public:stopdayactivities_2oct2018

This is an old revision of the document!


Stop-day activities October 2-3, 2018


Coordinator Jasmin Klipic roadmin@astron.nl
Software Support Adriaan Renting softwaresupport@astron.nl
Science, Operations and Support Pietro Zucca sos@astron.nl
Observer Henk Mulder observer@astron.nl

Description of stopday procedures
LOFAR Schedule cycle 10
⇒ The next stopdays are scheduled for December 4-5.

  • Reboots and idrac reboots. (Hopko)
  • Block access at 08:00 (Teun)
  • Replace 11 broken disks (Kees ?)
  • All nodes: file system check and reboot. (Kees)
Degraded CEP3 RAIDS  
 
Current list:

lof004 slot 7 "Foreign"
lof006 slot 1 "Failed"
lof014 slot 7 "Foreign"
lof016 slot 7 "Ready"
lof017 slot 5 "Foreign"
lof020 slot 7 "Foreign"
lof021 slot 2 "Ready
  • Lustre upgrade (Hopko/Robin/Reinoud)
  • Increase /tmp to 4GB and tmpfs
  • CEP4 /tmp to tmpfs (will not be done) since can have impact to SLURM (will be discussed/planned for next STOP Day)
  • No action. (need to be checked maybe will be upgraded to 7.5?)
  • No reboots
  • Update & reboot using Spacewalk
  • OS upgrade and reboot
  • ✔ lcs022/027/030/031 will be switched off (need confirmation from Jens K, and Teun)
  • OS upgrade and reboot
  • None
  • None
  • None
  • none
  • none
  • Activate disk quota
  • Check that software environment is the same on all nodes (lof015 included)
  • None
  • Slurm update (cpu/gpu nodes tbd)
  • None
  • none
  • none
  • update & reboot (if possible)

The minutes of the review meeting can be found here.

  • Last modified: 2018-10-02 11:24
  • by grit