It varies by class of fs server, for instance our INF servers are 200g (in two 
100g vicep), USR servers are 600G (3 * 200g vicep), JMB servers are 2T (one 
vicep).  

Across the entire environment, all fileservers in a given class are exactly the 
same.  Deployed from the same templates.  

In the event we need to change the design, the change is implemented across all 
VMs in the fs class to keep everything the same. 



> -----Original Message-----
> From: coyh...@gmail.com [mailto:coyh...@gmail.com] On Behalf Of Coy
> Hile
> Sent: Monday, June 20, 2011 2:55 PM
> To: Hoskins, Matthew
> Cc: openafs-info@openafs.org
> Subject: Re: [OpenAFS] Deploying OpenAFS on VMs
> 
> On Mon, Jun 20, 2011 at 12:56 PM, Hoskins, Matthew
> <matthew.hosk...@njit.edu> wrote:
> 
> > ·         Many fileservers / smaller fileservers:   This philosophy
> has
> > evolved as we have moved more into virtualized fileservers.   With
> physical
> > hardware you are limited by ABILITY TO PURCHASE.  Meaning, you can
> only get
> > "x" number of servers of "n" size.   This means if you want highly
> resilient
> > servers, you can only afford to by a few of them.   This can lead to
> very
> > fat fileservers.   If you go for many cheap fileservers, you might be
> able
> > to get more distributed but end up suffering more small individual
> outages.
> >   With virtualized fileservers you have full flexibility.  On the
> virtual
> > platform, you get HA by default on every VM.    After that you get to
> design
> > your fileserver layout decisions based on the DATA they will
> store.    For
> > example, in our layout we have the following classes of fileservers:
> >
> > o   Infrastructure (INF) Fileservers:  Very small fileserver, for
> highly
> > critical root.*, software, etc. the "bones" of the cell.  Replicated
> of
> > course.
> >
> > o   User fileservers (USR):  Home volumes, nuff said
> >
> > o   Bulk Fileservers (BLK): Almost everything else, projects, web
> content,
> > research data, yadda yadda
> >
> > o   Jumbo Fileservers (JMB):  Used for ridiculously large volumes.
> These
> > fileservers are the only fileserver that has a VARIABLE vicep
> partition
> > size.   Used for archival data and some research projects.
> >
> 
> Matt,
> 
> What do you use for vicep* partition sizes?
> 
> Thanks,
_______________________________________________
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Reply via email to