v4->v5 - Increase the decay to 1% per second. - Peter rewrote much of the logic.
This patch builds on patch 2 and periodically decays that max value to do idle balancing per sched domain by approximately 1% per second. Also decay the rq's max_idle_balance_cost value. Signed-off-by: Jason Low <[email protected]> Signed-off-by: Peter Zijlstra <[email protected]> --- arch/metag/include/asm/topology.h | 1 + include/linux/sched.h | 3 ++ include/linux/topology.h | 3 ++ kernel/sched/fair.c | 38 ++++++++++++++++++++++++++++++------ 4 files changed, 38 insertions(+), 7 deletions(-) diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h index db19292..8e9c0b3 100644 --- a/arch/metag/include/asm/topology.h +++ b/arch/metag/include/asm/topology.h @@ -27,6 +27,7 @@ .balance_interval = 1, \ .nr_balance_failed = 0, \ .max_newidle_lb_cost = 0, \ + .next_decay_max_lb_cost = jiffies, \ } #define cpu_to_node(cpu) ((void)(cpu), 0) diff --git a/include/linux/sched.h b/include/linux/sched.h index fe16b7d..b3d2a2d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -818,7 +818,10 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ u64 last_update; + + /* idle_balance() stats */ u64 max_newidle_lb_cost; + unsigned long next_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ diff --git a/include/linux/topology.h b/include/linux/topology.h index e2a2c3d..12ae6ce 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -107,6 +107,7 @@ int arch_update_cpu_topology(void); .balance_interval = 1, \ .smt_gain = 1178, /* 15% */ \ .max_newidle_lb_cost = 0, \ + .next_decay_max_lb_cost = jiffies, \ } #endif #endif /* CONFIG_SCHED_SMT */ @@ -137,6 +138,7 @@ int arch_update_cpu_topology(void); .last_balance = jiffies, \ .balance_interval = 1, \ .max_newidle_lb_cost = 0, \ + .next_decay_max_lb_cost = jiffies, \ } #endif #endif /* CONFIG_SCHED_MC */ @@ -169,6 +171,7 @@ int arch_update_cpu_topology(void); .last_balance = jiffies, \ .balance_interval = 1, \ .max_newidle_lb_cost = 0, \ + .next_decay_max_lb_cost = jiffies, \ } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8b33257..f1818f2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5677,15 +5677,39 @@ static void rebalance_domains(int cpu, 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; + int need_serialize, need_decay = 0; + u64 max_cost = 0; update_blocked_averages(cpu); rcu_read_lock(); for_each_domain(cpu, sd) { + /* + * Decay the newidle max times here because this is a regular + * visit to all the domains. Decay ~1% per second. + */ + if (time_after(jiffies, sd->next_decay_max_lb_cost)) { + sd->max_newidle_lb_cost = + (sd->max_newidle_lb_cost * 253) / 256; + sd->next_decay_max_lb_cost = jiffies + HZ; + need_decay = 1; + } + max_cost += sd->max_newidle_lb_cost; + if (!(sd->flags & SD_LOAD_BALANCE)) continue; + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!continue_balancing) { + if (need_decay) + continue; + break; + } + interval = sd->balance_interval; if (idle != CPU_IDLE) interval *= sd->busy_factor; @@ -5719,14 +5743,14 @@ out: next_balance = sd->last_balance + interval; update_next_balance = 1; } - + } + if (need_decay) { /* - * Stop the load balance at this level. There is another - * CPU in our sched group which is doing load balancing more - * actively. + * Ensure the rq-wide value also decays but keep it at a + * reasonable floor to avoid funnies with rq->avg_idle. */ - if (!continue_balancing) - break; + rq->max_idle_balance_cost = + max((u64)sysctl_sched_migration_cost, max_cost); } rcu_read_unlock(); -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
