The patch titled
mm: vmstat: use a single setter function and callback for adjusting percpu thresholds
has been removed from the -mm tree. Its filename was
mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: vmstat: use a single setter function and callback for adjusting percpu thresholds
From: Mel Gorman <mel@xxxxxxxxx>
reduce_pgdat_percpu_threshold() and restore_pgdat_percpu_threshold() exist
to adjust the per-cpu vmstat thresholds while kswapd is awake to avoid
errors due to counter drift. The functions duplicate some code so this
patch replaces them with a single set_pgdat_percpu_threshold() that takes
a callback function to calculate the desired threshold as a parameter.
[akpm@xxxxxxxxxxxxxxxxxxxx: readability tweak]
[kosaki.motohiro@xxxxxxxxxxxxxx: set_pgdat_percpu_threshold(): don't use for_each_online_cpu]
Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Reviewed-by: Christoph Lameter <cl@xxxxxxxxx>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/vmstat.h | 10 ++++++----
mm/vmscan.c | 19 +++++++++++++++++--
mm/vmstat.c | 36 +++++++-----------------------------
3 files changed, 30 insertions(+), 35 deletions(-)
diff -puN include/linux/vmstat.h~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds include/linux/vmstat.h
--- a/include/linux/vmstat.h~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds
+++ a/include/linux/vmstat.h
@@ -254,8 +254,11 @@ extern void dec_zone_state(struct zone *
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
void refresh_cpu_vm_stats(int);
-void reduce_pgdat_percpu_threshold(pg_data_t *pgdat);
-void restore_pgdat_percpu_threshold(pg_data_t *pgdat);
+
+int calculate_pressure_threshold(struct zone *zone);
+int calculate_normal_threshold(struct zone *zone);
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+ int (*calculate_pressure)(struct zone *));
#else /* CONFIG_SMP */
/*
@@ -300,8 +303,7 @@ static inline void __dec_zone_page_state
#define dec_zone_page_state __dec_zone_page_state
#define mod_zone_page_state __mod_zone_page_state
-static inline void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) { }
-static inline void restore_pgdat_percpu_threshold(pg_data_t *pgdat) { }
+#define set_pgdat_percpu_threshold(pgdat, callback) { }
static inline void refresh_cpu_vm_stats(int cpu) { }
#endif
diff -puN mm/vmscan.c~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds mm/vmscan.c
--- a/mm/vmscan.c~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds
+++ a/mm/vmscan.c
@@ -2448,9 +2448,24 @@ static int kswapd(void *p)
*/
if (!sleeping_prematurely(pgdat, order, remaining)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
- restore_pgdat_percpu_threshold(pgdat);
+
+ /*
+ * vmstat counters are not perfectly
+ * accurate and the estimated value
+ * for counters such as NR_FREE_PAGES
+ * can deviate from the true value by
+ * nr_online_cpus * threshold. To
+ * avoid the zone watermarks being
+ * breached while under pressure, we
+ * reduce the per-cpu vmstat threshold
+ * while kswapd is awake and restore
+ * them before going back to sleep.
+ */
+ set_pgdat_percpu_threshold(pgdat,
+ calculate_normal_threshold);
schedule();
- reduce_pgdat_percpu_threshold(pgdat);
+ set_pgdat_percpu_threshold(pgdat,
+ calculate_pressure_threshold);
} else {
if (remaining)
count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
diff -puN mm/vmstat.c~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds mm/vmstat.c
--- a/mm/vmstat.c~mm-vmstat-use-a-single-setter-function-and-callback-for-adjusting-percpu-thresholds
+++ a/mm/vmstat.c
@@ -83,7 +83,7 @@ EXPORT_SYMBOL(vm_stat);
#ifdef CONFIG_SMP
-static int calculate_pressure_threshold(struct zone *zone)
+int calculate_pressure_threshold(struct zone *zone)
{
int threshold;
int watermark_distance;
@@ -107,7 +107,7 @@ static int calculate_pressure_threshold(
return threshold;
}
-static int calculate_threshold(struct zone *zone)
+int calculate_normal_threshold(struct zone *zone)
{
int threshold;
int mem; /* memory in 128 MB units */
@@ -166,7 +166,7 @@ static void refresh_zone_stat_thresholds
for_each_populated_zone(zone) {
unsigned long max_drift, tolerate_drift;
- threshold = calculate_threshold(zone);
+ threshold = calculate_normal_threshold(zone);
for_each_online_cpu(cpu)
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
@@ -185,46 +185,24 @@ static void refresh_zone_stat_thresholds
}
}
-void reduce_pgdat_percpu_threshold(pg_data_t *pgdat)
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+ int (*calculate_pressure)(struct zone *))
{
struct zone *zone;
int cpu;
int threshold;
int i;
- get_online_cpus();
for (i = 0; i < pgdat->nr_zones; i++) {
zone = &pgdat->node_zones[i];
if (!zone->percpu_drift_mark)
continue;
- threshold = calculate_pressure_threshold(zone);
- for_each_online_cpu(cpu)
- per_cpu_ptr(zone->pageset, cpu)->stat_threshold
- = threshold;
- }
- put_online_cpus();
-}
-
-void restore_pgdat_percpu_threshold(pg_data_t *pgdat)
-{
- struct zone *zone;
- int cpu;
- int threshold;
- int i;
-
- get_online_cpus();
- for (i = 0; i < pgdat->nr_zones; i++) {
- zone = &pgdat->node_zones[i];
- if (!zone->percpu_drift_mark)
- continue;
-
- threshold = calculate_threshold(zone);
- for_each_online_cpu(cpu)
+ threshold = (*calculate_pressure)(zone);
+ for_each_possible_cpu(cpu)
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
= threshold;
}
- put_online_cpus();
}
/*
_
Patches currently in -mm which might be from mel@xxxxxxxxx are
origin.patch
linux-next.patch
writeback-io-less-balance_dirty_pages.patch
writeback-consolidate-variable-names-in-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages-fix.patch
writeback-prevent-duplicate-balance_dirty_pages_ratelimited-calls.patch
writeback-account-per-bdi-accumulated-written-pages.patch
writeback-bdi-write-bandwidth-estimation.patch
writeback-bdi-write-bandwidth-estimation-fix.patch
writeback-show-bdi-write-bandwidth-in-debugfs.patch
writeback-quit-throttling-when-bdi-dirty-pages-dropped-low.patch
writeback-reduce-per-bdi-dirty-threshold-ramp-up-time.patch
writeback-make-reasonable-gap-between-the-dirty-background-thresholds.patch
writeback-scale-down-max-throttle-bandwidth-on-concurrent-dirtiers.patch
writeback-add-trace-event-for-balance_dirty_pages.patch
writeback-make-nr_to_write-a-per-file-limit.patch
writeback-make-nr_to_write-a-per-file-limit-fix.patch
thp-add-pagetranscompound.patch
add-debugging-aid-for-memory-initialisation-problems.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
