Welcome to MilkyWay@home

Posts by jo1252

1) Message boards : News : Micromanaging CPU vs GPU Workunit Limits (Message 68183)
Posted 23 Feb 2019 by jo1252
Post:
Here is the thing happening with the database flickering between on and off everyday for many hours at a time.

With 200 WUs per GPU, I run out of work in <2 hours.
The database usually goes offline for longer than this amount of time, putting effectively my computer on a crunching break multiple times per day.

I would strongly encourage you to either improve the stability of your servers, increase the limit of GPU WUs we can have stored to a much higher amount (600WUs per GPU, for example). Another suggestion would be to increase the work you put in each WU. That way they would run for longer on GPU and the lower limit you now have in place would be adequate. If your database gets crunched by too many requests, maybe you could implement a higher time between requests, now it is every 90 seconds, what about every 10 minutes or something higher to reduce the load on your end.

I really hope you will improve this situation.




©2024 Astroinformatics Group