fold per-CPU vmstats remotely
Subsystems (3)
cover fold per-CPU vmstats remotely
This patch series addresses the following two problems:
1. A customer provided some evidence which indicates that the idle tick was stopped; albeit, CPU-specific vmstat counters still remained populated.
Thus one can only assume quiet_vmstat() was not invoked on return to the idle loop. If I understand correctly, I suspect this divergence might erroneously prevent a reclaim attempt by kswapd. If the number of zone specific free pages are below their per-cpu drift value then zone_page_state_snapshot() is used to compute a more accurate view of the aforementioned statistic. Thus any task blocked on the NUMA node specific pfmemalloc_wait queue will be unable to make significant progress via direct reclaim unless it is killed after being woken up by kswapd
(see throttle_direct_reclaim())
2. With a SCHED_FIFO task that busy loops on a given CPU, and kworker for that CPU at SCHED_OTHER priority, queuing work to sync per-vmstats will either cause that work to never execute, or stalld (i.e. stall daemon) boosts kworker priority which causes a latency violation
By having vmstat_shepherd flush the per-CPU counters to the global counters from remote CPUs.
This is done using cmpxchg to manipulate the counters, both CPU locally (via the account functions), and remotely (via cpu_vm_stats_fold).
Thanks to Aaron Tomlin for diagnosing issue 1 and writing the initial patch series.
include/linux/mmzone.h | 3 mm/vmstat.c | 424 ++++++++++++++++++++++++++++++++++++++++++++++++------------------------------------------ 2 files changed, 230 insertions(+), 197 deletions(-)
PATCH 1/5 mm/vmstat: remove remote node draining
Draining of pages from the local pcp for a remote zone was necessary since:
"Note that remote node draining is a somewhat esoteric feature that is required on large NUMA systems because otherwise significant portions of system memory can become trapped in pcp queues. The number of pcp is determined by the number of processors and nodes in a system. A system with 4 processors and 2 nodes has 8 pcps which is okay. But a system with 1024 processors and 512 nodes has 512k pcps with a high potential for large amount of memory being caught in them."
Since commit 443c2accd1b6679a1320167f8f56eed6536b806e ("mm/page_alloc: remotely drain per-cpu lists"), drain_all_pages() is able to remotely free those pages when necessary.
include/linux/mmzone.h +0 -3
@@ -577,9 +577,6 @@ struct per_cpu_pages {int high;/* high watermark, emptying needed */ int batch;/* chunk size for buddy add/remove */ short free_factor;/* batch scaling factor during free */ -#ifdef CONFIG_NUMA -short expire;/* When 0, remote pagesets are drained */ -#endif /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS ];
mm/vmstat.c +4 -43
85 lines not on this page · raw message
PATCH 2/5 mm/vmstat: switch counter modification to cmpxchg
In reply to Marcelo TosattiIn preparation to switch vmstat shepherd to flush per-CPU counters remotely, switch all functions that modify the counters to use cmpxchg.
To test the performance difference, a page allocator microbenchmark:
https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/bench/page_bench01.c
with loops=1000000 was used, on Intel Core i7-11850H @ 2.50GHz.
For the single_page_alloc_free test, which does
/** Loop to measure **/
for (i = 0; i < rec->loops; i++) {
my_page = alloc_page(gfp_mask);
if (unlikely(my_page == NULL))
return 0;
__free_page(my_page);
}Unit is cycles.
