On Tue, 2015-06-30 at 16:30 +0200, Rabin Vincent wrote:
> Hi,
> 
> We're seeing a livelock where two CPUs both loop with interrupts
> disabled in pick_next_task_fair() / idle_balance() and continuously
> fetch all tasks from each other...

Hm.  Does the below help?  Looks to me like we are over-balancing.

homer:/sys/kernel/debug/tracing # echo > trace;massive_intr 12 10 > 
/dev/null;cat trace|grep OINK | wc -l;tail trace
480
    massive_intr-8967  [003] d...   404.285682: load_balance: OINK - imbal: 1  
load: 83  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 83
    massive_intr-8960  [001] d.s.   404.293331: load_balance: OINK - imbal: 1  
load: 84  run: 1  det: 1  sload_was: 180 sload_is: 99  dload: 174
    massive_intr-8962  [002] d.s.   404.317572: load_balance: OINK - imbal: 1  
load: 83  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 161
    massive_intr-8967  [003] d...   404.318296: load_balance: OINK - imbal: 1  
load: 83  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 83
    massive_intr-8960  [005] d...   404.341049: load_balance: OINK - imbal: 1  
load: 84  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 84
    massive_intr-8962  [002] d.s.   404.381549: load_balance: OINK - imbal: 1  
load: 83  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 161
    massive_intr-8971  [005] d...   404.417148: load_balance: OINK - imbal: 1  
load: 84  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 84
    massive_intr-8964  [006] d.s.   404.418536: load_balance: OINK - imbal: 1  
load: 72  run: 1  det: 1  sload_was: 144 sload_is: 83  dload: 149
    massive_intr-8968  [003] d...   404.437861: load_balance: OINK - imbal: 1  
load: 83  run: 1  det: 1  sload_was: 180 sload_is: 83  dload: 83
    massive_intr-8970  [001] d.s.   404.485263: load_balance: OINK - imbal: 1  
load: 71  run: 1  det: 1  sload_was: 154 sload_is: 83  dload: 148
homer:/sys/kernel/debug/tracing # echo > trace;hackbench > /dev/null;cat 
trace|grep OINK | wc -l;tail trace
51
       hackbench-9079  [006] d...   425.982722: load_balance: OINK - imbal: 54  
load: 42  run: 4  det: 4  sload_was: 130 sload_is: 62  dload: 109
       hackbench-9231  [002] d...   425.982974: load_balance: OINK - imbal: 14  
load: 23  run: 1  det: 1  sload_was: 30 sload_is: 15  dload: 23
       hackbench-9328  [006] d...   425.983037: load_balance: OINK - imbal: 16  
load: 72  run: 2  det: 1  sload_was: 44 sload_is: 32  dload: 72
       hackbench-9197  [002] d...   425.984416: load_balance: OINK - imbal: 62  
load: 21  run: 3  det: 8  sload_was: 232 sload_is: 78  dload: 119
       hackbench-9196  [004] d...   425.984507: load_balance: OINK - imbal: 45  
load: 43  run: 1  det: 1  sload_was: 44 sload_is: 22  dload: 43
       hackbench-9201  [004] d...   425.984648: load_balance: OINK - imbal: 15  
load: 44  run: 1  det: 2  sload_was: 71 sload_is: 25  dload: 73
       hackbench-9235  [002] d...   425.984789: load_balance: OINK - imbal: 5  
load: 32  run: 2  det: 1  sload_was: 65 sload_is: 42  dload: 54
       hackbench-9327  [000] d...   425.985424: load_balance: OINK - imbal: 1  
load: 95  run: 1  det: 1  sload_was: 49 sload_is: 25  dload: 95
       hackbench-9193  [003] d...   425.988701: load_balance: OINK - imbal: 22  
load: 94  run: 1  det: 1  sload_was: 128 sload_is: 66  dload: 94
       hackbench-9197  [003] d...   425.988712: load_balance: OINK - imbal: 56  
load: 92  run: 1  det: 1  sload_was: 118 sload_is: 66  dload: 92
homer:/sys/kernel/debug/tracing # tail trace
            kwin-4654  [002] d...   460.627311: load_balance: kglobalaccel:4597 
is non-contributor - count as 37
         konsole-4707  [005] d...   460.627639: load_balance: kded4:4594 is 
non-contributor - count as 40
         konsole-4707  [005] d...   460.627640: load_balance: 
kactivitymanage:4611 is non-contributor - count as 40
            kwin-4654  [005] d...   460.627712: load_balance: 
kactivitymanage:4611 is non-contributor - count as 41
 kactivitymanage-4611  [005] d...   460.627726: load_balance: kded4:4594 is 
non-contributor - count as 40
            kwin-4654  [005] d...   460.828628: load_balance: OINK - imbal: 3  
load: 618  run: 1  det: 1  sload_was: 1024 sload_is: 0  dload: 618
  plasma-desktop-4665  [000] d...   461.886746: load_balance: baloo_file:4666 
is non-contributor - count as 141
 systemd-journal-397   [001] d...   466.209790: load_balance: pulseaudio:4718 
is non-contributor - count as 5
         systemd-1     [007] d...   466.209868: load_balance: kmix:4704 is 
non-contributor - count as 13
 gnome-keyring-d-9455  [002] d...   466.209902: load_balance: krunner:4702 is 
non-contributor - count as 8

---
 kernel/sched/fair.c |   19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5897,7 +5897,7 @@ static int detach_tasks(struct lb_env *e
 {
        struct list_head *tasks = &env->src_rq->cfs_tasks;
        struct task_struct *p;
-       unsigned long load;
+       unsigned long load, d_load = 0, s_load = env->src_rq->load.weight;
        int detached = 0;
 
        lockdep_assert_held(&env->src_rq->lock);
@@ -5936,6 +5936,11 @@ static int detach_tasks(struct lb_env *e
 
                detached++;
                env->imbalance -= load;
+               if (!load) {
+                       load = min_t(unsigned long, env->imbalance, 
p->se.load.weight);
+                       trace_printk("%s:%d is non-contributor - count as 
%ld\n", p->comm, p->pid, load);
+               }
+               d_load += load;
 
 #ifdef CONFIG_PREEMPT
                /*
@@ -5954,6 +5959,18 @@ static int detach_tasks(struct lb_env *e
                if (env->imbalance <= 0)
                        break;
 
+               /*
+                * We don't want to bleed busiest_rq dry either.  Weighted load
+                * and/or imbalance may be dinky, load contribution can even be
+                * zero, perhaps causing us to over balancem we had not assigned
+                * it above.
+                */
+               if (env->src_rq->load.weight <= env->dst_rq->load.weight + 
d_load) {
+                       trace_printk("OINK - imbal: %ld  load: %ld  run: %d  
det: %d  sload_was: %ld sload_is: %ld  dload: %ld\n",
+                               env->imbalance, load, env->src_rq->nr_running, 
detached, s_load, env->src_rq->load.weight, env->dst_rq->load.weight+d_load);
+                       break;
+               }
+
                continue;
 next:
                list_move_tail(&p->se.group_node, tasks);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to