This computer has reached a limit on tasks in progress??

Message boards : Number crunching : This computer has reached a limit on tasks in progress??
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 8 · Next

AuthorMessage
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1010922 - Posted: 2 Jul 2010, 18:21:54 UTC - in response to Message 1010918.  


I've got an E6600, no CUDA, Seti only & run with a 4 day cache. I've got about 24 hours work left on the system & am getting the "limit on tasks in progess" message whenever it requests new work.
Grant
Darwin NT
ID: 1010922 · Report as offensive
Numanoid
Volunteer tester

Send message
Joined: 13 Aug 99
Posts: 42
Credit: 4,119,139
RAC: 0
United States
Message 1010927 - Posted: 2 Jul 2010, 18:28:23 UTC - in response to Message 1010915.  

When seeing the message of task limit, how many tasks are currently in the queue? What is the threshold?

I'm thinking 20, because I downloaded 20 on an idle PC and then when I requested more, I got the message.

On another one, I have 20 either ready to start or running and get the same message. Once this completes the next runnin WU, I'll request more and see if it changes the message.



The big problem not in number per se, the problem is how it calculated. If it would be per computing device - no probs, but looks like having too many tasks on CPU will block GPU requests completely too and vice versa...


For what it's worth, the 20 limit for this PC has been confirmed. It finished the WU and sent it, requested work and got 1 more. Further requests yield the message.

I have a 10 day cache set and this is a Core 2 Duo 3Ghz machine. WUs generally complete in under 2 hours. In my opinion, the calculation is either way messed up or they have set a limit of stored WUs independent of performance calculation.
ID: 1010927 · Report as offensive
ToxicTBag

Send message
Joined: 5 Feb 10
Posts: 101
Credit: 57,197,902
RAC: 0
United Kingdom
Message 1010937 - Posted: 2 Jul 2010, 18:38:04 UTC

There's definately some truth in the thought that there is a limit of 20 tasks.
Luckily - or not depending on how you look at it i had 23 tasks remaining and was receiving the limit message, as soon as there were 19 it downloaded 1 task ....rinse cycle repeat 3 times now.
Whatever decides the limit it cannot be hardware performance i've just beefed the rig up to 3 x 480 and have a 10 day cache set, i am only hoping this may be a temporary thing to ease the innevitable strain on the servers today.....and we'll all wake up tommorrow with 10 day cache's ;-))
ID: 1010937 · Report as offensive
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1010939 - Posted: 2 Jul 2010, 18:40:35 UTC

confirmed here too. I got exactly 20 tasks.
Janice
ID: 1010939 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1010941 - Posted: 2 Jul 2010, 18:42:17 UTC

Then I can set SETI to NNT for whole 1-2 days and forget about any work for my ATI card... Too many CPU tasks onboard...
ID: 1010941 · Report as offensive
Profile Ghery S. Pettit
Avatar

Send message
Joined: 7 Nov 99
Posts: 325
Credit: 28,109,066
RAC: 82
United States
Message 1010942 - Posted: 2 Jul 2010, 18:42:32 UTC

20 on the machine I'm watching now, too. Report 1, get 1. Report 3, get 3. I sure hope this is temporary as three day server shutdowns will leave me looking for something else to crunch, or cool the machine as it sits idle.
ID: 1010942 · Report as offensive
Profile Geek@Play
Volunteer tester
Avatar

Send message
Joined: 31 Jul 01
Posts: 2467
Credit: 86,146,931
RAC: 0
United States
Message 1010943 - Posted: 2 Jul 2010, 18:42:38 UTC

This could be a mechanism that insures that everyone receives a little work at the beginning of the download cycle. It is not necessary to completely fill the cache in the first 2 or 3 hours. We have all weekend to fill the caches again.
Boinc....Boinc....Boinc....Boinc....
ID: 1010943 · Report as offensive
Profile skildude
Avatar

Send message
Joined: 4 Oct 00
Posts: 9541
Credit: 50,759,529
RAC: 60
Yemen
Message 1010946 - Posted: 2 Jul 2010, 18:44:32 UTC - in response to Message 1010943.  

