[Linux-cluster] GFS limits?

[Don MacAskill]

Hi there,

I've been peripherally following GFS's progress for the last two years 
or so, and I'm very interested in using it.  We were already on Red Hat 
when Sistina was acquired, so I've been waiting to see what Red Hat will 
do with it.   But before I get ahold of the sales people, I thought I'd 
find out a little more about it.

We have two use cases where I can see it being useful:

- For our web server clusters to share a single "snapshot" of our 
application code amongst themselves.  GFS obviously functions great in 
this environment and would be useful.

- For our backend image data storage.  We currently have 35TB of 
storage, and it's growing at a rapid rate.  I'd like to be able to scale 
into hundreds of petabytes some day, and would like to select a solution 
early that will scale large.  Migrating a few hundred TBs from one 
solution to another already keeps me up at night...   PBs would make me 
go insane.  This is the use case I'm not sure of with regards to GFS.

Does GFS somehow get around the 1TB block device issue?  Just how large 
can a single exported filesystem be with GFS?

Our current (homegrown) solution will scale very well for quite some 
time, but eventually we're going to get saturated with write requests to 
individual head units.  Does GFS intelligently "spread the load" among 
multiple storage entities for writing under high load?  Does it always 
write to any available storage units, or are there thresholds where it 
expands the pool of units it writes to?  (I'm not sure I'm making much 
sense, but we'll see if any of you grok it :)

In the event of some multiple-catastrophe failure (where some data isn't 
online at all, let alone redundant), how graceful is GFS?  Does it "rope 
off" the data that's not available and still allow full access to the 
data that is?  Or does the whole cluster go down?

I notice the pricing for GFS is $2200.  Is that per seat?  And if so, 
what's a "seat"?  Each client?  Each server with storage participating 
in the cluster?  Both?  Some other distinction?

Is AS a prereq for clients?  Servers?  Both?  Or will ES and WS boxes be 
able to participate as well?

Whew, that should be enough to get us started.

Thanks in advance!

Don




-------------- next part --------------
A non-text attachment was scrubbed...
Name: don.vcf
Type: text/x-vcard
Size: 253 bytes
Desc: not available
URL: <http://listman.redhat.com/archives/linux-cluster/attachments/20040713/c0f0bf5e/attachment.vcf>