NAME

hardclock − configure hardclock interrupt handling

SYNOPSIS

/usr/etc/hardclock [cpu-list]

DESCRIPTION

If a cpu-list is provided, hardclock attempts to enable hardclock interrupt handling for CPUs specified in the cpu-list and disable hardclock interrupt handling for CPUs NOT specified in the cpu-list.  Only the super-user or a user with the ACC_MPADVISE access vector may specify a cpu-list. 
 
It is intended that this command be used in a real-time environment. A cpu-list is a comma separated list of CPU IDs or CPU ID ranges.  For example: "1,3-5,7".  A cpu-list can also be one of the constants, all and boot, representing all active CPUs and the boot CPU respectively.  Hardclock interrupt handling for the boot CPU cannot be disabled.  Services normally performed by the hardclock interrupt routine will not occur on CPUs where handling is disabled.  These services include:
 

Keeping process CPU usage statistics and sending SIGXCPU
 
Expiring the process virtual interval timer and sending SIGVTALRM
 
Expiring the process profiling timer and sending SIGPROF
 
Initiating process and kernel profiling functions
 
Aging process rescheduling locks and sending SIGRESCHED
 
Keeping track of process resident memory usage
 
Round Robin scheduling within a priority level Quantum expiration will no longer occur.  A process may run to completion unless it blocks, is pre-empted by a higher priority process, or forks.

Refer to the CX/UX Programmer’s Guide for more information about hardclock interrupt handling. 

Hardclock returns cpu-list specifying the old and the new hardclock handling configuration. 

EXAMPLE

hardclock 1-3,5 will enable hardclock handling on CPUs 1,2,3, and 5. 

SEE ALSO

CX/UX Programmer’s Guide for a description of hardclock interrupt handling; mpadvise(2). 

CX/UX Administrator’s Reference