Primegrid does that on their challenges perhaps we are seeing that on seti now. I'm betting the limits will ease off as we hit the weekend. everyone will have their uploads done and they can start pumping out more work


In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope
ID: 1010946 · Report as offensive
Numanoid
Volunteer tester

Send message
Joined: 13 Aug 99
Posts: 42
Credit: 4,119,139
RAC: 0
United States
Message 1010948 - Posted: 2 Jul 2010, 18:49:13 UTC - in response to Message 1010943.  

This could be a mechanism that insures that everyone receives a little work at the beginning of the download cycle. It is not necessary to completely fill the cache in the first 2 or 3 hours. We have all weekend to fill the caches again.


This makes sense to me, and for me, I prefer this method as long as it eventually increases prior to the next outage. I hated waiting for potentially days to get work after an outage.
ID: 1010948 · Report as offensive
Profile perryjay
Volunteer tester
Avatar

Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 20,676,751
RAC: 0
United States
Message 1010949 - Posted: 2 Jul 2010, 18:50:00 UTC - in response to Message 1010943.  

This could be a mechanism that insures that everyone receives a little work at the beginning of the download cycle. It is not necessary to completely fill the cache in the first 2 or 3 hours. We have all weekend to fill the caches again.


Matt said this yesterday
Programming wise, Jeff was able to tackle some longstanding datarecorder issues. You may have noticed our results-to-send queue has been growing rather large - these are some test tapes Jeff's been splitting which will be sent out rather quickly once the floodgates open
Maybe these are the test work units he was talking about.



PROUD MEMBER OF Team Starfire World BOINC
ID: 1010949 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 65709
Credit: 55,293,173
RAC: 49
United States
Message 1010951 - Posted: 2 Jul 2010, 18:53:35 UTC - in response to Message 1010949.  

This could be a mechanism that insures that everyone receives a little work at the beginning of the download cycle. It is not necessary to completely fill the cache in the first 2 or 3 hours. We have all weekend to fill the caches again.


Matt said this yesterday
Programming wise, Jeff was able to tackle some longstanding datarecorder issues. You may have noticed our results-to-send queue has been growing rather large - these are some test tapes Jeff's been splitting which will be sent out rather quickly once the floodgates open
Maybe these are the test work units he was talking about.

Or maybe We've hit the Limiter? Someone might know, Or We wait until after Midnight(PDT) to see if any downloads happen. :D

Uploads went well, I only had two instances of HTTP errors, Not bad at all. :)
The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's
ID: 1010951 · Report as offensive
JohnDK Crowdfunding Project Donor*Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 28 May 00
Posts: 1222
Credit: 451,243,443
RAC: 1,127
Denmark
Message 1010958 - Posted: 2 Jul 2010, 19:13:49 UTC - in response to Message 1010943.  

This could be a mechanism that insures that everyone receives a little work at the beginning of the download cycle. It is not necessary to completely fill the cache in the first 2 or 3 hours. We have all weekend to fill the caches again.

But then why not come with a message that can be understood??

btw I DID get 2 new tasks 3-4 hours ago (even though I have more than 20 WUs in cache) but since then only been getting the limit message.
ID: 1010958 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 1010963 - Posted: 2 Jul 2010, 19:20:38 UTC

Like I already mentioned in one of the other threads..

MilkyWay@home have a limit of 12 tasks in progress.
If BOINC ask for more, BOINC get:

Message from server: No work sent
Message from server: (reached limit of 12 tasks in progress)


Because of the SETI@home server say not the max limit, I guess something is wrong here.

ID: 1010963 · Report as offensive
Profile Geek@Play
Volunteer tester
Avatar

Send message
Joined: 31 Jul 01
Posts: 2467
Credit: 86,146,931
RAC: 0
United States
Message 1010965 - Posted: 2 Jul 2010, 19:27:21 UTC


As can be seen below, upload a completed task, get one in return.

