Page 1 of 1

GPU's not working

Posted: Sat Dec 02, 2017 8:56 pm
by Ricorocks
All 5 gpu's today won't fold, 5 gpu's spread btwn 3 machines. All 64 bit, 2 win10, 1 win7.

Tried new driver 388.43, still they won't start, advanced (FAH) shows ready. Restart no help!

Code: Select all

*********************** Log Started 2017-12-02T20:38:56Z ***********************
20:38:56:************************* Folding@home Client *************************
20:38:56:        Website: http://folding.stanford.edu/
20:38:56:      Copyright: (c) 2009-2016 Stanford University
20:38:56:         Author: Joseph Coffland <joseph@cauldrondevelopment.com>
20:38:56:           Args: --open-web-control
20:38:56:         Config: C:\Users\Aileen\AppData\Roaming\FAHClient\config.xml
20:38:56:******************************** Build ********************************
20:38:56:        Version: 7.4.15
20:38:56:           Date: Aug 17 2016
20:38:56:           Time: 04:33:41
20:38:56:     Repository: Git
20:38:56:       Revision: 4f3e0e25571a9f691719f0c273739294bde517dd
20:38:56:         Branch: master
20:38:56:       Compiler: GNU 5.3.1 20160205
20:38:56:        Options: -std=gnu++98 -I/mingw64/include -O3 -funroll-loops -ffast-math
20:38:56:                 -mfpmath=sse -fno-unsafe-math-optimizations -msse2
20:38:56:       Platform: linux2 4.6.0-1-amd64
20:38:56:           Bits: 64
20:38:56:           Mode: Release
20:38:56:******************************* System ********************************
20:38:56:            CPU: Intel(R) Core(TM) i7 CPU 860 @ 2.80GHz
20:38:56:         CPU ID: GenuineIntel Family 6 Model 30 Stepping 5
20:38:56:           CPUs: 8
20:38:56:         Memory: 7.94GiB
20:38:56:    Free Memory: 5.92GiB
20:38:56:        Threads: WINDOWS_THREADS
20:38:56:     OS Version: 6.1
20:38:56:    Has Battery: false
20:38:56:     On Battery: false
20:38:56:     UTC Offset: -6
20:38:56:            PID: 8780
20:38:56:            CWD: C:\Users\Aileen\AppData\Roaming\FAHClient
20:38:56:             OS: Windows 7 Home Premium Service Pack 1
20:38:56:        OS Arch: AMD64
20:38:56:           GPUs: 1
20:38:56:          GPU 0: Bus:1 Slot:0 NVIDIA:7 GP107 [GeForce GTX 1050 Ti] 2138
20:38:56:  CUDA Device 0: Platform:0 Device:0 Bus:1 Slot:0 Compute:6.1 Driver:9.1
20:38:56:OpenCL Device 0: Platform:0 Device:0 Bus:1 Slot:0 Compute:1.2 Driver:388.43
20:38:56:  Win32 Service: false
20:38:56:***********************************************************************
20:38:56:<config>
20:38:56:  <!-- Slot Control -->
20:38:56:  <power v='FULL'/>
20:38:56:
20:38:56:  <!-- User Information -->
20:38:56:  <passkey v='********************************'/>
20:38:56:  <user v='Ricoocks'/>
20:38:56:
20:38:56:  <!-- Folding Slots -->
20:38:56:  <slot id='0' type='CPU'/>
20:38:56:  <slot id='1' type='GPU'/>
20:38:56:</config>
20:38:56:Trying to access database...
20:38:56:Successfully acquired database lock
20:38:56:Enabled folding slot 00: READY cpu:7
20:38:56:Enabled folding slot 01: READY gpu:0:GP107 [GeForce GTX 1050 Ti]  2138
20:38:57:WU00:FS00:Starting
20:38:57:WARNING:WU00:FS00:AS lowered CPUs from 7 to 6
20:38:57:WU00:FS00:Running FahCore: "C:\Program Files\FAHClient/FAHCoreWrapper.exe" C:\Users\Aileen\AppData\Roaming\FAHClient\cores/fahwebx.stanford.edu/cores/Win32/AMD64/Core_a4.fah/FahCore_a4.exe -dir 00 -suffix 01 -version 704 -lifeline 8780 -checkpoint 15 -np 6
20:38:57:WU00:FS00:Started FahCore on PID 8964