Vanilla Patched Diff
159 156 -1.9%
mm/vmstat.c +182 -143
@@ -334,6 +334,188 @@ void set_pgdat_percpu_threshold(pg_data_ } } +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +/* +* If we have cmpxchg_local support then we do not need to incur the overhead +* that comes with local_irq_save/restore if we use this_cpu_cmpxchg. +* +* mod_state() modifies the zone counter state through atomic per cpu +* operations. +* +* Overstep mode specifies how overstep should handled: +* 0 No overstepping +* 1 Overstepping half of threshold +* -1 Overstepping minus half of threshold +*/ +static inline void mod_zone_state (struct zone *zone,enum zone_stat_item item, +long delta,int overstep_mode) +{ +struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; +s8 __percpu *p = pcp->vm_stat_diff + item; +long o, n, t, z; + +do { + z =0 ;/* overflow to zone counters */ + +/* +* The fetching of the stat_threshold is racy. We may apply +* a counter threshold to the wrong the cpu if we get +* rescheduled while executing here. However, the next +* counter update will apply the threshold again and +* therefore bring the counter under the threshold again. +* +* Most of the time the thresholds are the same anyways +* for all cpus in a zone. +*/ + t =this_cpu_read (pcp->stat_threshold); + + o =this_cpu_read (*p); + n = delta + o; + +if (abs (n) > t) { +int os = overstep_mode * (t >>1 ); + +/* Overflow must be added to zone counters */ + z = n + os; + n = -os; + } + }while (this_cpu_cmpxchg (*p, o, n) != o); + +if (z) +zone_page_state_add (z, zone, item); +} + +void mod_zone_page_state (struct zone *zone,enum zone_stat_item item, +long delta) +{ +mod_zone_state (zone, item, delta,0 ); +} +EXPORT_SYMBOL (mod_zone_page_state); + +void __mod_zone_page_state (struct zone *zone,enum zone_stat_item item, +long delta) +{ +mod_zone_state (zone, item, delta,0 ); +} +EXPORT_SYMBOL (__mod_zone_page_state); + +void inc_zone_page_state (struct page *page,enum zone_stat_item item) +{ +mod_zone_state (page_zone (page), item,1 ,1 ); +} +EXPORT_SYMBOL (inc_zone_page_state); + +void __inc_zone_page_state (struct page *page,enum zone_stat_item item) +{ +mod_zone_state (page_zone (page), item,1 ,1 ); +} +EXPORT_SYMBOL (__inc_zone_page_state); + +void dec_zone_page_state (struct page *page,enum zone_stat_item item) +{ +mod_zone_state (page_zone (page), item,-1 ,-1 ); +} +EXPORT_SYMBOL (dec_zone_page_state); + +void __dec_zone_page_state (struct page *page,enum zone_stat_item item) +{ +mod_zone_state (page_zone (page), item,-1 ,-1 ); +} +EXPORT_SYMBOL (__dec_zone_page_state); + +static inline void mod_node_state (struct pglist_data *pgdat, +enum node_stat_item item, +int delta,int overstep_mode) +{ +struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; +s8 __percpu *p = pcp->vm_node_stat_diff + item; +long o, n, t, z; + +if (vmstat_item_in_bytes (item)) { +/* +* Only cgroups use subpage accounting right now; at +* the global level, these items still change in +* multiples of whole pages. Store them as pages +* internally to keep the per-cpu counters compact. +*/ +VM_WARN_ON_ONCE (delta & (PAGE_SIZE -1 )); + delta >>=PAGE_SHIFT ; + } + +do { + z =0 ;/* overflow to node counters */ + +/* +* The fetching of the stat_threshold is racy. We may apply +* a counter threshold to the wrong the cpu if we get +* rescheduled while executing here. However, the next +* counter update will apply the threshold again and +* therefore bring the counter under the threshold again. +* +* Most of the time the thresholds are the same anyways +* for all cpus in a node. +*/ + t =this_cpu_read (pcp->stat_threshold); + + o =this_cpu_read (*p); + n = delta + o; + +if (abs (n) > t) { +int os = overstep_mode * (t >>1 ); + +/* Overflow must be added to node counters */ + z = n + os; + n = -os; + } + }while (this_cpu_cmpxchg (*p, o, n) != o); + +if (z) +node_page_state_add (z, pgdat, item); +} + +void mod_node_page_state (struct pglist_data *pgdat,enum node_stat_item item, +long delta) +{ +mod_node_state (pgdat, item, delta,0 ); +} +EXPORT_SYMBOL (mod_node_page_state); + +void __mod_node_page_state (struct pglist_data *pgdat,enum node_stat_item item, +long delta) +{ +mod_node_state (pgdat, item, delta,0 ); +} +EXPORT_SYMBOL (__mod_node_page_state); + +void inc_node_state (struct pglist_data *pgdat,enum node_stat_item item) +{ +mod_node_state (pgdat, item,1 ,1 ); +} + +void inc_node_page_state (struct page *page,enum node_stat_item item) +{ +mod_node_state (page_pgdat (page), item,1 ,1 ); +} +EXPORT_SYMBOL (inc_node_page_state); + +void __inc_node_page_state (struct page *page,enum node_stat_item item) +{ +mod_node_state (page_pgdat (page), item,1 ,1 ); +} +EXPORT_SYMBOL (__inc_node_page_state); + +void dec_node_page_state (struct page *page,enum node_stat_item item) +{ +mod_node_state (page_pgdat (page), item,-1 ,-1 ); +} +EXPORT_SYMBOL (dec_node_page_state); + +void __dec_node_page_state (struct page *page,enum node_stat_item item) +{ +mod_node_state (page_pgdat (page), item,-1 ,-1 ); +} +EXPORT_SYMBOL (__dec_node_page_state); +#else /* * For use when we know that interrupts are disabled, * or when we know that preemption is disabled and that
