Update link

* Small fixes

.github/FUNDING.yml

@@ -0,0 +1,3 @@
+# These are supported funding model platforms
+
+github: patvdv

README.md

@@ -90,6 +90,11 @@ Additionally, there may be bundles for display or notification plugins, e.g.:
 * hc-display-terse
 * hc-notify-eif
 * hc-notify-sms
+* hc-notify-slack
+
+## Configure & deploy
+
+An Ansible role is available at: https://github.com/patvdv/kudos.check_health
 
 ## Execute (examples)
 
@@ -137,13 +142,14 @@ Additionally, there may be bundles for display or notification plugins, e.g.:
 * **Alerting** on failed health checks:
 ```
 /opt/hc/bin/check_health.sh --hc=check_hpux_root_crontab --run --notify=mail --mail-to="alert@acme.com"
+/opt/hc/bin/check_health.sh --hc=check_linux_fs_usage --run --notify=slack
 ```    
 
 ## References
 
 ### Documentation
 
-More documentation can be found at http://www.kudos.be/Projects/Health_checker.html
+More documentation can be found at <https://www.kudos.be/check_health/>
 
 ### Logo
 

build/aix/hc_aix_platform/hc_aix_platform.template

@@ -32,12 +32,14 @@ Fileset
 /opt/hc/lib/platform/aix/check_aix_subsystems.sh
 /opt/hc/lib/platform/aix/check_aix_sysbackup.sh
 /opt/hc/lib/platform/aix/check_aix_topasrec.sh
+/opt/hc/lib/platform/aix/check_aix_uptime.sh
 /etc/opt/hc
 /etc/opt/hc/check_aix_file_age.conf.dist
 /etc/opt/hc/check_aix_file_change.conf.dist
 /etc/opt/hc/check_aix_root_crontab.conf.dist
 /etc/opt/hc/check_aix_subsystems.conf.dist
 /etc/opt/hc/check_aix_sysbackup.conf.dist
+/etc/opt/hc/check_aix_uptime.conf.dist
   EOROOTFiles
   Relocatable: N
 EOFileset

build/aix/hc_notify_slack/hc_notify_slack.reqs

@@ -0,0 +1 @@
+*prereq hc_aix.rte

build/aix/hc_notify_slack/hc_notify_slack.template

@@ -0,0 +1,31 @@
+Package Name: hc_notify_slack
+Package VRMF: %BUILD_DATE%
+Update: N
+Fileset
+  Fileset Name: hc_notify_slack.rte
+  Fileset VRMF: %BUILD_DATE%
+  Fileset Description: Health Checker - core Slack plugin
+  USRLIBLPPFiles
+  EOUSRLIBLPPFiles
+  ROOTLIBLPPFiles
+     Post-installation Script: /export/nim/build/hc_notify_slack/scripts/hc_notify_slack.postinstall
+     Unpost-installation Script: /export/nim/build/hc_notify_slack/scripts/hc_notify_slack.postuninstall
+  EOROOTLIBLPPFiles
+  Bosboot required: N
+  License agreement acceptance required: N
+  Include license files in this package: N
+  Requisites: /export/nim/build/hc_notify_slack/hc_notify_slack.reqs
+  USRFiles
+  EOUSRFiles
+  ROOT Part: Y
+  ROOTFiles
+/opt/hc/lib
+/opt/hc/lib/core
+/opt/hc/lib/platform/aix/notify_slack.sh
+/etc/opt/hc
+/etc/opt/hc/core
+/etc/opt/hc/core/providers
+/etc/opt/hc/core/providers/notify_slack.conf.dist
+  EOROOTFiles
+  Relocatable: N
+EOFileset

build/aix/hc_notify_slack/scripts/hc_notify_sms.postinstall

@@ -0,0 +1,51 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) post-install script for hc_notify_slack LPP package
+#******************************************************************************
+# @(#) Copyright (C) 2022 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of ETC dir
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+print "INFO: starting post-install script ..."
+
+# copy plugin config file from dist (if needed)
+if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_slack.conf ]]
+then
+	cp -p ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist ${HC_ETC_DIR}/core/providers/notify_slack.conf >/dev/null || \
+	{
+		print -u2 "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
+		exit 1
+	}
+fi
+
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+	${HC_BIN} --fix-symlinks || print -u2 "WARN: updating symlinks failed"
+else
+	print -u2 "ERROR: could not locate or excute the HC main script (${HC_BIN})"
+fi
+
+print "INFO: finished post-install script"
+
+exit 0
+
+#******************************************************************************
+# END of script
+#******************************************************************************

build/aix/hc_notify_slack/scripts/hc_notify_sms.postuninstall

@@ -0,0 +1,48 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) post-uninstall script for hc_notify_slack LPP package
+#******************************************************************************
+# @(#) Copyright (C) 2022 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+print "INFO: starting post-uninstall script ..."
+
+# remove plugin configuration file (.dist only)
+if [[ -d ${HC_ETC_DIR}/core/providers ]]
+then
+    rm -f ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist >/dev/null
+    (( $? == 0 )) || echo "WARN: could not remove plugin config file in directory ${HC_ETC_DIR}/core/providers"
+fi
+
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+	${HC_BIN} --fix-symlinks || print -u2 "WARN: updating symlinks failed"
+else
+	print -u2 "ERROR: could not locate or excute the HC main script (${HC_BIN})"
+fi
+
+print "INFO: finished post-uninstall script"
+
+exit 0
+
+#******************************************************************************
+# END of script
+#******************************************************************************

build/exadata/linux/ARCH/hc-exadata-platform/PKGBUILD

@@ -28,7 +28,9 @@ package() {
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_cell_luns.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_cell_luns.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_cell_physicaldisks.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_cell_physicaldisks.sh
+    install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_ib_status.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_ib_status.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_megaraid.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_megaraid.sh
+    install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh
     install -D -m 755 opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh ${pkgdir}/opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh
@@ -43,6 +45,7 @@ package() {
     install -D -m 644 etc/opt/hc/check_exadata_cell_megaraid.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_cell_megaraid.conf.dist
     install -D -m 644 etc/opt/hc/check_exadata_cell_physicaldisks.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_cell_physicaldisks.conf.dist
     install -D -m 644 etc/opt/hc/check_exadata_megaraid.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_megaraid.conf.dist
+    install -D -m 644 etc/opt/hc/check_exadata_zfs_cluster.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_zfs_cluster.conf.dist
     install -D -m 644 etc/opt/hc/check_exadata_zfs_logs.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_zfs_logs.conf.dist
     install -D -m 644 etc/opt/hc/check_exadata_zfs_pool_usage.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_zfs_pool_usage.conf.dist
     install -D -m 644 etc/opt/hc/check_exadata_zfs_services.conf.dist ${pkgdir}/etc/opt/hc/check_exadata_zfs_services.conf.dist

build/exadata/linux/SPECS/hc-exadata-platform.spec

@@ -36,7 +36,9 @@ cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_cell_griddisks.sh $RPM_B
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_cell_luns.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_cell_luns.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_cell_physicaldisks.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_cell_physicaldisks.sh
+cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_ib_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_ib_status.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_megaraid.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_megaraid.sh
+cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh
 cp ../SOURCES/opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh
@@ -52,6 +54,7 @@ cp ../SOURCES/etc/opt/hc/check_exadata_cell_luns.conf.dist $RPM_BUILD_ROOT/etc/o
 cp ../SOURCES/etc/opt/hc/check_exadata_cell_megaraid.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_cell_megaraid.conf.dist
 cp ../SOURCES/etc/opt/hc/check_exadata_cell_physicaldisks.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_cell_physicaldisks.conf.dist
 cp ../SOURCES/etc/opt/hc/check_exadata_megaraid.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_megaraid.conf.dist
+cp ../SOURCES/etc/opt/hc/check_exadata_zfs_cluster.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_zfs_cluster.conf.dist
 cp ../SOURCES/etc/opt/hc/check_exadata_zfs_logs.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_zfs_logs.conf.dist
 cp ../SOURCES/etc/opt/hc/check_exadata_zfs_pool_usage.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_zfs_pool_usage.conf.dist
 cp ../SOURCES/etc/opt/hc/check_exadata_zfs_services.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_exadata_zfs_services.conf.dist
@@ -103,7 +106,9 @@ echo "INFO: finished post-uninstall script"
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_cell_luns.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_cell_physicaldisks.sh
+%attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_ib_status.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_megaraid.sh
+%attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh
 %attr(755, root, root) /opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh
@@ -118,6 +123,7 @@ echo "INFO: finished post-uninstall script"
 %attr(644, root, root) /etc/opt/hc/check_exadata_cell_megaraid.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_exadata_cell_physicaldisks.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_exadata_megaraid.conf.dist
+%attr(644, root, root) /etc/opt/hc/check_exadata_zfs_cluster.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_exadata_zfs_logs.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_exadata_zfs_pool_usage.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_exadata_zfs_services.conf.dist
@@ -126,6 +132,10 @@ echo "INFO: finished post-uninstall script"
 
 
 %changelog
+* Tue Jul 07 2020 <patrick@kudos.be> - 0.5.0
+- Added check_exadata_ib_status
+* Fri Jul 07 2019 <patrick@kudos.be> - 0.4.0
+- Added check_exadata_zfs_cluster
 * Fri May 14 2019 <patrick@kudos.be> - 0.3.0
 - Added include_exadata
 - Added plugin check_exadata_cell_alerts

build/hpux/hc_hpux_platform/hc_hpux_platform.psf

@@ -59,9 +59,11 @@ This is the OS/platform plugin package"
         file_permissions -u 0222 -o root -g sys
 
         directory       ../../../opt/hc/lib/platform/hp-ux=/opt/hc/lib/platform/hp-ux
+        file            -m 755 check_hpux_autofs.sh
         file            -m 755 check_hpux_autopath.sh
         file            -m 755 check_hpux_cdsf_cluster.sh
         file            -m 755 check_hpux_cron_status.sh
+        file            -m 755 check_hpux_defunct_processes.sh
         file            -m 755 check_hpux_drd_status.sh
         file            -m 755 check_hpux_file_age.sh
         file            -m 755 check_hpux_file_change.sh
@@ -71,7 +73,7 @@ This is the OS/platform plugin package"
         file            -m 755 check_hpux_ignite_backup.sh
         file            -m 755 check_hpux_ioscan.sh
         file            -m 755 check_hpux_guid_status.sh
-        file            -m 644 check_hpux_hpvm_vpar_status.sh
+        file            -m 755 check_hpux_hpvm_vpar_status.sh
         file            -m 755 check_hpux_httpd_status.sh
         file            -m 755 check_hpux_kernel_params.sh
         file            -m 755 check_hpux_kernel_usage.sh
@@ -86,6 +88,7 @@ This is the OS/platform plugin package"
         file            -m 755 check_hpux_sshd_status.sh
         file            -m 755 check_hpux_syslog.sh
         file            -m 755 check_hpux_syslogd_status.sh
+        file            -m 755 check_hpux_uptime.sh
         file            -m 755 check_hpux_vg_minor_number.sh
     end
 
@@ -102,6 +105,9 @@ This is the OS/platform plugin package"
         file_permissions -u 0222 -o root -g sys
 
         directory       ../../../etc/opt/hc/=/etc/opt/hc
+        file            -m 644 check_hpux_autofs.conf.dist
+        file            -m 644 check_hpux_cron_status.conf.dist
+        file            -m 644 check_hpux_defunct_processes.conf.dist
         file            -m 644 check_hpux_drd_status.conf.dist
         file            -m 644 check_hpux_file_age.conf.dist
         file            -m 644 check_hpux_file_change.conf.dist
@@ -113,11 +119,12 @@ This is the OS/platform plugin package"
         file            -m 644 check_hpux_kernel_params.conf.dist
         file            -m 644 check_hpux_kernel_usage.conf.dist
         file            -m 644 check_hpux_ntp_status.conf.dist
-        file            -m 755 check_hpux_ovpa_status.conf.dist
-        file            -m 755 check_hpux_patch_version.conf.dist
+        file            -m 644 check_hpux_ovpa_status.conf.dist
+        file            -m 644 check_hpux_patch_version.conf.dist
         file            -m 644 check_hpux_root_crontab.conf.dist
         file            -m 644 check_hpux_sfm_status.conf.dist
         file            -m 644 check_hpux_syslog.conf.dist
+        file            -m 644 check_hpux_uptime.conf.dist
     end
 
     fileset

build/hpux/hc_notify_slack/hc_notify_slack.psf

@@ -0,0 +1,80 @@
+# Depot definition:
+depot
+    layout_version  1.0
+
+# Vendor definition:
+vendor
+        tag             KUDOS
+        title           "KUDOS BVBA - http://www.kudos.be"
+end
+
+# Bundle definitions:
+bundle
+        tag             HC-NOTIFY-SLACK
+        title           "The Health Checker (HC) for UNIX (core SLACK plugin)"
+        os_name         HP-UX
+        revision        %BUILD_DATE%
+        architecture    HP-UX_B.11_32/64
+        machine_type    ia64*
+        vendor_tag      KUDOS
+        contents        HC-NOTIFY-SLACK-MAIN,r=,a=,v=
+end
+
+# Product definitions:
+product
+    tag             HC-NOTIFY-SLACK-MAIN
+    revision        %BUILD_DATE%
+    category        tools
+    category_title  Tools
+    title           "The Health Checker (HC) for UNIX (OS plugins)"
+    description     "The Health Checker is collection of scripts (plugins)
+designed to perform regular - but not intensive - health checks on
+UNIX/Linux systems. It provides plugins for AIX, HP-UX and Linux as
+well customer specific checks. Checks may include topics such file
+system mounts, process checks, file consistency etc.
+This is the core SLACK plugin package"
+    architecture    S700/S800_HP-UX_10/HP-UX_11/IA64_HP-UX_11
+    machine_type    9000/7*|9000/8*|ia64*
+    os_name         HP-UX
+    os_release      ?.1?.*
+    os_version      [A-Z]
+    directory       /opt/hc
+    is_locatable    false
+    is_patch        false
+
+    postinstall     scripts/hc_notify_slack.postinstall
+    postremove      scripts/hc_notify_slack.postremove
+
+    # Fileset definitions:
+    fileset
+        tag             core_plugins
+        title           UX Health Checker (core SLACK plugins)
+        is_kernel       false
+        is_locatable    false
+        is_reboot       false
+        is_sparse       false
+        is_patch        false
+        prerequisite    HC-HPUX-MAIN
+
+        file_permissions -u 0222 -o root -g sys
+
+        directory       ../../../opt/hc/lib/core=/opt/hc/lib/core
+        file            -m 755 notify_slack.sh
+    end
+
+    fileset
+        tag             config
+        title           UX Health Checker (core SLACK plugins: configuration)
+        is_kernel       false
+        is_locatable    false
+        is_reboot       false
+        is_sparse       false
+        is_patch        false
+        prerequisite    HC-NOTIFY-SLACK-MAIN.core_plugins
+
+        file_permissions -u 0222 -o root -g sys
+
+        directory       ../../../etc/opt/hc/core/providers=/etc/opt/hc/core/providers
+        file            -m 644 notify_slack.conf.dist
+    end
+end

build/hpux/hc_notify_slack/scripts/hc_notify_slack.postinstall

@@ -0,0 +1,51 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) post-install script for HC-NOTIFY-SLACK SD package
+#******************************************************************************
+# @(#) Copyright (C) 2022 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of ETC dir
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+print "INFO: starting post-install script ..."
+
+# copy plugin config file from dist (if needed)
+if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_slack.conf ]]
+then
+	cp -p ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist ${HC_ETC_DIR}/core/providers/notify_slack.conf >/dev/null || \
+	{
+		print -u2 "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
+		exit 1
+	}
+fi
+
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+	${HC_BIN} --fix-symlinks || print -u2 "WARN: updating symlinks failed"
+else
+	print -u2 "ERROR: could not locate or excute the HC main script (${HC_BIN})"
+fi
+
+print "INFO: finished post-install script"
+
+exit 0
+
+#******************************************************************************
+# END of script
+#******************************************************************************

build/hpux/hc_notify_slack/scripts/hc_notify_slack.postremove

@@ -0,0 +1,48 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) post-remove script for HC-NOTIFY-SLACK SD package
+#******************************************************************************
+# @(#) Copyright (C) 2022 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+print "INFO: starting post-remove script ..."
+
+# remove plugin configuration file (.dist only)
+if [[ -d ${HC_ETC_DIR}/core/providers ]]
+then
+    rm -f ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist >/dev/null
+    (( $? == 0 )) || echo "WARN: could not remove plugin config file in directory ${HC_ETC_DIR}/core/providers"
+fi
+
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+	${HC_BIN} --fix-symlinks || print -u2 "WARN: updating symlinks failed"
+else
+	print -u2 "ERROR: could not locate or excute the HC main script (${HC_BIN})"
+fi
+
+print "INFO: finished post-remove script"
+
+exit 0
+
+#******************************************************************************
+# END of script
+#******************************************************************************

