Skip site navigation (1) Skip section navigation (2)

Re: testing HS/SR - 1 vs 2 performance

From: Aidan Van Dyk <aidan(at)highrise(dot)ca>
To: Robert Haas <robertmhaas(at)gmail(dot)com>
Cc: Fujii Masao <masao(dot)fujii(at)gmail(dot)com>, Erik Rijkers <er(at)xs4all(dot)nl>,pgsql-hackers(at)postgresql(dot)org
Subject: Re: testing HS/SR - 1 vs 2 performance
Date: 2010-04-12 13:30:01
Message-ID: 20100412133001.GH5554@oak.highrise.ca (view raw or flat)
Thread:
Lists: pgsql-hackers
* Robert Haas <robertmhaas(at)gmail(dot)com> [100412 07:10]:
 
> I think we need to investigate this more.  It's not going to look good
> for the project if people find that a hot standby server runs two
> orders of magnitude slower than the primary.

Yes, it's not "good", but it's a known problem.  We've had people
complaining that wal-replay can't keep up with a wal stream from a heavy
server.

The master producing the wal stream has $XXX seperate read/modify
processes working over the data dir, and is bottle-necked by the
serialized WAL stream.  All the seek+read delays are parallized and
overlapping.

But on the slave (traditionally PITR slave, now also HS/SR), has al
lthat read-modify-write happening in a single thread fasion, meaning
that WAL record $X+1 waits until the buffer $X needs to modify is read
in.  All the seek+read delays are serialized.

You can optimize that by keepdng more of them in buffers (shared, or OS
cache), but the WAL producer, by it's very nature being a
multi-task-io-load producing random read/write is always going to go
quicker than single-stream random-io WAL consumer...

a.

-- 
Aidan Van Dyk                                             Create like a god,
aidan(at)highrise(dot)ca                                       command like a king,
http://www.highrise.ca/                                   work like a slave.

In response to

Responses

pgsql-hackers by date

Next:From: Aidan Van DykDate: 2010-04-12 13:46:49
Subject: Re: testing HS/SR - 1 vs 2 performance
Previous:From: Robert HaasDate: 2010-04-12 13:17:56
Subject: Re: testing HS/SR - 1 vs 2 performance

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group