@@ -541,149 +723,6 @@ void __dec_node_page_state(struct page * }EXPORT_SYMBOL (__dec_node_page_state); -#ifdef CONFIG_HAVE_CMPXCHG_LOCAL -/* -* If we have cmpxchg_local support then we do not need to incur the overhead -* that comes with local_irq_save/restore if we use this_cpu_cmpxchg. -* -* mod_state() modifies the zone counter state through atomic per cpu -* operations. -* -* Overstep mode specifies how overstep should handled: -* 0 No overstepping -* 1 Overstepping half of threshold -* -1 Overstepping minus half of threshold -*/ -static inline void mod_zone_state (struct zone *zone, -enum zone_stat_item item,long delta,int overstep_mode) -{ -struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; -s8 __percpu *p = pcp->vm_stat_diff + item; -long o, n, t, z; - -do { - z =0 ;/* overflow to zone counters */ - -/* -* The fetching of the stat_threshold is racy. We may apply -* a counter threshold to the wrong the cpu if we get -* rescheduled while executing here. However, the next -* counter update will apply the threshold again and -* therefore bring the counter under the threshold again. -* -* Most of the time the thresholds are the same anyways -* for all cpus in a zone. -*/ - t =this_cpu_read (pcp->stat_threshold); - - o =this_cpu_read (*p); - n = delta + o; - -if (abs (n) > t) { -int os = overstep_mode * (t >>1 ) ; - -/* Overflow must be added to zone counters */ - z = n + os; - n = -os; - } - }while (this_cpu_cmpxchg (*p, o, n) != o); - -if (z) -zone_page_state_add (z, zone, item); -} - -void mod_zone_page_state (struct zone *zone,enum zone_stat_item item, -long delta) -{ -mod_zone_state (zone, item, delta,0 ); -} -EXPORT_SYMBOL (mod_zone_page_state); - -void inc_zone_page_state (struct page *page,enum zone_stat_item item) -{ -mod_zone_state (page_zone (page), item,1 ,1 ); -} -EXPORT_SYMBOL (inc_zone_page_state); - -void dec_zone_page_state (struct page *page,enum zone_stat_item item) -{ -mod_zone_state (page_zone (page), item,-1 ,-1 ); -} -EXPORT_SYMBOL (dec_zone_page_state); - -static inline void mod_node_state (struct pglist_data *pgdat, -enum node_stat_item item,int delta,int overstep_mode) -{ -struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; -s8 __percpu *p = pcp->vm_node_stat_diff + item; -long o, n, t, z; - -if (vmstat_item_in_bytes (item)) { -/* -* Only cgroups use subpage accounting right now; at -* the global level, these items still change in -* multiples of whole pages. Store them as pages -* internally to keep the per-cpu counters compact. -*/ -VM_WARN_ON_ONCE (delta & (PAGE_SIZE -1 )); - delta >>=PAGE_SHIFT ; - } - -do { - z =0 ;/* overflow to node counters */ - -/* -* The fetching of the stat_threshold is racy. We may apply -* a counter threshold to the wrong the cpu if we get -* rescheduled while executing here. However, the next -* counter update will apply the threshold again and -* therefore bring the counter under the threshold again. -* -* Most of the time the thresholds are the same anyways -* for all cpus in a node. -*/ - t =this_cpu_read (pcp->stat_threshold); - - o =this_cpu_read (*p); - n = delta + o; - -if (abs (n) > t) { -int os = overstep_mode * (t >>1 ) ; - -/* Overflow must be added to node counters */ - z = n + os; - n = -os; - } - }while (this_cpu_cmpxchg (*p, o, n) != o); - -if (z) -node_page_state_add (z, pgdat, item); -} - -void mod_node_page_state (struct pglist_data *pgdat,enum node_stat_item item, -long delta) -{ -mod_node_state (pgdat, item, delta,0 ); -} -EXPORT_SYMBOL (mod_node_page_state); - -void inc_node_state (struct pglist_data *pgdat,enum node_stat_item item) -{ -mod_node_state (pgdat, item,1 ,1 ); -} - -void inc_node_page_state (struct page *page,enum node_stat_item item) -{ -mod_node_state (page_pgdat (page), item,1 ,1 ); -} -EXPORT_SYMBOL (inc_node_page_state); - -void dec_node_page_state (struct page *page,enum node_stat_item item) -{ -mod_node_state (page_pgdat (page), item,-1 ,-1 ); -} -EXPORT_SYMBOL (dec_node_page_state); -#else /* * Use interrupt disable to serialize counter updates */
PATCH 3/5 mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
In reply to Marcelo TosattiIn preparation to switch vmstat shepherd to flush
per-CPU counters remotely, use a cmpxchg loop
instead of a pair of read/write instructions.
