Re: swarm of processes in BIND state?

On Sat, May 28, 2016 at 07:25:18AM +0200, Pavel Stehule wrote:
> It is looking like spinlock issue.
> try to look there by "perf top"

First results look like:

Samples: 64K of event 'cpu-clock', Event count (approx.): 2394094576                                                                                                                                                                                     [0/65]
 32.08%  [unknown]                [.] 0x00007f27ed20a296
  6.31%  [kernel]                 [k] finish_task_switch
  5.72%  [kernel]                 [k] _raw_spin_unlock_irqrestore
  3.46%  postgres                 [.] 0x00000000002764ec
  3.38%  libruby-2.1.so.2.1.0     [.] 0x000000000008a8d0
  2.76%  [kernel]                 [k] __do_page_fault
  2.08%  postgres                 [.] hash_search_with_hash_value
  1.94%  libc-2.19.so             [.] 0x0000000000160b96
  1.79%  postgres                 [.] LWLockAcquire
  1.50%  postgres                 [.] heap_page_prune_opt
  1.28%  postgres                 [.] LWLockRelease
  1.09%  postgres                 [.] heap_hot_search_buffer
  1.00%  [kernel]                 [k] tick_nohz_idle_enter

I guess I have to use pg with debugging flags?

Best regards,

depesz