[volunteergrid2-l] Recommended settings

[Peter Secor]

Sure, the biggest a single grid we had in production was about 150 
nodes, each with a 1-2TB drive associated with it, giving about 250TB of 
raw storage. The servers were bought in tranches, so over time the disks 
grew larger (roughly the same price point). We also ran a few helpers 
which the Windows clients defaulted to using, a public web gateway 
(round-robin'ed among multiple public-facing nodes), and an FTP server 
(SFTP wasn't completed yet). I'll try to dig up some stats on the file 
type distribution, sizes, and other information.

Allmydata fully sponsored the Tahoe project both with people and 
equipment until it (Allmydata) ran out of funding (end 2008/early 2009), 
and currently the costs of the Tahoe-LAFS project infrastructure 
(machines, bandwidth, hosting, etc.) are partially covered by donations 
and the remaining covered by personal contributions (myself and a couple 
others) and a couple sponsoring organizations (see the wiki).

Ps

On 6/30/11 12:05 PM, Shawn Willden wrote:
> On Thu, Jun 30, 2011 at 12:21 PM, Peter Secor <secorp at gmail.com
> <mailto:secorp at gmail.com>> wrote:
>
>     Shawn - good overall summary, just a couple clarifications on the
>     "Allmydata problem" from my perspective.
>
>
> Thanks for the clarification, Peter.
>
> Would it be possible for you to tell us how many nodes are in the
> allmydata grid?  I think that's an important part of this story.
>
> Also, one other thing I should have mentioned is that the other relevant
> aspect of this story is that without allmydata, we wouldn't have Tahoe.
>
> --
> Shawn
>
>
>
> _______________________________________________
> volunteergrid2-l mailing list
> volunteergrid2-l at tahoe-lafs.org
> http://tahoe-lafs.org/cgi-bin/mailman/listinfo/volunteergrid2-l
> http://bigpig.org/twiki/bin/view/Main/WebHome