Messages in this thread | | | Subject | Re: [PATCH v2] sched/rt: Rework for_each_process_thread() iterations in tg_has_rt_tasks() | From | Kirill Tkhai <> | Date | Wed, 25 Apr 2018 18:42:11 +0300 |
| |
Peter,
could you please to give some comments on this?
Kirill
On 20.04.2018 13:06, Kirill Tkhai wrote: > From: Kirill Tkhai <ktkhai@virtuozzo.com> > > tg_rt_schedulable() iterates over all child task groups, > while tg_has_rt_tasks() iterates over all linked tasks. > In case of systems with big number of tasks, this may > take a lot of time. > > I observed hard LOCKUP on machine with 20000+ processes > after write to "cpu.rt_period_us" of cpu cgroup with > 39 children. The problem occurred because of tasklist_lock > is held for a long time and other processes can't do fork(). > > PID: 1036268 TASK: ffff88766c310000 CPU: 36 COMMAND: "criu" > #0 [ffff887f7f408e48] crash_nmi_callback at ffffffff81050601 > #1 [ffff887f7f408e58] nmi_handle at ffffffff816e0cc7 > #2 [ffff887f7f408eb0] do_nmi at ffffffff816e0fb0 > #3 [ffff887f7f408ef0] end_repeat_nmi at ffffffff816e00b9 > [exception RIP: tg_rt_schedulable+463] > RIP: ffffffff810bf49f RSP: ffff886537ad7d50 RFLAGS: 00000202 > RAX: 0000000000000000 RBX: 000000003b9aca00 RCX: ffff883e9cb4b1b0 > RDX: ffff887d0be43608 RSI: ffff886537ad7dd8 RDI: ffff8840a6ad0000 > RBP: ffff886537ad7d68 R8: ffff887d0be431b0 R9: 00000000000e7ef0 > R10: ffff88164fc39400 R11: 0000000000023380 R12: ffffffff81ef8d00 > R13: ffffffff810bea40 R14: 0000000000000000 R15: ffff8840a6ad0000 > ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 > --- <NMI exception stack> --- > #4 [ffff886537ad7d50] tg_rt_schedulable at ffffffff810bf49f > #5 [ffff886537ad7d70] walk_tg_tree_from at ffffffff810c6c91 > #6 [ffff886537ad7dc0] tg_set_rt_bandwidth at ffffffff810c6dd0 > #7 [ffff886537ad7e28] cpu_rt_period_write_uint at ffffffff810c6eea > #8 [ffff886537ad7e38] cgroup_file_write at ffffffff8111cfd3 > #9 [ffff886537ad7ec8] vfs_write at ffffffff8121eced > #10 [ffff886537ad7f08] sys_write at ffffffff8121faff > #11 [ffff886537ad7f50] system_call_fastpath at ffffffff816e8a7d > > The patch reworks tg_has_rt_tasks() and makes it to iterate over > task group process list instead of iteration over all tasks list. > This makes the function to scale well, and reduces its execution > time. > > Note, that since tasklist_lock doesn't protect a task against > sched_class changing, we don't introduce new races in comparison > to that we had before. > > Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> > --- > kernel/sched/rt.c | 22 +++++++++++----------- > 1 file changed, 11 insertions(+), 11 deletions(-) > > diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c > index 7aef6b4e885a..20be796d4e63 100644 > --- a/kernel/sched/rt.c > +++ b/kernel/sched/rt.c > @@ -2395,10 +2395,11 @@ const struct sched_class rt_sched_class = { > */ > static DEFINE_MUTEX(rt_constraints_mutex); > > -/* Must be called with tasklist_lock held */ > static inline int tg_has_rt_tasks(struct task_group *tg) > { > - struct task_struct *g, *p; > + struct css_task_iter it; > + struct task_struct *task; > + int ret = 0; > > /* > * Autogroups do not have RT tasks; see autogroup_create(). > @@ -2406,12 +2407,15 @@ static inline int tg_has_rt_tasks(struct task_group *tg) > if (task_group_is_autogroup(tg)) > return 0; > > - for_each_process_thread(g, p) { > - if (rt_task(p) && task_group(p) == tg) > - return 1; > - } > + css_task_iter_start(&tg->css, 0, &it); > + while ((task = css_task_iter_next(&it))) > + if (rt_task(task)) { > + ret = 1; > + break; > + } > + css_task_iter_end(&it); > > - return 0; > + return ret; > } > > struct rt_schedulable_data { > @@ -2510,7 +2514,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg, > return -EINVAL; > > mutex_lock(&rt_constraints_mutex); > - read_lock(&tasklist_lock); > err = __rt_schedulable(tg, rt_period, rt_runtime); > if (err) > goto unlock; > @@ -2528,7 +2531,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg, > } > raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); > unlock: > - read_unlock(&tasklist_lock); > mutex_unlock(&rt_constraints_mutex); > > return err; > @@ -2582,9 +2584,7 @@ static int sched_rt_global_constraints(void) > int ret = 0; > > mutex_lock(&rt_constraints_mutex); > - read_lock(&tasklist_lock); > ret = __rt_schedulable(NULL, 0, 0); > - read_unlock(&tasklist_lock); > mutex_unlock(&rt_constraints_mutex); > > return ret; >
| |