Execution velocity


Execution velocity is defined as the total number of samples where an address space was using CPU divided by the number of times an address space was using CPU plus the number of general execution delays the address space experienced. This value is then multiplied by 100 to get a percentage execution velocity.

The following list shows general execution delays, as defined by WLM:

Delay

Description

CPU delay

TCB or SRB waiting to be dispatched or a TCB waiting for a local lock

CPU capping delay

TCB or SRB marked nondispatchable because a resource group maximum is being enforced

Swap-in delay

Swap-in started, but not completed

MPL delay

Ready, but swap-in not started

Aux page from private

Delay waiting for a private page to be brought in from auxiliary storage

Aux page from common

Delay waiting for a common page to be brought in from auxiliary storage

Aux page from cross-mem

Delay waiting for a cross-memory page to be brought in from auxiliary storage

Aux page from VIO

Delay waiting for a VIO page to be brought in from auxiliary storage

Aux page from std hiper

Delay waiting for a standard hiperspace page to be brought in from auxiliary storage

Aux page from ESO hiper

Delay waiting for an ESO hiperspace page to be brought in from auxiliary storage

Shared paging

Delay waiting for a shared storage page to be brought in

DASD I/O delay samples

Number of samples of work delayed for paging DASD I/O

Queue delay samples

Number of samples of work that is waiting for a server

Server private area paging delay samples

Number of samples delayed for private area paging for a server

Server space VIO paging delay samples

Number of samples delayed for VIO paging for a server

Server hiperspace paging delay samples

Number of samples delayed for hiperspace paging for a server

Server MPL delay samples

Number of samples delayed for MPL for a server

Server swap-in delay samples

Number of samples delayed for swap-in for a server

zAAP

zAAP delay; work that has been delayed while waiting to be dispatched on a zAAP

zIIP

zIIP delay; work that has been delayed while waiting to be dispatched on a zIIP

 

Tip: For faster searching, add an asterisk to the end of your partial query. Example: cert*