The 'balancing' spinlock added in:
08c183f31bdb ("[PATCH] sched: add option to serialize load balancing")
.. is taken when the SD_SERIALIZE flag is set in a domain, but in reality it
is a glorified global atomic flag serializing the load-balancing of
those domains.
It doesn't have any explicit locking semantics per se: we just
spin_trylock() it.
Turn it into a ... global atomic flag. This makes it more
clear what is going on here, and reduces overhead and code
size a bit:
# kernel/sched/fair.o: [x86-64 defconfig]
text data bss dec hex filename
60730 2721 104 63555 f843 fair.o.before
60718 2721 104 63543 f837 fair.o.after
Also document the flag a bit.
No change in functionality intended.
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Valentin Schneider <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Shrikanth Hegde <[email protected]>
Cc: Vincent Guittot <[email protected]>
---
kernel/sched/fair.c | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6a16129f9a5c..2ef89b36aed1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11633,7 +11633,20 @@ static int active_load_balance_cpu_stop(void *data)
return 0;
}
-static DEFINE_SPINLOCK(balancing);
+/*
+ * This flag serializes load-balancing passes over large domains
+ * (above the NODE topology level) - only one load-balancing instance
+ * may run at a time, to reduce overhead on very large systems with
+ * lots of CPUs and large NUMA distances.
+ *
+ * - Note that load-balancing passes triggered while another one
+ * is executing are skipped and not re-tried.
+ *
+ * - Also note that this does not serialize rebalance_domains()
+ * execution, as non-SD_SERIALIZE domains will still be
+ * load-balanced in parallel.
+ */
+static atomic_t sched_balance_running = ATOMIC_INIT(0);
/*
* Scale the max load_balance interval with the number of CPUs in the system.
@@ -11711,7 +11724,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
need_serialize = sd->flags & SD_SERIALIZE;
if (need_serialize) {
- if (!spin_trylock(&balancing))
+ if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1))
goto out;
}
@@ -11729,7 +11742,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
interval = get_sd_balance_interval(sd, busy);
}
if (need_serialize)
- spin_unlock(&balancing);
+ atomic_set_release(&sched_balance_running, 0);
out:
if (time_after(next_balance, sd->last_balance + interval)) {
next_balance = sd->last_balance + interval;
--
2.40.1
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 214c1b7f13954559cf09d5d04b934bf32ba4d618
Gitweb: https://git.kernel.org/tip/214c1b7f13954559cf09d5d04b934bf32ba4d618
Author: Ingo Molnar <[email protected]>
AuthorDate: Fri, 08 Mar 2024 11:58:52 +01:00
Committer: Ingo Molnar <[email protected]>
CommitterDate: Tue, 12 Mar 2024 11:03:39 +01:00
sched/balancing: Switch the 'DEFINE_SPINLOCK(balancing)' spinlock into an 'atomic_t sched_balance_running' flag
The 'balancing' spinlock added in:
08c183f31bdb ("[PATCH] sched: add option to serialize load balancing")
.. is taken when the SD_SERIALIZE flag is set in a domain, but in reality it
is a glorified global atomic flag serializing the load-balancing of
those domains.
It doesn't have any explicit locking semantics per se: we just
spin_trylock() it.
Turn it into a ... global atomic flag. This makes it more
clear what is going on here, and reduces overhead and code
size a bit:
# kernel/sched/fair.o: [x86-64 defconfig]
text data bss dec hex filename
60730 2721 104 63555 f843 fair.o.before
60718 2721 104 63543 f837 fair.o.after
Also document the flag a bit.
No change in functionality intended.
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Valentin Schneider <[email protected]>
Cc: Shrikanth Hegde <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6a16129..2ef89b3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11633,7 +11633,20 @@ out_unlock:
return 0;
}
-static DEFINE_SPINLOCK(balancing);
+/*
+ * This flag serializes load-balancing passes over large domains
+ * (above the NODE topology level) - only one load-balancing instance
+ * may run at a time, to reduce overhead on very large systems with
+ * lots of CPUs and large NUMA distances.
+ *
+ * - Note that load-balancing passes triggered while another one
+ * is executing are skipped and not re-tried.
+ *
+ * - Also note that this does not serialize rebalance_domains()
+ * execution, as non-SD_SERIALIZE domains will still be
+ * load-balanced in parallel.
+ */
+static atomic_t sched_balance_running = ATOMIC_INIT(0);
/*
* Scale the max load_balance interval with the number of CPUs in the system.
@@ -11711,7 +11724,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
need_serialize = sd->flags & SD_SERIALIZE;
if (need_serialize) {
- if (!spin_trylock(&balancing))
+ if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1))
goto out;
}
@@ -11729,7 +11742,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
interval = get_sd_balance_interval(sd, busy);
}
if (need_serialize)
- spin_unlock(&balancing);
+ atomic_set_release(&sched_balance_running, 0);
out:
if (time_after(next_balance, sd->last_balance + interval)) {
next_balance = sd->last_balance + interval;
On 3/8/24 4:28 PM, Ingo Molnar wrote:
> The 'balancing' spinlock added in:
>
> Also document the flag a bit.
>
> No change in functionality intended.
>
> -static DEFINE_SPINLOCK(balancing);
> +/*
> + * This flag serializes load-balancing passes over large domains
> + * (above the NODE topology level) - only one load-balancing instance
> + * may run at a time, to reduce overhead on very large systems with
> + * lots of CPUs and large NUMA distances.
> + *
> + * - Note that load-balancing passes triggered while another one
> + * is executing are skipped and not re-tried.
> + *
> + * - Also note that this does not serialize rebalance_domains()
nit: please change rebalance_domains to sched_balance_domains.
> + * execution, as non-SD_SERIALIZE domains will still be
> + * load-balanced in parallel.
> + */
> +static atomic_t sched_balance_running = ATOMIC_INIT(0);
>
> /*
> * Scale the max load_balance interval with the number of CPUs in the system.
> @@ -11711,7 +11724,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
>
> need_serialize = sd->flags & SD_SERIALIZE;
> if (need_serialize) {