[prev in list] [next in list] [prev in thread] [next in thread] 

List:       postgresql-general
Subject:    Re: [HACKERS] Upgrading my BSDI box, again
From:       Andrew Sullivan <andrew () libertyrms ! info>
Date:       2003-07-31 14:51:52
[Download RAW message or body]

On Wed, Jul 30, 2003 at 04:18:39PM -0400, Lamar Owen wrote:
> 
> What Andrew is saying is that on some IDE drives it doesn't matter
> what the OS tells the drive to do.  According to the Linux hdparm

Right.  In other words, you can't really trust IDE drives, until the
manufacturers start guaranteeing that their drives will respond to
the commands you send.  I suspect that some manufacturers are better
than others, but I haven't been able to find any reliable data about
this.  The failure to obey commands to turn off write caching is
something I have both seen reported by others and experienced myself,
so I am sure that it happens.  But who does it (or doesn't do it),
I've no idea.  The case I saw was, I believe, a Maxtor drive, and it
happened about 2 years ago, IIRC.

A

-- 
----
Andrew Sullivan                         204-4141 Yonge Street
Liberty RMS                           Toronto, Ontario Canada
<andrew@libertyrms.info>                              M2P 2A8
                                         +1 416 646 3304 x110


---------------------------(end of broadcast)---------------------------
TIP 8: explain analyze is your friend
[prev in list] [next in list] [prev in thread] [next in thread]