build/linux/ARCH/hc-linux-platform/PKGBUILD

@@ -19,9 +19,13 @@ package() {
     install -d -m 755 ${pkgdir}/opt/hc/lib
     install -d -m 755 ${pkgdir}/opt/hc/lib/platform
     install -d -m 755 ${pkgdir}/opt/hc/lib/platform/linux
+    install -D -m 755 opt/hc/lib/platform/linux/check_linux_autofs.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_autofs.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_burp_backup.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_burp_backup.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_burp_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_burp_status.sh
+    install -D -m 755 opt/hc/lib/platform/linux/check_linux_dovecot_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_dovecot_status.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_es_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_es_status.sh
+    install -D -m 755 opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh
+    install -D -m 755 opt/hc/lib/platform/linux/check_linux_fetchmail_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_fetchmail_status.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_file_age.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_file_age.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_file_change.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_file_change.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_fs_mounts.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_fs_mounts.sh
@@ -41,11 +45,15 @@ package() {
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_hpssacli.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_hpssacli.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_process_limits.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_process_limits.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_root_crontab.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_root_crontab.sh
+    install -D -m 755 opt/hc/lib/platform/linux/check_linux_uptime.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_uptime.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_vz_ct_counters.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_vz_ct_counters.sh
     install -D -m 755 opt/hc/lib/platform/linux/check_linux_vz_ct_status.sh ${pkgdir}/opt/hc/lib/platform/linux/check_linux_vz_ct_status.sh
     install -d -m 755 ${pkgdir}/etc/opt/hc
+    install -D -m 644 etc/opt/hc/check_linux_autofs.conf.dist ${pkgdir}/etc/opt/hc/check_linux_autofs.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_burp_backup.conf.dist ${pkgdir}/etc/opt/hc/check_linux_burp_backup.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_es_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_es_status.conf.dist
+    install -D -m 644 etc/opt/hc/check_linux_fail2ban_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_fail2ban_status.conf.dist
+    install -D -m 644 etc/opt/hc/check_linux_fetchmail_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_fetchmail_status.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_file_age.conf.dist ${pkgdir}/etc/opt/hc/check_linux_file_age.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_file_change.conf.dist ${pkgdir}/etc/opt/hc/check_linux_file_change.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_fs_usage.conf.dist ${pkgdir}/etc/opt/hc/check_linux_fs_usage.conf.dist
@@ -53,10 +61,12 @@ package() {
     install -D -m 644 etc/opt/hc/check_linux_hpacucli.conf.dist ${pkgdir}/etc/opt/hc/check_linux_hpacucli.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_hplog.conf.dist ${pkgdir}/etc/opt/hc/check_linux_hplog.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_hpssacli.conf.dist ${pkgdir}/etc/opt/hc/check_linux_hpssacli.conf.dist
+    install -D -m 644 etc/opt/hc/check_linux_httpd_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_httpd_status.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_mysqld_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_mysqld_status.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_ntp_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_ntp_status.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_process_limits.conf.dist ${pkgdir}/etc/opt/hc/check_linux_process_limits.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_root_crontab.conf.dist ${pkgdir}/etc/opt/hc/check_linux_root_crontab.conf.dist
+    install -D -m 644 etc/opt/hc/check_linux_uptime.conf.dist ${pkgdir}/etc/opt/hc/check_linux_uptime.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_vz_ct_counters.conf.dist ${pkgdir}/etc/opt/hc/check_linux_vz_ct_counters.conf.dist
     install -D -m 644 etc/opt/hc/check_linux_vz_ct_status.conf.dist ${pkgdir}/etc/opt/hc/check_linux_vz_ct_status.conf.dist
     install -d -m 755 ${pkgdir}/etc/opt/hc/core

build/linux/ARCH/hc-linux/.install

@@ -40,6 +40,34 @@ post_install() {
     else
         echo "ERROR: could not locate or excute the HC main script (${HC_BIN})"
     fi
+    # set SELinux contexts for logrotate
+    SESTATUS_BIN=$(command -v sestatus 2>/dev/null)
+    if [[ -n "${SESTATUS_BIN}" ]]
+    then
+        IS_ENFORCING=$(${SESTATUS_BIN} | grep -c "Current mode.*enforcing" 2>/dev/null)
+        if (( IS_ENFORCING > 0 ))
+        then
+            SEMANAGE_BIN=$(command -v semanage 2>/dev/null)
+            if [[ -n "${SEMANAGE_BIN}" ]]
+            then
+                ${SEMANAGE_BIN} fcontext -a -t var_log_t "${HC_VAR_DIR}(/check_health\.sh\.log.*)?"
+                echo "INFO: SELinux fcontexts configured for log rotation"
+                if [[ -d ${HC_VAR_DIR} ]]
+                then
+                    RESTORECON_BIN=$(command -v restorecon 2>/dev/null)
+                    if [[ -n "${RESTORECON_BIN}" ]]
+                    then
+                        ${RESTORECON_BIN} -Frv ${HC_VAR_DIR}
+                        echo "INFO: SELinux fcontexts set on ${HC_VAR_DIR} for log rotation"
+                    else
+                        echo "WARN: SELinux is set to 'enforcing' but could not found 'restorecon' to set fcontexts for log rotation"
+                    fi
+                fi
+            else
+                echo "WARN: SELinux is set to 'enforcing' but could not found 'semanage' to set fcontexts for log rotation"
+            fi
+        fi
+    fi
     echo "INFO: finished post-install script"
 }
 

build/linux/ARCH/hc-notify-slack/.install

@@ -0,0 +1,33 @@
+# -- post-install --
+post_install() {
+    # ------------------------- CONFIGURATION starts here -------------------------
+    # location of check_health.sh
+    HC_BIN="/opt/hc/bin/check_health.sh"
+    PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+    # ------------------------- CONFIGURATION ends here ---------------------------
+    echo "INFO: starting post-install script ..."
+    # refresh symbolic FPATH links
+    if [[ -x ${HC_BIN} ]]
+    then
+        ${HC_BIN} --fix-symlinks
+        (( $? == 0 )) || echo "WARN: updating symlinks failed"
+    fi
+    echo "INFO: finished post-install script"
+}
+
+# -- post-remove --
+post_remove() {
+    # ------------------------- CONFIGURATION starts here -------------------------
+    # location of check_health.sh
+    HC_BIN="/opt/hc/bin/check_health.sh"
+    PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+    # ------------------------- CONFIGURATION ends here ---------------------------
+    echo "INFO: starting post-uninstall script ..."
+    # refresh symbolic FPATH links
+    if [[ -x ${HC_BIN} ]]
+    then
+        ${HC_BIN} --fix-symlinks
+        (( $? == 0 )) || echo "WARN: updating symlinks failed"
+    fi
+    echo "INFO: finished post-uninstall script"
+}

build/linux/ARCH/hc-notify-slack/PKGBUILD

@@ -0,0 +1,26 @@
+# Maintainer: Patrick Van der Veken <patrick@kudos.be>
+
+_pkgname="check_health"
+pkgname="hc-notify-slack"
+pkgver="%BUILD_DATE%"
+pkgrel=1
+pkgdesc="The KUDOS Health Checker (HC) for UNIX (Slack notify core plugin)"
+arch=("any")
+url="https://github.com/patvdv/${_pkgname}"
+license=('GPL3')
+makedepends=('git')
+depends=('hc-linux')
+source=("${_pkgname}::git+${url}.git#branch=master")
+install=".install"
+sha256sums=('SKIP')
+
+package() {
+    cd "${srcdir}/${_pkgname}"
+    install -d -m 755 ${pkgdir}/opt/hc/lib
+    install -d -m 755 ${pkgdir}/opt/hc/lib/core
+    install -D -m 755 opt/hc/lib/core/notify_slack.sh ${pkgdir}/opt/hc/lib/core/notify_slack.sh
+    install -d -m 755 ${pkgdir}/etc/opt/hc
+    install -d -m 755 ${pkgdir}/etc/opt/hc/core
+    install -d -m 755 ${pkgdir}/etc/opt/hc/core/providers
+    install -D -m 644 etc/opt/hc/core/providers/notify_slack.conf.dist ${pkgdir}/etc/opt/hc/core/providers/notify_slack.conf.dist
+}

build/linux/DEBIAN/hc-display-csv/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (CSV display core plugin).

build/linux/DEBIAN/hc-display-init/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX (init display core plugin).

build/linux/DEBIAN/hc-display-json/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (JSON display core plugin).

build/linux/DEBIAN/hc-display-terse/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (terse display core plugin).

build/linux/DEBIAN/hc-display-zenoss/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (Zenoss display core plugin).

build/linux/DEBIAN/hc-linux-platform/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 300
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX (platform plugins).

build/linux/DEBIAN/hc-linux/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 300
-Depends: ksh
+Depends: ksh, aptitude
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX.

build/linux/DEBIAN/hc-linux/postinst

@@ -16,8 +16,10 @@ chown -R root:root /opt/hc /etc/opt/hc 2>/dev/null
 chown root:root /etc/logrotate.d/check_health 2>/dev/null
 chmod 644 /etc/logrotate.d/check_health 2>/dev/null
 # copy configuration files
-if [[ ! -f ${HC_ETC_DIR}/core/check_health.conf ]]
+if [[ -f ${HC_ETC_DIR}/core/check_health.conf.dist ]]
 then
+    if [[ ! -f ${HC_ETC_DIR}/core/check_health.conf ]]
+    then
         # copy main configuration file
         cp -p ${HC_ETC_DIR}/core/check_health.conf.dist ${HC_ETC_DIR}/core/check_health.conf >/dev/null
         (( $? == 0 )) || \
@@ -25,9 +27,14 @@ then
             echo "ERROR: could not copy main config file in ${HC_ETC_DIR}/core"
             exit 1
         }
+    fi
+else
+    echo "WARN: could not check_health config .dist file in ${HC_ETC_DIR}/core"
 fi
-if [[ ! -f ${HC_ETC_DIR}/check_host.conf ]]
+if [[ -f ${HC_ETC_DIR}/check_host.conf.dist ]]
 then
+    if [[ ! -f ${HC_ETC_DIR}/check_host.conf ]]
+    then
         # copy host check configuration file
         cp -p ${HC_ETC_DIR}/check_host.conf.dist ${HC_ETC_DIR}/check_host.conf >/dev/null
         (( $? == 0 )) || \
@@ -35,6 +42,9 @@ then
             echo "ERROR: could not copy host check config file in ${HC_ETC_DIR}"
             exit 1
         }
+    fi
+else
+    echo "WARN: could not find check_host config .dist file in ${HC_ETC_DIR}"
 fi
 # refresh symbolic FPATH links for core includes & plugins
 if [[ -x ${HC_BIN} ]]
@@ -43,4 +53,32 @@ then
 else
     echo "ERROR: could not locate or excute the HC main script (${HC_BIN})"
 fi
+# set SELinux contexts for logrotate
+SESTATUS_BIN=$(command -v sestatus 2>/dev/null)
+if [[ -n "${SESTATUS_BIN}" ]]
+then
+    IS_ENFORCING=$(${SESTATUS_BIN} | grep -c "Current mode.*enforcing" 2>/dev/null)
+    if (( IS_ENFORCING > 0 ))
+    then
+        SEMANAGE_BIN=$(command -v semanage 2>/dev/null)
+        if [[ -n "${SEMANAGE_BIN}" ]]
+        then
+            ${SEMANAGE_BIN} fcontext -a -t var_log_t "${HC_VAR_DIR}(/check_health\.sh\.log.*)?"
+            echo "INFO: SELinux fcontexts configured for log rotation"
+            if [[ -d ${HC_VAR_DIR} ]]
+            then
+                RESTORECON_BIN=$(command -v restorecon 2>/dev/null)
+                if [[ -n "${RESTORECON_BIN}" ]]
+                then
+                    ${RESTORECON_BIN} -Frv ${HC_VAR_DIR}
+                    echo "INFO: SELinux fcontexts set on ${HC_VAR_DIR} for log rotation"
+                else
+                    echo "WARN: SELinux is set to 'enforcing' but could not found 'restorecon' to set fcontexts for log rotation"
+                fi
+            fi
+        else
+            echo "WARN: SELinux is set to 'enforcing' but could not found 'semanage' to set fcontexts for log rotation"
+        fi
+    fi
+fi
 echo "INFO: finished post-install script"

build/linux/DEBIAN/hc-linux/postrm

@@ -10,8 +10,9 @@ HC_VAR_DIR="/var/opt/hc"
 echo "INFO: starting post-uninstall script ..."
 if [[ -d ${HC_DIR} ]]
 then
-    rm -rf ${HC_DIR} 2>/dev/null
-    (( $? == 0 )) || echo "WARN: failed to remove ${HC_DIR}"
+    # remove all symlinks
+    find ${HC_DIR} -type l -exec rm -f {} \; 2>/dev/null
+    (( $? == 0 )) || echo "WARN: failed to remove symlinks in ${HC_DIR}"
 fi
 if [[ -d ${HC_ETC_DIR} ]]
 then

build/linux/DEBIAN/hc-notify-eif/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (EIF notify core plugin).

build/linux/DEBIAN/hc-notify-eif/postinst

@@ -10,14 +10,19 @@ echo "INFO: starting post-install script ..."
 # debian: reset ownerships
 chown -R root:root /opt/hc /etc/opt/hc 2>/dev/null
 # copy plugin configuration file
-if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_eif.conf ]]
+if [[ -f ${HC_ETC_DIR}/core/providers/notify_eif.conf.dist ]]
 then
+    if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_eif.conf ]]
+    then
         cp -p ${HC_ETC_DIR}/core/providers/notify_eif.conf.dist ${HC_ETC_DIR}/core/providers/notify_eif.conf >/dev/null
         (( $? == 0 )) || \
         {
             echo "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
             exit 1
         }
+    fi
+else
+    echo "WARN: could not find plugin config .dist file in ${HC_ETC_DIR}/core/providers"
 fi
 # refresh symbolic FPATH links
 if [[ -x ${HC_BIN} ]]

build/linux/DEBIAN/hc-notify-slack/control

@@ -0,0 +1,10 @@
+Package: hc-notify-slack
+Version: %BUILD_DATE%
+Architecture: all
+Maintainer: Patrick Van der Veken <patrick@kudos.be>
+Essential: no
+Installed-Size: 50
+Pre-Depends: hc-linux
+Section: tools
+Priority: extra
+Description: The KUDOS Health Checker (HC) for UNIX (Slack notify core plugin).

build/linux/DEBIAN/hc-notify-slack/postinst

@@ -0,0 +1,33 @@
+#!/bin/bash
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+echo "INFO: starting post-install script ..."
+# debian: reset ownerships
+chown -R root:root /opt/hc /etc/opt/hc 2>/dev/null
+# copy plugin configuration file
+if [[ -f ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist ]]
+then
+    if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_slack.conf ]]
+    then
+        cp -p ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist ${HC_ETC_DIR}/core/providers/notify_slack.conf >/dev/null
+        (( $? == 0 )) || \
+        {
+            echo "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
+            exit 1
+        }
+    fi
+else
+    echo "WARN: could not find plugin config .dist file in ${HC_ETC_DIR}/core/providers"
+fi
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+    ${HC_BIN} --fix-symlinks
+    (( $? == 0 )) || echo "WARN: updating symlinks failed"
+fi
+echo "INFO: finished post-install script"

build/linux/DEBIAN/hc-notify-slack/postrm

@@ -0,0 +1,32 @@
+#!/bin/bash
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+# update or uninstall?
+if (( $1 == 0 ))
+then
+    echo "INFO: starting post-uninstall script ..."
+    # copy plugin configuration file (.dist only)
+    if [[ -d ${HC_ETC_DIR}/core/providers ]]
+    then
+        rm -f ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist 2>/dev/null
+        (( $? == 0 )) || \
+        {
+            echo "ERROR: could not remove plugin config file in ${HC_ETC_DIR}/core/providers"
+            exit 1
+        }
+    fi
+else
+    echo "INFO: starting post-uninstall script (RPM upgrade)"
+fi
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+    ${HC_BIN} --fix-symlinks
+    (( $? == 0 )) || echo "WARN: updating symlinks failed"
+fi
+echo "INFO: finished post-uninstall script"

build/linux/DEBIAN/hc-notify-sms/control

@@ -4,7 +4,7 @@ Architecture: all
 Maintainer: Patrick Van der Veken <patrick@kudos.be>
 Essential: no
 Installed-Size: 50
-Depends: hc-linux
+Pre-Depends: hc-linux
 Section: tools
 Priority: extra
 Description: The KUDOS Health Checker (HC) for UNIX  (SMS notify core plugin).

