IJ52694: UNABLE TO START STORAGE SCALE ON AIX NODE DUE TO LARGE PAGEPOOL

APAR status

• Closed as program error.

Error description

• Unable to start Storage Scale on AIX Nodes due to large
  pagepool can end up with
  errno 28 vm_galloc return 28 (ENOSPC = Not enough space
  in the galloc heap to
  perform the allocation). This can occur if the pagepool
  set ist >= 1 TB.
  
  Reported in:
  5.2.0.0
  

Local fix

• Workaround can be to lower the value of
  pagepoolMaxPhysMemPct from its default 75 to about 50.
  By lowering value of pagepoolMaxPhysMemPct from its
  default 75 to about 50 and rebooting the
  Node can overcome that issue.
  

Problem summary

• GPFS can't start on AIX even though the node over 1TB RAM and a
  small pagepool .
  

Problem conclusion

• This problem is fixed in 5.1.9.7
  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:
  Fixed the code so that even if GPFS requests over 1TB using 4K
  pages (which is over the current limit for AIX using 4K pages),
  GPFS can still start on AIX.
  
  
  Work Around:
  reduce the pagepoolMaxPhysMemPct to 50 on the node that GPFS
  can't start, by# mmchconfig pagepoolMaxPhysMemPct=50Restart
  GPFS.
  
  Problem trigger:
  The max shared segment size was increased to a value that caused
  GPFS to request more than 1TB using 4K pages, that goes beyond
  what AIX can accept.
  
  Symptom:
  Abend/Crash
  
  Platforms affected:
  AIX Only
  
  Functional Area affected:
  All Scale Users
  
  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 DME

• Fixed component ID

  5737F34AP

Applicable component levels