@ > +Scheduler debugfs > + How about a small intro? --- diff --git a/Documentation/scheduler/debug.txt b/Documentation/scheduler/debug.txt index 848d83c3123c..08600de5b90e 100644 --- a/Documentation/scheduler/debug.txt +++ b/Documentation/scheduler/debug.txt @@ -1,4 +1,10 @@ +================= Scheduler debugfs +================= + +Booting a kernel with CONFIG_SCHED_DEBUG=y will give access to scheduler +-specific debug files under /sys/kernel/debug/sched. Some of those files are +described below. numa_balancing -------------- --- > +numa_balancing > +-------------- I think you got the heading ordering wrong, see Documentation/doc-guide/sphinx.rst#Specific guidelines for the kernel documentation IIRC Sphinx/reST only requires heading ordering to be consistent within a given file, but having consistency throughout the project simplifies reviewing/contributing. In this case, headings with "=" must appear before headings with "-". > + > +`numa_balancing` directory is used to hold files to control NUMA > +balancing feature. If the system overhead from the feature is too > +high then the rate the kernel samples for NUMA hinting faults may be > +controlled by the `scan_period_min_ms, scan_delay_ms, > +scan_period_max_ms, scan_size_mb` files. > + > + > +scan_period_min_ms, scan_delay_ms, scan_period_max_ms, scan_size_mb > +=================================================================== > + > +Automatic NUMA balancing scans tasks address space and unmaps pages to > +detect if pages are properly placed or if the data should be migrated to a > +memory node local to where the task is running. Every "scan delay" the task > +scans the next "scan size" number of pages in its address space. When the > +end of the address space is reached the scanner restarts from the beginning. > + > +In combination, the "scan delay" and "scan size" determine the scan rate. > +When "scan delay" decreases, the scan rate increases. The scan delay and > +hence the scan rate of every task is adaptive and depends on historical > +behaviour. If pages are properly placed then the scan delay increases, > +otherwise the scan delay decreases. The "scan size" is not adaptive but > +the higher the "scan size", the higher the scan rate. > + > +Higher scan rates incur higher system overhead as page faults must be > +trapped and potentially data must be migrated. However, the higher the scan > +rate, the more quickly a tasks memory is migrated to a local node if the > +workload pattern changes and minimises performance impact due to remote > +memory accesses. These files control the thresholds for scan delays and > +the number of pages scanned. > + > +``scan_period_min_ms`` is the minimum time in milliseconds to scan a > +tasks virtual memory. It effectively controls the maximum scanning > +rate for each task. > + > +``scan_delay_ms`` is the starting "scan delay" used for a task when it > +initially forks. > + > +``scan_period_max_ms`` is the maximum time in milliseconds to scan a > +tasks virtual memory. It effectively controls the minimum scanning > +rate for each task. > + > +``scan_size_mb`` is how many megabytes worth of pages are scanned for > +a given scan. > -- > 2.30.2
Valentin Schneider <valentin.schneider@arm.com> writes: > On 09/12/21 08:44, Huang Ying wrote: >> After commit 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to >> debugfs"), some NUMA balancing sysctls enclosed with SCHED_DEBUG has >> been moved to debugfs. This patch move the document for these >> sysctls from >> >> Documentation/admin-guide/sysctl/kernel.rst >> >> to >> >> Documentation/scheduler/debug.txt >> > > AFAIA new documentation files should be written in reST, and the "source" > file is .rst so the new one should be too (as much as Peter hates it). > > Also, most files in there are named sched-*.rst, does that want to be > sched-debug.rst ? OK. Will do that. >> to make the document consistent with the code. >> >> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> >> Fixes: 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to debugfs") >> Cc: Mel Gorman <mgorman@techsingularity.net> >> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> >> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> >> Cc: Valentin Schneider <valentin.schneider@arm.com> >> Cc: stable@vger.kernel.org # since v5.13 > >> diff --git a/Documentation/scheduler/debug.txt b/Documentation/scheduler/debug.txt >> new file mode 100644 >> index 000000000000..848d83c3123c >> --- /dev/null >> +++ b/Documentation/scheduler/debug.txt >> @@ -0,0 +1,48 @@ >> +Scheduler debugfs >> + > > How about a small intro? > > --- > diff --git