build/linux/DEBIAN/hc-notify-sms/postinst

@@ -10,14 +10,19 @@ echo "INFO: starting post-install script ..."
 # debian: reset ownerships
 chown -R root:root /opt/hc /etc/opt/hc 2>/dev/null
 # copy plugin configuration file
-if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_sms.conf ]]
+if [[ -f ${HC_ETC_DIR}/core/providers/notify_sms.conf.dist ]]
 then
+    if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_sms.conf ]]
+    then
         cp -p ${HC_ETC_DIR}/core/providers/notify_sms.conf.dist ${HC_ETC_DIR}/core/providers/notify_sms.conf >/dev/null
         (( $? == 0 )) || \
         {
             echo "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
             exit 1
         }
+    fi
+else
+    echo "WARN: could not find plugin config .dist file in ${HC_ETC_DIR}/core/providers"
 fi
 # refresh symbolic FPATH links
 if [[ -x ${HC_BIN} ]]

build/linux/SPECS/hc-linux-platform.spec

@@ -27,9 +27,13 @@ rm -rf $RPM_BUILD_ROOT
 install -d -m 755 $RPM_BUILD_ROOT/opt/hc/lib
 install -d -m 755 $RPM_BUILD_ROOT/opt/hc/lib/platform
 install -d -m 755 $RPM_BUILD_ROOT/opt/hc/lib/platform/linux
+cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_autofs.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_autofs.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_burp_backup.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_burp_backup.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_burp_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_burp_status.sh
+cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_dovecot_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_dovecot_status.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_es_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_es_status.sh
+cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh
+cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_fetchmail_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_fetchmail_status.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_file_age.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_file_age.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_file_change.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_file_change.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_fs_mounts.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_fs_mounts.sh
@@ -49,11 +53,15 @@ cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_hplog.sh $RPM_BUILD_ROOT/opt
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_hpssacli.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_hpssacli.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_process_limits.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_process_limits.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_root_crontab.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_root_crontab.sh
+cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_uptime.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_uptime.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_vz_ct_counters.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_vz_ct_counters.sh
 cp ../SOURCES/opt/hc/lib/platform/linux/check_linux_vz_ct_status.sh $RPM_BUILD_ROOT/opt/hc/lib/platform/linux/check_linux_vz_ct_status.sh
 install -d -m 755 $RPM_BUILD_ROOT/etc/opt/hc
+cp ../SOURCES/etc/opt/hc/check_linux_autofs.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_autofs.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_burp_backup.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_burp_backup.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_es_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_es_status.conf.dist
+cp ../SOURCES/etc/opt/hc/check_linux_fail2ban_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_fail2ban_status.conf.dist
+cp ../SOURCES/etc/opt/hc/check_linux_fetchmail_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_fetchmail_status.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_file_age.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_file_age.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_file_change.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_file_change.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_fs_usage.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_fs_usage.conf.dist
@@ -61,10 +69,12 @@ cp ../SOURCES/etc/opt/hc/check_linux_hpasmcli.conf.dist $RPM_BUILD_ROOT/etc/opt/
 cp ../SOURCES/etc/opt/hc/check_linux_hpacucli.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_hpacucli.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_hplog.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_hplog.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_hpssacli.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_hpssacli.conf.dist
+cp ../SOURCES/etc/opt/hc/check_linux_httpd_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_httpd_status.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_mysqld_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_mysqld_status.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_ntp_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_ntp_status.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_process_limits.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_process_limits.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_root_crontab.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_root_crontab.conf.dist
+cp ../SOURCES/etc/opt/hc/check_linux_uptime.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_uptime.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_vz_ct_counters.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_vz_ct_counters.conf.dist
 cp ../SOURCES/etc/opt/hc/check_linux_vz_ct_status.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/check_linux_vz_ct_status.conf.dist
 install -d -m 755 $RPM_BUILD_ROOT/etc/opt/hc/core
@@ -107,9 +117,13 @@ echo "INFO: finished post-uninstall script"
 %dir /opt/hc/lib
 %dir /opt/hc/lib/platform
 %dir /opt/hc/lib/platform/linux
+%attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_autofs.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_burp_backup.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_burp_status.sh
+%attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_dovecot_status.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_es_status.sh
+%attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh
+%attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_fetchmail_status.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_file_age.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_file_change.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_fs_mounts.sh
@@ -129,11 +143,15 @@ echo "INFO: finished post-uninstall script"
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_hpssacli.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_process_limits.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_root_crontab.sh
+%attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_uptime.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_vz_ct_counters.sh
 %attr(755, root, root) /opt/hc/lib/platform/linux/check_linux_vz_ct_status.sh
 %dir /etc/opt/hc
+%attr(644, root, root) /etc/opt/hc/check_linux_autofs.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_burp_backup.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_es_status.conf.dist
+%attr(644, root, root) /etc/opt/hc/check_linux_fail2ban_status.conf.dist
+%attr(644, root, root) /etc/opt/hc/check_linux_fetchmail_status.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_file_age.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_file_change.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_fs_usage.conf.dist
@@ -141,10 +159,12 @@ echo "INFO: finished post-uninstall script"
 %attr(644, root, root) /etc/opt/hc/check_linux_hpacucli.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_hplog.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_hpssacli.conf.dist
+%attr(644, root, root) /etc/opt/hc/check_linux_httpd_status.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_mysqld_status.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_ntp_status.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_process_limits.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_root_crontab.conf.dist
+%attr(644, root, root) /etc/opt/hc/check_linux_uptime.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_vz_ct_counters.conf.dist
 %attr(644, root, root) /etc/opt/hc/check_linux_vz_ct_status.conf.dist
 %dir /etc/opt/hc/core
@@ -153,6 +173,17 @@ echo "INFO: finished post-uninstall script"
 %attr(644, root, root) /etc/opt/hc/core/templates/mail_body.tpl-check_linux_root_crontab
 
 %changelog
+* Sat Dec 26 2020 <patrick@kudos.be> - 0.3.5
+- Added check_linux_fetchmail_status plugin
+- Added check_linux_dovecot_status plugin
+* Mon Dec 21 2020 <patrick@kudos.be> - 0.3.4
+- Added check_linux_uptime plugin
+* Fri Oct 18 2020 <patrick@kudos.be> - 0.3.3
+- Added check_linux_fail2ban_status plugin
+* Fri Nov  1 2019 <patrick@kudos.be> - 0.3.2
+- Added configuration file for check_linux_httpd_status plugin
+* Sun Jul 14 2019 <patrick@kudos.be> - 0.3.1
+- Removed check_linux_autofs plugin
 * Sat Apr 20 2019 <patrick@kudos.be> - 0.3.0
 - Removed Serviceguard plugins
 * Tue Mar 26 2019 <patrick@kudos.be> - 0.2.0

build/linux/SPECS/hc-linux.spec

@@ -88,6 +88,34 @@ then
 else
     echo "ERROR: could not locate or excute the HC main script (${HC_BIN})"
 fi
+# set SELinux contexts for logrotate
+SESTATUS_BIN=$(command -v sestatus 2>/dev/null)
+if [[ -n "${SESTATUS_BIN}" ]]
+then
+    IS_ENFORCING=$(${SESTATUS_BIN} | grep -c "Current mode.*enforcing" 2>/dev/null)
+    if (( IS_ENFORCING > 0 ))
+    then
+        SEMANAGE_BIN=$(command -v semanage 2>/dev/null)
+        if [[ -n "${SEMANAGE_BIN}" ]]
+        then
+            ${SEMANAGE_BIN} fcontext -a -t var_log_t "${HC_VAR_DIR}(/check_health\.sh\.log.*)?"
+            echo "INFO: SELinux fcontexts configured for log rotation"
+            if [[ -d ${HC_VAR_DIR} ]]
+            then
+                RESTORECON_BIN=$(command -v restorecon 2>/dev/null)
+                if [[ -n "${RESTORECON_BIN}" ]]
+                then
+                    ${RESTORECON_BIN} -Frv ${HC_VAR_DIR}
+                    echo "INFO: SELinux fcontexts set on ${HC_VAR_DIR} for log rotation"
+                else
+                    echo "WARN: SELinux is set to 'enforcing' but could not found 'restorecon' to set fcontexts for log rotation"
+                fi
+            fi
+        else
+            echo "WARN: SELinux is set to 'enforcing' but could not found 'semanage' to set fcontexts for log rotation"
+        fi
+    fi
+fi
 echo "INFO: finished post-install script"
 
 %postun

build/linux/SPECS/hc-notify-slack.spec

@@ -0,0 +1,107 @@
+%define build_timestamp %(date +"%Y%m%d")
+
+Name:           hc-notify-slack
+Version:        %{build_timestamp}
+Release:        1
+
+Summary:        The KUDOS Health Checker (HC) for UNIX (Slack notify core plugin)
+Group:          Tools/Monitoring
+
+License:        GNU General Public License either version 2 of the License, or (at your option) any later version
+URL:            http://www.kudos.be
+
+Requires:       ksh,hc-linux
+BuildArch:      noarch
+BuildRoot:      %{_topdir}/%{name}-%{version}-root
+
+%description
+The Health Checker is collection of scripts (plugins) designed to perform regular - but not intensive - health checks on UNIX/Linux systems. It provides plugins for AIX, HP-UX and Linux as well customer specific checks. Checks may include topics such file system mounts, process checks, file consistency etc.
+This package contains core plugins (notify).
+
+%prep
+
+%build
+
+%install
+rm -rf $RPM_BUILD_ROOT
+install -d -m 755 $RPM_BUILD_ROOT/opt/hc/lib
+install -d -m 755 $RPM_BUILD_ROOT/opt/hc/lib/core
+cp ../SOURCES/opt/hc/lib/core/notify_slack.sh $RPM_BUILD_ROOT/opt/hc/lib/core/notify_slack.sh
+install -d -m 755 $RPM_BUILD_ROOT/etc/opt/hc
+install -d -m 755 $RPM_BUILD_ROOT/etc/opt/hc/core
+install -d -m 755 $RPM_BUILD_ROOT/etc/opt/hc/core/providers
+cp ../SOURCES/etc/opt/hc/core/providers/notify_slack.conf.dist $RPM_BUILD_ROOT/etc/opt/hc/core/providers/notify_slack.conf.dist
+
+%post
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+echo "INFO: starting post-install script ..."
+# copy plugin configuration file
+if [[ ! -f ${HC_ETC_DIR}/core/providers/notify_slack.conf ]]
+then
+    cp -p ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist ${HC_ETC_DIR}/core/providers/notify_slack.conf >/dev/null
+    (( $? == 0 )) || \
+    {
+        echo "ERROR: could not copy plugin config file in ${HC_ETC_DIR}/core/providers"
+        exit 1
+    }
+fi
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+    ${HC_BIN} --fix-symlinks
+    (( $? == 0 )) || echo "WARN: updating symlinks failed"
+fi
+echo "INFO: finished post-install script"
+
+%postun
+# ------------------------- CONFIGURATION starts here -------------------------
+# location of the HC configuration files
+HC_ETC_DIR="/etc/opt/hc"
+# location of check_health.sh
+HC_BIN="/opt/hc/bin/check_health.sh"
+PATH="$PATH:/usr/bin:/etc:/usr/sbin:/usr/ucb:/usr/bin/X11:/sbin"
+# ------------------------- CONFIGURATION ends here ---------------------------
+# update or uninstall?
+if (( $1 == 0 ))
+then
+    echo "INFO: starting post-uninstall script ..."
+    # copy plugin configuration file (.dist only)
+    if [[ -d ${HC_ETC_DIR}/core/providers ]]
+    then
+        rm -f ${HC_ETC_DIR}/core/providers/notify_slack.conf.dist 2>/dev/null
+        (( $? == 0 )) || \
+        {
+            echo "ERROR: could not remove plugin config file in ${HC_ETC_DIR}/core/providers"
+            exit 1
+        }
+    fi
+else
+    echo "INFO: starting post-uninstall script (RPM upgrade)"
+fi
+# refresh symbolic FPATH links
+if [[ -x ${HC_BIN} ]]
+then
+    ${HC_BIN} --fix-symlinks
+    (( $? == 0 )) || echo "WARN: updating symlinks failed"
+fi
+echo "INFO: finished post-uninstall script"
+
+%files
+%defattr(-,root,root,755)
+%dir /opt/hc/lib
+%dir /opt/hc/lib/core
+%attr(755, root, root) /opt/hc/lib/core/notify_slack.sh
+%dir /etc/opt/hc
+%dir /etc/opt/hc/core
+%dir /etc/opt/hc/core/providers
+%attr(644, root, root) /etc/opt/hc/core/providers/notify_slack.conf.dist
+
+%changelog
+* Sun Oct 14 2022 <patrick@kudos.be> - 0.0.1
+- Initial build

build/linux/hc_build_linux_rpms.sh

@@ -47,6 +47,7 @@ rpmbuild -bb ${BUILD_DIR}/SPECS/hc-linux-platform.spec
 # build core plugins
 rpmbuild -bb ${BUILD_DIR}/SPECS/hc-notify-eif.spec
 rpmbuild -bb ${BUILD_DIR}/SPECS/hc-notify-sms.spec
+rpmbuild -bb ${BUILD_DIR}/SPECS/hc-notify-slack.spec
 rpmbuild -bb ${BUILD_DIR}/SPECS/hc-display-init.spec
 rpmbuild -bb ${BUILD_DIR}/SPECS/hc-display-json.spec
 rpmbuild -bb ${BUILD_DIR}/SPECS/hc-display-csv.spec

etc/opt/hc/check_aix_sysbackup.conf.dist

@@ -13,9 +13,11 @@ log_healthy="no"
 
 # full path to the location of mksysb images, the tool expects sub-directories
 # per host underneath this location
+# [default: /export/images]
 backup_path=/export/images
 
 # name of the file containing the mksysb output
+# [default: mksysb.log]
 mksysb_log=mksysb.log
 
 # maximum days before backup gets flagged as 'too old'

etc/opt/hc/check_aix_uptime.conf.dist

@@ -0,0 +1,41 @@
+#******************************************************************************
+# @(#) check_aix_uptime.conf
+#******************************************************************************
+# This is a configuration file for the check_aix_uptime HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# trigger event when current uptime is less than previously record uptime?
+# [default: yes]
+check_reboot="yes"
+
+# time to wait before the current uptime is considered for the reboot check.
+# Example: a value of 60m means the check for a previous reboot will be at earliest
+#          performed 1 hour after the last reboot of the host.
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 60m]
+reboot_time="60m"
+
+# trigger event when current uptime goes over the maximum threshold?
+# [default: no]
+check_old_age="no"
+
+# time to expire before the current uptime is considered "old age".
+# Example: a value of 365d means a must-reboot will be flagged at earliest after
+#          1 year of uptime of the host
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 365d]
+old_age_time="365d"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_exadata_cell_megaraid.conf.dist

@@ -27,6 +27,10 @@ check_controller="yes"
 # [default: yes]
 check_bbu="yes"
 
+# specify whether to check the BBU (supercap) state (yes|no)
+# [default: yes]
+check_supercap="yes"
+
 # specify whether to check the physical devices (yes|no)
 # [default: yes]
 check_physical="yes"
@@ -35,6 +39,14 @@ check_physical="yes"
 # [default: yes]
 check_virtual="yes"
 
+# individual checks that should be disabled (wildcards are not supported)
+#  cell_exclude:<cell_server>:<controller|bbu|supercap|physical|virtual>
+# Examples:
+# disable controller check on mycell1
+# cell_exclude:mycell1:controller
+# disable bbu check on mycell2
+# cell_exclude:mycell2:bbu
+
 
 #******************************************************************************
 # End of FILE

etc/opt/hc/check_exadata_megaraid.conf.dist

@@ -19,6 +19,10 @@ check_controller="yes"
 # [default: yes]
 check_bbu="yes"
 
+# specify whether to check the BBU (supercap) state (yes|no)
+# [default: yes]
+check_supercap="yes"
+
 # specify whether to check the physical devices (yes|no)
 # [default: yes]
 check_physical="yes"

etc/opt/hc/check_exadata_zfs_cluster.conf.dist

@@ -0,0 +1,35 @@
+#******************************************************************************
+# @(#) check_exadata_zfs_cluster.conf
+#******************************************************************************
+# This is a configuration file for the check_exadata_zfs_cluster HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="yes"
+
+# specify the user account for the SSH session to the ZFS appliance(s)
+# [default: root]
+ssh_user=""
+
+# specify the private key file for the SSH session to the ZFS appliance(s)
+# [default: ~root/.ssh/id_rsa]
+ssh_key_file=""
+
+# specify additional options for the SSH session to the ZFS appliance(s)
+# [default: null]
+ssh_opts=""
+
+# specify the ZFS hostname(s) to check the cluster states on
+# Format:
+#  zfs:<host_name>
+# Examples:
+# zfs:myzfs1
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_exadata_zfs_logs.conf.dist

@@ -1,7 +1,7 @@
 #******************************************************************************
-# @(#) check_exadata_zfs_share_usage.conf
+# @(#) check_exadata_zfs_logs.conf
 #******************************************************************************
-# This is a configuration file for the check_exadata_zfs_share_usage HC plugin.
+# This is a configuration file for the check_exadata_zfs_logs HC plugin.
 # All lines starting with a '#' are comment lines.
 # [default: indicates hardcoded script values if no value is defined here]
 #******************************************************************************

etc/opt/hc/check_exadata_zfs_share_replication.conf.dist

@@ -33,21 +33,26 @@ max_replication_lag=300
 # will for this given share will be skipped (this allows for exclusion of shares)
 # In order to check share(s) for a given ZFS appliance at least one configuration
 # entry must be present: either a wildcard or custom entry.
+# Caveat: any share must finally resolve to one entry only.
 # Format:
-#  zfs:<host_name>:<replication_name|*>:<true|false|*>:<success|failed|*>:[<max_replication_lag>]
+#  zfs:<host_name>:<replication_name|*>:<true|false|*>:<success|failed|*>:[<max_replication_lag>]:[day1,day2,..|*>]:[<hour|<start_hour-end_hour>|*>]
+#
+#   <day>: 3 letter day name (case insensitive)
+#   <hour>: 24 hours notation (start and end hours are inclusive)
+#
 # Examples:
-# check rep_share1 on myzfs1 with a custom threshold of 300 seconds
-# zfs:myzfs1:rep_share1:*:*:600
-# check all shares of myzfs2 with a custom threshold of 1200 seconds
-# zfs:myzfs2:*:*:*:1200
-# check all shares of myzfs3 with the general threshold
-# zfs:myzfs3:*:*:*:
+# check rep_share1 on myzfs1 with a custom threshold of 300 seconds on every day of the week
+# zfs:myzfs1:rep_share1:*:*:600:*
+# check all shares of myzfs2 with a custom threshold of 1200 seconds on Sunday and Monday
+# zfs:myzfs2:*:*:*:1200:Sun,Mon
+# check all shares of myzfs3 with the general threshold but only on Friday between 7am-10m
+# zfs:myzfs3:*:*:*:Fri:07-10
 # disable all shares of myzfs4 from checking
-# zfs:myzfs4:*:*:*:0
+# zfs:myzfs4:*:*:*:0:*
 # disable check of rep_share7 on myzfs5
-# zfs:myzfs5:rep_share7:*:*:0
-# check that rep_share4 on myzfs6 is inactive
-# zfs:myzfs6:rep_share4:false:*:
+# zfs:myzfs5:rep_share7:*:*:0:*
+# check that rep_share4 on myzfs6 is inactive (every day of the week)
+# zfs:myzfs6:rep_share4:false:*:*
 
