before: last 6 bits of PID is used as index to store
information about tasks accessing VMA's.
after: hash_32 is used to take of cases where tasks are
created over a period of time, and thus improve collision
probability.
Result:
The patch series overall improving autonuma cost by a huge
margin.
Kernbench anbd dbench showed around 5% improvement and
system time in mmtest autonuma showed 80% improvement
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Raghavendra K T <raghavendra.kt@xxxxxxx>
---
include/linux/mm.h | 2 +-
kernel/sched/fair.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bd07289fc68e..8493697d1dce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1393,7 +1393,7 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
{
unsigned int pid_bit;
- pid_bit = current->pid % BITS_PER_LONG;
+ pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG));
if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) {
__set_bit(pid_bit, &vma->numab_state->access_pids[1]);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f76d5ecaf345..46fd9b372e4c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2929,7 +2929,7 @@ static bool vma_is_accessed(struct vm_area_struct *vma)
return true;
pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1];
- return test_bit(current->pid % BITS_PER_LONG, &pids);
+ return test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids);
}
#define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay)
--
2.34.1
