diff options
| -rw-r--r-- | Documentation/admin-guide/sysctl/vm.rst | 19 | ||||
| -rw-r--r-- | include/linux/mmzone.h | 3 | ||||
| -rw-r--r-- | kernel/sysctl.c | 8 | ||||
| -rw-r--r-- | mm/page_alloc.c | 55 |
4 files changed, 4 insertions, 81 deletions
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 586cd4b86428..2fcafccb53a8 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -64,7 +64,6 @@ Currently, these files are in /proc/sys/vm: - overcommit_ratio - page-cluster - panic_on_oom -- percpu_pagelist_fraction - stat_interval - stat_refresh - numa_stat @@ -790,24 +789,6 @@ panic_on_oom=2+kdump gives you very strong tool to investigate why oom happens. You can get snapshot. -percpu_pagelist_fraction -======================== - -This is the fraction of pages at most (high mark pcp->high) in each zone that -are allocated for each per cpu page list. The min value for this is 8. It -means that we don't allow more than 1/8th of pages in each zone to be -allocated in any single per_cpu_pagelist. This entry only changes the value -of hot per cpu pagelists. User can specify a number like 100 to allocate -1/100th of each zone to each per cpu page list. - -The batch value of each per cpu pagelist is also updated as a result. It is -set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8) - -The initial value is zero. Kernel does not use this value at boot time to set -the high water marks for each per cpu page list. If the user writes '0' to this -sysctl, it will revert to this default behavior. - - stat_interval ============= diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f86018d5e362..7937a1d1d166 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1027,15 +1027,12 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d4a78e08f6d8..51213c33171e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2909,14 +2909,6 @@ static struct ctl_table vm_table[] = { .extra2 = &one_thousand, }, { - .procname = "percpu_pagelist_fraction", - .data = &percpu_pagelist_fraction, - .maxlen = sizeof(percpu_pagelist_fraction), - .mode = 0644, - .proc_handler = percpu_pagelist_fraction_sysctl_handler, - .extra1 = SYSCTL_ZERO, - }, - { .procname = "page_lock_unfairness", .data = &sysctl_page_lock_unfairness, .maxlen = sizeof(sysctl_page_lock_unfairness), diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 941a75b9fb5a..5abf2c1d4c58 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -120,7 +120,6 @@ typedef int __bitwise fpi_t; /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); -#define MIN_PERCPU_PAGELIST_FRACTION (8) struct pagesets { local_lock_t lock; @@ -193,7 +192,6 @@ EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); EXPORT_SYMBOL(init_on_alloc); @@ -6735,22 +6733,15 @@ static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long h /* * Calculate and set new high and batch values for all per-cpu pagesets of a - * zone, based on the zone's size and the percpu_pagelist_fraction sysctl. + * zone based on the zone's size. */ static void zone_set_pageset_high_and_batch(struct zone *zone) { unsigned long new_high, new_batch; - if (percpu_pagelist_fraction) { - new_high = zone_managed_pages(zone) / percpu_pagelist_fraction; - new_batch = max(1UL, new_high / 4); - if ((new_high / 4) > (PAGE_SHIFT * 8)) - new_batch = PAGE_SHIFT * 8; - } else { - new_batch = zone_batchsize(zone); - new_high = 6 * new_batch; - new_batch = max(1UL, 1 * new_batch); - } + new_batch = zone_batchsize(zone); + new_high = 6 * new_batch; + new_batch = max(1UL, 1 * new_batch); if (zone->pageset_high == new_high && zone->pageset_batch == new_batch) @@ -8413,44 +8404,6 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, return 0; } -/* - * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu - * pagelist can have before it gets flushed back to buddy allocator. - */ -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos) -{ - struct zone *zone; - int old_percpu_pagelist_fraction; - int ret; - - mutex_lock(&pcp_batch_high_lock); - old_percpu_pagelist_fraction = percpu_pagelist_fraction; - - ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || ret < 0) - goto out; - - /* Sanity checking to avoid pcp imbalance */ - if (percpu_pagelist_fraction && - percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { - percpu_pagelist_fraction = old_percpu_pagelist_fraction; - ret = -EINVAL; - goto out; - } - - /* No change? */ - if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) - goto out; - - for_each_populated_zone(zone) - zone_set_pageset_high_and_batch(zone); -out: - mutex_unlock(&pcp_batch_high_lock); - return ret; -} - #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES /* * Returns the number of pages that arch has reserved but |