On Fri, 18 Mar 2005 14:56:37 +0100
Lars Marowsky-Bree <[EMAIL PROTECTED]> wrote:
> Activating the same md raid on more than one node will destroy your
> data, is the gist of it.
No. Happened to me multiple times and I still have all the data.
It's not much of a problem if two machines are syncin
berk walker wrote:
as I understand it, the topic is what happens when a RAID0 which is
split twixt remote sites loses communication. What would you suggest
as a method to keep the obvious from happening?
oops! RAID1.. sorry
A proactive approach, perhaps? Since, it seems, that write requests
as I understand it, the topic is what happens when a RAID0 which is
split twixt remote sites loses communication. What would you suggest as
a method to keep the obvious from happening?
A proactive approach, perhaps? Since, it seems, that write requests do
not have to be ack'd immediatly, ther
Luca Berra <[EMAIL PROTECTED]> wrote:
> we can have a series of failures which must be accounted for and dealt
> with according to a policy that might be site specific.
>
> A) Failure of the standby node
> A.1) the active is allowed to continue in the absence of a data replica
> A.2) disk writ
Hi Neil
> Right about what? I don't think that anything that I wrote can
> reasonably be interpreted to say that you can just use one channel
> without losing performance.
>
> I said "If ... the devices handles the required parallelism". I don't
> know much in detail about IDE (I use SCSI mostl
On Friday March 25, [EMAIL PROTECTED] wrote:
> >
> > The raid0 driver is 'clever' at all.
Hmm.. that should have been "The raid0 drivers isn't 'clever' at all.
^
> > It is given requests by the filesystem or mm subsystem, maps them to
> > the co
>
> The raid0 driver is 'clever' at all.
> It is given requests by the filesystem or mm subsystem, maps them to
> the correct device/sector, and sends them straight on to the
> appropriate driver. It never waits for requests, just maps and
> forwards.
>
> So if the filesystem sends 128 4k read-