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 -- Sent via pgsql-general mailing list (pgsql-general@xxxxxxxxxxxxxx) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-general
