Message boards : BOINC client : 'Use no more than' preference change request
Message board moderation
Author | Message |
---|---|
Send message Joined: 26 Mar 06 Posts: 91 |
I would like it if when BOINC was suspended that it would force a write to the disk. That way one wouldn't lose any work due to 'Write to disk at most every'. To clarify, I have it set to 900/s and if I have to restart my computer then I lose out on X amount of work progress (even if I suspend the project[s]). I'm not about forcing when a computer crashes or such. |
Send message Joined: 29 Aug 05 Posts: 304 |
Unfortunately this is likely to be impossible or impractical. Some science applications can not checkpoint on command due to the calculations invovled. BOINC WIKI BOINCing since 2002/12/8 |
Send message Joined: 26 Mar 06 Posts: 91 |
Ok, thanks the answer. The reason I increased the disk write from default was because I had read in the BOINC wiki that doing so would increase performance. To quote, "The last setting is the one for the "write to disk interval". This setting, made high enough can get you a lot more if you do not mind the risk of losing an hour or so of work." I am curious as to why, to save on cycle usage? All in all it is a minor irration; thought I'd ask about it. Another question I have is how high is "high enough"? I have two computers working on Einstein (P4 3.0 1014MB & Cel. 2.4 254MB). Or should I ask this on the Einstein forum? Also sorry about the bogus 'Use no more than' header for the thread. Synapse collapse. |
Send message Joined: 6 Apr 06 Posts: 11 |
I do not know about science apps which perform better with longer "Write to disk intervalls". For some they are hardcoded (climateprediction for example) for other s they vary according to the WU (Rosetta for example). Longer "write to disk" periods can reduce hard disk stress but that is hardly of any importance. |
Send message Joined: 26 Mar 06 Posts: 91 |
Thanks for the answer folks. I put the same questions to the Einstein board and received pretty much the same. |
Send message Joined: 29 Aug 05 Posts: 304 |
Disks are much slower than memory. The rest of the system can spend significant amounts of time waiting on the disk to do it's I/O operations. In most cases the science application will have to wait until the disk I/O is done before it can go to the next step. For some projects with minimal data needed for a checkpoint the hit is not too bad for others with large data sets it the hit per checkpoint is much greater. On any project the more often the checkpoint is done the more time the app spends waiting on the disk. BOINC WIKI BOINCing since 2002/12/8 |
Send message Joined: 10 Mar 06 Posts: 73 |
Longer "write to disk" periods can reduce hard disk stress but that is hardly of any importance. On laptops this option could help keeping heat down and/or extending battery life. Even though I don't run BOINC on batteries, some might and this option, if honored by the application, would help keeping the HD spun down. |
Copyright © 2025 University of California.
Permission is granted to copy, distribute and/or modify this document
under the terms of the GNU Free Documentation License,
Version 1.2 or any later version published by the Free Software Foundation.