 
 #******************************************************************************

etc/opt/hc/check_exadata_zfs_share_usage.conf.dist

@@ -33,6 +33,7 @@ max_space_usage=90
 # will for this given share will be skipped (this allows for exclusion of shares)
 # In order to check share(s) for a given ZFS appliance at least one configuration
 # entry must be present: either a wildcard or custom entry.
+# Caveat: any share must finally resolve to one entry only.
 # Format:
 #  zfs:<host_name>:<project_name|*>:<share_name|*>:[<usage_threshold_%>]
 # Examples:

etc/opt/hc/check_hpux_autofs.conf.dist

@@ -0,0 +1,31 @@
+#******************************************************************************
+# @(#) check_hpux_autofs.conf
+#******************************************************************************
+# This is a configuration file for the check_hpux_autofs HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify whether to fix autofs (if needed)
+# [default: no]
+fix_autofs="no"
+
+# number of times to attempt to restart the autofs daemon
+# (requires fix_autofs=yes)
+# [default: 3]
+retry_start=3
+
+# number of seconds to sleep between daemon restart attempts
+# (requires fix_autofs=yes)
+# [default: 5]
+sleep_time=5
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_hpux_cron_status.conf.dist

@@ -0,0 +1,25 @@
+#******************************************************************************
+# @(#) check_hpux_cron_status.conf
+#******************************************************************************
+# This is a configuration file for the check_hpux_cron_status HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify the wait time (in seconds) between registering and checking a cron task
+# [default: 10]
+wait_time=10
+
+# specify the path the cron log file
+# [default: /var/adm/cron/log]
+cron_log="/var/adm/cron/log"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_hpux_defunct_processes.conf.dist

@@ -0,0 +1,27 @@
+#******************************************************************************
+# @(#) check_hpux_defunct_processes.conf
+#******************************************************************************
+# This is a configuration file for the check_hpux_defunct_processes HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="yes"
+
+# specify above which threshold of defunct processes to generate a HC fail event
+# If group_by_ppid is set to 'yes' then the value of 'process_threshold' will
+# apply for each PPID, otherwise it will apply to all defunct processes together
+# [default: 10]
+process_threshold=10
+
+# specify whether to group by parent ID or not.
+# [default: yes]
+group_by_ppid="yes"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_hpux_fs_usage.conf.dist

@@ -32,7 +32,7 @@ max_space_usage=90
 # defining a threshold of 0 (zero), then the check will for this give filesystem
 # will be skipped (this allows for exclusion of filesystems)
 # Format:
-#  fs:<mount_point>:[<max_inode_usage_%>]:[<max_space_usage_%]
+#  fs:<mount_point>:[<max_inodes_usage_%>]:[<max_space_usage_%]
 # Examples:
 # check myfs1 with a custom inodes + space usage threshold
 #fs:myfs1:70:95

etc/opt/hc/check_hpux_hpvm_vpar_status.conf.dist

@@ -11,7 +11,7 @@
 # [default: no]
 log_healthy="no"
 
-# specify properties as displayed by the 'vzlist -a -H -o ctid,status,onboot' command
+# specify properties as displayed by the 'hpvmstatus -M' command
 # Format:
 #  [vpar:<parid>:<runtime_status>:<boot_status>]
 # runtime_status should be 'on' or 'off'

etc/opt/hc/check_hpux_uptime.conf.dist

@@ -0,0 +1,41 @@
+#******************************************************************************
+# @(#) check_hpux_uptime.conf
+#******************************************************************************
+# This is a configuration file for the check_hpux_uptime HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# trigger event when current uptime is less than previously record uptime?
+# [default: yes]
+check_reboot="yes"
+
+# time to wait before the current uptime is considered for the reboot check.
+# Example: a value of 60m means the check for a previous reboot will be at earliest
+#          performed 1 hour after the last reboot of the host.
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 60m]
+reboot_time="60m"
+
+# trigger event when current uptime goes over the maximum threshold?
+# [default: no]
+check_old_age="no"
+
+# time to expire before the current uptime is considered "old age".
+# Example: a value of 365d means a must-reboot will be flagged at earliest after
+#          1 year of uptime of the host
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 365d]
+old_age_time="365d"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_autofs.conf.dist

@@ -0,0 +1,31 @@
+#******************************************************************************
+# @(#) check_linux_autofs.conf
+#******************************************************************************
+# This is a configuration file for the check_linux_autofs HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify whether to fix autofs (if needed)
+# [default: no]
+fix_autofs="no"
+
+# number of times to attempt to restart the autofs daemon
+# (requires fix_autofs=yes)
+# [default: 3]
+retry_start=3
+
+# number of seconds to sleep between daemon restart attempts
+# (requires fix_autofs=yes)
+# [default: 5]
+sleep_time=5
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_fail2ban_status.conf.dist

@@ -0,0 +1,27 @@
+#******************************************************************************
+# @(#) check_linux_fail2ban_status.conf
+#******************************************************************************
+# This is a configuration file for the check_linux_fail2ban_status HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify which type of process check to use
+# Format: <auto|pgrep|sysv|systemd>. NULL value equals to "auto"
+# [default: auto]
+check_type="auto"
+
+# specify the list jails to status check (comma-separated)
+# Format: jail1,jail2,jail3,...
+# [default: none]
+check_jails=""
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_fetchmail_status.conf.dist

@@ -0,0 +1,28 @@
+#******************************************************************************
+# @(#) check_linux_fetchmail_status.conf
+#******************************************************************************
+# This is a configuration file for the check_linux_fetchmail_status HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify the regex of error codes that will be used to search the log file_path
+# [default: error|authfail|lockbusy|ioerr]
+error_regex="error|authfail|lockbusy|ioerr"
+
+# specify fetchmail details
+# Format:
+#   fetchmail:<account>:<rc_file>:<check_log=Yes|No>
+# Examples:
+#fetchmail:vmail:/srv/vmail/janedoe/.fetchmailrc:Yes
+#fetchmail:vmail:/srv/vmail/johndoe/.fetchmailrc:No
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_fs_usage.conf.dist

@@ -32,7 +32,7 @@ max_space_usage=90
 # defining a threshold of 0 (zero), then the check will for this give filesystem
 # will be skipped (this allows for exclusion of filesystems)
 # Format:
-#  fs:<mount_point>:[<max_inode_usage_%>]:[<max_space_usage_%]
+#  fs:<mount_point>:[<max_inodes_usage_%>]:[<max_space_usage_%]
 # Examples:
 # check myfs1 with a custom inodes + space usage threshold
 #fs:myfs1:70:95

etc/opt/hc/check_linux_hpacucli.conf.dist

@@ -12,18 +12,23 @@
 log_healthy="no"
 
 # location of 'hpacucli' tool
+# [default: /usr/sbin/hpacucli]
 hpacucli_bin="/usr/sbin/hpacucli"
 
-# controller all show status (0=off, 1=on) [default: 1]
+# controller all show status (0=off, 1=on)
+# [default: 1]
 do_acu_controller=1
 
-# controller slot=X enclosure all show (0=off, 1=on) [default: 1]
+# controller slot=X enclosure all show (0=off, 1=on)
+# [default: 1]
 do_acu_enclosure=1
 
-# controller slot=X physicaldrive all show status (0=off, 1=on) [default: 1]
+# controller slot=X physicaldrive all show status (0=off, 1=on)
+# [default: 1]
 do_acu_physical=1
 
-#  controller slot=X logicaldrive all show status (0=off, 1=on) [default: 1]
+#  controller slot=X logicaldrive all show status (0=off, 1=on)
+# [default: 1]
 do_acu_logical=1
 
 

etc/opt/hc/check_linux_hpasmcli.conf.dist

@@ -12,21 +12,27 @@
 log_healthy="no"
 
 # location of 'hpasmcli' tool
+# [default: /sbin/hpasmcli]
 hpasmcli_bin="/sbin/hpasmcli"
 
-# SHOW FANS (0=off, 1=on) [default: 1]
+# SHOW FANS (0=off, 1=on)
+# [default: 1]
 do_asm_fans=1
 
-# SHOW DIMM (0=off, 1=on) [default: 1]
+# SHOW DIMM (0=off, 1=on)
+# [default: 1]
 do_asm_dimm=1
 
-# SHOW POWERSUPPLY (0=off, 1=on) [default: 1]
+# SHOW POWERSUPPLY (0=off, 1=on)
+# [default: 1]
 do_asm_powersupply=1
 
-# SHOW SERVER (0=off, 1=on) [default: 1]
+# SHOW SERVER (0=off, 1=on)
+# [default: 1]
 do_asm_server=1
 
-# SHOW TEMPERATURE (0=off, 1=on) [default: 1]
+# SHOW TEMPERATURE (0=off, 1=on)
+# [default: 1]
 do_asm_temperature=1
 
 

etc/opt/hc/check_linux_hplog.conf.dist

@@ -12,6 +12,7 @@
 log_healthy="no"
 
 # location of 'hpacucli' tool
+# [default: /sbin/hplog]
 hplog_bin="/sbin/hplog"
 
 # comma-separated list of severities to search for (case insensitive)

etc/opt/hc/check_linux_hpssacli.conf.dist

@@ -12,18 +12,23 @@
 log_healthy="no"
 
 # location of 'hpssacli' tool
+# [default: /usr/sbin/hpssacli]
 hpssacli_bin="/usr/sbin/hpssacli"
 
-# controller all show status (0=off, 1=on) [default: 1]
+# controller all show status (0=off, 1=on)
+# [default: 1]
 do_ssa_controller=1
 
-# controller slot=X enclosure all show (0=off, 1=on) [default: 1]
+# controller slot=X enclosure all show (0=off, 1=on)
+# [default: 1]
 do_ssa_enclosure=1
 
-# controller slot=X physicaldrive all show status (0=off, 1=on) [default: 1]
+# controller slot=X physicaldrive all show status (0=off, 1=on)
+# [default: 1]
 do_ssa_physical=1
 
-#  controller slot=X logicaldrive all show status (0=off, 1=on) [default: 1]
+# controller slot=X logicaldrive all show status (0=off, 1=on)
+# [default: 1]
 do_ssa_logical=1
 
 #******************************************************************************

etc/opt/hc/check_linux_httpd_status.conf.dist

@@ -0,0 +1,34 @@
+#******************************************************************************
+# @(#) check_linux_httpd_status.conf
+#******************************************************************************
+# This is a configuration file for the check_linux_httpd_status HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# specify which type of process check to use
+# Format: <auto|pgrep|sysv|systemd>. NULL value equals to "auto"
+# [default: auto]
+# [release >20191101]
+check_type="auto"
+
+# specify name of the httpd binary
+# Format: httpd|apache|apache2
+# [default: httpd]
+# [release >20201010]
+httpd_bin="httpd"
+
+# specify custom path to the httpd binary
+# [default: null]
+# [release >20201010]
+httpd_path=""
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_ntp_status.conf.dist

@@ -19,6 +19,11 @@ force_chrony="no"
 # [default: no]
 force_ntp="no"
 
+# whether to force the use of systemd-timesyncd?
+# [default: no]
+# [release >20220129]
+force_systemd="no"
+
 # maximum allowed offset (in milliseconds (positive integers only)
 # [default: 500]
 max_offset=500

etc/opt/hc/check_linux_uptime.conf.dist

@@ -0,0 +1,41 @@
+#******************************************************************************
+# @(#) check_linux_uptime.conf
+#******************************************************************************
+# This is a configuration file for the check_linux_uptime HC plugin.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# specify whether to also log passed health checks
+# (warning: this may rapidly grow the HC log)
+# [default: no]
+log_healthy="no"
+
+# trigger event when current uptime is less than previously record uptime?
+# [default: yes]
+check_reboot="yes"
+
+# time to wait before the current uptime is considered for the reboot check.
+# Example: a value of 60m means the check for a previous reboot will be at earliest
+#          performed 1 hour after the last reboot of the host.
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 60m]
+reboot_time="60m"
+
+# trigger event when current uptime goes over the maximum threshold?
+# [default: no]
+check_old_age="no"
+
+# time to expire before the current uptime is considered "old age".
+# Example: a value of 365d means a must-reboot will be flagged at earliest after
+#          1 year of uptime of the host
+# Format: <value>m|h|d where m=minutes, h=hours, d=days (lowercase suffix).
+#         if no suffix is specified, then minutes are assumed.
+# [default: 365d]
+old_age_time="365d"
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

etc/opt/hc/check_linux_vz_ct_counters.conf.dist

@@ -11,6 +11,12 @@
 # [default: no]
 log_healthy="no"
 
+# specify UBC names to exclude (comma-separated list) (release >20200411)
+# [default: none]
+# [release >2020410]
+# Examples: numfile,numpty
+exclude_counters=""
+
 # specify containers for which to check the UBC
 # Format:
 #  [ct:<ct_id>]

etc/opt/hc/check_linux_vz_ct_status.conf.dist

@@ -11,13 +11,18 @@
 # [default: no]
 log_healthy="no"
 
-# specify properties as displayed by the 'vzlist -a -H -o ctid,status,onboot' command
+# specify properties as displayed by the following commands:
+#   OpenVZ 6.x: 'vzlist -a -H -o ctid,status,onboot'
+#   OpenVZ 7.x: 'prlctl list --info -a' (release >20200411)
 # Format:
 #  [ct:<ct_id>:<runtime_status>:<boot_status>]
 # runtime_status should be 'running' or 'stopped'
-# boot_status should be 'yes' or 'no'
-# Examples:
+# boot_status should be 'yes' or 'no' (OpenVZ 6.x)
+# boot_status should be 'on' of 'off' (OpenVZ 7.x)
+# Examples (OpenVZ 6.x):
 #ct:100:running:yes
+# Examples (OpenVZ 7.x) (release >20200411): 
+#ct:621240e6-fa79-406a-a3f9-26de47b5d789:running:on
 
 
 #******************************************************************************

etc/opt/hc/check_serviceguard_package_status.conf.dist

@@ -1,7 +1,7 @@
 #******************************************************************************
-# @(#) check_linux_sg_package_status.conf
+# @(#) check_serviceguard_package_status.conf
 #******************************************************************************
-# This is a configuration file for the check_linux_sg_package_status HC plugin.
+# This is a configuration file for the check_serviceguard_package_status HC plugin.
 # All lines starting with a '#' are comment lines.
 # [default: indicates hardcoded script values if no value is defined here]
 #******************************************************************************

etc/opt/hc/core/check_health.conf.dist

@@ -10,6 +10,31 @@
 # maximum timeout for HC calls/plugins (seconds) [default: 60]
 HC_TIME_OUT=60
 
+# enable/disable logging of passed health checks (warning: this may rapidly grow the HC log)
+# see also: '--log-healthy' command-line parameter
+#           'log_healthy' setting in HC plugin configuration file(s)
+# [values: Yes|No]
+HC_LOG_HEALTHY="No"
+
+# enable/disable healing logic if available in HC plugin(s)
+# see also: '--no-fix' command-line parameter
+# [values: Yes|No]
+HC_WILL_FIX="Yes"
+
+# cache "last" reporting entries. Set to 'Yes' to speed up reporting of the last
+# registered HC events
+# [values: Yes|No]
+HC_REPORT_CACHE_LAST="No"
+
+# cache "today" reporting entries.  Set to 'Yes' to speed up reporting of today's
+# registered HC events
+# [values: Yes|No]
+HC_REPORT_CACHE_TODAY="No"
+
+# Show log entry count(s) after archiving. Disabling this will speed up archiving.
+# [values: Yes|No]
+HC_COUNT_ARCHIVES="Yes"
+
 
 #******************************************************************************
 # End of FILE

etc/opt/hc/core/providers/notify_slack.conf.dist

@@ -0,0 +1,15 @@
+#******************************************************************************
+# @(#) notify_slack.conf
+#******************************************************************************
+# This is the the configuration file for the notify_slack.sh provider.
+# All lines starting with a '#' are comment lines.
+# [default: indicates hardcoded script values if no value is defined here]
+#******************************************************************************
+
+# URL of the webhook of the Slack app
+SLACK_WEBHOOK=""
+
+
+#******************************************************************************
+# End of FILE
+#******************************************************************************

opt/hc/bin/check_health.sh

@@ -23,8 +23,8 @@
 # REQUIRES: ksh88/93 (mksh/pdksh will probably work too but YMMV)
 #           build_fpath(), check_config(), check_core(), check_lock_dir(),
 #           check_params(), check_platform(), check_user(), check_shell(),
-#           display_usage(), do_cleanup, fix_symlinks(), read_config()
-#           + include functions
+#           display_usage(), do_cleanup, fix_symlinks(), get_disable_comment(),
+#           read_config() + include functions
 #           For other pre-requisites see the documentation in display_usage()
 # REQUIRES (OPTIONAL): display_*(), notify_*(), report_*()
 # EXISTS: 0=no errors encountered, >0=some errors encountered
@@ -38,7 +38,7 @@
 
