Re: win32 performance - fsync question - Mailing list pgsql-hackers

From Greg Stark
Subject Re: win32 performance - fsync question
Date
Msg-id 87is4qygu7.fsf@stark.xeocode.com
Whole thread Raw
In response to Re: win32 performance - fsync question  (Oliver Jowett <oliver@opencloud.com>)
Responses Re: win32 performance - fsync question  (Oliver Jowett <oliver@opencloud.com>)
Re: win32 performance - fsync question  (Evgeny Rodichev <er@sai.msu.su>)
List pgsql-hackers
Oliver Jowett <oliver@opencloud.com> writes:

> So Linux is indeed doing a cache flush on fsync

Actually I think the root of the problem was precisely that Linux does not
issue any sort of cache flush commands to drives on fsync. There was some talk
on linux-kernel of what how they could take advantage of new ATA features
planned on new SATA drives coming out now to solve this. But they didn't seem
to think it was urgent or worth the performance hit of doing a complete cache
flush.

-- 
greg



pgsql-hackers by date:

Previous
From: "Sergey E. Koposov"
Date:
Subject: Re: Strange RETURN NEXT behaviour in Postgres 8.0
Next
From: Oliver Jowett
Date:
Subject: Re: win32 performance - fsync question