Gluster users - Jul 2010 - error handling for cluster/replicate across 2 or more nodes

I am setting up a gluster configuration to replicate data across 3 nodes
using:

volume afr-volume
  type cluster/replicate
  subvolumes brick1 brick2 brick3
end-volume

Can someone say what safeguards exist with such a configuration to ensure
that if one of the nodes disks, starts to go bad and thus introduce errors
in one or more of the copies of files, that these bad sectors don't get
replicated across the cluster.

John

Am I to take it that this is not an issue using gluster. I really would like
even to be pointed in the right direction about this issue (or non issue).

John

On Thu, Jul 8, 2010 at 8:03 AM, John Preston <byhisdeeds at gmail.com>
wrote:
> I am setting up a gluster configuration to replicate data across 3 nodes
> using:
>
> volume afr-volume
>   type cluster/replicate
>   subvolumes brick1 brick2 brick3
> end-volume
>
> Can someone say what safeguards exist with such a configuration to ensure
> that if one of the nodes disks, starts to go bad and thus introduce errors
> in one or more of the copies of files, that these bad sectors don't get
> replicated across the cluster.
>
> John
>

On 7/8/10, John Preston <byhisdeeds at gmail.com>
wrote:
> I am setting up a gluster configuration to replicate data across 3 nodes
> using:
>
> volume afr-volume
>   type cluster/replicate
>   subvolumes brick1 brick2 brick3
> end-volume
>
> Can someone say what safeguards exist with such a configuration to ensure
> that if one of the nodes disks, starts to go bad and thus introduce errors
> in one or more of the copies of files, that these bad sectors don't get
> replicated across the cluster.
I'm not certain but if the disk develops hard problems, I'll assume
the host node will report it as an IO error and therefore the node is
considered as failed? I suppose the problem would be if the node
manages to read "something" after a retry.

Just giving my 2cents and hoping to stir up some interest in this :)