memory-hotplug: fix zone stat mismatch

During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing so that kernel are hang out.

The cause is that when we do memory-hotadd after memory-remove, __zone_pcp_update clear out zone's ZONE_STAT_ITEMS in setup_pageset although vm_stat_diff of all CPU still have value.

In addtion, when we offline all pages of the zone, we reset them in zone_pcp_reset without drain so that we lost zone stat item.

This patch fixes it.

* from v2
* Add Reviewed-by - Wen

* from v1
* drain offline patch - KOSAKI, Wen

Cc Kamezawa Hiroyuki <[email protected]>

Cc Yasuaki Ishimatsu <[email protected]>

Cc KOSAKI Motohiro <[email protected]>

Reviewed-by Wen Congyang <[email protected]>

Signed-off-by Minchan Kim <[email protected]>

---
  include/linux/vmstat.h |    4 ++++
  mm/page_alloc.c        |    7 +++++++
  mm/vmstat.c            |   12 ++++++++++++
  3 files changed, 23 insertions(+)

include/linux/vmstat.h +4 -0

index ad2cfd5..5d31876 100644
@@ -198,6 +198,8 @@ extern void __dec_zone_state(struct zone *, enum zone_stat_item);
  void refresh_cpu_vm_stats(int);
  void refresh_zone_stat_thresholds(void);
 
+void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
+
  int calculate_pressure_threshold(struct zone *zone);
  int calculate_normal_threshold(struct zone *zone);
  void set_pgdat_percpu_threshold(pg_data_t *pgdat,

@@ -251,6 +253,8 @@ static inline void __dec_zone_page_state(struct page *page,
  static inline void refresh_cpu_vm_stats(int cpu) { }
  static inline void refresh_zone_stat_thresholds(void) { }
 
+static inline void drain_zonestat(struct zone *zone,
+			struct per_cpu_pageset *pset) { }
  #endif		/* CONFIG_SMP */
 
  extern const char * const vmstat_text[];

mm/page_alloc.c +7 -0

index ab58346..980f2e7 100644
@@ -5904,6 +5904,7 @@ static int __meminit __zone_pcp_update(void *data)
  		local_irq_save(flags);
  		if (pcp->count > 0)
  			free_pcppages_bulk(zone, pcp->count, pcp);
+		drain_zonestat(zone, pset);
  		setup_pageset(pset, batch);
  		local_irq_restore(flags);
  	}

@@ -5920,10 +5921,16 @@ void __meminit zone_pcp_update(struct zone *zone)
  void zone_pcp_reset(struct zone *zone)
  {
  	unsigned long flags;
+	int cpu;
+	struct per_cpu_pageset *pset;
 
  	/* avoid races with drain_pages()  */
  	local_irq_save(flags);
  	if (zone->pageset != &boot_pageset) {
+		for_each_online_cpu(cpu) {
+			pset = per_cpu_ptr(zone->pageset, cpu);
+			drain_zonestat(zone, pset);
+		}
  		free_percpu(zone->pageset);
  		zone->pageset = &boot_pageset;
  	}

mm/vmstat.c +5 -0

index b3e3b9d..d4cc1c2 100644
@@ -495,6 +495,18 @@ void refresh_cpu_vm_stats(int cpu)
  			atomic_long_add(global_diff[i], &vm_stat[i]);
  }
 
+void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
+{
+	int i;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)

Hi Minchan,

Sorry for late reply.

Quoted 2 lines · Minchan Kim

During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing so that kernel are hang out.

Why does your system hang out by increasing NR_ISOLATED_[ANON|FILE]? I cannot understand what has happened by your system.

During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing so that kernel are hang out.

The cause is that when we do memory-hotadd after memory-remove, __zone_pcp_update clear out zone's ZONE_STAT_ITEMS in setup_pageset although vm_stat_diff of all CPU still have value.

In addtion, when we offline all pages of the zone, we reset them in zone_pcp_reset without drain so that we lost zone stat item.

Quoted 10 lines · On Thu, 20 Sep 2012 15:43:25 +0900 Minchan Kim <[email protected]> wrote:

During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing so that kernel are hang out.

The cause is that when we do memory-hotadd after memory-remove, __zone_pcp_update clear out zone's ZONE_STAT_ITEMS in setup_pageset although vm_stat_diff of all CPU still have value.

In addtion, when we offline all pages of the zone, we reset them in zone_pcp_reset without drain so that we lost zone stat item.

Here's what I ended up with for a changelog:

: During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing, : causing the kernel to hang. When the system doesn't have enough free : pages, it enters reclaim but never reclaim any pages due to : too_many_isolated()==true and loops forever.
:
: The cause is that when we do memory-hotadd after memory-remove, : __zone_pcp_update() clears a zone's ZONE_STAT_ITEMS in setup_pageset() : although the vm_stat_diff of all CPUs still have values.
:
: In addtion, when we offline all pages of the zone, we reset them in : zone_pcp_reset without draining so we loss some zone stat item.

As memory hotplug seems fairly immature and broken, I'm thinking there's no point in backporting this into -stable. And I don't *think*

we really need it in 3.6 either? (It doesn't apply cleanly to current mainline anyway - I didn't check why).

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>