Re: ATA disks and RAID controllers for database servers - Mailing list pgsql-general

From Mark Kirkwood
Subject Re: ATA disks and RAID controllers for database servers
Date
Msg-id 3FB6DDEA.3000708@paradise.net.nz
Whole thread Raw
In response to Re: ATA disks and RAID controllers for database servers  (Christopher Browne <cbbrowne@acm.org>)
List pgsql-general
>Furthermore, if the disk drives are lying to the controller, it's
>anybody's guess whether or not data ever actually gets to the disk.
>
>When is it safe to let blocks expire out of the controller cache?
>
>If your computer can't know if the data has been written (because of
>drives that lie), I can't imagine how the controller would (since the
>drives are lying to the controller, too).
>

As I understand it, there is only 1 lie : the actual write to the disk.
The receipt into the drive *cache* is not lied about - hence the
discussion on mlist.limux.kernel about capacitors to allow enough power
for a cache flush in a power off situation.

regards

Mark




pgsql-general by date:

Previous
From: bpalmer
Date:
Subject: Re: how to find version?
Next
From: Mark Kirkwood
Date:
Subject: Re: ATA disks and RAID controllers for database servers