Changes between Version 3 and Version 4 of Public/User_Guide/PaS


Ignore:
Timestamp:
Apr 3, 2020, 6:50:54 PM (4 years ago)
Author:
Jochen Kreutz
Comment:

filled in currently known issues discussed in last admin telco

Legend:

Unmodified
Added
Removed
Modified

  • Public/User_Guide/PaS

    v3 v4  
     1[[TOC]]
     2
     3This page is intended to give a short overview on known issues and to provide potential solutions and workarounds to the issues seen.
     4
     5To stay informed, please also read the information presented in the "Message of the day" when logging onto the system.
    16
    27
     8== Software issues ==
     9
     10=== GPU direct usage with Extoll ==
     11
     12- new Extoll driver for GPU direct over Extoll currently being tested on the DAM nodes
     13- only available via Developer statge, for testing load:
     14
     15{{{
     16module --force purge
     17module use $OTHERSTAGES
     18module load Stages/Devel-2019a
     19module load GCC/8.3.0
     20module load ParaStationMPI
     21}}}
     22
     23- expect performance and stability issues
     24
     25== Detected HW and node issues ==
     26
     27=== CM nodes ===
     28 
     29* dp-cn49 and dp-cn50: nodes currently reserved for special use case
     30
     31=== DAM nodes ===
     32
     33* dp-dam03: being investigated after unexptected reboot (#2323)
     34* dp-dam07: showing problems with its FPGA (#2353)
     35* dp-dam08: issues with second socket CPU seen (#2304)
     36
     37=== ESB nodes ===
     38
     39* dp-esb08: GPU shows PCIe x8 connection only (#2370)
     40* dp-esb11: no GPU device detected, under repair (#2358)
     41* dp-esb23: MCE problems (#2350)