IT25373: CF MEMBER COMMUNICATION TIMEOUT LEADS TO CONNECTION RESET IMPACTING PERFORMANCE

APAR status

• Closed as fixed if next.

Error description

• The following error is noticed in the db2diag.log to indicate an
  XI timeout:
  
  2018-05-23-15.55.16.840725+600 I334076216E684        LEVEL:
  Severe
  PID     : 17721                TID : 140109940778752 PROC :
  db2sysc 1
  INSTANCE: inst1             NODE : 001            DB   : TESTDB
  HOSTNAME: hostname
  EDUID   : 925                  EDUNAME: db2XInot GBP 1-0
  (TESTDB)
  1
  FUNCTION: DB2 UDB, RAS/PD component, pdLogCaPrintf, probe:876
  DATA #1 : <preformatted>
  do_dequeue: Timed-out waiting for completion of RDMA write of an
  link status buffer.  EP: 0x7f6e4c001ae0
  DATA #1 : <preformatted>
  If a CF return code is displayed above and you wish to get
  more information then please run the following command:
  
  If the timeout is on the Notification connection thread the
  following diag log message is observed
  
  2018-01-02-10.51.15.616046+060 I177825120E664        LEVEL:
  Severe
  PID     : 2931                 TID : 140189880018688 PROC :
  db2sysc 0
  INSTANCE: inst1             NODE : 000            DB   : TESTDB
  HOSTNAME: hostname
  EDUID   : 1240                 EDUNAME: db2LLMn12 (P2001) 0
  FUNCTION: DB2 UDB, RAS/PD component, pdLogCaPrintf, probe:876
  DATA #1 : <preformatted>
  do_dequeue: Timed-out waiting for completion of RDMA write of an
  link status buffer.  EP: 0x7f7ed01912d0
  DATA #1 : <preformatted>
  If a CF return code is displayed above and you wish to get
  more information then please run the following command:
  
  Upon checking networking, if no other reason for timeout is
  found, its likely the network being slow causing this issue.
  This fix allows for the timeout parameter to be tune-able for
  such cases.
  

Local fix

Problem summary

• ****************************************************************
  * USERS AFFECTED:                                              *
  * pureScale environment                                        *
  ****************************************************************
  * PROBLEM DESCRIPTION:                                         *
  * See Error Description                                        *
  ****************************************************************
  * RECOMMENDATION:                                              *
  * Check "Problem Conclusion" section.                          *
  ****************************************************************
  

Problem conclusion

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

Applicable component levels