RCU's CPU Stall Detector

2019-11-08 00:13:58

字体：大中小

来源：转载

供稿：网友

有时候可以会打印INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies) 类似的log。这不是bug，而是提醒你可能某些code执行太久了，超过CONFIG_RCU_CPU_STALL_TIMEOUT 定义的时间了。具体的call flow如下：在每个时间中断函数中都会走这个flow，也就说这个flow是每次time中断都会检查的在update_PRocess_times->rcu_check_callbacks->rcu_pending->__rcu_pending->check_cpu_stall->print_other_cpu_stall/print_cpu_stall详细的情况可以查询Documentation/RCU/stallwarn.txt从下面的code中可以看出，如果没有定义CONFIG_RCU_CPU_STALL_TIMEOUT的话till_stall_check=3.static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;module_param(rcu_cpu_stall_timeout, int, 0644);int rcu_jiffies_till_stall_check(void){ int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout); /* * Limit check must be consistent with the Kconfig limits * for CONFIG_RCU_CPU_STALL_TIMEOUT. */ if (till_stall_check < 3) { WRITE_ONCE(rcu_cpu_stall_timeout, 3); till_stall_check = 3; } else if (till_stall_check > 300) { WRITE_ONCE(rcu_cpu_stall_timeout, 300); till_stall_check = 300; } return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;}

上一篇：listview的又一次认识

下一篇：自定义Switch开关控件