On Tue, Nov 20, 2012 at 9:02 AM, Shaun Thomas <sthomas@optionshouse.com> wrote:
> On 11/16/2012 02:31 PM, Merlin Moncure wrote:
>
>> no single thing really stands out -- contention is all over the place.
>> lwlock, pinbuffer, dynahash (especially). I am again suspicious of
>> bad scheduler interaction. any chance we can fire up pgbouncer?
>
>
> Just want to throw it out there, but we've been having really bad luck with
> the scheduler recently. But only when we use 8GB (on our 72GB system) for
> shared_buffers. Cut that down to 4GB, and everything is fine and dandy.
>
> I think the kernel devs have added in some overzealous scheduler code on us.
Shared buffer manipulation changing contention is suggesting you're
running into free list lock issues. How many active backends/cores?
merlin