From: Tim Chen Date: Mon, 10 Nov 2025 18:47:35 +0000 (-0800) Subject: sched/fair: Skip sched_balance_running cmpxchg when balance is not due X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=3324b2180c17b21c31c16966cc85ca41a7c93703;p=thirdparty%2Flinux.git sched/fair: Skip sched_balance_running cmpxchg when balance is not due The NUMA sched domain sets the SD_SERIALIZE flag by default, allowing only one NUMA load balancing operation to run system-wide at a time. Currently, each sched group leader directly under NUMA domain attempts to acquire the global sched_balance_running flag via cmpxchg() before checking whether load balancing is due or whether it is the designated load balancer for that NUMA domain. On systems with a large number of cores, this causes significant cache contention on the shared sched_balance_running flag. This patch reduces unnecessary cmpxchg() operations by first checking that the balancer is the designated leader for a NUMA domain from should_we_balance(), and the balance interval has expired before trying to acquire sched_balance_running to load balance a NUMA domain. On a 2-socket Granite Rapids system with sub-NUMA clustering enabled, running an OLTP workload, 7.8% of total CPU cycles were previously spent in sched_balance_domain() contending on sched_balance_running before this change. : 104 static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) : 105 { : 106 return arch_cmpxchg(&v->counter, old, new); 0.00 : ffffffff81326e6c: xor %eax,%eax 0.00 : ffffffff81326e6e: mov $0x1,%ecx 0.00 : ffffffff81326e73: lock cmpxchg %ecx,0x2394195(%rip) # ffffffff836bb010 : 110 sched_balance_domains(): : 12234 if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1)) 99.39 : ffffffff81326e7b: test %eax,%eax 0.00 : ffffffff81326e7d: jne ffffffff81326e99 : 12238 if (time_after_eq(jiffies, sd->last_balance + interval)) { 0.00 : ffffffff81326e7f: mov 0x14e2b3a(%rip),%rax # ffffffff828099c0 0.00 : ffffffff81326e86: sub 0x48(%r14),%rax 0.00 : ffffffff81326e8a: cmp %rdx,%rax After applying this fix, sched_balance_domain() is gone from the profile and there is a 5% throughput improvement. [peterz: made it so that redo retains the 'lock' and split out the CPU_NEWLY_IDLE change to a separate patch] Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Chen Yu Reviewed-by: Vincent Guittot Reviewed-by: Shrikanth Hegde Reviewed-by: K Prateek Nayak Reviewed-by: Srikar Dronamraju Tested-by: Mohini Narkhede Tested-by: Shrikanth Hegde Link: https://patch.msgid.link/6fed119b723c71552943bfe5798c93851b30a361.1762800251.git.tim.c.chen@linux.intel.com --- diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b4617d6315496..59b17f09166b8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11680,6 +11680,21 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd } } +/* + * 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); + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. @@ -11705,6 +11720,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq, .fbq_type = all, .tasks = LIST_HEAD_INIT(env.tasks), }; + bool need_unlock = false; cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask); @@ -11716,6 +11732,14 @@ redo: goto out_balanced; } + if (!need_unlock && (sd->flags & SD_SERIALIZE) && idle != CPU_NEWLY_IDLE) { + int zero = 0; + if (!atomic_try_cmpxchg_acquire(&sched_balance_running, &zero, 1)) + goto out_balanced; + + need_unlock = true; + } + group = sched_balance_find_src_group(&env); if (!group) { schedstat_inc(sd->lb_nobusyg[idle]); @@ -11956,6 +11980,9 @@ out_one_pinned: sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; out: + if (need_unlock) + atomic_set_release(&sched_balance_running, 0); + return ld_moved; } @@ -12080,21 +12107,6 @@ out_unlock: return 0; } -/* - * 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 sched_balance_rq interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. @@ -12150,7 +12162,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; - int need_serialize, need_decay = 0; + int need_decay = 0; u64 max_cost = 0; rcu_read_lock(); @@ -12174,13 +12186,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) } interval = get_sd_balance_interval(sd, busy); - - need_serialize = sd->flags & SD_SERIALIZE; - if (need_serialize) { - if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1)) - goto out; - } - if (time_after_eq(jiffies, sd->last_balance + interval)) { if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) { /* @@ -12194,9 +12199,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) sd->last_balance = jiffies; interval = get_sd_balance_interval(sd, busy); } - if (need_serialize) - atomic_set_release(&sched_balance_running, 0); -out: if (time_after(next_balance, sd->last_balance + interval)) { next_balance = sd->last_balance + interval; update_next_balance = 1;