On Mon, Jun 20, 2011 at 12:56 PM, Hoskins, Matthew
<[email protected]> 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
[email protected]
https://lists.openafs.org/mailman/listinfo/openafs-info

Reply via email to