mm/vmstat.c +10 -7
@@ -885,7 +885,7 @@ static int refresh_cpu_vm_stats(void) }/* -* Fold the data for an offline cpu into the global array. +* Fold the data for a cpu into the global array. * There cannot be any access by the offline cpu and therefore * synchronization is simplified. */
@@ -906,8 +906,9 @@ void cpu_vm_stats_fold(int cpu)if (pzstats->vm_stat_diff[i]) {int v; - v = pzstats->vm_stat_diff[i]; - pzstats->vm_stat_diff[i] =0 ; +do { + v = pzstats->vm_stat_diff[i]; + }while (cmpxchg (&pzstats->vm_stat_diff[i], v,0 ) != v);atomic_long_add (v, &zone->vm_stat[i]); global_zone_diff[i] += v; }
@@ -917,8 +918,9 @@ void cpu_vm_stats_fold(int cpu)if (pzstats->vm_numa_event[i]) {unsigned long v; - v = pzstats->vm_numa_event[i]; - pzstats->vm_numa_event[i] =0 ; +do { + v = pzstats->vm_numa_event[i]; + }while (cmpxchg (&pzstats->vm_numa_event[i], v,0 ) != v);zone_numa_event_add (v, zone, i); } }
@@ -934,8 +936,9 @@ void cpu_vm_stats_fold(int cpu)if (p->vm_node_stat_diff[i]) {int v; - v = p->vm_node_stat_diff[i]; - p->vm_node_stat_diff[i] =0 ; +do { + v = p->vm_node_stat_diff[i]; + }while (cmpxchg (&p->vm_node_stat_diff[i], v,0 ) != v);atomic_long_add (v, &pgdat->vm_stat[i]); global_node_diff[i] += v; }
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 3 lines · Marcelo Tosatti
In preparation to switch vmstat shepherd to flush
per-CPU counters remotely, use a cmpxchg loop
instead of a pair of read/write instructions.
You are mixing full atomic cmpxchg and per cpu atomic cmpxchg? That does not work.
I thought you would only run this while the kernel is not active on the remote cpu? Then you dont need any cmpxchg and you can leave the function as is.
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 8 lines · Christoph Lameter
Quoted 3 lines · Marcelo Tosatti
In preparation to switch vmstat shepherd to flush
per-CPU counters remotely, use a cmpxchg loop
instead of a pair of read/write instructions.You are mixing full atomic cmpxchg and per cpu atomic cmpxchg? That does not work.
OK, missing locked on the local functions. Can fix that.
Quoted 3 lines
I thought you would only run this while the kernel is not active on the remote cpu? Then you dont need any cmpxchg and you can leave the function as is.
The remote cpu can enter kernel mode while this function executes.
There is no mode which indicates userspace cannot enter the kernel.
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 5 lines · Marcelo Tosatti
Quoted 3 lines
I thought you would only run this while the kernel is not active on the remote cpu? Then you dont need any cmpxchg and you can leave the function as is.
The remote cpu can enter kernel mode while this function executes.
Isnt there some lock/serializtion to stall the kernel until you are done?
Quoted 1 line
There is no mode which indicates userspace cannot enter the kernel.
