Questions and Answers :
Windows :
Not 100% even though number of tasks per core
Message board moderation
Author | Message |
---|---|
Phoenix Send message Joined: 11 Sep 99 Posts: 10 Credit: 105,312,672 RAC: 91 |
I seem to have an unusual situation where by my new gaming rig isn't being taxed by Boinc tasks. I run Seti and Rosetta and have a 6core i7 5930k with HT and a Nvidia 980 graphics card. That gives me 1 GPU task (which only runs the GPU at 40%) and 12 CPU tasks which once again doesnt load up the CPU to 100% (bad example below as there are no gpu tasks at present). 08/04/2015 21:49:07 | | cc_config.xml not found - using defaults 08/04/2015 21:49:07 | | Starting BOINC client version 7.4.42 for windows_x86_64 08/04/2015 21:49:07 | | log flags: file_xfer, sched_ops, task 08/04/2015 21:49:07 | | Libraries: libcurl/7.39.0 OpenSSL/1.0.1j zlib/1.2.8 08/04/2015 21:49:07 | | Data directory: C:\ProgramData\BOINC 08/04/2015 21:49:07 | | Running under account vivfx_000 08/04/2015 21:49:07 | | CUDA: NVIDIA GPU 0: GeForce GTX 980 (driver version 347.88, CUDA version 7.0, compute capability 5.2, 4096MB, 3704MB available, 5599 GFLOPS peak) 08/04/2015 21:49:07 | | OpenCL: NVIDIA GPU 0: GeForce GTX 980 (driver version 347.88, device version OpenCL 1.1 CUDA, 4096MB, 3704MB available, 5599 GFLOPS peak) 08/04/2015 21:49:07 | | Host name: ManCave 08/04/2015 21:49:07 | | Processor: 12 GenuineIntel Intel(R) Core(TM) i7-5930K CPU @ 3.50GHz [Family 6 Model 63 Stepping 2] 08/04/2015 21:49:07 | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx tm2 dca pbe fsgsbase bmi1 smep bmi2 08/04/2015 21:49:07 | | OS: Microsoft Windows 8.1: Professional x64 Edition, (06.03.9600.00) 08/04/2015 21:49:07 | | Memory: 15.91 GB physical, 31.91 GB virtual 08/04/2015 21:49:07 | | Disk: 931.19 GB total, 808.42 GB free 08/04/2015 21:49:07 | | Local time is UTC +1 hours 08/04/2015 21:49:07 | rosetta@home | URL http://boinc.bakerlab.org/rosetta/; Computer ID 2256288; resource share 100 08/04/2015 21:49:07 | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 7534739; resource share 100 08/04/2015 21:49:07 | rosetta@home | General prefs: from rosetta@home (last modified 06-Apr-2015 11:00:04) 08/04/2015 21:49:07 | rosetta@home | Computer location: home 08/04/2015 21:49:07 | rosetta@home | General prefs: no separate prefs for home; using your defaults 08/04/2015 21:49:07 | | Reading preferences override file 08/04/2015 21:49:07 | | Preferences: 08/04/2015 21:49:07 | | max memory usage when active: 8143.43MB 08/04/2015 21:49:07 | | max memory usage when idle: 14658.18MB 08/04/2015 21:49:07 | | max disk usage: 100.00GB 08/04/2015 21:49:07 | | (to change preferences, visit a project web site or select Preferences in the Manager) 08/04/2015 21:49:07 | | Not using a proxy 08/04/2015 21:49:08 | rosetta@home | Sending scheduler request: To fetch work. 08/04/2015 21:49:08 | rosetta@home | Requesting new tasks for CPU and NVIDIA GPU 08/04/2015 21:49:20 | rosetta@home | Scheduler request completed: got 12 new tasks 08/04/2015 21:49:22 | rosetta@home | Started download of tj_lp_1_12_X11_1_15_2_ct1_fc_fragments_fold_data.zip 08/04/2015 21:49:22 | rosetta@home | Started download of gr032315_nods_eehee_rank407_data.zip 08/04/2015 21:49:25 | SETI@home | Sending scheduler request: To fetch work. 08/04/2015 21:49:25 | SETI@home | Requesting new tasks for CPU and NVIDIA GPU 08/04/2015 21:49:26 | rosetta@home | Finished download of gr032315_nods_eehee_rank407_data.zip 08/04/2015 21:49:26 | rosetta@home | Started download of tj_lp_4_12_X18_4_12_2_ct0_fd_fragments_fold_data.zip 08/04/2015 21:49:26 | SETI@home | Scheduler request completed: got 0 new tasks 08/04/2015 21:49:26 | SETI@home | Project has no tasks available 08/04/2015 21:49:27 | rosetta@home | Finished download of tj_lp_1_12_X11_1_15_2_ct1_fc_fragments_fold_data.zip 08/04/2015 21:49:27 | rosetta@home | Started download of gr032315_nods_eehee_rank1394_data.zip 08/04/2015 21:49:32 | rosetta@home | Finished download of gr032315_nods_eehee_rank1394_data.zip 08/04/2015 21:49:32 | rosetta@home | Started download of EEEH_1028_vegf.pdb.gz 08/04/2015 21:49:34 | rosetta@home | Finished download of EEEH_1028_vegf.pdb.gz 08/04/2015 21:49:34 | rosetta@home | Started download of