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

Re: [HACKERS] fsync method checking

From: markw(at)osdl(dot)org
To: pgman(at)candle(dot)pha(dot)pa(dot)us
Cc: manfred(at)colorfullife(dot)com, tgl(at)sss(dot)pgh(dot)pa(dot)us, josh(at)agliodbs(dot)com,Q(at)ping(dot)be, markir(at)paradise(dot)net(dot)nz, pgsql-performance(at)postgresql(dot)org,pgsql-hackers(at)postgresql(dot)org
Subject: Re: [HACKERS] fsync method checking
Date: 2004-03-26 17:00:56
Message-ID: 200403261701.i2QH0x203524@mail.osdl.org (view raw or flat)
Thread:
Lists: pgsql-hackerspgsql-performance
On 26 Mar, Bruce Momjian wrote:
> markw(at)osdl(dot)org wrote:
>> On 26 Mar, Manfred Spraul wrote:
>> > markw(at)osdl(dot)org wrote:
>> > 
>> >>Compare file sync methods with one 8k write:
>> >>        (o_dsync unavailable)  
>> >>        open o_sync, write       6.270724
>> >>        write, fdatasync        13.275225
>> >>        write, fsync,           13.359847
>> >>  
>> >>
>> > Odd. Which filesystem, which kernel? It seems fdatasync is broken and 
>> > syncs the inode, too.
>> 
>> It's linux-2.6.5-rc1 with ext2 filesystems.
> 
> Would you benchmark open_sync for wal_sync_method too?

Oh yeah.  Will try to get results later today.

Mark 


In response to

pgsql-performance by date

Next:From: Qing ZhaoDate: 2004-03-26 17:29:20
Subject: Re: column size too large, is this a bug?
Previous:From: Bruce MomjianDate: 2004-03-26 16:54:59
Subject: Re: [HACKERS] fsync method checking

pgsql-hackers by date

Next:From: Richard HuxtonDate: 2004-03-26 18:31:35
Subject: Re: Per database users/admins, handy for database virtual hosting...
Previous:From: Bruce MomjianDate: 2004-03-26 17:00:19
Subject: Re: Nested transaction proposal - take N (N > 2)

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