 # ------------------------- CONFIGURATION starts here -------------------------
 # define the version (YYYY-MM-DD)
-typeset -r SCRIPT_VERSION="2019-05-14"
+typeset -r SCRIPT_VERSION="2021-03-31"
 # location of parent directory containing KSH functions/HC plugins
 typeset -r FPATH_PARENT="/opt/hc/lib"
 # location of custom HC configuration files
@@ -86,14 +86,15 @@ typeset EXIT_CODE=0
 typeset FDIR=""
 typeset FFILE=""
 typeset FPATH=""
-typeset HC_ARCHIVE=""
 typeset HC_CHECK=""
+typeset HC_COMMENT=""
 typeset HC_DISABLE=""
 typeset HC_ENABLE=""
 typeset HC_RUN=""
 typeset HC_FAIL_ID=""
 # shellcheck disable=SC2034
 typeset HC_FILE_LINE=""
+typeset HC_LOG_HEALTHY=""
 typeset HC_NOW=""
 typeset HC_TIME_OUT=60
 typeset HC_MIN_TIME_OUT=30
@@ -101,10 +102,20 @@ typeset HC_MIN_TIME_OUT=30
 typeset HC_MSG_VAR=""
 typeset HC_STDOUT_LOG=""
 typeset HC_STDERR_LOG=""
+set -A HC_STDOUT_LOG_ARRAY
+set -A HC_STDERR_LOG_ARRAY
+# shellcheck disable=SC2034
+typeset HC_COUNT_ARCHVES=""
+typeset HC_WILL_FIX=""
+# shellcheck disable=SC2034
+typeset HC_REPORT_CACHE_LAST=""
+# shellcheck disable=SC2034
+typeset HC_REPORT_CACHE_TODAY=""
 # shellcheck disable=SC2034
 typeset LINUX_DISTRO=""
 # shellcheck disable=SC2034
 typeset LINUX_RELEASE=""
+typeset PREVIOUS_HC_TIME_OUT=""
 typeset ARCHIVE_RC=0
 typeset DISABLE_RC=0
 typeset ENABLE_RC=0
@@ -120,6 +131,7 @@ typeset DEBUG_OPTS=""
 # command-line parameters
 typeset ARG_ACTION=0            # HC action flag
 typeset ARG_CHECK_HOST=0        # host check is off by default
+typeset ARG_COMMENT=""
 typeset ARG_CONFIG_FILE=""      # custom configuration file for a HC, none by default
 typeset ARG_DEBUG=0             # debug is off by default
 typeset ARG_DEBUG_LEVEL=0       # debug() only by default
@@ -132,8 +144,10 @@ typeset ARG_HC_ARGS=""          # no extra arguments to HC plug-in by default
 typeset ARG_HISTORY=0           # include historical events is off by default
 typeset ARG_LAST=0              # report last events
 typeset ARG_LIST=""             # list all by default
+typeset ARG_LIST_DETAILS=0      # list with full details is off by default
 typeset ARG_LOCK=1              # lock for concurrent script executions is on by default
 typeset ARG_LOG=1               # logging is on by default
+typeset ARG_NO_FIX=0            # fix/healing is not disabled by default
 typeset ARG_LOG_HEALTHY=0       # logging of healthy health checks is off by default
 typeset ARG_MONITOR=1           # killing long running HC processes is on by default
 typeset ARG_NEWER=""
@@ -243,20 +257,47 @@ then
     print -u2 "ERROR: library file ${FPATH_PARENT}/core/include_core(.sh) is not present (tip: run --fix-symlinks)"
     exit 1
 fi
-# include include_*
-find ${FPATH_PARENT}/core -name "include_*.sh" -type f -print 2>/dev/null | while read INCLUDE_FILE
-do
+
+# PDKSH hack (IS_PDKSH is not yet set here)
+case "${KSH_VERSION}" in
+    *MIRBSD*|*PD*|*LEGACY*)
+        # shellcheck source=/dev/null
+        . ${FPATH_PARENT}/core/include_core.sh
+        if [[ -r ${FPATH_PARENT}/core/include_data.sh && -h ${FPATH_PARENT}/core/include_data ]]
+        then
+                (( ARG_DEBUG > 0 )) && print -u2 "DEBUG: including ${FPATH_PARENT}/core/include_data.sh"
+                # shellcheck source=/dev/null
+                . ${FPATH_PARENT}/core/include_data.sh
+        else
+                print -u2 "ERROR: library file ${FPATH_PARENT}/core/include_data.sh is not present (tip: run --fix-symlinks)"
+                exit 1
+        fi
+        if [[ -r ${FPATH_PARENT}/core/include_os.sh && -h ${FPATH_PARENT}/core/include_os ]]
+        then
+                (( ARG_DEBUG > 0 )) && print -u2 "DEBUG: including ${FPATH_PARENT}/core/include_os.sh"
+                # shellcheck source=/dev/null
+                . ${FPATH_PARENT}/core/include_os.sh
+        else
+                print -u2 "ERROR: library file ${FPATH_PARENT}/core/include_os.sh is not present (tip: run --fix-symlinks)"
+                exit 1
+        fi
+        ;;
+    *)
+        # include include_*
+        find ${FPATH_PARENT}/core -name "include_*.sh" -type f -print 2>/dev/null | while read -r INCLUDE_FILE
+        do
             if [[ -h ${INCLUDE_FILE%%.sh} ]]
             then
                 # shellcheck source=/dev/null
                 (( ARG_DEBUG > 0 )) && print -u2 "DEBUG: including ${INCLUDE_FILE}"
                 # shellcheck source=/dev/null
-        . ${INCLUDE_FILE}
+                . "${INCLUDE_FILE}"
             else
                 print -u2 "ERROR: library file ${INCLUDE_FILE} exists but has no symlink. Run --fix-symlinks"
                 exit 1
             fi
-done
+        done
+esac
 
 # check for core directories
 [[ -d ${ARCHIVE_DIR} ]] || mkdir -p "${ARCHIVE_DIR}" >/dev/null 2>&1
@@ -299,18 +340,19 @@ function check_lock_dir
 (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 if (( ARG_LOCK > 0 ))
 then
-    mkdir ${LOCK_DIR} >/dev/null || {
+    mkdir "${LOCK_DIR}" >/dev/null 2>/dev/null || {
         print -u2 "ERROR: unable to acquire lock ${LOCK_DIR}"
         ARG_VERBOSE=0 warn "unable to acquire lock ${LOCK_DIR}"
         if [[ -f ${LOCK_DIR}/.pid ]]
         then
-            typeset LOCK_PID="$(<${LOCK_DIR}/.pid)"
+            # shellcheck disable=SC2086
+            typeset LOCK_PID=$(<"${LOCK_DIR}/.pid")
             print -u2 "ERROR: active health checker running on PID: ${LOCK_PID}"
             ARG_VERBOSE=0 warn "active health checker running on PID: ${LOCK_PID}. Exiting!"
         fi
         exit 1
     }
-    print $$ >${LOCK_DIR}/.pid
+    print $$ > "${LOCK_DIR}/.pid"
 else
     (( ARG_DEBUG > 0 )) && print "DEBUG: locking has been disabled"
 fi
@@ -434,11 +476,14 @@ then
         exit 1
     fi
 fi
-# --log-healthy
-if (( ARG_LOG_HEALTHY > 0 && ARG_ACTION != 4 ))
+# --comment
+if [[ -n "${ARG_COMMENT}" ]]
 then
-    print -u2 "ERROR: you can only use '--log-healthy' in combination with '--run'"
+    if (( ARG_ACTION != 2 )) && (( ARG_ACTION != 6 ))
+    then
+        print -u2 "ERROR: you can only use '--comment' in combination with '--disable' or '--disable-all'"
         exit 1
+    fi
 fi
 # check log location
 if (( ARG_LOG > 0 ))
@@ -541,9 +586,9 @@ cat << EOT
 Execute/report simple health checks (HC) on UNIX hosts.
 
 Syntax: ${SCRIPT_DIR}/${SCRIPT_NAME} [--help] | [--help-terse] | [--version] |
-    [--list=<needle>] | [--list-core] | [--list-include] | [--fix-symlinks] | [--show-stats] | (--archive-all | --disable-all | --enable-all) | [--fix-logs [--with-history]] |
-        (--check-host | ((--archive | --check | --enable | --disable | --run [--timeout=<secs>] | --show) --hc=<list_of_checks> [--config-file=<configuration_file>] [hc-args="<arg1,arg2=val,arg3">]))
-            [--display=<method>] ([--debug] [--debug-level=<level>]) [--log-healthy] [--no-monitor] [--no-log] [--no-lock] [[--flip-rc] [--with-rc=<count|max|sum>]]]
+    [--list=<needle>] | [--list-details] | [--list-core] | [--list-include] | [--fix-symlinks] | [--show-stats] | (--archive-all | --disable-all [--comment=<text>] | --enable-all) | [--fix-logs [--with-history]] |
+        (--check-host | ((--archive | --check | --enable | --disable [--comment=<text>] | --run [--timeout=<secs>] | --show) --hc=<list_of_checks> [--config-file=<configuration_file>] [hc-args="<arg1,arg2=val,arg3">]))
+            [--display=<method>] ([--debug] [--debug-level=<level>]) [--log-healthy] [--no-fix] [--no-log] [--no-lock] [--no-monitor] [[--flip-rc] [--with-rc=<count|max|sum>]]]
                 [--notify=<method_list>] [--mail-to=<address_list>] [--sms-to=<sms_rcpt> --sms-provider=<name>]
                     [--report=<method> [--with-history] ( ([--last] | [--today]) | [(--older|--newer)=<date>] | [--reverse] [--id=<fail_id> [--detail]] )]
 
@@ -558,6 +603,7 @@ Parameters:
 --archive-all   : move events for all HCs from the HC log file into archive log files
 --check         : display HC state.
 --check-host    : execute all configured HC(s) (see check_host.conf)
+--comment       : add comment to requested action (--disable). WARNING: comments may not contain spaces!
 --config-file   : custom configuration file for a HC (may only be specified when executing a single HC plugin)
 --debug         : run script in debug mode
 --debug-level   : level of debugging information to show (0,1,2)
@@ -576,18 +622,23 @@ Parameters:
                   in double quotes (example: --hc_args="arg1,arg2=value,arg3").
 --id            : value of a FAIL ID (must be specified as uninterrupted sequence of numbers)
 --last          : show the last (failed) events for each HC and their combined STC value
---list          : show the available health checks. Use <needle> to search with wildcards. Following details are shown:
+--list          : show the available health checks in a terse manner. Use --list-details for a more extensive list.
+--list-details  : show the available health checks with following details included:
                   - health check (plugin) name
                   - state of the HC plugin (disabled/enabled)
                   - version of the HC plugin
                   - whether the HC plugin requires a configuration file in ${CONFIG_DIR}
                   - whether the HC plugin is scheduled by cron
+                  - whether the plugin contains a facility for --log-healthy and/or whether it is enabled
+                  - whether the plugin contains fix/healing logic (see --no-fix)
 --list-core     : show the available core plugins (mail,SMS,...)
 --list-include  : show the available includes/libraries
 --log-healthy   : log/show also passed health checks. By default this is off when the plugin support this feature.
-                  (can be overridden by --no-log to disable all logging)
+                  (overrides \$HC_LOG_HEALTHY and can itself be overridden by --no-log to disable all logging)
 --mail-to       : list of e-mail address(es) to which an e-mail alert will be send to [requires mail core plugin]
 --newer         : show the (failed) events for each HC that are newer than the given date
+--no-fix        : do not apply fix/healing logic for failed health checks (if available)
+                  (overrides \$HC_WILL_FIX)
 --no-lock       : disable locking to allow concurrent script executions
 --no-log        : do not log any messages to the script log file or health check results.
 --no-monitor    : do not stop the execution of a HC after \$HC_TIME_OUT seconds
@@ -601,7 +652,7 @@ Parameters:
 --sms-provider  : name of a supported SMS provider (see \$SMS_PROVIDERS) [requires SMS core plugin]
 --sms-to        : name of person or group to which a sms alert will be send to [requires SMS core plugin]
 --timeout       : maximum runtime of a HC plugin in seconds (overrides \$HC_TIME_OUT)
---today         : show today's (failed) events (HC and their combined STC value)
+--today         : show (failed) events of today (HC and their combined STC value)
 --version       : show the timestamp of the script.
 --with-history  : also include events that have been archived already (reporting)
 --with-rc       : define RC handling (plugin) when --flip-rc is used
@@ -624,16 +675,28 @@ function do_cleanup
 log "performing cleanup ..."
 
 # remove temporary files
-[[ -f "${HC_MSG_FILE}" ]] && rm -f ${HC_MSG_FILE} >/dev/null 2>&1
+[[ -f "${HC_MSG_FILE}" ]] && rm -f "${HC_MSG_FILE}" >/dev/null 2>&1
 
-# remove trailing log files
-[[ -f "${HC_STDOUT_LOG}" ]] && rm -f ${HC_STDOUT_LOG} >/dev/null 2>&1
-[[ -f "${HC_STDERR_LOG}" ]] && rm -f ${HC_STDERR_LOG} >/dev/null 2>&1
+# remove left over plugin log files (pop from array stacks)
+FILE_COUNT=1
+while (( FILE_COUNT <= ${#HC_STDOUT_LOG_ARRAY[*]} ))
+do
+    (( ARG_DEBUG > 0 )) && debug "cleaning up plugin log file ${HC_STDOUT_LOG_ARRAY[FILE_COUNT]}"
+    [[ -f "${HC_STDOUT_LOG_ARRAY[FILE_COUNT]}" ]] && rm -f "${HC_STDOUT_LOG_ARRAY[FILE_COUNT]}" >/dev/null 2>&1
+    FILE_COUNT=$(( FILE_COUNT + 1 ))
+done
+FILE_COUNT=1
+while (( FILE_COUNT <= ${#HC_STDERR_LOG_ARRAY[*]} ))
+do
+    (( ARG_DEBUG > 0 )) && debug "cleaning up plugin log file ${HC_STDERR_LOG_ARRAY[FILE_COUNT]}"
+    [[ -f "${HC_STDERR_LOG_ARRAY[FILE_COUNT]}" ]] && rm -f "${HC_STDERR_LOG_ARRAY[FILE_COUNT]}" >/dev/null 2>&1
+    FILE_COUNT=$(( FILE_COUNT + 1 ))
+done
 
 # remove lock directory
 if [[ -d ${LOCK_DIR} ]]
 then
-    rm -rf ${LOCK_DIR} >/dev/null 2>&1
+    rm -rf "${LOCK_DIR}" >/dev/null 2>&1
     log "${LOCK_DIR} lock directory removed"
 fi
 
@@ -658,6 +721,7 @@ typeset FSYML=""
 # find missing symlinks (do not skip core plug-ins here)
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | while read -r FDIR
 do
+    # shellcheck disable=SC2086
     find ${FDIR} -type f -print 2>/dev/null | while read -r FFILE
     do
         FSYML="${FFILE%.sh}"
@@ -676,7 +740,7 @@ done
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | while read -r FDIR
 do
     # do not use 'find -type l' here!
-    # shellcheck disable=SC2010
+    # shellcheck disable=SC2010,SC2086
     ls ${FDIR} 2>/dev/null | grep -v "\." 2>/dev/null | while read -r FSYML
     do
         # check if file is a dead symlink
@@ -714,6 +778,24 @@ else
     . "${CONFIG_FILE}"
 fi
 
+# reconcile global settings w/ cmd-line parameters
+if (( ARG_LOG_HEALTHY == 0 ))
+then
+    case "${HC_LOG_HEALTHY}" in
+        yes|YES|Yes)
+            ARG_LOG_HEALTHY=1
+            ;;
+    esac
+fi
+if (( ARG_NO_FIX == 0 ))
+then
+    case "${HC_WILL_FIX}" in
+        no|NO|No)
+            ARG_NO_FIX=1
+            ;;
+    esac
+fi
+
 return 0
 }
 
