Previously, to probe the working set of a task, we'd use
a very simple and crude method: mark all of its address
space PROT_NONE.
That method has various (obvious) disadvantages:
- it samples the working set at dissimilar rates,
giving some tasks a sampling quality advantage
over others.
- creates performance problems for tasks with very
large working sets
- over-samples processes with large address spaces but
which only very rarely execute
Improve that method by keeping a rotating offset into the
address space that marks the current position of the scan,
and advance it by a constant rate (in a CPU cycles execution
proportional manner). If the offset reaches the last mapped
address of the mm then it then it starts over at the first
address.
The per-task nature of the working set sampling functionality
in this tree allows such constant rate, per task,
execution-weight proportional sampling of the working set,
with an adaptive sampling interval/frequency that goes from
once per 100 msecs up to just once per 1.6 seconds.
The current sampling volume is 256 MB per interval.
As tasks mature and converge their working set, so does the
sampling rate slow down to just a trickle, 256 MB per 1.6
seconds of CPU time executed.
This, beyond being adaptive, also rate-limits rarely
executing systems and does not over-sample on overloaded
systems.
[ In AutoNUMA speak, this patch deals with the effective sampling
rate of the 'hinting page fault'. AutoNUMA's scanning is
currently rate-limited, but it is also fundamentally
single-threaded, executing in the knuma_scand kernel thread,
so the limit in AutoNUMA is global and does not scale up with
the number of CPUs, nor does it scan tasks in an execution
proportional manner.
So the idea of rate-limiting the scanning was first implemented
in the AutoNUMA tree via a global rate limit. This patch goes
beyond that by implementing an execution rate proportional
working set sampling rate that is not implemented via a single
global scanning daemon. ]
[ Dan Carpenter pointed out a possible NULL pointer dereference in the
first version of this patch. ]
Based-on-idea-by: Andrea Arcangeli <[email protected]>
Bug-Found-By: Dan Carpenter <[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Mel Gorman <[email protected]>
[ Wrote changelog and fixed bug. ]
Signed-off-by: Ingo Molnar <[email protected]>
---
include/linux/mm_types.h | 1 +
include/linux/sched.h | 1 +
kernel/sched/fair.c | 43 ++++++++++++++++++++++++++++++-------------
kernel/sysctl.c | 7 +++++++
4 files changed, 39 insertions(+), 13 deletions(-)
Index: linux/include/linux/mm_types.h
===================================================================
--- linux.orig/include/linux/mm_types.h
+++ linux/include/linux/mm_types.h
@@ -405,6 +405,7 @@ struct mm_struct {
#endif
#ifdef CONFIG_SCHED_NUMA
unsigned long numa_next_scan;
+ unsigned long numa_scan_offset;
int numa_scan_seq;
#endif
struct uprobes_state uprobes_state;
Index: linux/include/linux/sched.h
===================================================================
--- linux.orig/include/linux/sched.h
+++ linux/include/linux/sched.h
@@ -2047,6 +2047,7 @@ extern enum sched_tunable_scaling sysctl
extern unsigned int sysctl_sched_numa_scan_period_min;
extern unsigned int sysctl_sched_numa_scan_period_max;
+extern unsigned int sysctl_sched_numa_scan_size;
extern unsigned int sysctl_sched_numa_settle_count;
#ifdef CONFIG_SCHED_DEBUG
Index: linux/kernel/sched/fair.c
===================================================================
--- linux.orig/kernel/sched/fair.c
+++ linux/kernel/sched/fair.c
@@ -825,8 +825,9 @@ static void account_numa_dequeue(struct
/*
* numa task sample period in ms: 5s
*/
-unsigned int sysctl_sched_numa_scan_period_min = 5000;
-unsigned int sysctl_sched_numa_scan_period_max = 5000*16;
+unsigned int sysctl_sched_numa_scan_period_min = 100;
+unsigned int sysctl_sched_numa_scan_period_max = 100*16;
+unsigned int sysctl_sched_numa_scan_size = 256; /* MB */
/*
* Wait for the 2-sample stuff to settle before migrating again
@@ -912,6 +913,9 @@ void task_numa_work(struct callback_head
unsigned long migrate, next_scan, now = jiffies;
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
+ struct vm_area_struct *vma;
+ unsigned long offset, end;
+ long length;
WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -938,18 +942,31 @@ void task_numa_work(struct callback_head
if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
return;
- ACCESS_ONCE(mm->numa_scan_seq)++;
- {
- struct vm_area_struct *vma;
-
- down_write(&mm->mmap_sem);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- if (!vma_migratable(vma))
- continue;
- change_protection(vma, vma->vm_start, vma->vm_end, vma_prot_none(vma), 0);
- }
- up_write(&mm->mmap_sem);
+ offset = mm->numa_scan_offset;
+ length = sysctl_sched_numa_scan_size;
+ length <<= 20;
+
+ down_write(&mm->mmap_sem);
+ vma = find_vma(mm, offset);
+ if (!vma) {
+ ACCESS_ONCE(mm->numa_scan_seq)++;
+ offset = 0;
+ vma = mm->mmap;
+ }
+ for (; vma && length > 0; vma = vma->vm_next) {
+ if (!vma_migratable(vma))
+ continue;
+
+ offset = max(offset, vma->vm_start);
+ end = min(ALIGN(offset + length, HPAGE_SIZE), vma->vm_end);
+ length -= end - offset;
+
+ change_prot_none(vma, offset, end);
+
+ offset = end;
}
+ mm->numa_scan_offset = offset;
+ up_write(&mm->mmap_sem);
}
/*
Index: linux/kernel/sysctl.c
===================================================================
--- linux.orig/kernel/sysctl.c
+++ linux/kernel/sysctl.c
@@ -367,6 +367,13 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "sched_numa_scan_size_mb",
+ .data = &sysctl_sched_numa_scan_size,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "sched_numa_settle_count",
.data = &sysctl_sched_numa_settle_count,
.maxlen = sizeof(unsigned int),