Re: Large shared_buffer stalls WAS: proposal: Set effective_cache_size to greater of .conf value, shared_buffers - Mailing list pgsql-hackers

From Merlin Moncure
Subject Re: Large shared_buffer stalls WAS: proposal: Set effective_cache_size to greater of .conf value, shared_buffers
Date
Msg-id CAHyXU0x+npMkCPVQRhdWhcJ_5QWKaUmySRHVzz8NAEkzrR=_Vg@mail.gmail.com
Whole thread Raw
In response to Re: Large shared_buffer stalls WAS: proposal: Set effective_cache_size to greater of .conf value, shared_buffers  (Josh Berkus <josh@agliodbs.com>)
List pgsql-hackers
On Fri, Sep 13, 2013 at 2:36 PM, Josh Berkus <josh@agliodbs.com> wrote:
> On 09/13/2013 09:27 AM, Merlin Moncure wrote:
>> I happen to be one of those "couple" people.  Load goes from 0.1 to
>> 500 without warning then back to 0.1 equally without warning.
>> Unfortunately the server is in a different jurisdiction such that it
>> makes deep forensic analysis impossible.  I think this is happening
>> more and more often as postgres is becoming increasingly deployed on
>> high(er) -end servers.  I've personally (alone) dealt with 4-5
>> confirmed cases and there have been many more.  We have a problem.
>
> Can you explain a bit more about this?  I'm currently grappling with a
> db cluster which has periodic mysterious total LWLock paralysis, and is
> configured with 8GB shared_buffers (and 512GB ram installed).

see thread: http://postgresql.1045698.n5.nabble.com/StrategyGetBuffer-optimization-take-2-td5766307.html
plus others.  In this particular case, s_b needs to be set to 2GB or
lower (they tried raising to 4GB for no good reason) and problem
reoccured.

what are the specific symptoms of your problem?  anything interesting
in pg_locks?  is $client willing to experiment with custom patches?

merlin



pgsql-hackers by date:

Previous
From: Stephen Frost
Date:
Subject: Re: Strange hanging bug in a simple milter
Next
From: Josh Berkus
Date:
Subject: Re: Large shared_buffer stalls WAS: proposal: Set effective_cache_size to greater of .conf value, shared_buffers