IC80705: PERFORMANCE DEGRADATION WITH MOVE NODE DATA FROM DEDUPLICATED POOL TO TAPE

APAR status

• Closed as program error.

Error description

• Performance degradation may be greater than expected when moving
  node data from a deduplicated stgpool to a non-deduplicated
  stgpool. This may be due to improper transaction batching for
  deduplicated files when they are being hydrated for transfer to
  the non-deduplicated storage pool.
  
  Customer/L2 Diagnostics (if applicable)
   We would see this degradation in an environment where the file
  sizes being moved are large (each file is 1GB+).
  
  The diagnostics will show many of the following locks under the
  transaction that is moving the data.
  Example:
     Locks held by Tsn=0:XXXXXX :
       Type=46001(bf aggregate (superbitfile) id), NameSpace=0,
  SummMode=xLock, Mode=xLock,
  Key='XXXXXXX'
       Type=46001(bf aggregate (superbitfile) id), NameSpace=0,
  SummMode=xLock, Mode=xLock,
  Key='225993754'
       Type=46001(bf aggregate (superbitfile) id), NameSpace=0,
  SummMode=xLock, Mode=xLock,
  Key='225993755'
       Type=46001(bf aggregate (superbitfile) id), NameSpace=0,
  SummMode=xLock, Mode=xLock,
  Key='225993756
  ...
  
  In the Server Performance output (instrumentation tracing), DB2
  section, the number of locks may be seen to increase over time.
  DB2 STATISTICS DURING INSTRUMENTATION INTERVAL:
  
   Note that items marked (*) will be zero unless DB2
   monitor switches (SORT and LOCK) are enabled.
   ---------------------------------------------------------------
  ---------------
               Deadlocks detected:         0.0/sec
       Number of lock escalations:     0.0/sec
                       Lock waits:                0.0/sec
          Time waited on locks(*):    0.000 sec
                       Locks held: 12821231 before, 13435126 after
  <--- check this
  ...
  
  *NOTE*
  A performance impact is expected behavior when moving data from
  a deduplicated pool to a non-deduplicated pool as the data needs
  to be re-hydrated.
  
  Platforms affected:
  All TSM 5.4, 5.5, 6.1, 6.2, 6.3 Unix/Linux/Windows
  
  Initial Impact: Medium
  
  Additional Keywords: dedup deduplicated migrate migration
  

Local fix

Problem summary

• ****************************************************************
  * USERS AFFECTED: All Tivoli Storage Manager server users.     *
  ****************************************************************
  * PROBLEM DESCRIPTION: See ERROR DESCRIPTION.                  *
  ****************************************************************
  * RECOMMENDATION: Apply fixing level when available.           *
  *                 This problem is currently projected to be    *
  *                 fixed in levels 6.2.4 and 6.3.1.             *
  *                 Note that this is subject to change at       *
  *                 the discretion of IBM.                       *
  ****************************************************************
  *
  

Problem conclusion

• The described problem has been resolved.
  
  AFFECTED PLATFORMS:
  AIX, HP-UX, Solaris, Linux, and Windows.
  

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

  TSM SERVER

• Fixed component ID

  5698ISMSV

Applicable component levels

• R61A PSY

     UP

• R61H PSY

     UP

• R61L PSY

     UP

• R61S PSY

     UP

• R61W PSY

     UP

• R62A PSY

     UP

• R62H PSY

     UP

• R62L PSY

     UP

• R62S PSY

     UP

• R62W PSY

     UP

• R63A PSY

     UP

• R63H PSY

     UP

• R63L PSY

     UP

• R63S PSY

     UP

• R63W PSY

     UP