In an analysis of our afs down time for the last four years hardware faults are the number one roto cause by a huge margin, followed by the crypt bug last year.
If we can eliminate downtime for hardware faults we will eliminate our number one outage factor. If the experiment does not work we can alway change.
Nothing tried, nothing learned.
Cheers
Matt
Rodney M Dyer wrote:
At 11:51 PM 4/20/2005, Derek Atkins wrote:
I've never seen any reason to virtualize an AFS server. Ever. The key is IO
bandwith, which isn't increased by virtualization. You really want separate
PHYSICAL servers for AFS servers. Virtualization does not give you any
benefits due to hardware failure, power failure, or any other failure. It just
adds overhead.
I agree. I've never understood the "big honking box" syndrom. It has always seemed to me to be an indication of "Pointy Haired Bosses" being marketed to that causes this situation. The point of AFS is speed, distribution, and scaleability, but you also get redundancy. Putting an AFS cell on a virtualized server is just IMHO...silly. I can't see how in the long run you save money with specialized boxes when server PCs from DELL, which can be used for AFS file servers, cost less than $500 a pop. Of course if you go rack mount, things get more pricey, but still, compared to some specialized box from a proprietary vendor?
Rodney
_______________________________________________ OpenAFS-info mailing list [email protected] https://lists.openafs.org/mailman/listinfo/openafs-info
