GPU compuation error, OpenSuse, GTX1050

Forums › Problems and Bug Reports

John
John
Joined: 17 Jan 18
Posts: 7
Credit: 3275058426
RAC: 10323597
31 Jan 2018 9:56:58 UTC
Topic 213067
(moderation:
    )

    All GPU WUs on this machine are failing, with error code 2:

    LATeah0051L_1084.0_0_0.0_12139615_1

    Workunit ID: 334617487
    Created: 17 Jan 2018 15:32:18 GMT
    Sent: 17 Jan 2018 16:06:15 GMT
    Report deadline: 31 Jan 2018 16:06:15 GMT
    Received: 17 Jan 2018 17:12:06 GMT
    Server state: Over
    Outcome: Computation error
    Client state: Compute error
    Exit status: 2 (0x00000002) Unknown error code
    Computer: 12617713
    Run time (sec): 0.00
    CPU time (sec): 0.00
    Peak working set size (MB): 0
    Peak swap size (MB): 0
    Peak disk usage (MB): 0
    Validation state: Invalid
    Granted credit: 0
    Application: Gamma-ray pulsar binary search #1 on GPUs v1.20 (FGRPopencl1K-nvidia) x86_64-pc-linux-gnu

    Stderr output

    <core_client_version>7.2.42</core_client_version>
<![CDATA[
<message>
process exited with code 2 (0x2, -254)
</message>
<stderr_txt>
16:19:23 (2947): [normal]: This Einstein@home App was built at: Feb 15 2017 10:50:14

    16:19:23 (2947): [normal]: Start of BOINC application '../../projects/einstein.phys.uwm.edu/hsgamma_FGRPB1G_1.20_x86_64-pc-linux-gnu__FGRPopencl1K-nvidia'.
    16:19:23 (2947): [debug]: 1e+16 fp, 2e+09 fp/s, 5249670 s, 1458h14m30s41
    16:19:23 (2947): [normal]: % CPU usage: 1.000000, GPU usage: 1.000000
    command line: ../../projects/einstein.phys.uwm.edu/hsgamma_FGRPB1G_1.20_x86_64-pc-linux-gnu__FGRPopencl1K-nvidia --inputfile ../../projects/einstein.phys.uwm.edu/LATeah0051L.dat --alpha 4.42281478648 --delta -0.0345027837249 --skyRadius 2.152570e-06 --ldiBins 15 --f0start 1076.0 --f0Band 8.0 --firstSkyPoint 0 --numSkyPoints 1 --f1dot -1e-13 --f1dotBand 1e-13 --df1dot 3.344368011e-15 --ephemdir ../../projects/einstein.phys.uwm.edu/JPLEPH --Tcoh 2097152.0 --toplist 10 --cohFollow 10 --numCells 1 --useWeights 1 --Srefinement 1 --CohSkyRef 1 --cohfullskybox 1 --mmfu 0.1 --reftime 56100 --model 0 --f0orbit 0.005 --mismatch 0.1 --demodbinary 1 --BinaryPointFile ../../projects/einstein.phys.uwm.edu/templates_LATeah0051L_1084_12139615.dat --debug 1 --device 0 -o LATeah0051L_1084.0_0_0.0_12139615_1_0.out
    output files: 'LATeah0051L_1084.0_0_0.0_12139615_1_0.out' '../../projects/einstein.phys.uwm.edu/LATeah0051L_1084.0_0_0.0_12139615_1_0' 'LATeah0051L_1084.0_0_0.0_12139615_1_0.out.cohfu' '../../projects/einstein.phys.uwm.edu/LATeah0051L_1084.0_0_0.0_12139615_1_1'
    16:19:23 (2947): [debug]: Flags: X64 SSE SSE2 GNUC X86 GNUX86
    16:19:23 (2947): [debug]: glibc version/release: 2.22/stable
    16:19:23 (2947): [debug]: Set up communication with graphics process.
    Could not create topdir for cache
    </stderr_txt>
    ]]>

     

    mikey
    mikey
    Joined: 22 Jan 05
    Posts: 12783
    Credit: 1873219624
    RAC: 1892407

    John_328 wrote:All GPU WUs on

    31 Jan 2018 11:57:48 UTC
    Message 164076
    (moderation:
      )

      John_328 wrote:

      All GPU WUs on this machine are failing, with error code 2:

      LATeah0051L_1084.0_0_0.0_12139615_1

      Your latest one finished validated!!

       

       

      Gary Roberts
      Gary Roberts
      Moderator
      Joined: 9 Feb 05
      Posts: 5874
      Credit: 118443431730
      RAC: 25897315

      John_328 wrote:All GPU WUs on

      31 Jan 2018 22:34:00 UTC
      Message 164084
      (moderation:
        )

        John_328 wrote:

        All GPU WUs on this machine are failing, with error code 2:

        ....

        16:19:23 (2947): [debug]: Flags: X64 SSE SSE2 GNUC X86 GNUX86
16:19:23 (2947): [debug]: glibc version/release: 2.22/stable
16:19:23 (2947): [debug]: Set up communication with graphics process.
Could not create topdir for cache
</stderr_txt>
]]>

         

        The task seems to fail immediately, and the error message, "Could not create ..." makes it look very much like a 'permissions' problem.  Do you run BOINC as your normal user or was a special boinc:boinc user and group set up for the purpose?

        You should browse the complete BOINC directory structure looking for anything unusual in the ownership/permissions of all files and subdirectories.  During startup, slot directories are created/populated, one for each separate task that is running.  You might be able to find the particular slot directory for the last GPU task that crashed and examine all the remnants there to see if you can get any clues.  I've never felt the need to delve into the slot directories in detail (other than an occasional brief look) so I don't have any experience with which to guide you, unfortunately.  Maybe someone else with more knowledge about this might be able to chime in.

         

        Cheers,
        Gary.

        Comment viewing options

        Select your preferred way to display the comments and click "Save settings" to activate your changes.

        Forums › Problems and Bug Reports