It isn't outages, it's anything that hoses up the even distribution of 
uploads.

Even random luck.

Same is true to a lesser extent with downloads and scheduler requests.

Nicolás Alvarez wrote:
> El Dom 12 Jul 2009 20:58:00 Lynn W. Taylor escribió:
>> If every work unit went out, was out for a few hours, and then returned,
>> 24/7/365, the problem I'm talking about does not exist -- the flow is even.
> 
> The problem I had involved no outages. A few hundred workunits went out, were 
> out for a few hours, then the majority tried to come back at the same time. 
> My project was running on a "home" Internet connection, so two or three users 
> could be enough to saturate the project bandwidth.
> 
> But increase the numbers and it could happen to a "real" project too.
> A project without a constant stream of work. It sends a bunch of workunits, 
> clients get them and go quiet for a while. If most take around the same time 
> to finish, you get a DDoS when they try to upload.
> 
_______________________________________________
boinc_dev mailing list
[email protected]
http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev
To unsubscribe, visit the above URL and
(near bottom of page) enter your email address.

Reply via email to