@@ -761,6 +843,12 @@ do
             fi
             ARG_CHECK_HOST=1
             ;;
+        -comment=*)
+            ARG_COMMENT="${CMD_PARAMETER#-comment=}"
+            ;;
+        --comment=*)
+            ARG_COMMENT="${CMD_PARAMETER#--comment=}"
+            ;;
         -config-file=*)
             ARG_CONFIG_FILE="${CMD_PARAMETER#-config-file=}"
             ;;
@@ -904,6 +992,11 @@ do
                 ARG_ACTION=9
             fi
             ;;
+        -list-details|--list-details)
+            # shellcheck disable=SC2034
+            ARG_LIST_DETAILS=1
+            ARG_ACTION=9
+            ;;
         -list-hc|--list-hc|-list-all|--list-all)
             print -u2 "WARN: deprecated option. Use --list | --list=<needle>"
             exit 0
@@ -952,8 +1045,13 @@ do
             # shellcheck disable=SC2034
             ARG_NOTIFY="${CMD_PARAMETER#--notify=}"
             ;;
+        -no-fix|--no-fix)
+            ARG_NO_FIX=1
+            ;;
         -no-log|--no-log)
             ARG_LOG=0
+            # --no-log always means --no-fix!
+            ARG_NO_FIX=1
             ;;
         -no-lock|--no-lock)
             ARG_LOCK=0
@@ -1151,7 +1249,13 @@ case ${ARG_ACTION} in
             # shellcheck disable=SC2181
             if (( $? == 0 ))
             then
+                HC_COMMENT=$(get_disable_comment "${HC_CHECK}")
+                if [[ -n "${HC_COMMENT}" ]]
+                then
+                    log "HC ${HC_CHECK} is currently disabled (${HC_COMMENT})"
+                else
                     log "HC ${HC_CHECK} is currently disabled"
+                fi
             else
                 log "HC ${HC_CHECK} is currently enabled"
             fi
@@ -1173,6 +1277,11 @@ case ${ARG_ACTION} in
             exists_hc "${HC_DISABLE}" && die "cannot find HC: ${HC_DISABLE}"
             log "disabling HC: ${HC_DISABLE}"
             touch "${STATE_PERM_DIR}/${HC_DISABLE}.disabled" >/dev/null 2>&1
+            # write comment if supplied
+            if [[ -n "${ARG_COMMENT}" ]]
+            then
+                print "${ARG_COMMENT}" >"${STATE_PERM_DIR}/${HC_DISABLE}.disabled"
+            fi
             # shellcheck disable=SC2181
             if (( $? == 0 ))
             then
@@ -1220,7 +1329,7 @@ case ${ARG_ACTION} in
             # re-initialize messages stash (log of failed checks)
             # shellcheck disable=SC2034
             HC_MSG_VAR=""
-            : >${HC_MSG_FILE} 2>/dev/null
+            : > "${HC_MSG_FILE}" 2>/dev/null
             # shellcheck disable=SC2181
             if (( $? > 0 ))
             then
@@ -1258,13 +1367,16 @@ case ${ARG_ACTION} in
             # set & initialize STDOUT/STDERR locations (not in init_hc()!)
             HC_STDOUT_LOG="${TMP_DIR}/${HC_RUN}.stdout.log.$$"
             HC_STDERR_LOG="${TMP_DIR}/${HC_RUN}.stderr.log.$$"
-            : >${HC_STDOUT_LOG} 2>/dev/null
+            # push plugin log files to array stacks (index starts at 1!)
+            HC_STDOUT_LOG_ARRAY[${#HC_STDOUT_LOG_ARRAY[*]}+1]="${HC_STDOUT_LOG}"
+            HC_STDERR_LOG_ARRAY[${#HC_STDERR_LOG_ARRAY[*]}+1]="${HC_STDERR_LOG}"
+            : > "${HC_STDOUT_LOG}" 2>/dev/null
             # shellcheck disable=SC2181
             if (( $? > 0 ))
             then
                 die "unable to reset the \${HC_STDOUT_LOG} file"
             fi
-            : >${HC_STDERR_LOG} 2>/dev/null
+            : > "${HC_STDERR_LOG}" 2>/dev/null
             # shellcheck disable=SC2181
             if (( $? > 0 ))
             then
@@ -1274,6 +1386,7 @@ case ${ARG_ACTION} in
             # --check-host handling: alternative configuration file, mangle ARG_CONFIG_FILE & HC_TIME_OUT
             if (( ARG_CHECK_HOST == 1 ))
             then
+                PREVIOUS_HC_TIME_OUT=${HC_TIME_OUT}
                 ARG_CONFIG_FILE=""      # reset from previous call
                 RUN_CONFIG_FILE=$(grep -i -E -e "^hc:${HC_RUN}:" ${HOST_CONFIG_FILE} 2>/dev/null | cut -f3 -d':')
                 [[ -n "${RUN_CONFIG_FILE}" ]] && ARG_CONFIG_FILE="${CONFIG_DIR}/${RUN_CONFIG_FILE}"
@@ -1283,13 +1396,14 @@ case ${ARG_ACTION} in
                     (( RUN_TIME_OUT > HC_TIME_OUT )) && HC_TIME_OUT=${RUN_TIME_OUT}
                 else
                     # reset for next HC
-                    HC_TIME_OUT=60
+                    HC_TIME_OUT=${PREVIOUS_HC_TIME_OUT}
                 fi
             fi
 
             # run HC with or without monitor
             if (( ARG_MONITOR == 0 ))
             then
+                # shellcheck disable=SC2086
                 ${HC_RUN} ${ARG_HC_ARGS}
                 RUN_RC=$?
                 EXIT_CODE=${RUN_RC}
@@ -1328,6 +1442,7 @@ case ${ARG_ACTION} in
                 # SLEEP_PID is the PID of the sleep subshell itself
                 SLEEP_PID=$!
 
+                # shellcheck disable=SC2086
                 ${HC_RUN} ${ARG_HC_ARGS} &
                 CHILD_PID=$!
                 log "spawning child process with time-out of ${HC_TIME_OUT} secs for HC call [PID=${CHILD_PID}]"
@@ -1378,7 +1493,7 @@ case ${ARG_ACTION} in
             handle_hc "${HC_RUN}"
             # exit with return code from handle_hc() (see --flip-rc)
             EXIT_CODE=$?
-            rm -f ${HC_MSG_FILE} >/dev/null 2>&1
+            rm -f "${HC_MSG_FILE}" >/dev/null 2>&1
         done
         ;;
     5)  # show info on HC (single)
@@ -1398,6 +1513,11 @@ case ${ARG_ACTION} in
             exists_hc "${HC_DISABLE}" && die "cannot find HC: ${HC_DISABLE}"
             log "disabling HC: ${HC_DISABLE}"
             touch "${STATE_PERM_DIR}/${HC_DISABLE}.disabled" >/dev/null 2>&1
+            # write comment if supplied
+            if [[ -n "${ARG_COMMENT}" ]]
+            then
+                print "${ARG_COMMENT}" >"${STATE_PERM_DIR}/${HC_DISABLE}.disabled"
+            fi
             DISABLE_RC=$?
             if (( DISABLE_RC == 0 ))
             then
@@ -1472,26 +1592,7 @@ case ${ARG_ACTION} in
         esac
         ;;
     13) # archive current log entries for all HCs
-        list_hc "list" | while read -r HC_ARCHIVE
-        do
-            # check for HC (function)
-            exists_hc "${HC_ARCHIVE}" && die "cannot find HC: ${HC_ARCHIVE}"
-            log "archiving current log entries for HC: ${HC_ARCHIVE}"
-            archive_hc "${HC_ARCHIVE}"
-            ARCHIVE_RC=$?
-            case ${ARCHIVE_RC} in
-                0)
-                    log "no archiving needed for ${HC_ARCHIVE}"
-                    ;;
-                1)
-                    log "successfully archived log entries for ${HC_ARCHIVE}"
-                    ;;
-                2)
-                    log "failed to archive log entries for ${HC_ARCHIVE} [RC=${ARCHIVE_RC}]"
-                    EXIT_CODE=1
-                    ;;
-            esac
-        done
+        archive_hc_all
         ;;
 esac
 

opt/hc/lib/core/display_init.sh

@@ -31,7 +31,7 @@
 function display_init
 {
 # ------------------------- CONFIGURATION starts here -------------------------
-typeset _VERSION="2019-03-22"                               # YYYY-MM-DD
+typeset _VERSION="2020-10-10"                               # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="AIX,HP-UX,Linux"              # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -139,7 +139,7 @@ fi
 
 # print status line (but also check for terminal support)
 # shellcheck disable=SC1117
-printf "%-30s %50s\t[ %8s ]%s\n" \
+printf "%-45s %50s\t[ %8s ]%s\n" \
             "${_DISPLAY_HC}" \
             "(${_DISPLAY_CFG})" \
             "${_DISPLAY_COLOR}${_DISPLAY_CODE}${_NORMAL}" \

opt/hc/lib/core/include_core.sh

@@ -30,7 +30,7 @@
 # RETURNS: 0
 function version_include_core
 {
-typeset _VERSION="2019-04-03"                               # YYYY-MM-DD
+typeset _VERSION="2022-10-14"           # YYYY-MM-DD
 
 print "INFO: $0: ${_VERSION#version_*}"
 
@@ -50,6 +50,7 @@ typeset HC_NAME="${1}"
 typeset ARCHIVE_FILE=""
 typeset ARCHIVE_RC=0
 typeset YEAR_MONTH=""
+typeset COUNT_STATS=1
 typeset LOG_COUNT=0
 typeset PRE_LOG_COUNT=0
 typeset TODO_LOG_COUNT=0
@@ -62,65 +63,137 @@ typeset TMP2_FILE="${TMP_DIR}/.$0.tmp2.archive.$$"
 # shellcheck disable=SC2064
 trap "rm -f ${TMP1_FILE} ${TMP2_FILE} ${SAVE_LOG_FILE} >/dev/null 2>&1; return 1" 1 2 3 15
 
-# get pre-archive log co
-PRE_LOG_COUNT=$(wc -l ${HC_LOG} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+# get pre-archive log count
+PRE_LOG_COUNT=$(wc -l "${HC_LOG}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
 if (( PRE_LOG_COUNT == 0 ))
 then
     warn "${HC_LOG} is empty, nothing to archive"
     return 0
 fi
 
+# check log count toggle (only affects $LOG_COUNT)
+case "${HC_COUNT_ARCHIVES}" in
+    No|no|NO)
+        COUNT_STATS=0
+        ;;
+    *)
+        : # default is to do additional stats
+        ;;
+esac
+
 # isolate messages from HC, find unique %Y-%m combinations
-grep ".*${LOG_SEP}${HC_NAME}${LOG_SEP}" ${HC_LOG} 2>/dev/null |\
+grep ".*${LOG_SEP}${HC_NAME}${LOG_SEP}" "${HC_LOG}" 2>/dev/null |\
     cut -f1 -d"${LOG_SEP}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null |\
     cut -f1-2 -d'-' 2>/dev/null | sort -u 2>/dev/null |\
     while read -r YEAR_MONTH
 do
+    # skip messages with bogus date
+    if [[ -z "${YEAR_MONTH}" ]]
+    then
+       warn "skipping bogus log lines (lines without proper datestamp)"
+       continue
+    fi
+
     # find all messages for that YEAR-MONTH combination
-    grep "${YEAR_MONTH}.*${LOG_SEP}${HC_NAME}${LOG_SEP}" ${HC_LOG} >${TMP1_FILE}
-    TODO_LOG_COUNT=$(wc -l ${TMP1_FILE} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+    grep "${YEAR_MONTH}.*${LOG_SEP}${HC_NAME}${LOG_SEP}" "${HC_LOG}" >"${TMP1_FILE}"
+    TODO_LOG_COUNT=$(wc -l "${TMP1_FILE}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
     log "# of entries in ${YEAR_MONTH} to archive: ${TODO_LOG_COUNT}"
 
     # combine existing archived messages and resort
     ARCHIVE_FILE="${ARCHIVE_DIR}/hc.${YEAR_MONTH}.log"
-    cat ${ARCHIVE_FILE} ${TMP1_FILE} 2>/dev/null | sort -u >${TMP2_FILE} 2>/dev/null
-    mv ${TMP2_FILE} ${ARCHIVE_FILE} 2>/dev/null || {
+    cat "${ARCHIVE_FILE}" "${TMP1_FILE}" 2>/dev/null | sort -u >"${TMP2_FILE}" 2>/dev/null
+    mv "${TMP2_FILE}" "${ARCHIVE_FILE}" 2>/dev/null || {
         warn "failed to move archive file, aborting"
         return 2
     }
-    LOG_COUNT=$(wc -l ${ARCHIVE_FILE} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+    if (( COUNT_STATS > 0 ))
+    then
+        LOG_COUNT=$(wc -l "${ARCHIVE_FILE}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
         log "# of entries in ${ARCHIVE_FILE} now: ${LOG_COUNT}"
+    fi
 
     # remove archived messages from the $HC_LOG (but create a backup first!)
-    cp -p ${HC_LOG} ${SAVE_HC_LOG} 2>/dev/null
+    cp -p "${HC_LOG}" "${SAVE_HC_LOG}" 2>/dev/null
     # compare with the sorted $HC_LOG
-    sort ${HC_LOG} >${TMP1_FILE}
-    comm -23 ${TMP1_FILE} ${ARCHIVE_FILE} 2>/dev/null >${TMP2_FILE}
+    sort "${HC_LOG}" >"${TMP1_FILE}"
+    comm -23 "${TMP1_FILE}" "${ARCHIVE_FILE}" 2>/dev/null >"${TMP2_FILE}"
 
     # check archive action (HC_LOG should not be empty unless it contained
     # only messages from one single HC plugin before archival)
     if [[ -s ${TMP2_FILE} ]] || (( PRE_LOG_COUNT == TODO_LOG_COUNT ))
     then
-        mv ${TMP2_FILE} ${HC_LOG} 2>/dev/null || {
+        mv "${TMP2_FILE}" "${HC_LOG}" 2>/dev/null || {
             warn "failed to move HC log file, aborting"
             return 2
         }
-        LOG_COUNT=$(wc -l ${HC_LOG} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+        if (( COUNT_STATS > 0 ))
+        then
+            LOG_COUNT=$(wc -l "${HC_LOG}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
             log "# entries in ${HC_LOG} now: ${LOG_COUNT}"
+        fi
         ARCHIVE_RC=1
     else
         warn "a problem occurred. Rolling back archival"
-        mv ${SAVE_HC_LOG} ${HC_LOG} 2>/dev/null
+        mv "${SAVE_HC_LOG}" "${HC_LOG}" 2>/dev/null
         ARCHIVE_RC=2
     fi
 done
 
 # clean up temporary file(s)
-rm -f ${TMP1_FILE} ${TMP2_FILE} ${SAVE_HC_LOG} >/dev/null 2>&1
+rm -f "${TMP1_FILE}" "${TMP2_FILE}" "${SAVE_HC_LOG}" >/dev/null 2>&1
 
 return ${ARCHIVE_RC}
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: archive_hc_all()
+# DOES: archive log entries for all HCs
+# EXPECTS: n/a
+# RETURNS: 0
+# REQUIRES: ${HC_LOG}
+function archive_hc_all
+{
+typeset HC_ARCHIVE=""
+
+# build list with all HCs in $HC_LOG and sort them by highest number of messages
+# first (to speed up the archiving operation)
+log "parsing log file ${HC_LOG} for messages ..."
+awk -F"${LOG_SEP}" '
+    {
+        # only do records with a proper HC name in $2
+        if ($2 ~ /check_/) {
+            count[$2]++;
+        }
+    }
+
+    END {
+        for (hc in count) {
+            print count[hc] ":" hc;
+        }
+    }' "${HC_LOG}" 2>/dev/null | sort -rn 2>/dev/null |\
+while IFS=":" read -r HC_COUNT HC_ARCHIVE
+do
+    # check for HC (function)
+    exists_hc "${HC_ARCHIVE}" && die "cannot find HC: ${HC_ARCHIVE}"
+    log "archiving ${HC_COUNT} log entries for HC ${HC_ARCHIVE}"
+    archive_hc "${HC_ARCHIVE}"
+    ARCHIVE_RC=$?
+    case ${ARCHIVE_RC} in
+        0)
+            log "no archiving needed for ${HC_ARCHIVE}"
+            ;;
+        1)
+            log "successfully archived log entries for ${HC_ARCHIVE}"
+            ;;
+        2)
+            warn "failed to archive log entries for ${HC_ARCHIVE} [RC=${ARCHIVE_RC}]"
+            ;;
+    esac
+done
+
+return 0
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: count_log_errors()
 # DOES: check hc log file(s) for rogue entries (=lines with NF<>$NUM_LOG_FIELDS
@@ -138,6 +211,7 @@ function count_log_errors
 typeset LOG_STASH="${1}"
 typeset ERROR_COUNT=0
 
+# shellcheck disable=SC2002,SC2086
 ERROR_COUNT=$(cat ${LOG_STASH} 2>/dev/null | awk -F"${LOG_SEP}" '
     BEGIN { num = 0 }
     {
@@ -147,7 +221,7 @@ ERROR_COUNT=$(cat ${LOG_STASH} 2>/dev/null | awk -F"${LOG_SEP}" '
     }
     END { print num }' 2>/dev/null)
 
-print ${ERROR_COUNT}
+print "${ERROR_COUNT}"
 
 return 0
 }
@@ -189,7 +263,7 @@ then
         print - "$*" | while read -r LOG_LINE
         do
             # shellcheck disable=SC2153
-            print "${NOW}: ERROR: [$$]:" "${LOG_LINE}" >>${LOG_FILE}
+            print "${NOW}: ERROR: [$$]:" "${LOG_LINE}" >>"${LOG_FILE}"
         done
     fi
     print - "$*" | while read -r LOG_LINE
@@ -233,6 +307,7 @@ DO_DISPLAY_CUSTOM9=0
 DO_NOTIFY_EIF=0
 DO_NOTIFY_MAIL=0
 DO_NOTIFY_SMS=0
+DO_NOTIFY_SLACK=0
 DO_REPORT_STD=0
 HAS_DISPLAY_CSV=0
 HAS_DISPLAY_INIT=0
@@ -251,12 +326,13 @@ HAS_DISPLAY_CUSTOM9=0
 HAS_NOTIFY_EIF=0
 HAS_NOTIFY_MAIL=0
 HAS_NOTIFY_SMS=0
+HAS_NOTIFY_SLACK=0
 HAS_REPORT_STD=0
 
 # check which core display/notification plugins are installed
 # do not use a while-do loop here because mksh/pdksh does not pass updated
 # variables back from the sub shell (only works for true ksh88/ksh93)
-# shellcheck disable=SC2010
+# shellcheck disable=SC2010,SC2086
 for FFILE in $(ls -1 ${FPATH_PARENT}/core/*.sh 2>/dev/null | grep -v "include_" 2>/dev/null)
 do
     case "${FFILE}" in
@@ -328,6 +404,10 @@ do
             HAS_NOTIFY_EIF=1
             (( ARG_DEBUG > 0 )) && debug "notify_eif plugin is available"
             ;;
+        *notify_slack.sh)
+            HAS_NOTIFY_SLACK=1
+            (( ARG_DEBUG > 0 )) && debug "notify_slack plugin is available"
+            ;;
         *report_std.sh)
             # shellcheck disable=SC2034
             HAS_REPORT_STD=1
@@ -485,6 +565,9 @@ then
             *mail*) # by mail
                 DO_NOTIFY_MAIL=1
                 ;;
+            *slack*) # by Slack
+                DO_NOTIFY_SLACK=1
+                ;;
             *sms*) # by sms
                 DO_NOTIFY_SMS=1
                 ;;
@@ -643,8 +726,10 @@ return 0
 function dump_logs
 {
 log "=== STDOUT ==="
+# shellcheck disable=SC2086
 log "$(<${HC_STDOUT_LOG})"
 log "=== STDERR ==="
+# shellcheck disable=SC2086
 log "$(<${HC_STDERR_LOG})"
 
 return 0
@@ -733,24 +818,26 @@ fi
 trap "[[ -f ${TMP_FILE} ]] && rm -f ${TMP_FILE} >/dev/null 2>&1; return 1" 1 2 3 15
 
 # check and rewrite log file(s)
+# shellcheck disable=SC2086
 find ${LOG_STASH} -type f -print 2>/dev/null | while read -r FIX_FILE
 do
     log "fixing log file ${FIX_FILE} ..."
 
