[Planetlab-users] node availability benchmarks

[Sean C. Rhea]

On Jun 18, 2004, at 6:43 AM, Larry Peterson wrote:
> In this context, it's worth noting that we've recently
> seen numbers posted to this mailing list ranging from around 200 to 
> nearly 300. Why
> the wide range?

I'm pretty sure that most of us running DHTs are not using the 
Internet2-only nodes, as DHTs tend to assume connectivity is 
transitive.  With that restriction, I'm seeing around 235 reachable 
hosts, about 210 of which seem to run OpenHash well at any given time.

> What I don't have a good handle on is the extent to which users are 
> able to
> successfully work around the churn that happens on PlanetLab. Insights 
> on this
> point would be helpful.

Node reboots aren't a bid deal for OpenHash, since it stores state on 
disk.  They cause a little data movement as the DHT reacts to a 
perceived loss of redundancy, but as soon as a node comes back up, that 
movement stops.  Nodes that go away and never come back are much more 
of a problem.

Sean
-- 
      Other people can talk about how to expand the destiny of mankind.
      I just want to talk about how to fix a motorcycle.  I think that
                 what I have to say has more lasting value.
       -- Robert M. Pirsig, Zen and the Art of Motorcycle Maintenance

-------------- next part --------------
A non-text attachment was scrubbed...
Name: PGP.sig
Type: application/pgp-signature
Size: 186 bytes
Desc: This is a digitally signed message part
Url : http://lists.planet-lab.org/pipermail/users/attachments/20040618/c66129df/PGP.bin