EEEH_1028_vegf.patchdock 08/04/2015 21:49:35 | rosetta@home | Finished download of tj_lp_4_12_X18_4_12_2_ct0_fd_fragments_fold_data.zip 08/04/2015 21:49:35 | rosetta@home | Finished download of EEEH_1028_vegf.patchdock 08/04/2015 21:49:35 | rosetta@home | Started download of fold_and_dock_zibochen.helix.control49_data.zip 08/04/2015 21:49:35 | rosetta@home | Started download of zibochen.helix.control49_fold_and_dock_flags 08/04/2015 21:49:37 | rosetta@home | Finished download of zibochen.helix.control49_fold_and_dock_flags 08/04/2015 21:49:37 | rosetta@home | Started download of FFF_1cc9def190909e78abcbd787c2f36f56_TrkA1_Wed_Apr__8_01_55_12_PDT_2015.zip 08/04/2015 21:49:39 | rosetta@home | Finished download of fold_and_dock_zibochen.helix.control49_data.zip 08/04/2015 21:49:39 | rosetta@home | Finished download of FFF_1cc9def190909e78abcbd787c2f36f56_TrkA1_Wed_Apr__8_01_55_12_PDT_2015.zip 08/04/2015 21:49:39 | rosetta@home | Started download of tj_lp_1_12_X11_1_11_2_ct0_fc_fragments_fold_data.zip 08/04/2015 21:49:39 | rosetta@home | Started download of gr032315_nods_eehee_rank460_data.zip 08/04/2015 21:49:44 | rosetta@home | Finished download of tj_lp_1_12_X11_1_11_2_ct0_fc_fragments_fold_data.zip 08/04/2015 21:49:44 | rosetta@home | Started download of rb_04_08_54711_100161_ab_stage0_h001___robetta_FLAGS 08/04/2015 21:49:45 | rosetta@home | Finished download of gr032315_nods_eehee_rank460_data.zip 08/04/2015 21:49:45 | rosetta@home | Finished download of rb_04_08_54711_100161_ab_stage0_h001___robetta_FLAGS 08/04/2015 21:49:45 | rosetta@home | Started download of rb_04_08_54711_100161_ab_stage0_h001___robetta.zip 08/04/2015 21:49:45 | rosetta@home | Started download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.3mers.gz 08/04/2015 21:49:50 | rosetta@home | Finished download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.3mers.gz 08/04/2015 21:49:50 | rosetta@home | Started download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.16mers.gz 08/04/2015 21:49:53 | rosetta@home | Finished download of rb_04_08_54711_100161_ab_stage0_h001___robetta.zip 08/04/2015 21:49:53 | rosetta@home | Started download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.10mers.gz 08/04/2015 21:49:58 | rosetta@home | Finished download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.16mers.gz 08/04/2015 21:49:58 | rosetta@home | Finished download of rb_04_08_54711_100161_ab_stage0_h001___robetta_h001_.200.10mers.gz 08/04/2015 21:49:58 | rosetta@home | Started download of gr032315_nods_eehee_rank2454_data.zip 08/04/2015 21:49:58 | rosetta@home | Started download of FFF_00313316d3dbb9880bccad87b0ff6b59_TrkA1_Wed_Apr__8_04_15_02_PDT_2015.zip 08/04/2015 21:50:07 | rosetta@home | Finished download of FFF_00313316d3dbb9880bccad87b0ff6b59_TrkA1_Wed_Apr__8_04_15_02_PDT_2015.zip 08/04/2015 21:50:09 | rosetta@home | Finished download of gr032315_nods_eehee_rank2454_data.zip 08/04/2015 21:53:38 | rosetta@home | Task rb_04_06_54115_100134_ab_stage0_t000___robetta_cstwt_3.0_IGNORE_THE_REST_03_09_259803_107_0 exited with zero status but no 'finished' file 08/04/2015 21:53:38 | rosetta@home | If this happens repeatedly you may need to reset the project. 08/04/2015 21:55:32 | rosetta@home | Sending scheduler request: To fetch work. 08/04/2015 21:55:32 | rosetta@home | Requesting new tasks for NVIDIA GPU 08/04/2015 21:55:35 | rosetta@home | Scheduler request completed: got 0 new tasks 08/04/2015 21:56:01 | rosetta@home | Task gr032315_nods_eehee_rank1716_fold_SAVE_ALL_OUT_256802_191_0 exited with zero status but no 'finished' file 08/04/2015 21:56:01 | rosetta@home | If this happens repeatedly you may need to reset the project. |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
If you want to utilize more of your card, then you would need to run more than 1 instance of work units on it. If you check in "COMMUNITY" and then select number crunching, you can search the thread on how to do this http://setiathome.berkeley.edu/forum_thread.php?id=77049&postid=1661436 this will give you a general idea about how to go about it. Hope this helps. Zalster |
Phoenix Send message Joined: 11 Sep 99 Posts: 10 Credit: 105,312,672 RAC: 91 |