     # count before rewrite
-    STASH_COUNT=$(wc -l ${FIX_FILE} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+    STASH_COUNT=$(wc -l "${FIX_FILE}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
 
     # does it have errors?
-    ERROR_COUNT=$(count_log_errors ${FIX_FILE})
+    ERROR_COUNT=$(count_log_errors "${FIX_FILE}")
 
     # we count the empty lines (again)
-    EMPTY_COUNT=$(grep -c -E -e '^$' ${FIX_FILE} 2>/dev/null)
+    EMPTY_COUNT=$(grep -c -E -e '^$' "${FIX_FILE}" 2>/dev/null)
 
     # rewrite if needed
     if (( ERROR_COUNT > 0 ))
     then
-        : >${TMP_FILE} 2>/dev/null
-        cat ${FIX_FILE} 2>/dev/null | awk -F"${LOG_SEP}" -v OFS="${LOG_SEP}" '
+        : >"${TMP_FILE}" 2>/dev/null
+        # shellcheck disable=SC2002
+        cat "${FIX_FILE}" 2>/dev/null | awk -F"${LOG_SEP}" -v OFS="${LOG_SEP}" '
 
             BEGIN { max_log_fields = '"${NUM_LOG_FIELDS}"'
                     max_fields = (max_log_fields - 1) * 2
@@ -826,10 +913,10 @@ do
                     # correct log line, no rewrite needed
                     print $0
                 }
-            }' >${TMP_FILE} 2>/dev/null
+            }' >"${TMP_FILE}" 2>/dev/null
 
         # count after rewrite (include empty lines again in the count)
-        TMP_COUNT=$(wc -l ${TMP_FILE} 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
+        TMP_COUNT=$(wc -l "${TMP_FILE}" 2>/dev/null | cut -f1 -d' ' 2>/dev/null)
         TMP_COUNT=$(( TMP_COUNT + EMPTY_COUNT ))
 
         # bail out when we do not have enough records
@@ -840,16 +927,16 @@ do
         fi
 
         # swap log file (but create a backup first!)
-        cp -p ${FIX_FILE} ${SAVE_TMP_FILE} 2>/dev/null
+        cp -p "${FIX_FILE}" "${SAVE_TMP_FILE}" 2>/dev/null
         # shellcheck disable=SC2181
         if (( $? == 0 ))
         then
-            mv ${TMP_FILE} ${FIX_FILE} 2>/dev/null
+            mv "${TMP_FILE}" "${FIX_FILE}" 2>/dev/null
             # shellcheck disable=SC2181
             if (( $? > 0 ))
             then
                 warn "failed to move/update log file, rolling back"
-                mv ${SAVE_TMP_FILE} ${FIX_FILE} 2>/dev/null
+                mv "${SAVE_TMP_FILE}" "${FIX_FILE}" 2>/dev/null
                 return 2
             fi
             FIX_RC=1
@@ -859,7 +946,7 @@ do
         fi
 
         # clean up temporary file(s)
-        rm -f ${SAVE_TMP_FILE} ${TMP_FILE} >/dev/null 2>&1
+        rm -f "${SAVE_TMP_FILE}" "${TMP_FILE}" >/dev/null 2>&1
     else
         log "no fixing needed for ${FIX_FILE}"
     fi
@@ -870,12 +957,33 @@ done
 return ${FIX_RC}
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: get_disable_comment()
+# DOES: retrieve comment for a disabled HC
+# EXPECTS: HC name [string]
+# OUTPUTS: comment [string]
+# RETURNS: 0
+# REQUIRES: n/a
+function get_disable_comment
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset COMMENT_HC="${1}"
+
+if [[ -s "${STATE_PERM_DIR}/${COMMENT_HC}.disabled" ]]
+then
+    cat "${STATE_PERM_DIR}/${COMMENT_HC}.disabled" 2>/dev/null
+fi
+
+return 0
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: handle_hc()
 # DOES: handle HC results
 # EXPECTS: 1=HC name [string], $HC_MSG_FILE temporary file
 # RETURNS: 0 or $HC_STC_RC
-# REQUIRES: die(), display_*(), notify_*(), warn()
+# REQUIRES: data_contains_string(), data_is_numeric(), die(), display_*(),
+#           notify_*(), warn()
 function handle_hc
 {
 (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
@@ -889,12 +997,21 @@ typeset ONE_MSG_TEXT=""
 typeset ONE_MSG_CUR_VAL=""
 typeset ONE_MSG_EXP_VAL=""
 typeset ALL_MSG_STC=0
+typeset HC_CACHE_LAST_DATE=""
+typeset HC_CACHE_TODAY_DATE=""
+typeset HC_CACHE_LAST_NOW="$(date '+%Y-%m-%d %H:%M:%S' 2>/dev/null)"    # see also $HC_NOW
+typeset HC_CACHE_TODAY_NOW="$(date '+%Y-%m-%d' 2>/dev/null)"            # see also $HC_NOW
+typeset HC_REPORT_CACHE_LAST_STUB="${STATE_PERM_DIR}/cache.report-last"
+typeset HC_REPORT_CACHE_LAST_FILE=""
+typeset HC_REPORT_CACHE_TODAY_FILE="${STATE_PERM_DIR}/cache.report-today"
+typeset LOG_STRING_GOOD=""
+typeset LOG_STRING_FAIL=""
 
 if [[ -s ${HC_MSG_FILE} ]]
 then
     # load messages file into memory
     # do not use array: max 1024 items in ksh88; regular variable is only 32-bit memory limited
-    HC_MSG_VAR=$(<${HC_MSG_FILE})
+    HC_MSG_VAR=$(<"${HC_MSG_FILE}")
 
     # DEBUG: dump TMP file
     if (( ARG_DEBUG > 0 ))
@@ -912,6 +1029,7 @@ else
     # nothing to do, respect current EXIT_CODE
     if (( EXIT_CODE > 0 ))
     then
+        # shellcheck disable=SC2086
         return ${EXIT_CODE}
     else
         return 0
@@ -1129,15 +1247,56 @@ then
                 ONE_MSG_EXP_VAL=$(data_magic_unquote "${ONE_MSG_EXP_VAL}")
             fi
         fi
-        printf "%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}" \
-                "${ONE_MSG_TIME}" \
-                "${HC_NAME}" \
-                ${ONE_MSG_STC} \
-                "${ONE_MSG_TEXT}" >>${HC_LOG}
+
         if (( ONE_MSG_STC > 0 ))
         then
+            # build log string
+            LOG_STRING_FAIL=$(printf "%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}" "${ONE_MSG_TIME}" "${HC_NAME}" "${ONE_MSG_STC}" "${ONE_MSG_TEXT}" "${HC_FAIL_ID}")
+
+            # do atomic log update
             # shellcheck disable=SC1117
-            printf "%s${LOG_SEP}\n" "${HC_FAIL_ID}" >>${HC_LOG}
+            print "${LOG_STRING_FAIL}" >>"${HC_LOG}"
+
+            # cache report (--report --last)
+            HC_REPORT_CACHE_LAST_FILE="${HC_REPORT_CACHE_LAST_STUB}-${HC_NAME}"
+            case "${HC_REPORT_CACHE_LAST}" in
+                Yes|yes|YES)
+                    # fetch date of last cache entry (did we rollover from last HC event?)
+                    HC_CACHE_LAST_DATE=$(tail -n 1 "${HC_REPORT_CACHE_LAST_FILE}" 2>/dev/null | cut -f1 -d"${LOG_SEP}" 2>/dev/null)
+                    if [[ -z "${HC_CACHE_LAST_DATE}" ]] || [[ "${HC_CACHE_LAST_DATE}" != "${HC_CACHE_LAST_NOW}" ]]
+                    then
+                        # set and update cache file
+                        print "${LOG_STRING_FAIL}" >"${HC_REPORT_CACHE_LAST_FILE}"
+                    else
+                        # append cache file
+                        print "${LOG_STRING_FAIL}" >>"${HC_REPORT_CACHE_LAST_FILE}"
+                    fi
+                    ;;
+                *)
+                    # remove cache file if it exists
+                    [[ -f "${HC_REPORT_CACHE_LAST_FILE}" ]] && rm -f "${HC_REPORT_CACHE_LAST_FILE}" >/dev/null 2>/dev/null
+                    ;;
+            esac
+            # cache report (--report --today)
+            case "${HC_REPORT_CACHE_TODAY}" in
+                Yes|yes|YES)
+                    # fetch date of last cache entry (did we rollover midnight?)
+                    HC_CACHE_TODAY_DATE=$(tail -n 1 "${HC_REPORT_CACHE_TODAY_FILE}" 2>/dev/null | cut -f1 -d"${LOG_SEP}" 2>/dev/null | awk '{ print $1 }' 2>/dev/null)
+                    if [[ -z "${HC_CACHE_TODAY_DATE}" ]] || [[ "${HC_CACHE_TODAY_DATE}" != "${HC_CACHE_TODAY_NOW}" ]]
+                    then
+                        # rotate and update cache file
+                        (( ARG_DEBUG > 0 )) && debug "rotating today's cache file at ${HC_REPORT_CACHE_TODAY_FILE}"
+                        print "${LOG_STRING_FAIL}" >"${HC_REPORT_CACHE_TODAY_FILE}"
+                    else
+                        # append cache file
+                        print "${LOG_STRING_FAIL}" >>"${HC_REPORT_CACHE_TODAY_FILE}"
+                    fi
+                    ;;
+                *)
+                    # remove cache file if it exists
+                    [[ -f "${HC_REPORT_CACHE_TODAY_FILE}" ]] && rm -f "${HC_REPORT_CACHE_TODAY_FILE}" >/dev/null 2>/dev/null
+                    ;;
+            esac
             # RC handling (max/sum/count)
             if (( ARG_FLIP_RC > 0 ))
             then
@@ -1157,8 +1316,53 @@ then
                     HC_STC_RC=$(( HC_STC_RC + 1 ))
             fi
         else
+            # build log string
+            LOG_STRING_GOOD=$(printf "%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}%s${LOG_SEP}" "${ONE_MSG_TIME}" "${HC_NAME}" "${ONE_MSG_STC}" "${ONE_MSG_TEXT}")
+
+            # do atomic log update
             # shellcheck disable=SC1117
-            printf "\n" >>${HC_LOG}
+            print "${LOG_STRING_GOOD}" >>"${HC_LOG}"
+
+            # cache report (--report --last)
+            HC_REPORT_CACHE_LAST_FILE="${HC_REPORT_CACHE_LAST_STUB}-${HC_NAME}"
+            case "${HC_REPORT_CACHE_LAST}" in
+                Yes|yes|YES)
+                    # fetch date of last cache entry (did we rollover from last HC event?)
+                    HC_CACHE_LAST_DATE=$(tail -n 1 "${HC_REPORT_CACHE_LAST_FILE}" 2>/dev/null | cut -f1 -d"${LOG_SEP}" 2>/dev/null)
+                    if [[ -z "${HC_CACHE_LAST_DATE}" ]] || [[ "${HC_CACHE_LAST_DATE}" != "${HC_CACHE_LAST_NOW}" ]]
+                    then
+                        # set and update cache file
+                        print "${LOG_STRING_GOOD}" >"${HC_REPORT_CACHE_LAST_FILE}"
+                    else
+                        # append cache file
+                        print "${LOG_STRING_GOOD}" >>"${HC_REPORT_CACHE_LAST_FILE}"
+                    fi
+                    ;;
+                *)
+                    # remove cache file if it exists
+                    [[ -f "${HC_REPORT_CACHE_LAST_FILE}" ]] && rm -f "${HC_REPORT_CACHE_LAST_FILE}" >/dev/null 2>/dev/null
+                    ;;
+            esac
+            # cache report (--report --today)
+            case "${HC_REPORT_CACHE_TODAY}" in
+                Yes|yes|YES)
+                    # fetch date of last cache last_entry (did we rollover midnight?)
+                    HC_CACHE_TODAY_DATE=$(tail -n 1 "${HC_REPORT_CACHE_TODAY_FILE}" 2>/dev/null | cut -f1 -d"${LOG_SEP}" 2>/dev/null | awk '{ print $1 }' 2>/dev/null)
+                    if [[ -z "${HC_CACHE_TODAY_DATE}" ]] || [[ "${HC_CACHE_TODAY_DATE}" != "${HC_CACHE_TODAY_NOW}" ]]
+                    then
+                        # rotate and update cache file
+                        (( ARG_DEBUG > 0 )) && debug "rotating today's cache file at ${HC_REPORT_CACHE_TODAY_FILE}"
+                        print "${LOG_STRING_GOOD}" >"${HC_REPORT_CACHE_TODAY_FILE}"
+                    else
+                        # append cache file
+                        print "${LOG_STRING_GOOD}" >>"${HC_REPORT_CACHE_TODAY_FILE}"
+                    fi
+                    ;;
+                *)
+                    # remove cache file if it exists
+                    [[ -f ${HC_REPORT_CACHE_TODAY_FILE} ]] && rm -f "${HC_REPORT_CACHE_TODAY_FILE}" >/dev/null 2>/dev/null
+                    ;;
+            esac
         fi
     done
 
@@ -1175,14 +1379,14 @@ then
             then
                 # cut off the path and the .$$ part from the file location
                 HC_STDOUT_LOG_SHORT="${HC_STDOUT_LOG##*/}"
-                mv ${HC_STDOUT_LOG} "${EVENTS_DIR}/${DIR_PREFIX}/${HC_FAIL_ID}/${HC_STDOUT_LOG_SHORT%.*}" >/dev/null 2>&1 || \
+                mv "${HC_STDOUT_LOG}" "${EVENTS_DIR}/${DIR_PREFIX}/${HC_FAIL_ID}/${HC_STDOUT_LOG_SHORT%.*}" >/dev/null 2>&1 || \
                 die "failed to move ${HC_STDOUT_LOG} to event directory at ${1}"
             fi
             if [[ -f ${HC_STDERR_LOG} ]]
             then
                 # cut off the path and the .$$ part from the file location
                 HC_STDERR_LOG_SHORT="${HC_STDERR_LOG##*/}"
-                mv ${HC_STDERR_LOG} "${EVENTS_DIR}/${DIR_PREFIX}/${HC_FAIL_ID}/${HC_STDERR_LOG_SHORT%.*}" >/dev/null 2>&1 || \
+                mv "${HC_STDERR_LOG}" "${EVENTS_DIR}/${DIR_PREFIX}/${HC_FAIL_ID}/${HC_STDERR_LOG_SHORT%.*}" >/dev/null 2>&1 || \
                 die "failed to move ${HC_STDERR_LOG} to event directory at ${1}"
             fi
         fi
@@ -1221,6 +1425,17 @@ then
                 warn "notify_sms plugin is not avaible, cannot send alert via sms!"
             fi
         fi
+        # by Slack?
+        if (( DO_NOTIFY_SLACK == 1 ))
+        then
+            if (( HAS_NOTIFY_SLACK == 1 ))
+            then
+                # call plugin
+                notify_slack "${HC_NAME}" "${HC_FAIL_ID}"
+            else
+                warn "notify_slack plugin is not avaible, cannot send alert via Slack!"
+            fi
+        fi
     fi
 fi
 
@@ -1245,6 +1460,7 @@ fi
 function handle_timeout
 {
 (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+# shellcheck disable=SC2086
 [[ -n "${CHILD_PID}" ]] && kill -s TERM ${CHILD_PID}
 warn "child process with PID ${CHILD_PID} has been forcefully stopped"
 # shellcheck disable=SC2034
@@ -1374,8 +1590,8 @@ esac
 