There are lot of thinngs that happen upon entry to the kernel. I would hope that you can do something there. Scheduler?
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 9 lines · Christoph Lameter
Quoted 5 lines · Marcelo Tosatti
Quoted 3 lines
I thought you would only run this while the kernel is not active on the remote cpu? Then you dont need any cmpxchg and you can leave the function as is.
The remote cpu can enter kernel mode while this function executes.
Isnt there some lock/serializtion to stall the kernel until you are done?
Not that i know of. Anyway, an additional datapoint is:
"Software defined PLC"
(https://www.redhat.com/en/blog/software-defined-programmable-logic-controller-introduction),
applications
can perform system calls in their time sensitive loop.
One example of an opensource software is OpenPLC.
One would like to avoid interruptions for those cases as well.
Quoted 4 lines
Quoted 1 line
There is no mode which indicates userspace cannot enter the kernel.
There are lot of thinngs that happen upon entry to the kernel. I would hope that you can do something there. Scheduler?
The use-case in question is with isolation, where a CPU is dedicated to a single task. So the scheduler should not be an issue.
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 4 lines · Marcelo Tosatti
Quoted 1 line
Isnt there some lock/serializtion to stall the kernel until you are done?
Not that i know of. Anyway, an additional datapoint is:
Quoted 8 lines
"Software defined PLC"
(https://www.redhat.com/en/blog/software-defined-programmable-logic-controller-introduction),
applications
can perform system calls in their time sensitive loop.One example of an opensource software is OpenPLC.
One would like to avoid interruptions for those cases as well.
Well allowing sytem calls during "time sensitiveness" implies it is not that sensitive to vmstat updates which have a smaller impact than system calls.
Unless we are talking about virtual system calls like gettimeofday or clock_gettime. These do not enter the kernel if configured correctly.
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
Quoted 11 lines · Christoph Lameter
Quoted 9 lines · Marcelo Tosatti
Quoted 1 line
Isnt there some lock/serializtion to stall the kernel until you are done?
Not that i know of. Anyway, an additional datapoint is:
"Software defined PLC"
(https://www.redhat.com/en/blog/software-defined-programmable-logic-controller-introduction),
applications
can perform system calls in their time sensitive loop.
Quoted 7 lines
Quoted 3 lines
One example of an opensource software is OpenPLC.
One would like to avoid interruptions for those cases as well.
Well allowing sytem calls during "time sensitiveness" implies it is not that sensitive to vmstat updates
which have a smaller impact than system calls.
Not necessarily. Certain system calls won't touch per-CPU vmstats: nanosleep, for example. Perhaps i misunderstood your suggestion:
So the patchset in discussion uses (or should use, in v2), in both vmstat_shepherd and vmstat counter modification, LOCK CMPXCHG.
There is the potential that LOCK CMPXCHG, from vmstat counter modification, incurs a performance degradation.
Note however, that cachelocking should hopefully "hide" the costs.
Do you have any concerns about this patchset other than the performance degradation due to addition of LOCK in CMPXCHG?
The other possible concern is that the preempt-disabled functions, namely:__inc_node_page_state, __dec_node_page_state, __mod_node_page_state, __inc_zone_page_state, __dec_zone_page_state, __mod_zone_page_state have been switched to cmpxchg loop. Is that a problem?
Would expect that measuring LOCK CMPXCHG does not incur significant performance degradation as compared to CMPXCHG (from the page allocation benchmark) would address your concerns?
Thanks
Re: [PATCH 3/5] mm/vmstat: use cmpxchg loop in cpu_vm_stats_fold
In reply to Marcelo TosattiQuoted 3 lines · Marcelo Tosatti
In preparation to switch vmstat shepherd to flush
per-CPU counters remotely, use a cmpxchg loop
instead of a pair of read/write instructions.
FYI, try_cmpxchg() is preferred to plain cmpxchg() these days. Apparently it generates better code on x86.
mm/vmstat.c void cpu_vm_stats_fold(int cpu) · line 911
Quoted 5 lines
mm/vmstat.c +3
-2- v = pzstats->vm_stat_diff[i]; - pzstats->vm_stat_diff[i] =0 ; +do { + v = pzstats->vm_stat_diff[i]; + }while (cmpxchg (&pzstats->vm_stat_diff[i], v,0 ) != v);
I think this would be:
do {
v = pzstats->vm_stat_diff[i];
} while (!try_cmpxchg(&pzstats->vm_stat_diff[i], v, 0));PATCH 4/5 mm/vmstat: switch vmstat shepherd to flush per-CPU counters remotely
In reply to Marcelo TosattiNow that the counters are modified via cmpxchg both CPU locally (via the account functions), and remotely (via cpu_vm_stats_fold), its possible to switch vmstat_shepherd to perform the per-CPU vmstats folding remotely.
