[Linux-cluster] iSCSI GFS

[jr]

Hi Mike,


> How would this machine be turned into an aggregator? Would it handle knowing 
> where everything is or would servers still need to know which share to connect 
> to in order to get the needed data?

actually, you need to know all that and then set it up :)

> 
> I also happen to have a BlueArc i7500 machine which can offer up NFS shares. I 
> didn't want to use anything like that because I've read too many message about 
> NFS not being a good protocol to grow on. Do you disagree?

Depends. For instance, there are many people that use NFS as a backend
for a cluster of mailservers or even webservers. 

> 
> > Exactly. You have a machine that pretends to be a SAN when it in fact
> > has no space on it. Instead, it connects to all the individual storage
> > nodes, mounts their volumes, merges them into one big volume, and then
> > presents that one big volume via iSCSI.
> 
> Ok, I like it :). I don't get how I aggregate it all into a single volume, 
> guess I've not played with software RAID which expands to different storage 
> devices and volumes. I get the idea though.

You won't even necessarily need software RAID for that. Think LVM! 
you basically initialize all your storage as Physical Volumes and then
slice some VolumeGroups from those depending on your needs.
You can still use software RAID though.

> 
> For hardware, would this aggregator need massive resources in terms of CPU or 
> memory? I have IBM's which have 8-way CPU's and can have up to 64GB of memory. 

wow, christ. I don't think you need that much woom for I/O :) 

> 
> Would the aggregator be a potential cluster candidate perhaps? Might it be 
> possible to run a cluster of them to be safe and to offload? 
> 
> This is interesting. I can see that if I could get to VM/shareroot and 
> something like this, I would have something quite nice going.
> 
> > It's a central connection point AND a router, only it isn't just
> > straight routing, because the data is RAID striped for redundancy.
> 
> Right, I just don't yet get how the aggregator handles all of that I/O. Or 
> perhaps it just tells the servers which storage device to connect to so that 
> it doesn't actually have to take on all of the I/O?

nah. actually all this FC-Head/Aggregator think calls for openfiler once
again! It basically does what you guys are talking to.
And no, it actually acts some kind of bridge between your servers
connecting with iSCSI and your FC-Storage. so yeah, all the I/O has to
go through that machine..
I'd say the I/O is mostly limited by the number of FC-links you give it
to use.
Johannes
> -
> Linux-cluster mailing list
> Linux-cluster at redhat.com
> https://www.redhat.com/mailman/listinfo/linux-cluster