[tahoe-dev] Real-world Tahoe-LAFS grid deployment

[Greg Troxel]

Brian Warner <warner at lothar.com> writes:

> In a sense, by desiring this, you're putting more emphasis on the
> unreliability of the server hardware (CPU) itself. (I guess that my
> inclination, one tahoe node per disk, shows that I'm putting more
> emphasis on the unreliability of the disks, and assuming that the CPU
> will survive longer.. the few failures that AllMyData recorded show that
> your assumptions are more accurate than mine).

You are, I think, assuming a failure model that consists entirely of CPU
and disk failures.  For server operators that commit to maintain nodes,
modulo short-duration power issues, that's probably accurate.  But in a
loosely-coupled social grid, people fading away seems like a bigger
risk.

I realize you were probably talking about the enterprise situation.  But
even there, the "off site backup" concern applies.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 194 bytes
Desc: not available
URL: <http://tahoe-lafs.org/pipermail/tahoe-dev/attachments/20101116/a67f6814/attachment.pgp>