Import

2017-09-02 23:27:01 +02:00
parent b23126799b
commit 2775da5f44
175 changed files with 17098 additions and 2 deletions
@@ -0,0 +1,31 @@
+#******************************************************************************
+# @(#) check_health.conf
+#******************************************************************************
+# This is the main configuration file for the check_health.sh tool.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# --- general settings ---
+# maximum timeout for HC calls (seconds)
+HC_TIME_OUT=60
+
+# location of log directory, see also --log-dir)
+LOG_DIR="/var/opt/hc"
+
+# location of events directory
+EVENTS_DIR="${LOG_DIR}/events"
+
+# location of state directory
+STATE_DIR="${LOG_DIR}/state"
+
+# location of persistent state directory
+STATE_PERM_DIR="${STATE_DIR}/persistent"
+
+# location of temporary state directory
+STATE_TEMP_DIR="${STATE_DIR}/temporary"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************
@@ -0,0 +1,22 @@
+#******************************************************************************
+# @(#) notify_eif.conf
+#******************************************************************************
+# This is the configuration file for the notify_eif.sh provider.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# --- EIF settings ---
+# location of the posteifmsg tool
+EIF_BIN="/opt/eif/bin/posteifmsg"
+
+# location of the posteifmsg configuration file
+EIF_ETC="/etc/opt/eif/posteifmsg.conf"
+
+# default ITM severity
+EIF_SEVERITY="MINOR"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************
@@ -0,0 +1,18 @@
+#******************************************************************************
+# @(#) notify_sms.conf
+#******************************************************************************
+# This is the the configuration file for the notify_sms.sh provider.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# --- SMS settings ---
+# list of supported SMS providers (comma-separated)
+SMS_PROVIDERS=""
+
+# configuration settings for individual SMS providers go here
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************
@@ -0,0 +1,3 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
@@ -0,0 +1,13 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+File system is mounted with incorrect options. Remount the file system with the correct options.
+* Check /etc/fstab
+* Check /etc/cmcluster/<PKG_NAME>/<PKG_NAME>.conf files (directive "fs_mount_opt")
+
+Keep in mind that special mount options may apply for:
+* NFS file systems
+* SAP file systems
+* Oracle data/redo files
+
@@ -0,0 +1,10 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+Check any faulty devices or error messages:
+* ioscan -P health (look for 'offline' devices)
+* ioscan -fnN (look for 'NO_HW' devices)
+* dmesg
+* /var/adm/syslog/syslog.log
+
@@ -0,0 +1,10 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+Execute:
+* mwa start all
+* /sbin/init.d/ovpa start
+Verify:
+* perfstat -p
+
@@ -0,0 +1,7 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMMENDATION ***
+Check the root crontab for any wrongly commented lines and fix:
+* crontab -l | grep '^#'
+
@@ -0,0 +1,12 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+Check current cluster status:
+* cmviewcl [-v]
+If the cluster is down:
+* cmruncl
+Check for possible errors in:
+* /var/adm/cmcluster/log/*
+* /var/adm/syslog/syslog.log (cmcld)
+
@@ -0,0 +1,15 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+Check current package status:
+* cmviewcl [-v] -p <PKG_NAME>
+If the package is down:
+* cmrunpkg <PKG_NAME> (on the primary node)
+- or -
+* cmmodpkg -e <PKG_NAME>
+* cmmodpkg -e -n <PRIMARY_NODE> <PKG_NAME>
+Check for possible errors in:
+* /var/adm/cmcluster/log/*
+* /var/adm/syslog/syslog.log (cmcld)
+
@@ -0,0 +1,11 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+If this host is part of Serviceguard cluster and the affected volume group
+is cluster aware, then major/minor numbers must be unique AND identical on
+all cluster nodes.
+
+View the current major/minor:
+* vgs
+
@@ -0,0 +1,12 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMENDATION ***
+File system is mounted with incorrect options. Remount the file system with the correct options.
+* Check /etc/fstab
+
+Keep in mind that special mount options may apply for:
+* NFS file systems
+* SAP file systems
+* Oracle data/redo files
+
@@ -0,0 +1,7 @@
+*** MESSAGE ***
+<## @_HC_BODY ##>
+
+*** RECOMMMENDATION ***
+Check the root crontab for any wrongly commented lines and fix:
+* crontab -l | grep '^#'
+
@@ -0,0 +1,11 @@
+*** LOGS ***
+Please check the corresponding log file(s) for more details. At <## @HOST_NAME ##>:<## @LOG_DIR ##>)
+
+You can also run /opt/hc/bin/check_health.sh --report --id=<## @_MAIL_FAIL_ID ##> (--detail) on <## @HOST_NAME ##>
+
+Following log files have been attached to this e-mail:
+
+STDOUT : <## @_MAIL_STDOUT_MSG ##>
+STDERR : <## @_MAIL_STDERR_MSG ##>
+
+******* END OF MAIL. DO NOT REPLY TO THIS E-MAIL. NOBODY WILL SEE IT! ********
@@ -0,0 +1,4 @@
+*** ID ***
+HC NAME : <## @_MAIL_HC ##>
+FAIL ID : <## @_MAIL_FAIL_ID ##>
+
@@ -0,0 +1,3 @@
+To: <## @ARG_MAIL_TO ##>
+Subject: <## @_SUBJ_MSG ##>
+From: <## @_FROM_MSG ##>