88f5acf88a
Commitaa45484("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pullaa454840"mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
89 lines
1.8 KiB
C
89 lines
1.8 KiB
C
/*
|
|
* linux/mm/mmzone.c
|
|
*
|
|
* management codes for pgdats and zones.
|
|
*/
|
|
|
|
|
|
#include <linux/stddef.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/module.h>
|
|
|
|
struct pglist_data *first_online_pgdat(void)
|
|
{
|
|
return NODE_DATA(first_online_node);
|
|
}
|
|
|
|
struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
|
|
{
|
|
int nid = next_online_node(pgdat->node_id);
|
|
|
|
if (nid == MAX_NUMNODES)
|
|
return NULL;
|
|
return NODE_DATA(nid);
|
|
}
|
|
|
|
/*
|
|
* next_zone - helper magic for for_each_zone()
|
|
*/
|
|
struct zone *next_zone(struct zone *zone)
|
|
{
|
|
pg_data_t *pgdat = zone->zone_pgdat;
|
|
|
|
if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
|
|
zone++;
|
|
else {
|
|
pgdat = next_online_pgdat(pgdat);
|
|
if (pgdat)
|
|
zone = pgdat->node_zones;
|
|
else
|
|
zone = NULL;
|
|
}
|
|
return zone;
|
|
}
|
|
|
|
static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
return node_isset(zonelist_node_idx(zref), *nodes);
|
|
#else
|
|
return 1;
|
|
#endif /* CONFIG_NUMA */
|
|
}
|
|
|
|
/* Returns the next zone at or below highest_zoneidx in a zonelist */
|
|
struct zoneref *next_zones_zonelist(struct zoneref *z,
|
|
enum zone_type highest_zoneidx,
|
|
nodemask_t *nodes,
|
|
struct zone **zone)
|
|
{
|
|
/*
|
|
* Find the next suitable zone to use for the allocation.
|
|
* Only filter based on nodemask if it's set
|
|
*/
|
|
if (likely(nodes == NULL))
|
|
while (zonelist_zone_idx(z) > highest_zoneidx)
|
|
z++;
|
|
else
|
|
while (zonelist_zone_idx(z) > highest_zoneidx ||
|
|
(z->zone && !zref_in_nodemask(z, nodes)))
|
|
z++;
|
|
|
|
*zone = zonelist_zone(z);
|
|
return z;
|
|
}
|
|
|
|
#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
|
|
int memmap_valid_within(unsigned long pfn,
|
|
struct page *page, struct zone *zone)
|
|
{
|
|
if (page_to_pfn(page) != pfn)
|
|
return 0;
|
|
|
|
if (page_zone(page) != zone)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
|