IJ34136: MMADDDISK IS VERY SLOW WHEN ADDING DISKS FROM ESS3000 OR ECE CLUSTER

APAR status

• Closed as program error.

Error description

• With thousands of client nodes mounted in the
  file system, adding some more disks
  serviced by ESS3000 nodes can cause long waiters
  trying to get NSD disk information on each client node.
  

Local fix

• Restart the GPFS service on the ESS3000 or ECE nodes,
  or failover the RG master from one node to the other one.
  

Problem summary

• With thousands of client nodes mounted in the
  file system, adding some more disks
  serviced by ESS3000 nodes can cause long waiters
  trying to get NSD disk information on each client node.
  

Problem conclusion

• This problem is fixed in 5.1.1  PTF 3
  To see all Spectrum Scale APARs and
  their respective fix solutions refer to page
  https://public.dhe.ibm.com/storage/spectrumscale/spectrum_scale_
  apars.html
  
  Benefits of the solution:
  Speed up the process for the accumulated
  RPC messages on the NSD server
  node by reducing the unnecessary
  NSD configuration reload requests.
  
  Work around:
  Restart the GPFS service on the ESS3000 or ECE nodes,
  or failover the RG master from one node to the other one.
  
  Problem trigger:
  Create new NSD disks from an ESS3000 or an ECE
  cluster and add them to a file system before starting
  GPFS service.
  
  Symptom:
  Stuck mmadddisk command
  
  Platforms affected:
  ESS3000 or ECE clusters
  
  Functional Area affected:
  Admin Commands
  
  Customer Impact:
  High Importance
  

Temporary fix

Comments

APAR Information

• APAR is sysrouted FROM one or more of the following:

• APAR is sysrouted TO one or more of the following:

Fix information

• Fixed component name

  SPEC SCALE STD

• Fixed component ID

  5737F33AP

Applicable component levels