a/Documentation/scheduler/debug.txt b/Documentation/scheduler/debug.txt > index 848d83c3123c..08600de5b90e 100644 > --- a/Documentation/scheduler/debug.txt > +++ b/Documentation/scheduler/debug.txt > @@ -1,4 +1,10 @@ > +================= > Scheduler debugfs > +================= > + > +Booting a kernel with CONFIG_SCHED_DEBUG=y will give access to scheduler > +-specific debug files under /sys/kernel/debug/sched. Some of those files are > +described below. > > numa_balancing > -------------- > --- > >> +numa_balancing >> +-------------- > > I think you got the heading ordering wrong, see > Documentation/doc-guide/sphinx.rst#Specific guidelines for the kernel documentation > > IIRC Sphinx/reST only requires heading ordering to be consistent within a > given file, but having consistency throughout the project simplifies > reviewing/contributing. In this case, headings with "=" must appear before > headings with "-". Thanks for reminding. Will change it in the next version. Best Regards, Huang, Ying >> + >> +`numa_balancing` directory is used to hold files to control NUMA >> +balancing feature. If the system overhead from the feature is too >> +high then the rate the kernel samples for NUMA hinting faults may be >> +controlled by the `scan_period_min_ms, scan_delay_ms, >> +scan_period_max_ms, scan_size_mb` files. >> + >> + >> +scan_period_min_ms, scan_delay_ms, scan_period_max_ms, scan_size_mb >> +=================================================================== >> + >> +Automatic NUMA balancing scans tasks address space and unmaps pages to >> +detect if pages are properly placed or if the data should be migrated to a >> +memory node local to where the task is running. Every "scan delay" the task >> +scans the next "scan size" number of pages in its address space. When the >> +end of the address space is reached the scanner restarts from the beginning. >> + >> +In combination, the "scan delay" and "scan size" determine the scan rate. >> +When "scan delay" decreases, the scan rate increases. The scan delay and >> +hence the scan rate of every task is adaptive and depends on historical >> +behaviour. If pages are properly placed then the scan delay increases, >> +otherwise the scan delay decreases. The "scan size" is not adaptive but >> +the higher the "scan size", the higher the scan rate. >> + >> +Higher scan rates incur higher system overhead as page faults must be >> +trapped and potentially data must be migrated. However, the higher the scan >> +rate, the more quickly a tasks memory is migrated to a local node if the >> +workload pattern changes and minimises performance impact due to remote >> +memory accesses. These files control the thresholds for scan delays and >> +the number of pages scanned. >> + >> +``scan_period_min_ms`` is the minimum time in milliseconds to scan a >> +tasks virtual memory. It effectively controls the maximum scanning >> +rate for each task. >> + >> +``scan_delay_ms`` is the starting "scan delay" used for a task when it >> +initially forks. >> + >> +``scan_period_max_ms`` is the maximum time in milliseconds to scan a >> +tasks virtual memory. It effectively controls the minimum scanning >> +rate for each task. >> + >> +``scan_size_mb`` is how many megabytes worth of pages are scanned for >> +a given scan. >> -- >> 2.30.2
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 0e486f41185e..603469d42fb9 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -609,51 +609,7 @@ be migrated to a local memory node. The unmapping of pages and trapping faults incur additional overhead that ideally is offset by improved memory locality but there is no universal guarantee. If the target workload is already bound to NUMA nodes then this -feature should be disabled. Otherwise, if the system overhead from the -feature is too high then the rate the kernel samples for NUMA hinting -faults may be controlled by the `numa_balancing_scan_period_min_ms, -numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, -numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls. - - -numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb -=============================================================================================================================== - - -Automatic NUMA balancing scans tasks address space and unmaps pages to -detect if pages are properly placed or if the data should be migrated to a -memory node local to where the task is running. Every "scan delay" the task -scans the next "scan size" number of pages in its address space. When the -end of the address space is reached the scanner restarts from the beginning. - -In combination, the "scan delay" and "scan size" determine the scan rate. -When "scan delay" decreases, the scan rate increases. The scan delay and -hence the scan rate of every task is adaptive and depends on historical -behaviour. If pages are properly placed then the scan delay increases, -otherwise the scan delay decreases. The "scan size" is not adaptive but -the higher the "scan size", the higher the scan rate. - -Higher scan rates incur higher system overhead as page faults must be -trapped and potentially data must be migrated. However, the higher the scan -rate, the more quickly a tasks memory is migrated to a local node if the -workload pattern changes and minimises performance impact due to remote -memory accesses. These sysctls control the thresholds for scan delays and -the number of pages scanned. - -``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to -scan a tasks virtual memory. It effectively controls the maximum scanning -rate for each task. - -``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task -when it initially forks. - -``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to -scan a tasks virtual memory. It effectively controls the minimum scanning -rate for each task. - -``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are -scanned for a given scan. - +feature should be disabled. oops_all_cpu_backtrace ====================== diff --git a/Documentation/scheduler/debug.txt b/Documentation/scheduler/debug.txt new file mode 100644 index 000000000000..848d83c3123c --- /dev/null +++ b/Documentation/scheduler/debug.txt @@ -0,0 +1,48 @@ +Scheduler debugfs + +numa_balancing +-------------- + +`numa_balancing` directory is used to hold files to control NUMA +balancing feature. If the system overhead from the feature is too +high then the rate the kernel samples for NUMA hinting faults may be +controlled by the `scan_period_min_ms, scan_delay_ms, +scan_period_max_ms, scan_size_mb` files. + + +scan_period_min_ms, scan_delay_ms, scan_period_max_ms, scan_size_mb +=================================================================== + +Automatic NUMA balancing scans tasks address space and unmaps pages to +detect if pages are properly placed or if the data should be migrated to a +memory node local to where the task is running. Every "scan delay" the task +scans the next "scan size" number of pages in its address space. When the +end of the address space is reached the scanner restarts from the beginning. + +In combination, the "scan delay" and "scan size" determine the scan rate. +When "scan delay" decreases, the scan rate increases. The scan delay and +hence the scan rate of every task is adaptive and depends on historical +behaviour. If pages are properly placed then the scan delay increases, +otherwise the scan delay decreases. The "scan size" is not adaptive but +the higher the "scan size", the higher the scan rate. + +Higher scan rates incur higher system overhead as page faults must be +trapped and potentially data must be migrated. However, the higher the scan +rate, the more quickly a tasks memory is migrated to a local node if the +workload pattern changes and minimises performance impact due to remote +memory accesses. These files control the thresholds for scan delays and +the number of pages scanned. + +``scan_period_min_ms`` is the minimum time in milliseconds to scan a +tasks virtual memory. It effectively controls the maximum scanning +rate for each task. + +``scan_delay_ms`` is the starting "scan delay" used for a task when it +initially forks. + +``scan_period_max_ms`` is the maximum time in milliseconds to scan a +tasks virtual memory. It effectively controls the minimum scanning +rate for each task. + +``scan_size_mb`` is how many megabytes worth of pages are scanned for +a given scan.
After commit 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to debugfs"), some NUMA balancing sysctls enclosed with SCHED_DEBUG has been moved to debugfs. This patch move the document for these sysctls from Documentation/admin-guide/sysctl/kernel.rst to Documentation/scheduler/debug.txt to make the document consistent with the code. Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Fixes: 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to debugfs") Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Valentin Schneider <valentin.schneider@arm.com> Cc: stable@vger.kernel.org # since v5.13 --- Documentation/admin-guide/sysctl/kernel.rst | 46 +------------------- Documentation/scheduler/debug.txt | 48 +++++++++++++++++++++ 2 files changed, 49 insertions(+), 45 deletions(-) create mode 100644 Documentation/scheduler/debug.txt