rpi_logo
reducing max_wus_in_progress
reducing max_wus_in_progress
log in

Advanced search

Message boards : News : reducing max_wus_in_progress

Author Message
Profile Travis
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 30 Aug 07
Posts: 2046
Credit: 26,480
RAC: 0

Message 47166 - Posted: 8 Apr 2011, 5:47:03 UTC

I think with the new server updates people are alleowd to get quite a few more workunits than before -- which is part of why the site is running so slow (there are almost 700,000 tasks floating around).



I've dropped the max_wus_in_progress to 3 for both CPUs ans GPUs. Hopefully this will make the site somewhat responsive again.
____________

Profile The Gas Giant
Avatar
Send message
Joined: 24 Dec 07
Posts: 1947
Credit: 240,884,648
RAC: 0

Message 47167 - Posted: 8 Apr 2011, 6:21:01 UTC

To 3! Holy cow that's drastic since it was 6!

Profile BladeD
Avatar
Send message
Joined: 2 Nov 10
Posts: 731
Credit: 131,536,342
RAC: 0

Message 47168 - Posted: 8 Apr 2011, 6:24:03 UTC - in response to Message 47166.

Did I miss the notice? I got 310 completed WUs and still have pages of WUs! What's the max number of units that you get now?

Profile Travis
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 30 Aug 07
Posts: 2046
Credit: 26,480
RAC: 0

Message 47169 - Posted: 8 Apr 2011, 6:24:11 UTC - in response to Message 47167.

To 3! Holy cow that's drastic since it was 6!


Just trying to get the server working. If things start going smoothly we'll try and increase it and see what happens.
____________

Profile The Gas Giant
Avatar
Send message
Joined: 24 Dec 07
Posts: 1947
Credit: 240,884,648
RAC: 0

Message 47170 - Posted: 8 Apr 2011, 22:50:10 UTC

959 wu's to report on my main cruncher...

cncguru
Avatar
Send message
Joined: 11 Jun 10
Posts: 329
Credit: 1,166,222,661
RAC: 0

Message 47171 - Posted: 8 Apr 2011, 23:10:40 UTC
Last modified: 8 Apr 2011, 23:14:26 UTC

4/8/2011 7:06:09 PM Milkyway@home Sending scheduler request: Requested by user.
4/8/2011 7:06:09 PM Milkyway@home Reporting 1411 completed tasks, requesting new tasks for GPU

and another guy:

4/8/2011 7:11:25 PM Milkyway@home Sending scheduler request: Requested by user.
4/8/2011 7:11:25 PM Milkyway@home Reporting 1137 completed tasks, requesting new tasks for GPU

and another:

4/8/2011 7:11:59 PM Milkyway@home Sending scheduler request: Requested by user.
4/8/2011 7:11:59 PM Milkyway@home Reporting 877 completed tasks, not requesting new tasks


In got more too LMAO

Profile Arif Mert Kapicioglu
Send message
Joined: 14 Dec 09
Posts: 161
Credit: 582,676,899
RAC: 39,949

Message 47172 - Posted: 9 Apr 2011, 0:17:04 UTC

I was scared when i saw 313 wus completed. Now i see why:)

Profile Arif Mert Kapicioglu
Send message
Joined: 14 Dec 09
Posts: 161
Credit: 582,676,899
RAC: 39,949

Message 47174 - Posted: 9 Apr 2011, 0:19:22 UTC

I was scared when i saw 313 wus completed. Now i see why:)

Profile The Gas Giant
Avatar
Send message
Joined: 24 Dec 07
Posts: 1947
Credit: 240,884,648
RAC: 0

Message 47175 - Posted: 9 Apr 2011, 0:42:27 UTC

Be nice to be able to report them...that would quickly reduce the DB size.

cncguru
Avatar
Send message
Joined: 11 Jun 10
Posts: 329
Credit: 1,166,222,661
RAC: 0

Message 47176 - Posted: 9 Apr 2011, 1:12:45 UTC

And yet another (with 2 more outstanding)

4/8/2011 9:08:16 PM Milkyway@home Sending scheduler request: Requested by user.
4/8/2011 9:08:16 PM Milkyway@home Reporting 1430 completed tasks, requesting new tasks for GPU

I wonder how they are going to process all these!!!

Ed.T
Send message
Joined: 1 Feb 11
Posts: 17
Credit: 14,873,794
RAC: 0

Message 47178 - Posted: 9 Apr 2011, 1:25:13 UTC

I don't know what a "feeder" is other than that it seems to be keeping my machines from reporting...

4/8/2011 9:19:27 PM Milkyway@home update requested by user
4/8/2011 9:19:28 PM Milkyway@home Sending scheduler request: Requested by user.
4/8/2011 9:19:28 PM Milkyway@home Reporting 106 completed tasks, not requesting new tasks
4/8/2011 9:19:36 PM Milkyway@home Scheduler request completed
4/8/2011 9:19:36 PM Milkyway@home Message from server: Server error: feeder not running

____________
Please: WCG - Help Cure Muscular Dystrophy

Jesse Viviano
Send message
Joined: 4 Feb 11
Posts: 82
Credit: 38,121,349
RAC: 16,354

Message 47240 - Posted: 9 Apr 2011, 15:38:43 UTC - in response to Message 47178.
Last modified: 9 Apr 2011, 15:39:05 UTC

The BOINC feeder is the program that maintains the pool of SQL database connections for the scheduler. It costs plenty of computing resources to set up a connection to an SQL database each time a scheduler request is made, so having this middleman saves these connections for reuse saves this overhead.

The reason the scheduler cannot maintain this is that there really is no one "the scheduler". Each time the scheduler is called, a new scheduler process or thread (I am not sure which) is spawned and then is torn down at the end of the scheduler request.

If the feeder is down, the scheduler cannot work.


Post to thread

Message boards : News : reducing max_wus_in_progress


Main page · Your account · Message boards


Copyright © 2018 AstroInformatics Group