From: Ron Mayer <rm_pg@cheapcomplexdevices.com>
Subject: Re: RES: Priority to a mission critical transaction
Date: Tue, 28 Nov 2006 17:20:38 -0800
Organization: Hub.Org Networking Services
Lines: 34
Message-ID: <456CE066.50803@cheapcomplexdevices.com>
References: <4939.1164740825@sss.pgh.pa.us>
	<200611282344.kASNijt09203@momjian.us>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
To: Bruce Momjian <bruce@momjian.us>
User-Agent: Icedove 1.5.0.7 (X11/20061013)
In-Reply-To: <200611282344.kASNijt09203@momjian.us>
To: pgsql-performance@postgresql.org

Before asking them to remove it, are we sure priority inversion
is really a problem?

I thought this paper: http://www.cs.cmu.edu/~bianca/icde04.pdf
did a pretty good job at studying priority inversion on RDBMs's
including PostgreSQL on various workloads (TCP-W and TCP-C) and
found that the benefits of setting priorities vastly outweighed
the penalties of priority inversion across all the databases and
all the workloads they tested.


Bruce Momjian wrote:
> Someone should ask them to remove the article.
> 
> ---------------------------------------------------------------------------
> 
> Tom Lane wrote:
>> "Carlos H. Reimer" <carlos.reimer@opendb.com.br> writes:
>>> There is an article about "Lowering the priority of a PostgreSQL query"
>>> (http://weblog.bignerdranch.com/?p=11) that explains how to use the
>>> setpriority() to lower PostgreSQL processes.
>>> I?m wondering how much effective it would be for i/o bound systems.
>> That article isn't worth the electrons it's written on.  Aside from the
>> I/O point, there's a little problem called "priority inversion".  See
>> the archives for (many) past discussions of nice'ing backends.
>>
>> 			regards, tom lane
>>
>> ---------------------------(end of broadcast)---------------------------
>> TIP 7: You can help support the PostgreSQL project by donating at
>>
>>                 http://www.postgresql.org/about/donate
>