summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorChengming Zhou <zhouchengming@bytedance.com>2022-09-07 17:03:32 +0800
committerPeter Zijlstra <peterz@infradead.org>2022-09-09 11:08:33 +0200
commit34f26a15611afb03c33df6819359d36f5b382589 (patch)
tree38765bb0112e0ba6c8f173d8a6a129bf0b9f92f0 /kernel
parentdc86aba751e2867244411adda1562f6664747019 (diff)
downloadlinux-stable-34f26a15611afb03c33df6819359d36f5b382589.tar.gz
linux-stable-34f26a15611afb03c33df6819359d36f5b382589.tar.bz2
linux-stable-34f26a15611afb03c33df6819359d36f5b382589.zip
sched/psi: Per-cgroup PSI accounting disable/re-enable interface
PSI accounts stalls for each cgroup separately and aggregates it at each level of the hierarchy. This may cause non-negligible overhead for some workloads when under deep level of the hierarchy. commit 3958e2d0c34e ("cgroup: make per-cgroup pressure stall tracking configurable") make PSI to skip per-cgroup stall accounting, only account system-wide to avoid this each level overhead. But for our use case, we also want leaf cgroup PSI stats accounted for userspace adjustment on that cgroup, apart from only system-wide adjustment. So this patch introduce a per-cgroup PSI accounting disable/re-enable interface "cgroup.pressure", which is a read-write single value file that allowed values are "0" and "1", the defaults is "1" so per-cgroup PSI stats is enabled by default. Implementation details: It should be relatively straight-forward to disable and re-enable state aggregation, time tracking, averaging on a per-cgroup level, if we can live with losing history from while it was disabled. I.e. the avgs will restart from 0, total= will have gaps. But it's hard or complex to stop/restart groupc->tasks[] updates, which is not implemented in this patch. So we always update groupc->tasks[] and PSI_ONCPU bit in psi_group_change() even when the cgroup PSI stats is disabled. Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lkml.kernel.org/r/20220907090332.2078-1-zhouchengming@bytedance.com
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup.c70
-rw-r--r--kernel/sched/psi.c70
2 files changed, 127 insertions, 13 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 772b35d65d1f..fa1cf836b66a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3708,8 +3708,8 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
return psi_show(seq, psi, PSI_CPU);
}
-static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
- size_t nbytes, enum psi_res res)
+static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, enum psi_res res)
{
struct cgroup_file_ctx *ctx = of->priv;
struct psi_trigger *new;
@@ -3746,21 +3746,21 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_IO);
+ return pressure_write(of, buf, nbytes, PSI_IO);
}
static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_MEM);
+ return pressure_write(of, buf, nbytes, PSI_MEM);
}
static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
+ return pressure_write(of, buf, nbytes, PSI_CPU);
}
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -3776,10 +3776,58 @@ static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
- return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ);
+ return pressure_write(of, buf, nbytes, PSI_IRQ);
}
#endif
+static int cgroup_pressure_show(struct seq_file *seq, void *v)
+{
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+ struct psi_group *psi = cgroup_psi(cgrp);
+
+ seq_printf(seq, "%d\n", psi->enabled);
+
+ return 0;
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ ssize_t ret;
+ int enable;
+ struct cgroup *cgrp;
+ struct psi_group *psi;
+
+ ret = kstrtoint(strstrip(buf), 0, &enable);
+ if (ret)
+ return ret;
+
+ if (enable < 0 || enable > 1)
+ return -ERANGE;
+
+ cgrp = cgroup_kn_lock_live(of->kn, false);
+ if (!cgrp)
+ return -ENOENT;
+
+ psi = cgroup_psi(cgrp);
+ if (psi->enabled != enable) {
+ int i;
+
+ /* show or hide {cpu,memory,io,irq}.pressure files */
+ for (i = 0; i < NR_PSI_RESOURCES; i++)
+ cgroup_file_show(&cgrp->psi_files[i], enable);
+
+ psi->enabled = enable;
+ if (enable)
+ psi_cgroup_restart(psi);
+ }
+
+ cgroup_kn_unlock(of->kn);
+
+ return nbytes;
+}
+
static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
poll_table *pt)
{
@@ -5175,6 +5223,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "io.pressure",
.flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
.seq_show = cgroup_io_pressure_show,
.write = cgroup_io_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5183,6 +5232,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "memory.pressure",
.flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
.seq_show = cgroup_memory_pressure_show,
.write = cgroup_memory_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5191,6 +5241,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "cpu.pressure",
.flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
.seq_show = cgroup_cpu_pressure_show,
.write = cgroup_cpu_pressure_write,
.poll = cgroup_pressure_poll,
@@ -5200,12 +5251,19 @@ static struct cftype cgroup_base_files[] = {
{
.name = "irq.pressure",
.flags = CFTYPE_PRESSURE,
+ .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
.seq_show = cgroup_irq_pressure_show,
.write = cgroup_irq_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
#endif
+ {
+ .name = "cgroup.pressure",
+ .flags = CFTYPE_PRESSURE,
+ .seq_show = cgroup_pressure_show,
+ .write = cgroup_pressure_write,
+ },
#endif /* CONFIG_PSI */
{ } /* terminate */
};
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 9a8aee80a087..9711827e31e5 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -181,6 +181,7 @@ static void group_init(struct psi_group *group)
{
int cpu;
+ group->enabled = true;
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
group->avg_last_update = sched_clock();
@@ -696,17 +697,16 @@ static void psi_group_change(struct psi_group *group, int cpu,
groupc = per_cpu_ptr(group->pcpu, cpu);
/*
- * First we assess the aggregate resource states this CPU's
- * tasks have been in since the last change, and account any
- * SOME and FULL time these may have resulted in.
