IBM Support

IJ08529: BALLOT COMPARISON BUG IN CCR CAUSING LONG RUNNING CLUSTER MANAGE

Subscribe to this APAR

By subscribing, you receive periodic emails alerting you to the status of the APAR, along with a link to the fix after it becomes available. You can track this item individually or track all items by product.

Notify me when this APAR changes.

Notify me when an APAR for this component changes.

 

APAR status

  • Closed as program error.

Error description

  • Ballot comparison bug in CCR causing long running cluster
manager elections

Reported In:
Spectrum Scale 4.2.3

Known Impact:
If there are concurrent synods are running and/or the CCR
is under heavy load/stress, the cluster manager election
may take long time.

Verification steps:
After "Running election", though there are enough quorum
to form a cluster but it takes very long time or never to
elect a new cluster manager.

Local fix

  • 



Problem summary


    

  • Long running cluster manager elections caused by concurrent
running CCR synods on different quorum nodes, when the quorum
nodes (CCR) are under heavy load.

    



Problem conclusion


    

  • Prioritizing concurrent running CCR synods on different quorum
nodes by introducing a ballot counter increment. Nodes with
lower node Ids will be preferred over nodes with higher node
Ids, because the lower numbered nodes may start a new cluster
manager election. In addition replaced the static delay logic
at the beginning of a synod by talking directly to the node
started.

    



Temporary fix


    

  • 



Comments


    

  • 



APAR Information




    

  • APAR number
    IJ08529
    • 

  • Reported component name
    SPECTRUM SCALE
    • 

  • Reported component ID
    5725Q01AP
    • 

  • Reported release
    423
    • 

  • Status
    CLOSED  PER
    • 

  • PE
    NoPE
    • 

  • HIPER
    NoHIPER
    • 

  • Special Attention
    NoSpecatt / Xsystem
    • 

  • Submitted date
    2018-08-16
    • 

  • Closed date
    2018-08-16
    • 

  • Last modified date
    2019-06-28
    • 





    

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

    
IJ07733
    

    • 

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

    • 



Fix information


    

  • Fixed component name
    SPECTRUM SCALE
    • 

  • Fixed component ID
    5725Q01AP
    • 



Applicable component levels


    

  • R423  PSY  U885025
       19/06/28  I  1000
    • 








      
              
                            

              

              [{"Business Unit":{"code":"BU058","label":"IBM Infrastructure w\/TPS"},"Product":{"code":"STXKQY","label":"IBM Spectrum Scale"},"Component":"","ARM Category":[],"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"423","Edition":"","Line of Business":{"code":"LOB26","label":"Storage"}},{"Business Unit":{"code":"BU058","label":"IBM Infrastructure w\/TPS"},"Product":{"code":"SSFKCN","label":"General Parallel File System"},"Component":"","ARM Category":[],"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"423","Edition":"","Line of Business":{"code":"","label":""}}]
              

                                                                    

          
 
        

      

    

      

        

          

            
Document Information


            

            


                        

            Modified date:
            

            28 June 2019
            

            
                      

        


        

        


      

    

  



    

  

  
    
            

          
Page Feedback