Message boards :
Number crunching :
SETI Server architecture Q
Message board moderation
Author | Message |
---|---|
PhonAcq Send message Joined: 14 Apr 01 Posts: 1656 Credit: 30,658,217 RAC: 1 |
I see various roles occurring multiple times on some of the servers. For example, transitioner 1 through 6 are running on Vader. Do the corresponding applications each run in their own VM on VAder, are they multiple instantiations, or something else? What would be the ideal structure for Seti's purposes? (e.g. VM's or multiple processes in one shell, or ?? You define "ideal".) |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
Doubt they in different VMs. For what? Just to isolate OS bugs? Multi-process OS with virtual memory addressing quite enough to isolate processes from each other is OS itself written right. VM just adds level of complexity and overhead in this case. VM usage - to isolate process from hardware, not process from another process. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Matt used to give a lot of detail about things in the Technical News posts. You may be able to get the exact information you are looking for from reading all of them. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
PhonAcq Send message Joined: 14 Apr 01 Posts: 1656 Credit: 30,658,217 RAC: 1 |
I don't think that is completely true. In an distributed system, performance bottle necks can occur. Separate VM's push the bottle neck into the base host OS, which could be better at resolving than is the case when threads in the same OS can. (I'm abbreviating here) |
©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.