Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 
World Community Grid Forums
  Category: Support
  Forum: BOINC Agent Support
  Thread: Huge increase in tasks in my buffer!

Quick Go ยป
No member browsing this thread
Thread Status: Active
Total posts in this thread: 9
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 1093 times and has 8 replies Next Thread
Byteball_730a2960
Senior Cruncher
Joined: Oct 29, 2010
Post Count: 318
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Huge increase in tasks in my buffer!
I have a 6 core (AMD 1100T) machine running 100% 24/7 on a 0.3 day buffer.
For some reason, I came home tonight and I have 330 tasks in my buffer. Any idea why?
There are 11 projects in the mix and example run times are

C4CW - 2 hours 13 mins
C4SW - 34 mins
DSFL - 3 hours 46 mins
FAAH 5 hours 47 mins

The machine is totally stock.

Benchmarks

12/07/2012 20:59:32 Suspending computation - running CPU benchmarks
12/07/2012 21:00:03 Benchmark results:
12/07/2012 21:00:03 Number of CPUs: 6
12/07/2012 21:00:03 2727 floating point MIPS (Whetstone) per CPU
12/07/2012 21:00:03 9489 integer MIPS (Dhrystone) per CPU


First few lines of messages...

11/07/2012 08:04:56 Starting BOINC client version 6.10.60 for windows_x86_64
11/07/2012 08:04:56 log flags: file_xfer, sched_ops, task
11/07/2012 08:04:56 Libraries: libcurl/7.19.7 OpenSSL/0.9.8l zlib/1.2.3
11/07/2012 08:04:56 Data directory: E:\BOINC
11/07/2012 08:04:56 Running under account Fred
11/07/2012 08:04:56 Processor: 6 AuthenticAMD AMD Phenom(tm) II X6 1100T Processor [Family 16 Model 10 Stepping 0]
11/07/2012 08:04:56 Processor: 512.00 KB cache
11/07/2012 08:04:56 Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 htt pni cx16 syscall nx lm svm sse4a osvw ibs skinit wdt page1gb rdtscp 3dnowext 3dnow
11/07/2012 08:04:56 OS: Microsoft Windows 7: Ultimate x64 Edition, Service Pack 1, (06.01.7601.00)
11/07/2012 08:04:56 Memory: 8.00 GB physical, 8.19 GB virtual
11/07/2012 08:04:56 Disk: 27.95 GB total, 26.80 GB free
11/07/2012 08:04:56 Local time is UTC +9 hours
11/07/2012 08:04:57 ATI GPU 0: ATI Radeon HD5x00 series (Cedar) (CAL version 1.4.1703, 512MB, 104 GFLOPS peak)
11/07/2012 08:04:57 World Community Grid URL http://www.worldcommunitygrid.org/; Computer ID 1591245; resource share 100
11/07/2012 08:04:57 World Community Grid General prefs: from World Community Grid (last modified 13-May-2012 14:57:02)
11/07/2012 08:04:57 World Community Grid Computer location: home
11/07/2012 08:04:57 General prefs: using separate prefs for home
11/07/2012 08:04:57 Reading preferences override file
11/07/2012 08:04:57 Preferences:
11/07/2012 08:04:57 max memory usage when active: 4913.71MB
11/07/2012 08:04:57 max memory usage when idle: 7370.57MB
11/07/2012 08:04:57 max disk usage: 10.00GB
11/07/2012 08:04:57 (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
11/07/2012 08:04:57 Not using a proxy
11/07/2012 08:04:57 World Community Grid Restarting task DSFL_000090-3_0000055_1098_0 using dsfl version 625
11/07/2012 08:04:58 World Community Grid Restarting task E208612_533_C.28.C26H18N2.01643476.1.set1d06_0 using cep2 version 640
11/07/2012 08:04:58 World Community Grid Restarting task c4cw_target06_078012610_0 using c4cw version 641
11/07/2012 08:04:58 World Community Grid Restarting task cfsw_7868_07868178_0 using cfsw version 612
11/07/2012 08:04:58 World Community Grid Restarting task CMD2_2502-1433ZA.clustersOccur-CASQ1A.clustersOccur_25_13349_13493_1 using hcmd2 version 640
11/07/2012 08:04:58 World Community Grid Restarting task c4cw_target06_078118612_0 using c4cw version 641
11/07/2012 08:07:00 World Community Grid Sending scheduler request: To fetch work.
11/07/2012 08:07:00 World Community Grid Reporting 1 completed tasks, requesting new tasks for GPU
11/07/2012 08:07:04 World Community Grid Scheduler request completed: got 0 new tasks
11/07/2012 08:07:04 World Community Grid Message from server: No tasks sent
11/07/2012 08:07:04 World Community Grid Message from server: No tasks are available for Discovering Dengue Drugs - Together - Phase 2
11/07/2012 08:07:04 World Community Grid Message from server: No tasks are available for Discovering Dengue Drugs - Together - Phase 2 (Type A)
11/07/2012 08:11:54 World Community Grid Computation for task cfsw_7868_07868178_0 finished
11/07/2012 08:11:54 World Community Grid Starting X0930065130966200602151123_0
11/07/2012 08:11:54 World Community Grid Starting task X0930065130966200602151123_0 using hcc1 version 642
11/07/2012 08:11:56 World Community Grid Started upload of cfsw_7868_07868178_0_0
11/07/2012 08:12:01 World Community Grid Finished upload of cfsw_7868_07868178_0_0
11/07/2012 08:15:25 World Community Grid Computation for task DSFL_000090-3_0000055_1098_0 finished
11/07/2012 08:15:25 World Community Grid Starting GFAM_x3bpmB_PfFP3_0030124_0262_0
11/07/2012 08:15:25 World Community Grid Starting task GFAM_x3bpmB_PfFP3_0030124_0262_0 using gfam version 612



