Message boards : Number crunching : project priority ideas.
Message board moderation

To post messages, you must log in.

Previous · 1 · 2

AuthorMessage
itenginerd
Avatar

Send message
Joined: 29 Aug 05
Posts: 42
Credit: 27,102
RAC: 0
Message 11438 - Posted: 22 Nov 2005, 18:51:25 UTC - in response to Message 11430.  

Don't know what you mean by:

(Don't make me add this as a check for EDF).


But I do know that Boinc is smart enough to switch to another project to make sure it gets done on time.


1) John means that he's the one writing the panic mode code
2) Someone correct me if I'm wrong, but I think the problem with a 24-hour value for 'switch every' would help DEFEAT the panic mode code. If what I remember is right, the EDF scheduler only kicks in when results are switched, i.e. at the end of the 'switch every' timer. So by going to a 24-hour value, the panic mode could only possible kick in A) every 24 hours or B) every time a work unit is done (or C) every time you hit Update manually). If you have a slow system crunching that takes more than 24 hours to crunch a result, then you would very likely miss deadlines.

Granted, this is founded on the ideas that: 1) you have a slower machine or large results, and 2) that I'm right about EDF and how it kicks in.

Can anyone affirm or correct this for me?

(j)
James
ID: 11438 · Report as offensive     Reply Quote
Profile Yeti
Volunteer moderator
Avatar

Send message
Joined: 2 Sep 04
Posts: 453
Credit: 193,576,736
RAC: 472
Message 11441 - Posted: 22 Nov 2005, 19:45:43 UTC - in response to Message 11438.  

1) John means that he's the one writing the panic mode code
Not only the panic-mode; as far as I know he has developed the complete actual version of the local scheduler:

  • Respecting the ResourceShare
  • Keep WUs in Time before Deadline
  • Calculate the best crunching-priority for users with dial-up-systems


To get all this things working he needed the panic-mode, but panic-mode is only a small aspect of his complete work




Supporting BOINC, a great concept !
ID: 11441 · Report as offensive     Reply Quote
itenginerd
Avatar

Send message
Joined: 29 Aug 05
Posts: 42
Credit: 27,102
RAC: 0
Message 11442 - Posted: 22 Nov 2005, 21:30:37 UTC - in response to Message 11441.  

1) John means that he's the one writing the panic mode code
Not only the panic-mode; as far as I know he has developed the complete actual version of the local scheduler:

  • Respecting the ResourceShare
  • Keep WUs in Time before Deadline
  • Calculate the best crunching-priority for users with dial-up-systems


To get all this things working he needed the panic-mode, but panic-mode is only a small aspect of his complete work



Correct. I didn't mean that EDF was John's only contribution. I just slid past the rest for brevity's sake... 8)

(j)
James
ID: 11442 · Report as offensive     Reply Quote
John McLeod VII
Avatar

Send message
Joined: 2 Sep 04
Posts: 165
Credit: 146,925
RAC: 0
Message 11444 - Posted: 23 Nov 2005, 0:07:42 UTC - in response to Message 11438.  

Don't know what you mean by:

(Don't make me add this as a check for EDF).


But I do know that Boinc is smart enough to switch to another project to make sure it gets done on time.


1) John means that he's the one writing the panic mode code
2) Someone correct me if I'm wrong, but I think the problem with a 24-hour value for 'switch every' would help DEFEAT the panic mode code. If what I remember is right, the EDF scheduler only kicks in when results are switched, i.e. at the end of the 'switch every' timer. So by going to a 24-hour value, the panic mode could only possible kick in A) every 24 hours or B) every time a work unit is done (or C) every time you hit Update manually). If you have a slow system crunching that takes more than 24 hours to crunch a result, then you would very likely miss deadlines.

Granted, this is founded on the ideas that: 1) you have a slower machine or large results, and 2) that I'm right about EDF and how it kicks in.

Can anyone affirm or correct this for me?

(j)
James

Confirmed.


BOINC WIKI
ID: 11444 · Report as offensive     Reply Quote
Profile meckano
Avatar

Send message
Joined: 17 Sep 04
Posts: 150
Credit: 20,315
RAC: 0
Message 11445 - Posted: 23 Nov 2005, 1:54:07 UTC - in response to Message 11444.  

ok put it back to 2 hours
thanks for the feedback
-----------------------
Click to see my tag
My tag
SNAFU'ed? Turn the Page! :D
ID: 11445 · Report as offensive     Reply Quote
Previous · 1 · 2

Message boards : Number crunching : project priority ideas.


©2024 CERN