[Linux-cluster] GFS on AOE

[Jeff Sturm]

> -----Original Message-----
> From: linux-cluster-bounces at redhat.com
[mailto:linux-cluster-bounces at redhat.com]
> On Behalf Of Gordan Bobic
> Sent: Tuesday, December 07, 2010 11:24 AM
> To: linux clustering
> Subject: Re: [Linux-cluster] GFS on AOE
> 
> > Note however that the AoE protocol does not specify caching, except
> > for optional asynchronous writes.  (The aoe Linux module does not
> > utilize asynchronous writes.)
> 
> It's still an unusual setup. Rather than use a lopsided setup of one
node using the disk
> directly and the other via AoE, it would probably be safer and more
reasonable to have
> the physical disk only accessed by the AoE server daemon and have both
nodes
> connect to that..

No question about it... I was commenting on one aspect of AoE, while
you're giving the OP better advice as to how he can configure a good
2-node cluster.

> DRBD is good for a "poor man's SAN" that does away with the SPOF,
unlike most
> "enterprise grade" SANs that are based on the assumption that the SAN
will never fail.

Agreed, DRBD works well for that.  If you need more than a 2-node
cluster, it might make sense to run AoE (or iSCSI) over DRBD.

Most "enterprise grade" SANs have some provisions for
failover/redundancy, but you make a good point--even if a single SAN
chassis is indeed bulletproof, you'll need to take them offline for
maintenance (e.g. firmware updates) from time to time.  (Then, there's
human error to deal with as well.)

-Jeff