lkml.org 
[lkml]   [2009]   [Jun]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH 4/4] Reintroduce zone_reclaim_interval for when zone_reclaim() scans and fails to avoid CPU spinning at 100% on NUMA
Date
> +
> +zone_reclaim_interval:
> +
> +The time allowed for off-node allocations after zone reclaim
> +has failed to reclaim enough pages to allow a local allocation.
> +
> +Time is set in seconds and set by default to 30 seconds.
> +
> +Reduce the interval if undesired off-node allocations occur or
> +set to 0 to always try and reclaim pages for node-local memory.
> +However, too frequent scans will have a negative impact on
> +off-node allocation performance and manifest as high CPU usage.
> +

good documentaion :)

Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

-kosaki



> ============ End of Document =================================
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 8895985..3a53e1c 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -335,6 +335,15 @@ struct zone {
> atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
>
> /*
> + * timestamp (in jiffies) of the last zone_reclaim that scanned
> + * but failed to free enough pages. This is used to avoid repeated
> + * scans when zone_reclaim() is unable to detect in advance that
> + * the scanning is useless. This can happen for example if a zone
> + * has large numbers of clean unmapped file pages on tmpfs
> + */
> + unsigned long zone_reclaim_failure;
> +
> + /*
> * prev_priority holds the scanning priority for this zone. It is
> * defined as the scanning priority at which we achieved our reclaim
> * target at the previous try_to_free_pages() or balance_pgdat()
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index c88b366..28a01e3 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -225,6 +225,7 @@ extern long vm_total_pages;
>
> #ifdef CONFIG_NUMA
> extern int zone_reclaim_mode;
> +extern int zone_reclaim_interval;
> extern int sysctl_min_unmapped_ratio;
> extern int sysctl_min_slab_ratio;
> extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 0554886..2afffa5 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -1221,6 +1221,15 @@ static struct ctl_table vm_table[] = {
> .extra1 = &zero,
> },
> {
> + .ctl_name = CTL_UNNUMBERED,
> + .procname = "zone_reclaim_interval",
> + .data = &zone_reclaim_interval,
> + .maxlen = sizeof(zone_reclaim_interval),
> + .mode = 0644,
> + .proc_handler = &proc_dointvec_jiffies,
> + .strategy = &sysctl_jiffies,
> + },
> + {
> .ctl_name = VM_MIN_UNMAPPED,
> .procname = "min_unmapped_ratio",
> .data = &sysctl_min_unmapped_ratio,
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 8be4582..5fa4843 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2315,6 +2315,13 @@ int zone_reclaim_mode __read_mostly;
> #define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
>
> /*
> + * Minimum time between zone_reclaim() scans that failed. Ordinarily, a
> + * scan will not fail because it will be determined in advance if it can
> + * succeeed but this does not always work. See mmzone.h
> + */
> +int zone_reclaim_interval __read_mostly = 30*HZ;
> +
> +/*
> * Priority for ZONE_RECLAIM. This determines the fraction of pages
> * of a node considered for each zone_reclaim. 4 scans 1/16th of
> * a zone.
> @@ -2464,6 +2471,15 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
> zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
> return ZONE_RECLAIM_FULL;
>
> + /* Watch for jiffie wraparound */
> + if (unlikely(jiffies < zone->zone_reclaim_failure))
> + zone->zone_reclaim_failure = jiffies;
> +
> + /* Do not attempt a scan if scanning failed recently */
> + if (time_before(jiffies,
> + zone->zone_reclaim_failure + zone_reclaim_interval))
> + return ZONE_RECLAIM_FULL;
> +
> if (zone_is_all_unreclaimable(zone))
> return ZONE_RECLAIM_FULL;
>
> @@ -2491,6 +2507,14 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
>
> if (!ret) {
> count_vm_events(PGSCAN_ZONERECLAIM_FAILED, 1);
> +
> + /*
> + * We were unable to reclaim enough pages to stay on node and
> + * unable to detect in advance that the scan would fail. Allow
> + * off node accesses for zone_reclaim_inteval jiffies before
> + * trying zone_reclaim() again
> + */
> + zone->zone_reclaim_failure = jiffies;
> }
>
> return ret;
> --
> 1.5.6.5
>





\
 
 \ /
  Last update: 2009-06-10 03:57    [W:0.187 / U:1.172 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site