From: Marcelo Tosatti <mtosatti@redhat.com>
To: atomlin@atomlin.com, frederic@kernel.org
Cc: cl@linux.com, tglx@linutronix.de, mingo@kernel.org,
peterz@infradead.org, pauld@redhat.com, neelx@redhat.com,
oleksandr@natalenko.name, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH v11 6/6] mm/vmstat: avoid queueing work item if cpu stats are clean
Date: Wed, 21 Dec 2022 13:58:07 -0300 [thread overview]
Message-ID: <20221221170436.449941687@redhat.com> (raw)
In-Reply-To: 20221221165801.362118576@redhat.com
It is not necessary to queue work item to run refresh_vm_stats
on a remote CPU if that CPU has no dirty stats and no per-CPU
allocations for remote nodes.
This fixes sosreport hang (which uses vmstat_refresh) with
spinning SCHED_FIFO process.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Index: linux-2.6/mm/vmstat.c
===================================================================
--- linux-2.6.orig/mm/vmstat.c
+++ linux-2.6/mm/vmstat.c
@@ -1917,6 +1917,31 @@ static const struct seq_operations vmsta
#ifdef CONFIG_SMP
#ifdef CONFIG_PROC_FS
+static bool need_drain_remote_zones(int cpu)
+{
+#ifdef CONFIG_NUMA
+ struct zone *zone;
+
+ for_each_populated_zone(zone) {
+ struct per_cpu_pages *pcp;
+
+ pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+ if (!pcp->count)
+ continue;
+
+ if (!pcp->expire)
+ continue;
+
+ if (zone_to_nid(zone) == cpu_to_node(cpu))
+ continue;
+
+ return true;
+ }
+#endif
+
+ return false;
+}
+
static void refresh_vm_stats(struct work_struct *work)
{
refresh_cpu_vm_stats(true);
@@ -1926,8 +1951,12 @@ int vmstat_refresh(struct ctl_table *tab
void *buffer, size_t *lenp, loff_t *ppos)
{
long val;
- int err;
- int i;
+ int i, cpu;
+ struct work_struct __percpu *works;
+
+ works = alloc_percpu(struct work_struct);
+ if (!works)
+ return -ENOMEM;
/*
* The regular update, every sysctl_stat_interval, may come later
@@ -1941,9 +1970,21 @@ 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);
- if (err)
- return err;
+ cpus_read_lock();
+ for_each_online_cpu(cpu) {
+ struct work_struct *work = per_cpu_ptr(works, cpu);
+ struct vmstat_dirty *vms = per_cpu_ptr(&vmstat_dirty_pcpu, cpu);
+
+ INIT_WORK(work, refresh_vm_stats);
+
+ if (vms->dirty || need_drain_remote_zones(cpu))
+ schedule_work_on(cpu, work);
+ }
+ for_each_online_cpu(cpu)
+ flush_work(per_cpu_ptr(works, cpu));
+ cpus_read_unlock();
+ free_percpu(works);
+
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
/*
* Skip checking stats known to go negative occasionally.
prev parent reply other threads:[~2022-12-21 17:12 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-21 16:58 [PATCH v11 0/6] Ensure quiet_vmstat() is called when returning to userpace and when idle tick is stopped Marcelo Tosatti
2022-12-21 16:58 ` [PATCH v11 1/6] mm/vmstat: Add CPU-specific variable to track a vmstat discrepancy Marcelo Tosatti
2022-12-21 16:58 ` [PATCH v11 2/6] mm/vmstat: Use vmstat_dirty to track CPU-specific vmstat discrepancies Marcelo Tosatti
2022-12-21 16:58 ` [PATCH v11 3/6] mm/vmstat: manage per-CPU stats from CPU context when NOHZ full Marcelo Tosatti
2022-12-23 14:41 ` Frederic Weisbecker
2022-12-21 16:58 ` [PATCH v11 4/6] tick/nohz_full: Ensure quiet_vmstat() is called on exit to user-mode when the idle tick is stopped Marcelo Tosatti
2022-12-21 16:58 ` [PATCH v11 5/6] tick/sched: Ensure quiet_vmstat() is called when the idle tick was stopped too Marcelo Tosatti
2022-12-21 16:58 ` Marcelo Tosatti [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221221170436.449941687@redhat.com \
--to=mtosatti@redhat.com \
--cc=atomlin@atomlin.com \
--cc=cl@linux.com \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@kernel.org \
--cc=neelx@redhat.com \
--cc=oleksandr@natalenko.name \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).