If you want to utilize more of your card, then you would need to run more than 1 instance of work units on it. Thanks for the reply. I'll give that thread a read regarding the GPU. Any thoughts on the CPU cores not being maxed out. Is it just an inefficiency of the computation by the application on the latest generation of processor. I had previously thought the work unit would just be done quicker. |
OzzFan Send message Joined: 9 Apr 02 Posts: 15691 Credit: 84,761,841 RAC: 28 |
I don't think it has anything to do with an inefficiency in the science application. I note in the screenshot you provide that at the time you were running all Rosetta applications. I also note in the logs you provide that you are getting errors in the output files. I'm thinking the application is spending more time in I/O error than CPU processing. Just my best guess at this point. Have you tried resetting the project as the messages suggest? If so, have you tried detaching and re-attaching to the project? Also, does the same thing happen when running SETI workunits? Are they SETI CPU or GPU workunits that are running? [Edit] Another thought I just had is that these high end Intel CPUs have automatic overclocking (Intel Turbo Boost), and they also run very hot, which can trigger/conflict with Intel's automatic downclocking (Intel Speedstep) during overheating. Have you turned off Intel Speedstep and/or all C-states? |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
08/04/2015 21:49:07 | | Reading preferences override file You use Local preferences - so check on "Processor usage" tab what is the value of "Use at most X % CPU time" http://boinc.berkeley.edu/wiki/Local_preferences#Processor_usage Do you use TThrottle ? (if you set too low temperature in TThrottle this may be the case) On Windows Task Manager you may also show the 'Processes' tab  - ALF - "Find out what you don't do well ..... then don't do it!" :)  |
Phoenix Send message Joined: 11 Sep 99 Posts: 10 Credit: 105,312,672 RAC: 91 |
Quick update as I found the fix. Anything in preferences that says "0" equals no restriction change it to "100". I.e. "on multiprocessor systems use at most" 100.00% and "use at most" 100% of CPU time even though they bother say (0 means no restriction) |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
... even though they bother say (0 means no restriction) Where did you see this 'say'? No mention of '0 means no restriction' for these 2 Settings on both web and Local preferences: Computing preferences Local preferences  - ALF - "Find out what you don't do well ..... then don't do it!" :)  |
Flibble Send message Joined: 17 May 99 Posts: 4 Credit: 59,326 RAC: 0 |
I'm having the same issue with only 40% of CPU being used. I've tried setting the limits to 0 but it doesn't make any difference. |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
Which 'limits'? And where you "tried setting" them? And why "to 0"? Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Flibble Send message Joined: 17 May 99 Posts: 4 Credit: 59,326 RAC: 0 |
In processor usage I've set the last 2 options, multi processor usage and processor usage time to 0 as it says that means no restrictions. |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
"Where" means: - in Computing preferences - or in Local preferences As you say "processor usage" this means Local preferences (so what you set must 'take' imediately) Set both to 100 Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Flibble Send message Joined: 17 May 99 Posts: 4 Credit: 59,326 RAC: 0 |
Wahooooo!!! Thanks, changed to 100% and had a huge surge in tasks being performed!! Now running 9 tasks instead of my previous 3. Thanks very much!!! |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
You also have very few tasks 'In progress' ('In progress' = still not reported as finished)): http://setiathome.berkeley.edu/results.php?hostid=7467930&offset=0&show_names=0&state=1&appid= So You may want to: Check/set the Local preferences for e.g.: Minimum work buffer 3 days Max additional work buffer 0.1 days (don't use more than 0.1 days for the second value, big value will make BOINC ask for work much less often) Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
©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.