lkml.org 
[lkml]   [2008]   [May]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patches in this message
    /
    Date
    From
    SubjectRe: [BUG] cpu hotplug vs scheduler
    Hi,

    > [ ... ]
    >
    > [4298303.713901] Call Trace:
    > [4298303.713901] [<ffffffff804373fe>] schedule+0x414/0x6ab
    > [4298303.713901] [<ffffffff8023060a>] ? hrtick_set+0x9d/0xe8
    > [4298303.713901] [<ffffffff8043772f>] ? thread_return+0x9a/0xbf
    > [4298303.713901] [<ffffffff80231652>] migration_thread+0x185/0x22d
    > [4298303.713901] [<ffffffff802314cd>] ? migration_thread+0x0/0x22d
    > [4298303.713901] [<ffffffff8024afe6>] kthread+0x49/0x77
    > [4298303.713901] [<ffffffff8020d228>] child_rip+0xa/0x12
    > [4298303.713901] [<ffffffff8024af9d>] ? kthread+0x0/0x77
    > [4298303.713901] [<ffffffff8020d21e>] ? child_rip+0x0/0x12
    > [4298303.713901]
    > [4298303.713901]
    > [4298303.713901] Code: c0 74 28 48 8b 7b 58 4c 8d 60 f0 48 85 ff 74 10 4c
    > 89 e6 e8 df cc ff ff 85 c0 75 04 4c 8b 63 58 4c 89 e6 48 89 df e8 4a e5 ff
    > ff <49> 8b 9c 24 58 01 00 00 48 85 db 75 bf 49 83 ec 38 4c 89 ef 4c
    > [4298303.713901] RIP [<ffffffff8022e722>] pick_next_task_fair+0x55/0x7c
    >
    > This seems to be the assignment to cfs_rq after pick_next_entity().

    [ cc'ed a few folks. ]


    So the cfs-tree likely gets out-of-sync. I pressume, it won't be
    reproducible with CONFIG_SCHED_GROUP options being disabled.

    Anyway, would you try one of these debug-patches (not sure about the
    workability of the second one though :-/)

    Let's check what are the values for 'cfs_rq->weight.load/nr_running'.

    thanks in advance,

    (non-whitespace-damaged versions are enclosed)

    ---
    --- a/kernel/sched_fair.c
    +++ b/kernel/sched_fair.c
    @@ -1291,6 +1291,12 @@ static struct task_struct
    *pick_next_task_fair(struct rq *rq)

    do {
    se = pick_next_entity(cfs_rq);
    +
    + if (unlikely(!se))
    + printk(KERN_ERR "BUG: se == NULL but
    nr_running (%ld), load (%ld),"
    + " rq-nr_running (%ld), rq-load (%ld)\n",
    + cfs_rq->nr_running,
    cfs_rq->load.weight, rq->nr_running, rq->load.weight);
    +
    cfs_rq = group_cfs_rq(se);
    } while (cfs_rq);

    ---
    --- a/kernel/sched_fair.c
    +++ b/kernel/sched_fair.c
    @@ -1280,6 +1280,8 @@ static void check_preempt_wakeup(struct rq *rq,
    struct task_str uct *p)
    resched_task(curr);
    }

    +static void sysrq_sched_debug_show(void);
    +
    static struct task_struct *pick_next_task_fair(struct rq *rq)
    {
    struct task_struct *p;
    @@ -1291,6 +1293,10 @@ static struct task_struct
    *pick_next_task_fair(struct rq *rq)

    do {
    se = pick_next_entity(cfs_rq);
    +
    + if (unlikely(!se))
    + sysrq_sched_debug_show();
    +
    cfs_rq = group_cfs_rq(se);
    } while (cfs_rq);

    ---
    --
    Best regards,
    Dmitry Adamushko
    diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
    index e24ecd3..1dcc470 100644
    --- a/kernel/sched_fair.c
    +++ b/kernel/sched_fair.c
    @@ -1280,6 +1280,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
    resched_task(curr);
    }

    +static void sysrq_sched_debug_show(void);
    +
    static struct task_struct *pick_next_task_fair(struct rq *rq)
    {
    struct task_struct *p;
    @@ -1291,6 +1293,10 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)

    do {
    se = pick_next_entity(cfs_rq);
    +
    + if (unlikely(!se))
    + sysrq_sched_debug_show();
    +
    cfs_rq = group_cfs_rq(se);
    } while (cfs_rq);
    diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
    index e24ecd3..e21e020 100644
    --- a/kernel/sched_fair.c
    +++ b/kernel/sched_fair.c
    @@ -1291,6 +1291,12 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)

    do {
    se = pick_next_entity(cfs_rq);
    +
    + if (unlikely(!se))
    + printk(KERN_ERR "BUG: se == NULL but nr_running (%ld), load (%ld),"
    + " rq-nr_running (%ld), rq-load (%ld)\n",
    + cfs_rq->nr_running, cfs_rq->load.weight, rq->nr_running, rq->load.weight);
    +
    cfs_rq = group_cfs_rq(se);
    } while (cfs_rq);
    \
     
     \ /
      Last update: 2008-05-14 10:17    [W:0.029 / U:0.668 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site