- *
- * Then we update the task counts according to the state
+ * First we update the task counts according to the state
* change requested through the @clear and @set bits.
+ *
+ * Then if the cgroup PSI stats accounting enabled, we
+ * assess the aggregate resource states this CPU's tasks
+ * have been in since the last change, and account any
+ * SOME and FULL time these may have resulted in.
*/
write_seqcount_begin(&groupc->seq);
- record_times(groupc, now);
-
/*
* Start with TSK_ONCPU, which doesn't have a corresponding
* task count - it's just a boolean flag directly encoded in
@@ -745,6 +745,23 @@ static void psi_group_change(struct psi_group *group, int cpu,
if (set & (1 << t))
groupc->tasks[t]++;
+ if (!group->enabled) {
+ /*
+ * On the first group change after disabling PSI, conclude
+ * the current state and flush its time. This is unlikely
+ * to matter to the user, but aggregation (get_recent_times)
+ * may have already incorporated the live state into times_prev;
+ * avoid a delta sample underflow when PSI is later re-enabled.
+ */
+ if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE)))
+ record_times(groupc, now);
+
+ groupc->state_mask = state_mask;
+
+ write_seqcount_end(&groupc->seq);
+ return;
+ }
+
for (s = 0; s < NR_PSI_STATES; s++) {
if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU))
state_mask |= (1 << s);
@@ -761,6 +778,8 @@ static void psi_group_change(struct psi_group *group, int cpu,
if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall))
state_mask |= (1 << PSI_MEM_FULL);
+ record_times(groupc, now);
+
groupc->state_mask = state_mask;
write_seqcount_end(&groupc->seq);
@@ -907,6 +926,9 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
group = task_psi_group(task);
do {
+ if (!group->enabled)
+ continue;
+
groupc = per_cpu_ptr(group->pcpu, cpu);
write_seqcount_begin(&groupc->seq);
@@ -1080,6 +1102,40 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
task_rq_unlock(rq, task, &rf);
}
+
+void psi_cgroup_restart(struct psi_group *group)
+{
+ int cpu;
+
+ /*
+ * After we disable psi_group->enabled, we don't actually
+ * stop percpu tasks accounting in each psi_group_cpu,
+ * instead only stop test_state() loop, record_times()
+ * and averaging worker, see psi_group_change() for details.
+ *
+ * When disable cgroup PSI, this function has nothing to sync
+ * since cgroup pressure files are hidden and percpu psi_group_cpu
+ * would see !psi_group->enabled and only do task accounting.
+ *
+ * When re-enable cgroup PSI, this function use psi_group_change()
+ * to get correct state mask from test_state() loop on tasks[],
+ * and restart groupc->state_start from now, use .clear = .set = 0
+ * here since no task status really changed.
+ */
+ if (!group->enabled)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ struct rq_flags rf;
+ u64 now;
+
+ rq_lock_irq(rq, &rf);
+ now = cpu_clock(cpu);
+ psi_group_change(group, cpu, 0, 0, now, true);
+ rq_unlock_irq(rq, &rf);
+ }
+}
#endif /* CONFIG_CGROUPS */
int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)