Re: Allowing WAL fsync to be done via O_SYNC - Mailing list pgsql-hackers

From Tom Lane
Subject Re: Allowing WAL fsync to be done via O_SYNC
Date
Msg-id 14892.984685546@sss.pgh.pa.us
Whole thread Raw
In response to Re: Allowing WAL fsync to be done via O_SYNC  (Alfred Perlstein <bright@wintelcom.net>)
Responses Re: Allowing WAL fsync to be done via O_SYNC  (Alfred Perlstein <bright@wintelcom.net>)
List pgsql-hackers
Alfred Perlstein <bright@wintelcom.net> writes:
> And since we're sorta on the topic of IO, I noticed that it looks
> like (at least in 7.0.3) that vacuum and certain other routines
> read files in reverse order.

Vacuum does that because it's trying to push tuples down from the end
into free space in earlier blocks.  I don't see much way around that
(nor any good reason to think that it's a critical part of vacuum's
performance anyway).  Where else have you seen such behavior?
        regards, tom lane


pgsql-hackers by date:

Previous
From: Alfred Perlstein
Date:
Subject: Re: Allowing WAL fsync to be done via O_SYNC
Next
From: Alfred Perlstein
Date:
Subject: Re: Allowing WAL fsync to be done via O_SYNC