This page is intended to give a short overview on known issues and to provide potential solutions and workarounds to the issues seen.

Last update: 2020-09-23

To stay informed, please refer to the News page. Also, please pay attention to the information contained in the "Message of the day" displayed when logging onto the system.

Detected HW and node issues

CM nodes

• dp-cn[01,09,10]: nodes currently reserved for special use case during working hours
• dp-cn33: memory issues (#2464)
• dp-cn49: configuration change required (#2291)
• dp-cn50: node not reachable (#2488)

DAM nodes

• dp-dam03: node currently reserved for special use case (#2242)
• dp-dam04: showing low streams performance (#2401)
• dp-dam05: node currently reserved for special use case
• dp-dam07: showing problems with its FPGA (#2353)
• dp-dam[09,10]: nodes currently reserved for special use case during working hours

ESB nodes

• dp-esb05: node hangs in state "Idle+Completing"
• dp-esb11: wrong GPU Link Speed detected (#2358)
• dp-esb24: CentOS8 Testbed (#2396)
• dp-esb39: energy meter reading issues (#2432)
• dp-esb52: energy meter reading issues (#2433)
• dp-esb61: node not reachable (#2469)
• dp-esb71: energy meter reading issues (#2432)
• dp-esb73: energy meter reading issues (#2433)

SDV nodes

• deeper-sdv01: node reachable via nework, but marked as down in SLURM
• nfgw[01,02]: node reachable via nework, but marked as down in SLURM
• knl01: NVMe issues (#2011)
• ml-gpu02: memory issues reported with MCE (#2489)

Software issues

Modular jobs failing

• users reported failing jobs that are doing MPI on more than one module using the gateways
• the problem is being investigated

SLURM jobs

• due to introduction of accounting with the start of the early access program there is some re-configuration of user accounts needed within SLURM to assign the correct QOS levels and priorities for the jobs
• this might lead to (temporary) failing job starts for certain users
• if you cannot start jobs via SLURM, please write an email to the support list: sup(at)deep-est.eu

GPU direct usage with IB on ESB

• currently only available via Developer stage, for testing load:

module --force purge
module use $OTHERSTAGES
module load Stages/Devel-2019a
module load GCC/8.3.0 or module load Intel
module load ParaStationMPI

• use PSP_CUDA=1 and PSP_UCP=1

GPU direct usage with Extoll on DAM

• new Extoll driver for GPU direct over Extoll currently being tested on the DAM nodes
• only available via Developer stage, for testing load:

module --force purge
module use $OTHERSTAGES
module load Stages/Devel-2019a
module load GCC/8.3.0 or module load Intel
module load ParaStationMPI

• expect performance and stability issues