Date: Tue, 3 Mar 2020 09:49:35 +0800
From: Adam Lee <ali@pivotal.io>
To: Jeff Davis <pgsql@j-davis.com>
Cc: pgsql-hackers@postgresql.org, Peter Geoghegan <pg@bowt.ie>,
        Heikki Linnakangas <heikki.linnakangas@iki.fi>
Subject: Re: Add LogicalTapeSetExtend() to logtape.c
Message-ID: <20200303014935.GA1022@earth.local>
References: <e54bfec11c59689890f277722aaaabd05f78e22c.camel@j-davis.com>
 <20200228061641.GA883@earth.local>
 <619e61919fd604c2caa629536ee87615b732e054.camel@j-davis.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <619e61919fd604c2caa629536ee87615b732e054.camel@j-davis.com>
Precedence: bulk

On Fri, Feb 28, 2020 at 12:38:55PM -0800, Jeff Davis wrote:
> On Fri, 2020-02-28 at 14:16 +0800, Adam Lee wrote:
> > I noticed another difference, I was using palloc0(), which could be
> > one of the
> > reason, but not sure.
> 
> I changed the palloc0()'s in your code to plain palloc(), and it didn't
> make any perceptible difference. Still slower than the version I posted
> that keeps the flexible array.
> 
> Did you compare all 3? Master, with your patch, and with my patch? I'd
> like to see if you're seeing the same thing that I am.
> 
> > Tested your hashagg-20200226.patch on my laptop(Apple clang version
> > 11.0.0),
> > the average time is 25.9s:
> 
> That sounds high -- my runs are about half that time. Is that with a
> debug build or an optimized one?
> 
> Regards,
> 	Jeff Davis

Yes, I was running a debug version. I usually do 'CFLAGS=-O0 -g3'
'--enable-cassert' '--enable-debug'.

Test with a general build:

Master: 12729ms 12970ms 12999ms
With my patch(a pointer): 12965ms 13273ms 13116ms
With your patch(flexible array): 12906ms 12991ms 13043ms

Not obvious I suppose, anyway, your patch looks good to me.

-- 
Adam Lee