Date: Tue, 3 May 2016 09:22:09 -0700
From: Andres Freund <andres@anarazel.de>
To: Kevin Grittner <kgrittn@gmail.com>
Cc: Robert Haas <robertmhaas@gmail.com>, Tom Lane <tgl@sss.pgh.pa.us>,
	"pgsql-hackers@postgresql.org" <pgsql-hackers@postgresql.org>
Subject: Re: what to revert
Message-ID: <20160503162209.ufuezlkovbrdrayp@alap3.anarazel.de>
References: 
 <CA+TgmoYOWTtBQEL+Bv=w93bvUjbXSUw3uGnp+R29dduZ==8K0Q@mail.gmail.com>
 <CACjxUsOuf_a6KMsFBNtt8Tn8y7qNLE2Wcb9BQeRFdHD6oAKp3g@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: 
 <CACjxUsOuf_a6KMsFBNtt8Tn8y7qNLE2Wcb9BQeRFdHD6oAKp3g@mail.gmail.com>
Precedence: bulk
Sender: pgsql-hackers-owner@postgresql.org

On 2016-05-03 11:12:03 -0500, Kevin Grittner wrote:
> On Tue, May 3, 2016 at 10:58 AM, Robert Haas <robertmhaas@gmail.com> wrote:
> 
> > - Snapshot Too Old.  Tom, Andres, and Bruce want this reverted.
> > It regresses performance significantly when turned on.
> 
> When turned on, it improves performance in some cases and regresses
> performance in others.  Don't forget it is currently back-patched
> to 9.4 and in use for production by users who could not use
> PostgreSQL without the feature.  PostgreSQL failed their
> performance tests miserably without the feature, and passes with
> it.
> 
> > It originally regressed performance significantly even when
> > turned off,
> 
> Which was wildly exaggerated since most of the benchmarks
> purporting to show that actually had it turned on.  I don't think
> the FUD from that has really evaporated.

Oh, ffs.  The first report of the whole issue was *with default
parameters*:
http://archives.postgresql.org/message-id/CAPpHfdtMONZFOXSsw1HkrD9Eb4ozF8Q8oCqH4tkpH_girJPPuA%40mail.gmail.com

The issue with 0 v. -1 (and 0 vs. > 0 makes a big performance
difference, so it's not that surprising to interpret numbers that way)
was immediately addressed by another round of benchmarks after you
pointed it out.

> > but that might be fixed now.
> 
> Certainly all evidence suggests that, FUD to the contrary.

So it's now FUD to report issues with a patch that obviously hasn't
received sufficient benchmarking? Give me break.


Andres


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