Why do I have so many tasks? I have suspended fetching of new tasks for the moment but I am super confused.
----------------------------------------
[Edit 1 times, last edit by vcd683s at Jul 13, 2012 4:29:11 PM]
[Jul 13, 2012 4:28:08 PM]   Link   Report threatening or abusive post: please login first  Go to top 
deltavee
Ace Cruncher
Texas Hill Country
Joined: Nov 17, 2004
Post Count: 4884
Status: Recently Active
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
I see you have a GPU. Did you process any HCC GPU Beta Workunits yesterday? If so read this thread. http://www.worldcommunitygrid.org/forums/wcg/viewthread_thread,33449
----------------------------------------
4849
[Jul 13, 2012 4:46:05 PM]   Link   Report threatening or abusive post: please login first  Go to top 
jonnieb-uk
Ace Cruncher
England
Joined: Nov 30, 2011
Post Count: 6105
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
It would appear to be caused by yesterday's HCC Beta and limited to machines operating BOINC client: 6.10.58

I don't thin the Techs have responded yet.
----------------------------------------

To Join follow this link: Join the UK Team All Welcome! UK Team thread
[Jul 13, 2012 4:50:01 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
Not limited to 6.10.58
I am running Win 7 x64 and Boinc 7.0.27 and I had the same problem.
It only happened on my ATI GPU machine.
The est. times on that computer were suddenly way too low on the CPU jobs after the GPU Betas ran. (ETAs went from 5 hours to 2 hours.)
On the NVidia machine (also Win 7 x64 & 7.0.27) the est. runtimes changed to being far too long... confused (ETAs went from 5 hours to 24+ hours.)
Something about running the GPU jobs is affecting the Duration Correction Factor.
Now my machines (both Windows and Linux) that didn't even run the Beta/GPU are WAY off on the ETAs for the SN2S jobs I am running. I guess it must be due to some Server side changes.

This is not really a new issue. I already said something about it back in March when I was still running 6.10.58 ... (last bit of my post)
https://secure.worldcommunitygrid.org/forums/wcg/printpost_post,369938
----------------------------------------
[Edit 3 times, last edit by Former Member at Jul 13, 2012 8:29:44 PM]
[Jul 13, 2012 4:58:42 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Sgt.Joe
Ace Cruncher
USA
Joined: Jul 4, 2006
Post Count: 7663
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
The SN2S jobs are probably off because there has been an increase in the times. These must be tougher molecules or something. I have seen the times of SN2S double on the machines running it. Vista Q6600, Linux Mint 11 and 12 E6410 Quad and Core 2 Duo 6610, Win 7 Amd Athlon. It appears to be machine and OS independent.

Cheers
----------------------------------------
Sgt. Joe
*Minnesota Crunchers*
[Jul 14, 2012 12:40:13 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
The new tasks might be bigger , but on one machine the ETAs on the jobs I already had went up x4 while the GPU beta were running
and down to less than half on a different computer , all in a space of about an hour. wink
The machine that went to less than half est. time started downloading mass amounts of new jobs until I set the cache to Zero.
[Jul 14, 2012 2:18:12 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Sgt.Joe
Ace Cruncher
USA
Joined: Jul 4, 2006
Post Count: 7663
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
The new tasks might be bigger , but on one machine the ETAs on the jobs I already had went up x4 while the GPU beta were running
and down to less than half on a different computer , all in a space of about an hour. wink
The machine that went to less than half est. time started downloading mass amounts of new jobs until I set the cache to Zero.


I am sure you are correct about the GPU tasks causing the DCF to go bonkers. The SN2S tasks getting longer probably did not help matters either.

Cheers
----------------------------------------
Sgt. Joe
*Minnesota Crunchers*
[Jul 14, 2012 2:31:57 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Byteball_730a2960
Senior Cruncher
Joined: Oct 29, 2010
Post Count: 318
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
Thanks everyone! The WCG community is awesome as always and pulls through.
I'll set the buffer to 0 and take it from there.
I did indeed have beta tests yesterday and I guess we'll have to wait on the techs to work out how to fix this.
[Jul 14, 2012 3:19:49 AM]   Link   Report threatening or abusive post: please login first  Go to top 
knreed
Former World Community Grid Tech
Joined: Nov 8, 2004
Post Count: 4504
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Huge increase in tasks in my buffer!
I experienced this on a couple of my machines as well. The change to set the beta use to 1 cpu + 1 gpu seems to have made the buffer fill issue a significantly worse problem than before.

I'm working to reliably reproduce in our development environment so that I can clearly follow the events that lead it to happen.
[Jul 16, 2012 2:00:33 PM]   Link   Report threatening or abusive post: please login first  Go to top 
[ Jump to Last Post ]
Post new Thread