diff options
| author | Mel Gorman <mgorman@suse.de> | 2012-11-21 05:18:23 +0400 |
|---|---|---|
| committer | Mel Gorman <mgorman@suse.de> | 2012-12-11 18:42:55 +0400 |
| commit | b8593bfda1652755136333cdd362de125b283a9c (patch) | |
| tree | c0395d9cf775fd9225e81b055fc8f5540a14333a /include | |
| parent | e42c8ff2999de1239a57d434bfbd8e9f2a56e814 (diff) | |
| download | linux-b8593bfda1652755136333cdd362de125b283a9c.tar.xz | |
mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
The PTE scanning rate and fault rates are two of the biggest sources of
system CPU overhead with automatic NUMA placement. Ideally a proper policy
would detect if a workload was properly placed, schedule and adjust the
PTE scanning rate accordingly. We do not track the necessary information
to do that but we at least know if we migrated or not.
This patch scans slower if a page was not migrated as the result of a
NUMA hinting fault up to sysctl_numa_balancing_scan_period_max which is
now higher than the previous default. Once every minute it will reset
the scanner in case of phase changes.
This is hilariously crude and the numbers are arbitrary. Workloads will
converge quite slowly in comparison to what a proper policy should be able
to do. On the plus side, we will chew up less CPU for workloads that have
no need for automatic balancing.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/mm_types.h | 3 | ||||
| -rw-r--r-- | include/linux/sched.h | 5 |
2 files changed, 6 insertions, 2 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c5fffa239861..e850a23dd6ec 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -410,6 +410,9 @@ struct mm_struct { */ unsigned long numa_next_scan; + /* numa_next_reset is when the PTE scanner period will be reset */ + unsigned long numa_next_reset; + /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; diff --git a/include/linux/sched.h b/include/linux/sched.h index 7d95a232b5b9..0f4ff2bd03f6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1562,9 +1562,9 @@ struct task_struct { #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) #ifdef CONFIG_NUMA_BALANCING -extern void task_numa_fault(int node, int pages); +extern void task_numa_fault(int node, int pages, bool migrated); #else -static inline void task_numa_fault(int node, int pages) +static inline void task_numa_fault(int node, int pages, bool migrated) { } #endif @@ -2009,6 +2009,7 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; extern unsigned int sysctl_numa_balancing_scan_delay; extern unsigned int sysctl_numa_balancing_scan_period_min; extern unsigned int sysctl_numa_balancing_scan_period_max; +extern unsigned int sysctl_numa_balancing_scan_period_reset; extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_numa_balancing_settle_count; |