Joined: 28 Jun 99
I noticed on the message boards that some people have reported their client is not requesting new work. I also noticed the same on my computers.
Other people are reporting they are getting work units that are showing extra long "to completion" times. I also have the same.
When I increased my cache size by a couple of days my clients requested more work and got it. The new units downloaded also show long completion times.
Some people have reported that these work units seem to process in the normal amount of time.
Have the project people done this to decrease the number of workunits downloaded over the weekend because they really haven't solved the workunit availability problem?
Joined: 17 Feb 01
I have it.
Venus & Mars
Joined: 15 Jan 04
Thats the only thing I can think of, to slow down automatic work unit acquiring by the clients. Reran benchmarks on computers and didn't change much. As far as the effect on my caching, its a good change for my P3 1.1, it was downloading far more WU than it should have been caching, the benchmarking for it seems to be far off.
Proc Avg CPU Time per WU Old Time Estimate New Time Est
P3 1.1 7:45 5:09 35:12
P4B 2.4 4:10 6:20 29:39
P4B 3.06 HT 3:40 (2 at a time) 6:10 27:55
P4C 2.6 HT 4:07 (2 at a time) 6:40 32:39
PM1.4 1MBL2 2:42 4:45 28:01
I can't believe what an efficient performer the Laptop is. That 1 MB L2 cache seems to make all the difference, as its a 400mhz bus and a 1.4 Ghz processor. These numbers taken from overnight crunching, i.e., computers not in heavy use.
©2017 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.