[Top] [All Lists]

Re: More on write caching

To: Juha Saarinen <juha@xxxxxxxxxxxx>, Steve Lord <lord@xxxxxxx>
Subject: Re: More on write caching
From: Seth Mos <knuffie@xxxxxxxxx>
Date: Fri, 06 Jul 2001 23:35:20 +0200
Cc: Andrew Klaassen <ak@xxxxxxx>, "linux-xfs@xxxxxxxxxxx" <linux-xfs@xxxxxxxxxxx>
In-reply-to: <Pine.LNX.4.33.0107070908560.326-100000@xxxxxxxxxxxxxxxxxxx rg>
References: <200107061738.f66Hcpb09219@xxxxxxxxxxxxxxxxxxxx>
Sender: owner-linux-xfs@xxxxxxxxxxx
At 09:12 7-7-2001 +1200, Juha Saarinen wrote:
On Fri, 6 Jul 2001, Steve Lord wrote:

> Using the rotational power of the spindle to
> generate power to move the head to a special track and flush the cache
> is not unheard of for instance.

My systems integrator friend tells me that certain drives from IBM have
large capacitors, which come in handy when the power goes out all of a

For obvious reasons, if the drives are connected to a caching controller,
make sure you have an UPS as well...

They have battery packs for caching raid controllers, well at least the decent ones. They can keep the data in there save for 72 hours untill you find time to spin up the disks adn write out the data when it is online again.

Every program has two purposes one for which
it was written and another for which it wasn't
I use the last kind.

<Prev in Thread] Current Thread [Next in Thread>