Questions and Answers :
Wish list :
Suggestion for a scalable BOINC infrastructure
Message board moderation
Author | Message |
---|---|
Hans Dorn Send message Joined: 3 Apr 99 Posts: 2262 Credit: 26,448,570 RAC: 0 |
Hi all. I'm wondering if it would make sense to have all required server processes (validator, splitter, scheduler, feeder, etc..) running on each machine, and split up users and WUs up front. e.g: Server1 runs all processes, but handles only the fraction of the users and the fraction of the WUs, that were assigned to it. Server2 handles a different fraction of WUs and users, and so on. Server1 users would only get WUs from server1 and send their results there to be validates against other results of Server1 users. There would be no more need to compare everything with everybody and generate a huge database load this way. Each server sees only so much users and WUs as it can handle. If you want to allow more users, just install another (identical) server. There would to be some kind of front end server to split up the work, but it wouldn't have too much to do, since it only needs to know where each user and each WU are residing. Regards Hans |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.