Message boards :
Theory Application :
Theory Jobs Active
Message board moderation
Author | Message |
---|---|
Send message Joined: 12 Sep 14 Posts: 1067 Credit: 334,882 RAC: 0 |
Theory jobs should be active again. |
Send message Joined: 12 Sep 14 Posts: 1067 Credit: 334,882 RAC: 0 |
They are working on my test machines. How is it looking for others? |
Send message Joined: 8 Apr 15 Posts: 780 Credit: 12,165,828 RAC: 2,284 |
I have some running right now and on this one it is almost to 80% finished So far so good. |
Send message Joined: 13 Feb 15 Posts: 1188 Credit: 859,767 RAC: 12 |
They are working on my test machines. How is it looking for others? Looks fine. 3 hours into the task. 10 jobs done so far on 4 cores. 2GB RAM dedicated - 1.3 in use. Edit: Not seen MCPlots updated yet. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
I think, the memory allocated should be reconsidered. As the number of threads varies a lot, it is difficult to come up with a single one. I suggest 1024MB, which even small machines can handle. Better would be, if the memory allocated is linked somewhat to the number of cores/threads involved in a mt-task. Suggesting: 768MB for the first and 128MB more, for each additional core. Comments? |
Send message Joined: 13 Feb 15 Posts: 1188 Credit: 859,767 RAC: 12 |
Not seen MCPlots updated yet. Now it is. |
Send message Joined: 12 Sep 14 Posts: 1067 Credit: 334,882 RAC: 0 |
I think that this is going to be case. A base value + x per core. |
©2024 CERN