7/2/2010 2:22:53 PM	SETI@home	Sending scheduler request: To fetch work.
7/2/2010 2:22:53 PM	SETI@home	Requesting new tasks for GPU
7/2/2010 2:22:54 PM	SETI@home	Scheduler request completed: got 0 new tasks
7/2/2010 2:22:54 PM	SETI@home	Message from server: No work sent
7/2/2010 2:22:54 PM	SETI@home	Message from server: This computer has reached a limit on tasks in progress
7/2/2010 2:22:55 PM	SETI@home	Started upload of 02mr07ah.11033.7843.15.10.247_3_0
7/2/2010 2:22:58 PM	SETI@home	Finished upload of 02mr07ah.11033.7843.15.10.247_3_0
7/2/2010 2:23:10 PM	SETI@home	Sending scheduler request: To report completed tasks.
7/2/2010 2:23:10 PM	SETI@home	Reporting 1 completed tasks, requesting new tasks for CPU and GPU
7/2/2010 2:23:12 PM	SETI@home	Scheduler request completed: got 1 new tasks


I suspect that this limit will increase as time goes on and the downloads will be more liberal.
Boinc....Boinc....Boinc....Boinc....
ID: 1010965 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 1010969 - Posted: 2 Jul 2010, 19:34:53 UTC

After the 3 day maintenance, my BOINC got 2 GPU WUs. ~ 15:55 UTC.
Every ~ 10 mins UL/report of a result.
But since 15:55 UTC no new DL.


If the limit of 20 tasks in progress per host, how we could use the ReSchedule tool? :-|
Usage of VLARkill CUDA app? -> damaged quota, backlog -> not ask for new work. :-|

SETI@home have always new surprises for us. :o)

ID: 1010969 · Report as offensive
Rasputin
Volunteer tester

Send message
Joined: 13 Jun 02
Posts: 1764
Credit: 6,132,221
RAC: 0
Russia
Message 1010978 - Posted: 2 Jul 2010, 20:05:32 UTC - in response to Message 1010965.  
Last modified: 2 Jul 2010, 20:11:55 UTC


As can be seen below, upload a completed task, get one in return.


Argh! I wish. I uploaded and reported 1200 tasks four hours ago and haven't gotten one single download..

800,000 tasks and none for me.

Edit: I see the problem after reading below. I still have 194 GPU tasks and 24 CPU tasks. Guess I won't get more work until they get down to 20 tasks..
ID: 1010978 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1010987 - Posted: 2 Jul 2010, 20:26:07 UTC - in response to Message 1010978.  


Network traffic has dropped right off & there is plenty of work ready to send, so i guess almost everyone has finally hit the task limit.
Grant
Darwin NT
ID: 1010987 · Report as offensive
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1010990 - Posted: 2 Jul 2010, 20:34:47 UTC - in response to Message 1010987.  


Network traffic has dropped right off & there is plenty of work ready to send, so i guess almost everyone has finally hit the task limit.


Network traffic may have dropped off, but the master server is still taking a pretty good beating.

It really would have been nice to know what their plans are on this.

Janice
ID: 1010990 · Report as offensive
Profile Hellsheep
Volunteer tester

Send message
Joined: 12 Sep 08
Posts: 428
Credit: 784,780
RAC: 0
Australia
Message 1010992 - Posted: 2 Jul 2010, 20:36:50 UTC - in response to Message 1010987.  


Network traffic has dropped right off & there is plenty of work ready to send, so i guess almost everyone has finally hit the task limit.


It does seem so. :)

Hopefully this will now even out a slow spread of cache limited work units to everyone. :)

Off-topic, where in Darwin are you bro? Maybe you should message me privately, i'm in Rapid Creek. :)
- Jarryd
ID: 1010992 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1011004 - Posted: 2 Jul 2010, 21:07:45 UTC - in response to Message 1010992.  

Off-topic, where in Darwin are you bro? Maybe you should message me privately, i'm in Rapid Creek. :)

I'm in Ludmilla.
It is a small world.
:-)

Grant
Darwin NT
ID: 1011004 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 8 · Next

Message boards : Number crunching : This computer has reached a limit on tasks in progress??


 
©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.