Re: [REVIEW] Re: Compression of full-page-writes

From: Craig Ringer <craig(at)2ndquadrant(dot)com>
To: "ktm(at)rice(dot)edu" <ktm(at)rice(dot)edu>, Arthur Silva <arthurprs(at)gmail(dot)com>
Cc: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Andres Freund <andres(at)2ndquadrant(dot)com>, Ants Aasma <ants(at)cybertec(dot)at>, Fujii Masao <masao(dot)fujii(at)gmail(dot)com>, Robert Haas <robertmhaas(at)gmail(dot)com>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>, Rahila Syed <rahilasyed(dot)90(at)gmail(dot)com>, Rahila Syed <rahilasyed90(at)gmail(dot)com>, Abhijit Menon-Sen <ams(at)2ndquadrant(dot)com>, Heikki Linnakangas <hlinnakangas(at)vmware(dot)com>
Subject: Re: [REVIEW] Re: Compression of full-page-writes
Date: 2014-09-15 04:27:05
Message-ID: 54166A99.4070008@2ndquadrant.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On 09/14/2014 09:27 AM, ktm(at)rice(dot)edu wrote:
> Thank you for running this sample benchmark. It definitely shows that the
> hardware version of the CRC is very fast, unfortunately it is really only
> available on x64 Intel/AMD processors which leaves all the rest lacking.

We're talking about something that'd land in 9.5 at best, and going by
the adoption rates I see, get picked up slowly over the next couple of
years by users.

Given that hardware support is already widespread now, I'm not at all
convinced that this is a problem. In mid-2015 we'd be talking about 4+
year old AMD CPUs and Intel CPUs that're 6+ years old.

In a quick search around I did find one class of machine I have access
to that doesn't have SSE 4.2 support. Well, two if you count the POWER7
boxes. It is a type of pre-OpenStack slated-for-retirement RackSpace
server with an Opteron 2374.

People on older, slower hardware won't get a big performance boost when
adopting a new PostgreSQL major release on their old gear. This doesn't
greatly upset me.

It'd be another thing if we were talking about something where people
without the required support would be unable to run the Pg release or
take a massive performance hit, but that doesn't appear to be the case here.

So I'm all for taking advantage of the hardware support.

--
Craig Ringer http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Noah Misch 2014-09-15 04:51:14 Re: orangutan seizes up during isolation-check
Previous Message Peter Geoghegan 2014-09-15 04:15:30 Re: Obsolete comment within execTuples.c