On Wed, Sep 18, 2013 at 10:30 AM, Lonni J Friedman <netllama@xxxxxxxxx> wrote:
>I think you're onto something here with respect to THP defrag going
> This looks similar to cases I've seen of THP defrag going wild.
> Did the OS version or configuration change? Did the PostgreSQL
> memory settings (like shared_buffers) change?
wild. I set /sys/kernel/mm/transparent_hugepage/defrag to 'never' and
immediately the load dropped on both slaves from over 5.00 to under
1.00.
So this raises the question, is this a kernel bug, or is there some
other solution to the problem?
Also, seems weird that the problem didn't happen until I switched from
9.2 to 9.3. Is it possible this is somehow related to the change from
using SysV shared memory to using Posix shared memory and mmap for
memory management?
I would guess that it is probably a kernel bug which gets efficiently exercised by the SysV to Posix change.
Cheers,
Jeff
