Advanced search

Message boards : Server and website : Too many workunits

Author Message
Toni
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 9 Dec 08
Posts: 1006
Credit: 5,068,599
RAC: 0
Level
Ser
Scientific publications
watwatwatwat
Message 20930 - Posted: 13 Apr 2011 | 16:38:45 UTC
Last modified: 13 Apr 2011 | 16:39:20 UTC

Is anybody experiencing (starting a few hours back) a problem with too many workunits downloaded (ie large queue)?

Kirby54925
Send message
Joined: 21 Jan 11
Posts: 31
Credit: 70,061,988
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 20932 - Posted: 13 Apr 2011 | 16:45:35 UTC

Nope, but then again, I keep my queue really low (I set the additional work buffer to 0.02 days).

Dagorath
Send message
Joined: 16 Mar 11
Posts: 509
Credit: 179,005,236
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 20938 - Posted: 13 Apr 2011 | 18:27:12 UTC

No. My client just did a work request and got it's normal 1 task. In my preferences I have "Connect every 0 days" and "Additional cache = 0.05 days".

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 7,520
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 20942 - Posted: 13 Apr 2011 | 22:00:35 UTC

I have three hosts, all of them has more WUs in progress than 2 per GPU.
Host 72651 - 3 GPUs - 7 WUs in progress.
Host 76412 - 2 GPUs - 6 WUs in progress.
Host 97538 - 1 GPU - 3 WUs in progress.
This situation is persistent. When one of my host reports a finished (or failed) task, it receives a new WU, regardless of 2 per GPU (or more) already present.

Betting Slip
Send message
Joined: 5 Jan 09
Posts: 670
Credit: 2,498,095,550
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 20943 - Posted: 13 Apr 2011 | 22:30:06 UTC

No and I have similar settings to Dagorath
____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 7,520
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 20944 - Posted: 13 Apr 2011 | 23:03:37 UTC
Last modified: 13 Apr 2011 | 23:03:58 UTC

While still receiving new WUs, I'm receiving these error messages also:

2011.04.13. 23:52:15 GPUGRID Sending scheduler request: To fetch work.
2011.04.13. 23:52:15 GPUGRID Requesting new tasks for GPU
2011.04.13. 23:52:16 GPUGRID Scheduler request failed: HTTP internal server error

Profile Bikermatt
Send message
Joined: 8 Apr 10
Posts: 37
Credit: 3,839,902,185
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 20945 - Posted: 13 Apr 2011 | 23:03:52 UTC

Yes, I set this host's buffer to two days and the host picked up 5 tasks, for a total of 8 with only 2 GPUs. I aborted 3 of the tasks and set my buffer back to .01 days.


Kirby54925
Send message
Joined: 21 Jan 11
Posts: 31
Credit: 70,061,988
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 20948 - Posted: 14 Apr 2011 | 5:37:37 UTC

Retvari, what is your work buffer set to?

Toni
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 9 Dec 08
Posts: 1006
Credit: 5,068,599
RAC: 0
Level
Ser
Scientific publications
watwatwatwat
Message 20955 - Posted: 14 Apr 2011 | 10:01:11 UTC - in response to Message 20948.

My guess is that the new scheduler is more "responsive" to the work buffer setting that the old was. Those getting too many WUs can try reducing the work buffer.

Toni
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 9 Dec 08
Posts: 1006
Credit: 5,068,599
RAC: 0
Level
Ser
Scientific publications
watwatwatwat
Message 20976 - Posted: 15 Apr 2011 | 11:51:13 UTC - in response to Message 20955.

As per other thread, please cancel all excess WUs.

Post to thread

Message boards : Server and website : Too many workunits

//