When tuning the watermark_scale_factor to reduce stalls and compactions
the high mark is also changed, it changed a bit too much. So this
patch introduces a slope that can reduce this overhead a bit, or
increase it if needed.
Signed-off-by: Peter Enderborg <peter.enderborg@xxxxxxxx>
---
Documentation/sysctl/vm.txt | 15 +++++++++++++++
include/linux/mm.h | 1 +
include/linux/mmzone.h | 2 ++
kernel/sysctl.c | 9 +++++++++
mm/page_alloc.c | 6 +++++-
5 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index eda628c..aecff6c 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -62,6 +62,7 @@ Currently, these files are in /proc/sys/vm:
- user_reserve_kbytes
- vfs_cache_pressure
- watermark_scale_factor
+- watermark_high_factor_slope
- zone_reclaim_mode
==============================================================
@@ -857,6 +858,20 @@ that the number of free pages kswapd maintains for latency reasons is
too small for the allocation bursts occurring in the system. This knob
can then be used to tune kswapd aggressiveness accordingly.
+=============================================================
+
+watermark_high_factor_slope:
+
+This factor is high mark for watermark_scale_factor.
+The unit is in percent.
+Max value is 1000 and min value is 100. (High watermark is the same as
+low water mark) Low watermark is min_wmark_pages + watermark_scale_factor.
+and high watermark is
+min_wmark_pages+(watermark_scale_factor * watermark_high_factor_slope).
+
+The default value is 200.
+
+
==============================================================
zone_reclaim_mode:
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7661156..c89536b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2094,6 +2094,7 @@ extern void zone_pcp_reset(struct zone *zone);
/* page_alloc.c */
extern int min_free_kbytes;
extern int watermark_scale_factor;
+extern int watermark_high_factor_slope;
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 67f2e3c..91bf842 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -886,6 +886,8 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
+//int watermark_high_factor_tilt_sysctl_handler(struct ctl_table *, int,
+// void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2fb4e27..83c48c9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1444,6 +1444,15 @@ static struct ctl_table vm_table[] = {
.extra2 = &one_thousand,
},
{
+ .procname = "watermark_high_factor_slope",
+ .data = &watermark_high_factor_slope,
+ .maxlen = sizeof(watermark_high_factor_slope),
+ .mode = 0644,
+ .proc_handler = watermark_scale_factor_sysctl_handler,
+ .extra1 = &one_hundred,
+ .extra2 = &one_thousand,
+ },
+ {
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48b5b01..3dc50ff 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -263,6 +263,7 @@ compound_page_dtor * const compound_page_dtors[] = {
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
int watermark_scale_factor = 10;
+int watermark_high_factor_slope = 200;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
@@ -6989,6 +6990,7 @@ static void __setup_per_zone_wmarks(void)
for_each_zone(zone) {
u64 tmp;
+ u64 tmp_high;
spin_lock_irqsave(&zone->lock, flags);
tmp = (u64)pages_min * zone->managed_pages;
@@ -7026,7 +7028,9 @@ static void __setup_per_zone_wmarks(void)
watermark_scale_factor, 10000));
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
+ tmp_high = mult_frac(tmp, watermark_high_factor_slope, 100);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp_high;
+
spin_unlock_irqrestore(&zone->lock, flags);
}
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
