Subject: Re: CPU costs of random_zipfian in pgbench
To: Tom Lane <tgl@sss.pgh.pa.us>, Fabien COELHO <coelho@cri.ensmp.fr>
Cc: PostgreSQL Hackers <pgsql-hackers@postgresql.org>
References: <b5e172e9-ad22-48a3-86a3-589afa20e8f7@2ndquadrant.com>
 <alpine.DEB.2.21.1902170907110.8818@lancre> <6065.1550419767@sss.pgh.pa.us>
From: Tomas Vondra <tomas.vondra@2ndquadrant.com>
Message-ID: <779980b4-a4a6-3bf9-7ecf-56cc9ce6f5be@2ndquadrant.com>
Date: Sun, 17 Feb 2019 23:08:31 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.5.0
MIME-Version: 1.0
In-Reply-To: <6065.1550419767@sss.pgh.pa.us>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 2/17/19 5:09 PM, Tom Lane wrote:
> Fabien COELHO <coelho@cri.ensmp.fr> writes:
>>> I'm trying to use random_zipfian() for benchmarking of skewed data sets, 
>>> and I ran head-first into an issue with rather excessive CPU costs. 
> 
>> If you want skewed but not especially zipfian, use exponential which is 
>> quite cheap. Also zipfian with a > 1.0 parameter does not have to compute 
>> the harmonic number, so it depends in the parameter.
> 
> Maybe we should drop support for parameter values < 1.0, then.  The idea
> that pgbench is doing something so expensive as to require caching seems
> flat-out insane from here.

Maybe.

It's not quite clear to me why we support the two modes at all? We use
one algorithm for values < 1.0 and another one for values > 1.0, what's
the difference there? Are those distributions materially different?

Also, I wonder if just dropping support for parameters < 1.0 would be
enough, because the docs say:

    The function's performance is poor for parameter values close and
    above 1.0 and on a small range.

which seems to suggest it might be slow even for values > 1.0 in some
cases. Not sure.

> That cannot be seen as anything but a foot-gun
> for unwary users.  Under what circumstances would an informed user use
> that random distribution rather than another far-cheaper-to-compute one?
> 
>> ... This is why I submitted a pseudo-random permutation 
>> function, which alas does not get much momentum from committers.
> 
> TBH, I think pgbench is now much too complex; it does not need more
> features, especially not ones that need large caveats in the docs.
> (What exactly is the point of having zipfian at all?)
> 

I wonder about the growing complexity of pgbench too ...


regards

-- 
Tomas Vondra                  http://www.2ndQuadrant.com
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services