#!/bin/bash
# cache error trigger. This shell script is executed by mcelog in daemon mode
# when a CPU reports excessive corrected cache errors. This could be a indication
# for future uncorrected errors.
# 
# environment:
# MESSAGE	  Human readable error message
# CPU		  Linux CPU number that triggered the error
# LEVEL		  Cache level affected by error
# TYPE		  Cache type affected by error (Data,Instruction,Generic)
# AFFECTED_CPUS   List of CPUs sharing the affected cache
# SOCKETID	  Socket ID of affected CPU
#
# note: will run as mcelog configured user
# this can be changed in mcelog.conf

#
# offline the CPUs (except CPU #0) sharing the affected cache
#
for i in $AFFECTED_CPUS ; do 
	if [ $i = 0 ] ; then
		logger -s -p daemon.warn -t mcelog "Not offlining CPU 0"	
		continue
	fi
	logger -s -p daemon.crit -t mcelog "Offlining CPU $i due to cache error threshold"
	F=$(printf "/sys/devices/system/cpu/cpu%d/online" $i)
	echo 0 > $F
	if [ "$(< $F)" != "0" ] then
		logger -s -p daemon.warn -t mcelog "Offlining CPU $i failed"
	fi
done

[ -x ./cache-error-trigger.local ] && . ./cache-error-trigger.local