The patch titled
Subject: vmstat: get rid of the ugly cpu_stat_off variable
has been added to the -mm tree. Its filename is
vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Christoph Lameter <cl@xxxxxxxxx>
Subject: vmstat: get rid of the ugly cpu_stat_off variable
The cpu_stat_off variable is unecessary since we can check if a workqueue
request is pending otherwise. Removal of cpu_stat_off makes it pretty
easy for the vmstat shepherd to ensure that the proper things happen.
Removing the state also removes all races related to it. Should a
workqueue not be scheduled as needed for vmstat_update then the shepherd
will notice and schedule it as needed. Should a workqueue be unecessarily
scheduled then the vmstat updater will disable it.
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1605061306460.17934@xxxxxxxxxxxxxxx
Signed-off-by: Christoph Lameter <cl@xxxxxxxxx>
Cc: Tejun Heo <htejun@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmstat.c | 49 +++++++++----------------------------------------
1 file changed, 9 insertions(+), 40 deletions(-)
diff -puN mm/vmstat.c~vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2 mm/vmstat.c
--- a/mm/vmstat.c~vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2
+++ a/mm/vmstat.c
@@ -1352,7 +1352,6 @@ static const struct file_operations proc
static struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
-static cpumask_var_t cpu_stat_off;
static void refresh_vm_stats(struct work_struct *work)
{
@@ -1419,24 +1418,10 @@ static void vmstat_update(struct work_st
* Counters were updated so we expect more updates
* to occur in the future. Keep on running the
* update worker thread.
- * If we were marked on cpu_stat_off clear the flag
- * so that vmstat_shepherd doesn't schedule us again.
*/
- if (!cpumask_test_and_clear_cpu(smp_processor_id(),
- cpu_stat_off)) {
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+ queue_delayed_work_on(smp_processor_id(), vmstat_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
- }
- } else {
- /*
- * We did not update any counters so the app may be in
- * a mode where it does not cause counter updates.
- * We may be uselessly running vmstat_update.
- * Defer the checking for differentials to the
- * shepherd thread on a different processor.
- */
- cpumask_set_cpu(smp_processor_id(), cpu_stat_off);
}
}
@@ -1468,16 +1453,17 @@ static bool need_update(int cpu)
return false;
}
+/*
+ * Switch off vmstat processing and then fold all the remaining differentials
+ * until the diffs stay at zero. The function is used by NOHZ and can only be
+ * invoked when tick processing is not active.
+ */
void quiet_vmstat(void)
{
if (system_state != SYSTEM_RUNNING)
return;
- /*
- * If we are already in hands of the shepherd then there
- * is nothing for us to do here.
- */
- if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
+ if (!delayed_work_pending(this_cpu_ptr(&vmstat_work)))
return;
if (!need_update(smp_processor_id()))
@@ -1492,7 +1478,6 @@ void quiet_vmstat(void)
refresh_cpu_vm_stats(false);
}
-
/*
* Shepherd worker thread that checks the
* differentials of processors that have their worker
@@ -1509,20 +1494,11 @@ static void vmstat_shepherd(struct work_
get_online_cpus();
/* Check processors whose vmstat worker threads have been disabled */
- for_each_cpu(cpu, cpu_stat_off) {
+ for_each_online_cpu(cpu) {
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
- if (need_update(cpu)) {
- if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+ if (!delayed_work_pending(dw) && need_update(cpu))
queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
- } else {
- /*
- * Cancel the work if quiet_vmstat has put this
- * cpu on cpu_stat_off because the work item might
- * be still scheduled
- */
- cancel_delayed_work(dw);
- }
}
put_online_cpus();
@@ -1538,10 +1514,6 @@ static void __init start_shepherd_timer(
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
vmstat_update);
- if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
- BUG();
- cpumask_copy(cpu_stat_off, cpu_online_mask);
-
vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
@@ -1576,16 +1548,13 @@ static int vmstat_cpuup_callback(struct
case CPU_ONLINE_FROZEN:
refresh_zone_stat_thresholds();
node_set_state(cpu_to_node(cpu), N_CPU);
- cpumask_set_cpu(cpu, cpu_stat_off);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
- cpumask_clear_cpu(cpu, cpu_stat_off);
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- cpumask_set_cpu(cpu, cpu_stat_off);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
_
Patches currently in -mm which might be from cl@xxxxxxxxx are
vmstat-get-rid-of-the-ugly-cpu_stat_off-variable-v2.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