20:38:57:WU00:FS00:Core PID:8620
20:38:57:WU00:FS00:FahCore 0xa4 started
20:38:57:WU01:FS01:Connecting to 171.67.108.45:80
20:38:57:WU00:FS00:0xa4:
20:38:57:WU00:FS00:0xa4:*------------------------------*
20:38:57:WU00:FS00:0xa4:Folding@Home Gromacs GB Core
20:38:57:WU00:FS00:0xa4:Version 2.27 (Dec. 15, 2010)
20:38:57:WU00:FS00:0xa4:
20:38:57:WU00:FS00:0xa4:Preparing to commence simulation
20:38:57:WU00:FS00:0xa4:- Looking at optimizations...
20:38:57:WU00:FS00:0xa4:- Files status OK
20:38:57:WU00:FS00:0xa4:- Expanded 1129502 -> 2621880 (decompressed 232.1 percent)
20:38:57:WU00:FS00:0xa4:Called DecompressByteArray: compressed_data_size=1129502 data_size=2621880, decompressed_data_size=2621880 diff=0
20:38:57:WU00:FS00:0xa4:- Digital signature verified
20:38:57:WU00:FS00:0xa4:
20:38:57:WU00:FS00:0xa4:Project: 8631 (Run 3, Clone 117, Gen 15)
20:38:57:WU00:FS00:0xa4:
20:38:57:WU00:FS00:0xa4:Assembly optimizations on if available.
20:38:57:WU00:FS00:0xa4:Entering M.D.
20:38:58:WARNING:WU01:FS01:Failed to get assignment from '171.67.108.45:80': No WUs available for this configuration
20:38:58:WU01:FS01:Connecting to 171.64.65.35:80
20:38:59:WARNING:WU01:FS01:Failed to get assignment from '171.64.65.35:80': No WUs available for this configuration
20:38:59:ERROR:WU01:FS01:Exception: Could not get an assignment
20:38:59:WU01:FS01:Connecting to 171.67.108.45:80
20:38:59:WARNING:WU01:FS01:Failed to get assignment from '171.67.108.45:80': No WUs available for this configuration
20:38:59:WU01:FS01:Connecting to 171.64.65.35:80
20:39:00:WARNING:WU01:FS01:Failed to get assignment from '171.64.65.35:80': No WUs available for this configuration
20:39:00:ERROR:WU01:FS01:Exception: Could not get an assignment
20:39:03:WU00:FS00:0xa4:Using Gromacs checkpoints
20:39:03:WU00:FS00:0xa4:Mapping NT from 6 to 6 
20:39:04:WU00:FS00:0xa4:Resuming from checkpoint
20:39:04:WU00:FS00:0xa4:Verified 00/wudata_01.log
20:39:04:WU00:FS00:0xa4:Verified 00/wudata_01.trr
20:39:04:WU00:FS00:0xa4:Verified 00/wudata_01.xtc
20:39:04:WU00:FS00:0xa4:Verified 00/wudata_01.edr
20:39:04:WU00:FS00:0xa4:Completed 46400 out of 1250000 steps  (3%)
20:39:14:13:127.0.0.1:New Web connection
20:39:59:WU01:FS01:Connecting to 171.67.108.45:80
20:39:59:WARNING:WU01:FS01:Failed to get assignment from '171.67.108.45:80': No WUs available for this configuration
20:39:59:WU01:FS01:Connecting to 171.64.65.35:80
20:40:00:WARNING:WU01:FS01:Failed to get assignment from '171.64.65.35:80': No WUs available for this configuration
20:40:00:ERROR:WU01:FS01:Exception: Could not get an assignment
20:41:25:WU00:FS00:0xa4:Completed 50000 out of 1250000 steps  (4%)
20:41:36:WU01:FS01:Connecting to 171.67.108.45:80
20:41:36:WARNING:WU01:FS01:Failed to get assignment from '171.67.108.45:80': No WUs available for this configuration
20:41:36:WU01:FS01:Connecting to 171.64.65.35:80
20:41:37:WARNING:WU01:FS01:Failed to get assignment from '171.64.65.35:80': No WUs available for this configuration
20:41:37:ERROR:WU01:FS01:Exception: Could not get an assignment
20:44:13:WU01:FS01:Connecting to 171.67.108.45:80
20:44:14:WARNING:WU01:FS01:Failed to get assignment from '171.67.108.45:80': No WUs available for this configuration
20:44:14:WU01:FS01:Connecting to 171.64.65.35:80
20:44:14:WARNING:WU01:FS01:Failed to get assignment from '171.64.65.35:80': No WUs available for this configuration
20:44:14:ERROR:WU01:FS01:Exception: Could not get an assignment