This fixes the following two problems:
1. A customer provided some evidence which indicates that the idle tick was stopped; albeit, CPU-specific vmstat counters still remained populated.
Thus one can only assume quiet_vmstat() was not invoked on return to the idle loop. If I understand correctly, I suspect this divergence might erroneously prevent a reclaim attempt by kswapd. If the number of zone specific free pages are below their per-cpu drift value then zone_page_state_snapshot() is used to compute a more accurate view of the aforementioned statistic. Thus any task blocked on the NUMA node specific pfmemalloc_wait queue will be unable to make significant progress via direct reclaim unless it is killed after being woken up by kswapd
(see throttle_direct_reclaim())
2. With a SCHED_FIFO task that busy loops on a given CPU, and kworker for that CPU at SCHED_OTHER priority, queuing work to sync per-vmstats will either cause that work to never execute, or stalld (i.e. stall daemon) boosts kworker priority which causes a latency violation
mm/vmstat.c +18 -0
@@ -2007,6 +2007,23 @@ static void vmstat_shepherd(struct work_ static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd); +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +/* Flush counters remotely if CPU uses cmpxchg to update its per-CPU counters */ +static void vmstat_shepherd (struct work_struct *w) +{ +int cpu; + +cpus_read_lock (); +for_each_online_cpu (cpu) { +cpu_vm_stats_fold (cpu); +cond_resched (); + } +cpus_read_unlock (); + +schedule_delayed_work (&shepherd, +round_jiffies_relative (sysctl_stat_interval)); +} +#else static void vmstat_shepherd (struct work_struct *w) {int cpu;
@@ -2026,6 +2043,7 @@ static void vmstat_shepherd(struct work_schedule_delayed_work (&shepherd, round_jiffies_relative(sysctl_stat_interval)); } +#endif static void __init start_shepherd_timer (void ) {
PATCH 5/5 mm/vmstat: refresh stats remotely instead of via work item
In reply to Marcelo TosattiRefresh per-CPU stats remotely, instead of queueing work items, for the stat_refresh procfs method.
This fixes sosreport hang (which uses vmstat_refresh) with spinning SCHED_FIFO process.
mm/vmstat.c +17 -2
@@ -1865,11 +1865,21 @@ static DEFINE_PER_CPU(struct delayed_worint sysctl_stat_interval__read_mostly =HZ ;#ifdef CONFIG_PROC_FS + +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +static int refresh_all_vm_stats (void ); +#else static void refresh_vm_stats (struct work_struct *work) {refresh_cpu_vm_stats (); } +static int refresh_all_vm_stats (void ) +{ +return schedule_on_each_cpu (refresh_vm_stats); +} +#endif +int vmstat_refresh (struct ctl_table *table,int write,void *buffer,size_t *lenp,loff_t *ppos) {
@@ -1889,7 +1899,7 @@ int vmstat_refresh(struct ctl_table *tab* transiently negative values, report an error here if any of * the stats is negative, so we know to go looking for imbalance. */ - err =schedule_on_each_cpu (refresh_vm_stats); + err =refresh_all_vm_stats ();if (err)return err;for (i =0 ; i <NR_VM_ZONE_STAT_ITEMS ; i++) {
@@ -2009,7 +2019,7 @@ static DECLARE_DEFERRABLE_WORK(shepherd,#ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* Flush counters remotely if CPU uses cmpxchg to update its per-CPU counters */ -static void vmstat_shepherd (struct work_struct *w) +static int refresh_all_vm_stats (void ) {int cpu;
@@ -2019,7 +2029,12 @@ static void vmstat_shepherd(struct work_cond_resched (); }cpus_read_unlock (); +return 0 ; +} +static void vmstat_shepherd (struct work_struct *w) +{ +refresh_all_vm_stats ();schedule_delayed_work (&shepherd,round_jiffies_relative (sysctl_stat_interval)); }