pg.ddx.io pgsql-performance@postgresql.org mailing list archivehelp / color / mirror / Atom feed
From: Markus Schaber <schabi@logix-tt.com>
To: pgsql-performance@postgresql.org
Subject: Re: What's the best hardver for PostgreSQL 8.1?
Date: Thu, 05 Jan 2006 17:44:05 +0100
Message-ID: <43BD4CD5.8080207@logix-tt.com> (raw)
In-Reply-To: <dokii5$2bba$1@news.hub.org>
References: <43A84D03.7090002@ritek.hu>
<docq5v$24ea$1@news.hub.org>
<200512212209.50234.caseroj@comcast.net>
<200512212231.55100.caseroj@comcast.net>
<20051224135042.484c6e32.frank@wiles.org>
<6.2.5.6.0.20051224161551.01dc5d98@earthlink.net>
<Pine.LNX.4.62.0512241350010.2807@qnivq.ynat.uz>
<dokii5$2bba$1@news.hub.org>
Hi, William,
William Yu wrote:
> Random write performance (small block that only writes to 1 drive):
> 1 write requires N-1 reads + N writes --> 1/2N-1 %
This is not true. Most Raid-5 engines use XOR or similar checksum
methods. As opposed to cryptographic checksums, those can be updated and
corrected incrementally.
check_new = check_old xor data_old xor data_new
So 2 reads and 2 writes are enough: read data and checksum, then adjust
the checksum via the data difference, and write data and new checksum.
And often, the old data block still is in cache, accounting to 1 read
and two writes.
HTH,
Markus
--
Markus Schaber | Logical Tracking&Tracing International AG
Dipl. Inf. | Software Development GIS
Fight against software patents in EU! www.ffii.org www.nosoftwarepatents.org
view thread (54+ messages)
Message-ID: <43BD4CD5.8080207@logix-tt.com> Permalink: ../43BD4CD5.8080207@logix-tt.com/ Also on: postgresql.org/message-id/43BD4CD5.8080207@logix-tt.com ·
reply
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Reply to all the recipients using the --to and --cc options: reply via email To: pgsql-performance@postgresql.org Cc: schabi@logix-tt.com Subject: Re: What's the best hardver for PostgreSQL 8.1? In-Reply-To: <43BD4CD5.8080207@logix-tt.com> * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions for how to clone and mirror all data and code used for this inbox