Re: GPU's not working

Posted: Sat Dec 02, 2017 9:21 pm
by Ricorocks
On a win 10's Fah log

Code: Select all

19:52:38:</config>
19:52:38:Trying to access database...
19:52:38:Successfully acquired database lock
19:52:38:Enabled folding slot 00: READY cpu:2
19:52:38:Enabled folding slot 01: READY gpu:0:GP104 [GeForce GTX 1070] 6463
19:52:38:ERROR:FS02:'opencl-index'=1 is in use by another folding slot but GPU 1 matches this device's PCI bus=3 and PCI slot=0, please correct this by removing any manually configured 'opencl-index' options.
19:52:38:ERROR:FS02:'cuda-index'=1 is in use by another folding slot but GPU 1 matches this device's PCI bus=3 and PCI slot=0, please correct this by removing any manually configured 'cuda-index' options.
19:52:38:Enabled folding slot 02: READY gpu:1:GP104 [GeForce GTX 1070] 6463
19:52:38:WU01:FS00:Starting
19:52:38:WU01:FS00:Running FahCore: "C:\Program Files\FAHClient/FAHCoreWrapper.exe" C:\Users\Rick\AppData\Roaming\FAHClient\cores/fahwebx.stanford.edu/cores/Win32/AMD64/Core_a4.fah/FahCore_a4.exe -dir 01 -suffix 01 -version 704 -lifeline 3468 -checkpoint 15 -np 2
19:52:38:WU01:FS00:Started FahCore on PID 6924
19:52:38:WU01:FS00:Core PID:6912

Re: GPU's not working

Posted: Sat Dec 02, 2017 9:25 pm
by Ricorocks
I see line #5 & 6, ERROR:FS02:'opencl...

I thought the new driver would fix

Re: GPU's not working

Posted: Sat Dec 02, 2017 9:42 pm
by Ricorocks
First post was win7 machine. I tried uninstalling/re-install FAHClient, after the re-install the log showed

Code: Select all

1:32:07:Successfully acquired database lock
21:32:07:Enabled folding slot 00: PAUSED cpu:6 (not configured)
21:32:07:Enabled folding slot 01: PAUSED gpu:0:GP107 [GeForce GTX 1050 Ti]  2138 (not configured)
21:32:14:13:127.0.0.1:New Web connection
21:32:19:Set client configured

Re: GPU's not working

Posted: Sat Dec 02, 2017 10:32 pm
by Ricorocks
Okay! When i discovered, GPu's not folding, 4 were idle & a machine with 2 GPU's had 1 gpu working. Reboot & all 5 were not working.

About a minute ago, decided to take one last look, at folding & the gpu came back to life. This one had the re-install FAHClient & new nividia driver & still would not start. 1 min ago it started

Now all GPU's (5) are back to work.

Re: GPU's not working

Posted: Sat Dec 02, 2017 10:34 pm
by Aurum
The Assignment Servers were down.

Re: GPU's not working

Posted: Sat Dec 02, 2017 10:38 pm
by bruce
With one GPU in your Win10 machine, I don't see how FAH can have index errors. Since you failed to post your config settings, I have to assume it's a self-inflicted problem. Remove any index settings you've added.

With regard to the Win7 machine, how long did you wait? When the AS has trouble finding an assignment, it sometimes takes a few minutes before the server can see recent assignment counts. The fact that it straightened itself out probably as nothing to do with anything you were trying to fix.

Re: GPU's not working

Posted: Sat Dec 02, 2017 11:40 pm
by Ricorocks
I waited quite some time, >1hr.

I fixed what was not broken. Stanford fixed what was broken, "The Assignment Servers were down."

Thanks Aurum, Bruce
Rico

Re: GPU's not working

Posted: Sat Dec 02, 2017 11:44 pm
by Joe_H
The assignment servers were not down, one of the work servers with a large portion of the GPU Wu's available was down. See this topic - viewtopic.php?f=18&t=30471. Nowhere in your first log did an AS not respond to your request, they just were not able to connect your system to a WS with available work for your GPU.