Re: Hash join gets slower as work_mem increases?

I ran operf on both backends, and they look quite similar, except that the
number of samples is different (this is "opreport -c" output):

CPU: Intel Sandy Bridge microarchitecture, speed 2899.8 MHz (estimated)
Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 90000
samples  %        image name               symbol name
-------------------------------------------------------------------------------
  112       0.0019  postgres                 ExecProcNode
  3020116  49.9904  postgres                 ExecScanHashBucket
  3021162  50.0077  postgres                 ExecHashJoin
3020116  92.8440  postgres                 ExecScanHashBucket
  3020116  49.9207  postgres                 ExecScanHashBucket [self]
  3020116  49.9207  postgres                 ExecScanHashBucket
  8190      0.1354  vmlinux                  apic_timer_interrupt

What could be an explanation for this?
Is this known behaviour?

Yours,
Laurenz Albe

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