Intel 170 Servers, AS/400 RISC Server, 7xx Servers MSD Affects on IPL Performance Measurements

16.6 NOTES on MSD

MSD is Mainstore Dump. General IPL phase as it relates to the SRCs posted on the operation panel: Processor MSD includes the D2xx xxxx and C2xx xxxx right after the system is forced to terminate. SLIC MSD IPL with Copy follows with the next series of C6xx xxxx, see the next heading for more information on the SLIC MSD IPL with Copy. The copy occurs during the C6xx 4404 SRCs. Shutdown includes the Dxxx xxxx SRCs. Hardware re-ipl includes the next phase of D2xx xxxx and C2xx xxxx. SLIC re-IPL follows which are the C600 xxxx SRCs. OS/400 completes with the C900 xxxx SRCs.

16.6.1 MSD Affects on IPL Performance Measurements

SLIC MSD IPL with Copy is affected by the number of DASD units and the jobs executing at the time of the mainstore dump.

When a system is abnormally terminated, in-process changes to the directories used by the system to manage storage may be lost. During the subsequent IPL, storage management directory recovery is performed to ensure the integrity of the directories and the underlying storage allocations.

The duration of this recovery step will depend on the type of recovery performed and on the size of the directories. In most cases, a subset directory recovery (SRC C6004250) will be performed which may typically run from 2 minutes to 30 minutes depending upon the system. In rare cases, a full directory recovery (SRC C6004260) is performed which typically runs much longer than a subset directory recovery. The duration of the subset directory recovery is dependent on the size of the directory (which relates to the amount of data stored on the system) and on the amount of in-process changes. With the amount of data stored on our largest configurations with one to two thousand disk units, subset directory recovery (SRC C6004250) took from 14 minutes to 50 minutes depending upon the system.

DASD Unit’s Effect on MSD Time - Through experimental testing we found the time spent in MSD copying the data to disk is related to the number of DASD arms available. Assigning the MSD copy to an ASP with a larger number of DASD can help reduce your recovery time if an MSD should occur.

IBM i 6.1 Performance Capabilities Reference - January/April/October 2008
© Copyright IBM Corp. 2008	Chapter 16 IPL Performance	276