Message boards :
Number crunching :
"reached a limit on tasks in progress"
Message board moderation
Author | Message |
---|---|
RottenMutt Send message Joined: 15 Mar 01 Posts: 1011 Credit: 230,314,058 RAC: 0 |
12/30/2011 7:50:12 PM | SETI@home | Reporting 2 completed tasks, requesting new tasks for CPU and NVIDIA GPU 12/30/2011 7:50:16 PM | SETI@home | No tasks sent 12/30/2011 7:50:16 PM | SETI@home | No tasks are available for Astropulse v5 12/30/2011 7:50:16 PM | SETI@home | No tasks are available for Astropulse v505 12/30/2011 7:50:16 PM | SETI@home | This computer has reached a limit on tasks in progress huh, i got 18 GPU work units and 381 CPU work units; how can i reach a limit on tasks in progress. this is the rig http://setiathome.berkeley.edu/show_host_detail.php?hostid=5637187, i7 930 with a gtx 480 and a gtx 475. |
RottenMutt Send message Joined: 15 Mar 01 Posts: 1011 Credit: 230,314,058 RAC: 0 |
12/30/2011 8:49:05 PM | SETI@home | Reporting 3 completed tasks, requesting new tasks for NVIDIA GPU 12/30/2011 8:49:10 PM | SETI@home | Scheduler request completed: got 0 new tasks 12/30/2011 8:49:10 PM | SETI@home | No tasks sent 12/30/2011 8:49:10 PM | SETI@home | No tasks are available for Astropulse v5 12/30/2011 8:49:10 PM | SETI@home | No tasks are available for Astropulse v505 12/30/2011 8:49:10 PM | SETI@home | This computer has reached a limit on tasks in progress GPU has 37 work units in queue!!!! i got another rig with two gtx 275's and it is plugged with GPU work and is struggling to get CPU work. the developers have built such a complicated mouse trap that it can't possibly work correctly!!! |
hbomber Send message Joined: 2 May 01 Posts: 437 Credit: 50,852,854 RAC: 0 |
I experienced same. My limit used to be 1000 task, now at around 840 i get limit message. Soon after, I got another 45 task, thus going well over number of WUs, which caused to get limit message just before that. Go figure. |
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
I'm having so much trouble even getting enough work to keep my top rig going that I don't even know what the limits ARE anymore...LOL. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Kevin Olley Send message Joined: 3 Aug 99 Posts: 906 Credit: 261,085,289 RAC: 572 |
I'm having so much trouble even getting enough work to keep my to rig going that I don't even know what the limits ARE anymore...LOL. +1 Kevin |
SciManStev Send message Joined: 20 Jun 99 Posts: 6652 Credit: 121,090,076 RAC: 0 |
I'm having so much trouble even getting enough work to keep my to rig going that I don't even know what the limits ARE anymore...LOL. +2 Steve Warning, addicted to SETI crunching! Crunching as a member of GPU Users Group. GPUUG Website |
James Sotherden Send message Joined: 16 May 99 Posts: 10436 Credit: 110,373,059 RAC: 54 |
I'm having so much trouble even getting enough work to keep my to rig going that I don't even know what the limits ARE anymore...LOL. +3 [/quote] Old James |
Kevin Olley Send message Joined: 3 Aug 99 Posts: 906 Credit: 261,085,289 RAC: 572 |
Oh dear Be careful what you wish for. Just got 70 GPU WU's in one go. All _2 to _5, not pretty, one of them has been -12 by 3 other machines. Kevin |
RottenMutt Send message Joined: 15 Mar 01 Posts: 1011 Credit: 230,314,058 RAC: 0 |
Even with limits imposed, cricket graphs are dropping, yet I still can't get GPU work. Yes my queues are dry!!! this is extremely frustrating, could drive one to drink!!! (well it is new years eve, :-D ) then my other rigs are only requesting CPU work when they are out of GPU work. Why can't we manually set the work unit limits for CPU and GPU (would help with the gorging problem, and others). |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
+4 |
Khangollo Send message Joined: 1 Aug 00 Posts: 245 Credit: 36,410,524 RAC: 0 |
|
Brian Priebe Send message Joined: 26 Dec 11 Posts: 19 Credit: 43,663,786 RAC: 0 |
I'm envious if others are getting dozens of WU's at a time. Even with project preferences set up for a 5-day cache, I've never seen more than 6 WU's downloaded total from SETI per machine. Even on machines with 24 cores. Is there some setup issue I'm missing? (Just joined SETI.) |
Mike Send message Joined: 17 Feb 01 Posts: 34258 Credit: 79,922,639 RAC: 80 |
Did you set up your prefernces on the account page ? With each crime and every kindness we birth our future. |
Brian Priebe Send message Joined: 26 Dec 11 Posts: 19 Credit: 43,663,786 RAC: 0 |
Did you set up your prefernces on the account page ? Yes. |
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4 |
I'm envious if others are getting dozens of WU's at a time. Even with project preferences set up for a 5-day cache, I've never seen more than 6 WU's downloaded total from SETI per machine. Even on machines with 24 cores. Most of your hosts have work from 5 different projects, that probably makes up a lot of your 5 day cache, Claggy |
Brian Priebe Send message Joined: 26 Dec 11 Posts: 19 Credit: 43,663,786 RAC: 0 |
Most of your hosts have work from 5 different projects, that probably makes up a lot of your 5 day cache It's had about a week now to rebalance the loading. S@H has resource share 100 just like the others. BOINC will download 30+ for Docking or Rosetta (about 3.5hrs each), for example, but only 1-6 for S@H. As I write this, S@H has only 17 WU's in progress with 60 processor cores to play with and 4 compatible GPU's spread over 4 machines. It is a puzzlement... |
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4 |
Most of your hosts have work from 5 different projects, that probably makes up a lot of your 5 day cache Seti has been in a Shortie Storm recently, and work has been fairly scarce with not every work request getting work, If Boinc fails to get work from Seti, it'll then ask each of your other projects in turn and get work from there instead, and so filling your cache up, The way round it is to set No New Tasks at your other projects so Boinc can only ask for work from Seti and so build up a bit of cache from here, unset NNT at your other projects when required. Claggy |
SciManStev Send message Joined: 20 Jun 99 Posts: 6652 Credit: 121,090,076 RAC: 0 |
Given Claggy's statement, BOINC doesn't try to fill the cache equally. If is missing a day's work, the first project to send a work request may fetch work for that project. Seti is a bit temperamental these days, and some requests either produce no tasks available, or just a few at a time. If between Seti work requests, another project makes the request, then if the project allows it, that will be refilled. When it gets turn for Seti to send another request, the cache may already be full from the other project's succesful request. Spreading out requests over 5 different projects really makes it a hit or miss for any particular project. Steve Edit: Claggy beat me to it. :) Warning, addicted to SETI crunching! Crunching as a member of GPU Users Group. GPUUG Website |
Brian Priebe Send message Joined: 26 Dec 11 Posts: 19 Credit: 43,663,786 RAC: 0 |
Seti is a bit temperamental these days, and some requests either produce no tasks available, or just a few at a time. Thanks all for the heads-up. A peruse of the event logs seems to show a majority of requests to S@H getting the 'no tasks available' response. This seems a bit perverse when the server page is showing 200,000+ available. |
Lionel Send message Joined: 25 Mar 00 Posts: 680 Credit: 563,640,304 RAC: 597 |
Even with limits imposed, cricket graphs are dropping, yet I still can't get GPU work. Yes my queues are dry!!! this is extremely frustrating... This is what some of us have been saying for weeks but alas, deaf ears ... L. |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.