 # mangle $ARG_HC to build the full list of HCs to be executed
 ARG_HC=""
-grep -i '^hc:' ${HOST_CONFIG_FILE} 2>/dev/null |\
-    while IFS=':' read _ HC_EXEC _ _
+grep -i '^hc:' "${HOST_CONFIG_FILE}" 2>/dev/null |\
+    while IFS=':' read -r _ HC_EXEC _ _
 do
     ARG_HC="${ARG_HC},${HC_EXEC}"
 done
@@ -1436,19 +1652,23 @@ case "${OS_NAME}" in
         # check system crontabs
         if (( CRON_COUNT == 0 ))
         then
+            # shellcheck disable=SC2002,SC2086
             CRON_COUNT=$(cat ${CRON_SYS_LOCATIONS} 2>/dev/null | grep -c -E -e "^[^#].*${CRON_HC}" 2>/dev/null)
         fi
         # check anacron
         if (( CRON_COUNT == 0 ))
         then
+            # shellcheck disable=SC2002,SC2086
             CRON_COUNT=$(cat ${CRON_ANACRON_LOCATIONS} 2>/dev/null | grep -c -E -e "^[^#].*${CRON_HC}" 2>/dev/null)
         fi
         ;;
     *)
         # use default root crontab
         CRON_COUNT=$(crontab -l 2>/dev/null | grep -c -E -e "^[^#].*${CRON_HC}" 2>/dev/null)
+        ;;
 esac
 
+# shellcheck disable=SC2086
 return ${CRON_COUNT}
 }
 
@@ -1480,11 +1700,11 @@ printf "%80s\n" | tr ' ' -
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | grep "core$" | sort 2>/dev/null | while read -r FDIR
 do
     # exclude core helper librar(y|ies)
-    # shellcheck disable=SC2010
+    # shellcheck disable=SC2010,SC2086
     ls -1 ${FDIR}/*.sh 2>/dev/null | grep -v "include_" | sort 2>/dev/null | while read -r FFILE
     do
         # cache script contents in memory
-        FSCRIPT=$(<${FFILE})
+        FSCRIPT="$(<${FFILE})"
 
         # reset state
         FSTATE="enabled"
@@ -1526,12 +1746,12 @@ print -n "Dead links: "
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | grep "core$" 2>/dev/null | while read -r FDIR
 do
     # do not use 'find -type l' here!
-    # shellcheck disable=SC2010,SC1117
+    # shellcheck disable=SC2010,SC1117,SC2086
     ls ${FDIR} 2>/dev/null | grep -v "\." 2>/dev/null | while read -r FFILE
     do
         if [[ -h "${FDIR}/${FFILE}" ]] && [[ ! -f "${FDIR}/${FFILE}" ]]
         then
-            printf "%s " ${FFILE##*/}
+            printf "%s " "${FFILE##*/}"
         fi
     done
 done
@@ -1563,6 +1783,7 @@ typeset FCONFIG=""
 typeset FSTATE=""
 typeset FFILE=""
 typeset FHEALTHY=""
+typeset FFIX=0
 typeset FSCHEDULED=0
 typeset FSCRIPT=""
 typeset HAS_FCONFIG=0
@@ -1580,21 +1801,44 @@ fi
 # print header
 if [[ "${FACTION}" != "list" ]]
 then
+    if (( ARG_LIST_DETAILS > 0 ))
+    then
         # shellcheck disable=SC1117
-    printf "%-40s\t%-8s\t%s\t\t%s\t%s\t%s\n" "Health Check" "State" "Version" "Config?" "Sched?" "H+?"
+        printf "%-40s\t%-8s\t%s\t\t%s\t%s\t%s\t%s\n" "Health Check" "State" "Version" "Config?" "Sched?" "H+?" "Fix?"
         # shellcheck disable=SC2183,SC1117
-    printf "%100s\n" | tr ' ' -
+        printf "%110s\n" | tr ' ' -
+    else
+        # shellcheck disable=SC1117
+        printf "%-40s\t%-8s\n" "Health Check" "State"
+        # shellcheck disable=SC2183,SC1117
+        printf "%60s\n" | tr ' ' -
+    fi
 fi
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | grep -v "core$" 2>/dev/null | sort 2>/dev/null |\
     while read -r FDIR
 do
+    # shellcheck disable=SC2012,SC2086
     ls -1 ${FDIR}/${FNEEDLE} 2>/dev/null | sort 2>/dev/null | while read -r FFILE
     do
         # cache script contents in memory
-        FSCRIPT=$(<${FFILE})
+        FSCRIPT="$(<${FFILE})"
 
+        # --list (basic)
         # find function name but skip helper functions in the plug-in file (function _name)
         FNAME=$(print -R "${FSCRIPT}" | grep -E -e "^function[[:space:]]+[^_]" 2>/dev/null)
+
+        # check state
+        DISABLE_FFILE="$(print ${FFILE##*/} | sed 's/\.sh$//')"
+        if [[ -f "${STATE_PERM_DIR}/${DISABLE_FFILE}.disabled" ]]
+        then
+            FSTATE="disabled"
+        else
+            FSTATE="enabled"
+        fi
+
+        # --list-details
+        if (( ARG_LIST_DETAILS > 0 ))
+        then
             # look for version string (cut off comments but don't use [:space:] in tr)
             FVERSION=$(print -R "${FSCRIPT}" | grep '^typeset _VERSION=' 2>/dev/null |\
                 awk 'match($0,/[0-9]+-[0-9]+-[0-9]+/){print substr($0, RSTART, RLENGTH)}' 2>/dev/null)
@@ -1648,14 +1892,14 @@ do
                     FCONFIG="No"
                     FHEALTHY="N/S"
                 fi
-        # check state
-        DISABLE_FFILE="$(print ${FFILE##*/} | sed 's/\.sh$//')"
-        if [[ -f "${STATE_PERM_DIR}/${DISABLE_FFILE}.disabled" ]]
+                # check fix
+                if (( $(print -R "${FSCRIPT}" | grep -c -E -e "_HC_CAN_FIX=1" 2>/dev/null) > 0 ))
                 then
-            FSTATE="disabled"
+                    FFIX="Yes"
                 else
-            FSTATE="enabled"
+                    FFIX="No"
                 fi
+
                 # reset state when unlinked
                 [[ -h ${FFILE%%.*} ]] || FSTATE="unlinked"
                 # check scheduling
@@ -1667,18 +1911,28 @@ do
                 else
                     FSCHEDULED="Yes"
                 fi
+        fi
 
         # show results
         if [[ "${FACTION}" != "list" ]]
+        then
+            if (( ARG_LIST_DETAILS > 0 ))
             then
                 # shellcheck disable=SC1117
-            printf "%-40s\t%-8s\t%s\t%s\t%s\t%s\n" \
+                printf "%-40s\t%-8s\t%s\t%s\t%s\t%s\t%s\n" \
                     "${FNAME#function *}" \
                     "${FSTATE}" \
                     "${FVERSION#typeset _VERSION=*}" \
                     "${FCONFIG}" \
                     "${FSCHEDULED}" \
-                "${FHEALTHY}"
+                    "${FHEALTHY}" \
+                    "${FFIX}"
+            else
+                # shellcheck disable=SC1117
+                printf "%-40s\t%-8s\n" \
+                    "${FNAME#function *}" \
+                    "${FSTATE}"
+            fi
         else
             # shellcheck disable=SC1117
             printf "%s\n" "${FNAME#function *}"
@@ -1694,12 +1948,12 @@ then
     print "${FPATH}" | tr ':' '\n' 2>/dev/null | grep -v "core" 2>/dev/null | while read -r FDIR
     do
         # do not use 'find -type l' here!
-        # shellcheck disable=SC2010,SC1117
+        # shellcheck disable=SC2010,SC1117,SC2086
         ls ${FDIR} 2>/dev/null | grep -v "\." 2>/dev/null | while read -r FFILE
         do
             if [[ -h "${FDIR}/${FFILE}" ]] && [[ ! -f "${FDIR}/${FFILE}" ]]
             then
-                printf "%s " ${FFILE##*/}
+                printf "%s " "${FFILE##*/}"
             fi
         done
     done
@@ -1713,10 +1967,18 @@ fi
 # legend
 if [[ "${FACTION}" != "list" ]]
 then
+    if (( ARG_LIST_DETAILS > 0 ))
+    then
         print
         print "Config?: plugin has a default configuration file (Yes/No)"
         print "Sched? : plugin is scheduled through cron (Yes/No)"
         print "H+?    : plugin can choose whether to log/show passed health checks (Yes/No/Supported/Not supported)"
+        print "Fix?   : plugin contains fix/healing logic (Yes/No) -- not used by default!"
+    else
+        print
+        print "Tip: use --list-details to see a list of health checks with more details"
+
+    fi
 fi
 
 return 0
@@ -1749,11 +2011,11 @@ printf "%100s\n" | tr ' ' -
 print "${FPATH}" | tr ':' '\n' 2>/dev/null  | grep "core$" 2>/dev/null | sort 2>/dev/null | while read -r FDIR
 do
     # exclude core helper librar(y|ies)
-    # shellcheck disable=SC2010
+    # shellcheck disable=SC2010,SC2086
     ls -1 ${FDIR}/*.sh 2>/dev/null | grep "include_" 2>/dev/null | sort 2>/dev/null | while read -r FFILE
     do
         # cache script contents in memory
-        FSCRIPT=$(<${FFILE})
+        FSCRIPT="$(<${FFILE})"
 
         # find function name
         FNAME=$(print -R "${FSCRIPT}" | grep -E -e "^function[[:space:]].*version_" 2>/dev/null)
@@ -1786,12 +2048,12 @@ print -n "Dead links: "
 print "${FPATH}" | tr ':' '\n' 2>/dev/null | grep "core$" 2>/dev/null | while read -r FDIR
 do
     # do not use 'find -type l' here!
-    # shellcheck disable=SC2010,SC1117
+    # shellcheck disable=SC2010,SC1117,SC2086
     ls ${FDIR} 2>/dev/null | grep -v "\." 2>/dev/null | while read -r FFILE
     do
         if [[ -h "${FDIR}/${FFILE}" ]] && [[ ! -f "${FDIR}/${FFILE}" ]]
         then
-            printf "%s " ${FFILE##*/}
+            printf "%s " "${FFILE##*/}"
         fi
     done
 done
@@ -1822,7 +2084,7 @@ then
     then
         print - "$*" | while read -r LOG_LINE
         do
-            print "${NOW}: INFO: [$$]:" "${LOG_LINE}" >>${LOG_FILE}
+            print "${NOW}: INFO: [$$]:" "${LOG_LINE}" >>"${LOG_FILE}"
         done
     fi
     if (( ARG_VERBOSE > 0 ))
@@ -1891,7 +2153,7 @@ fi
 
 # save the HC failure message for now
 print "${HC_STC}${MSG_SEP}${HC_NOW}${MSG_SEP}${HC_MSG_TEXT}${MSG_SEP}${HC_MSG_CUR_VAL}${MSG_SEP}${HC_MSG_EXP_VAL}" \
-    >>${HC_MSG_FILE}
+    >>"${HC_MSG_FILE}"
 
 return 0
 }
@@ -1946,13 +2208,14 @@ awk -F"${LOG_SEP}" '{
                         }
                     }
                 }
-                ' ${HC_LOG} 2>/dev/null
+                ' "${HC_LOG}" 2>/dev/null
 
 # archived events
 print; print
 print -R "--- ARCHIVED events --"
 print
-find ${ARCHIVE_DIR} -type f -name "hc.*.log" 2>/dev/null | while read -r _ARCHIVE_FILE
+# shellcheck disable=SC2086
+find ${ARCHIVE_DIR} -type f -name "hc.*.log" 2>/dev/null | sort -rn 2>/dev/null | while read -r _ARCHIVE_FILE
 do
     print "${_ARCHIVE_FILE}:"
     awk -F"${LOG_SEP}" '{
@@ -1988,7 +2251,7 @@ do
                             }
                         }
                     }
-                    ' ${_ARCHIVE_FILE} 2>/dev/null
+                    ' "${_ARCHIVE_FILE}" 2>/dev/null
 done
 
 return 0
@@ -2029,7 +2292,7 @@ then
     then
         print - "$*" | while read -r LOG_LINE
         do
-            print "${NOW}: WARN: [$$]:" "${LOG_LINE}" >>${LOG_FILE}
+            print "${NOW}: WARN: [$$]:" "${LOG_LINE}" >>"${LOG_FILE}"
         done
     fi
     if (( ARG_VERBOSE > 0 ))

opt/hc/lib/core/include_data.sh

@@ -30,7 +30,7 @@
 # RETURNS: 0
 function version_include_data
 {
-typeset _VERSION="2019-04-20"                               # YYYY-MM-DD
+typeset _VERSION="2020-12-27"                               # YYYY-MM-DD
 
 print "INFO: $0: ${_VERSION#version_*}"
 
@@ -51,7 +51,7 @@ typeset _PARAMETER="${1}"
 typeset _LVALUE=""
 typeset _RC=0
 
-_LVALUE=$(grep -i "^${_PARAMETER} *=" ${_CONFIG_FILE} | cut -f2- -d'=')
+_LVALUE=$(grep -i "^${_PARAMETER} *=" "${_CONFIG_FILE}" | cut -f2- -d'=')
 
 if [[ -n "${_LVALUE}" ]]
 then
@@ -196,6 +196,26 @@ done
 return 0
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_has_newline()
+# DOES: checks if a string contains newlines
+# EXPECTS: $1=haystack [string]
+# OUTPUTS: n/a
+# RETURNS: 0=no newline found; 1=newlines found
+# REQUIRES: n/a
+function data_has_newline
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+
+typeset _HAYSTACK="${1}"
+
+typeset _COUNT=$(print -R "${_HAYSTACK}" | wc -l 2>/dev/null)
+
+(( _COUNT > 1 )) && return 1
+
+return 0
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: data_magic_quote()
 # DOES: magically quotes a needle in a string (default needle is: %)
@@ -217,7 +237,7 @@ return 0
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: data_magic_unquote()
 # DOES: magically unquotes a needle in a string (default needle is: %)
-# EXPECTS: to be magically unquoted [string]; $2=needle [string]
+# EXPECTS: $1=to be magically unquoted [string]; $2=needle [string]
 # OUTPUTS: magically unquoted [string]
 # RETURNS: n/a
 # REQUIRES: n/a
@@ -593,6 +613,68 @@ esac
 return 0
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_expand_numerical_range()
+# DOES: expand numerical range (X-Y) to comma-separated list of numbers
+# EXPECTS: $1=numerical range [string]
+#          $2=flag for leading zeroes <10 [0=do not add (default),1=add]
+# OUTPUTS: [string]
+# RETURNS: 0=no error occurred; <>0=some error occurred
+# REQUIRES: n/a
+function data_expand_numerical_range
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _NUM_LIST=""
+typeset _HAS_LEAD_ZERO=${2:-0}
+
+case "${1}" in
+    *-*)
+        # range operator, expand
+        # check if there are only 2 operands (fields)
+        if (( $(print "${1}" | awk -F '-' '{ print NF }' 2>/dev/null) > 2 ))
+        then
+            (( ARG_DEBUG > 0 )) && debug "in range $1 found more than one range (-) operator"
+            return 1
+        fi
+        # check if X < Y
+        if print "${1}" | awk -F '-' '{ if ($1 < $2) { exit 1 }}' 2>/dev/null
+        then
+            (( ARG_DEBUG > 0 )) && debug "in range $1 operator Y is smaller or equal to operator Y"
+            return 1
+        fi
+        # expand list
+        _NUM_LIST=$(print "${1}"| awk -F '-' -v has_lead_zero=${_HAS_LEAD_ZERO} '
+            BEGIN { count = 0; }
+            {
+                while ($1 + count <= $2) {
+                    # add leading zero to sprintf when < 10
+                    if (has_lead_zero > 0 && $1 + count < 10) { lead_zero = "0" } else { lead_zero = "" }
+                    if (length (NUM_LIST) == 0) {
+                        NUM_LIST = sprintf ("%" lead_zero "2d", $1 + count);
+                    } else {
+                        NUM_LIST = sprintf ("%s,%" lead_zero "2d", NUM_LIST, $1 + count);                    }
+                    count++;
+                }
+            }
+            # remove space from end result and print
+            END { gsub(/[[:space:]]/, "", NUM_LIST); print NUM_LIST; }')
+        if [[ -z "${_NUM_LIST}" ]]
+        then
+            (( ARG_DEBUG > 0 )) && debug "range conversion returned empty list"
+            return 1
+        else
+            print "${_NUM_LIST}"
+        fi
+        ;;
+    *)
+        # no range, return as-is
+        print "${1}"
+        ;;
+esac
+
+return 0
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: data_encode_url
 # DOES: encode URL data
@@ -855,6 +937,7 @@ print ${_EPOCH}
 # REQUIRES: n/a
 function data_epoch2date
 {
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 typeset _UNIX_EPOCH="${1}"
 typeset _CONVERT_DATE=""
 
@@ -880,6 +963,154 @@ fi
 return 0
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_timestring_to_days()
+# DOES: converts a specific timestring to days (rounded to integer)
+# EXPECTS: time definition with a single s|m|h|d suffix [string]
+# OUTPUTS: time value in hours [string]
+# RETURNS: 0=conversion OK; 1=conversion failed
+# REQUIRES: n/a
+function data_timestring_to_days
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _DAYS=""
+
+case "${1}" in
+    *s|*s)
+        _DAYS=$(( $(print "${1%*[sS]}") / 60 / 60 / 24 ))
+        ;;
+    *m|*M)
+        _DAYS=$(( $(print "${1%*[mM]}") / 60 / 24 ))
+        ;;
+    *h|*H)
+        _DAYS=$(( $(print "${1%*[hH]}") / 24 ))
+        ;;
+    *d|*D)
+        _DAYS=$(print "${1%*[dD]}")
+        ;;
+    *)
+        # invalid suffix specified
+        (( ARG_DEBUG > 0 )) && debug "invalid time suffix specified (only s[econds]|m[inutes]|h[ours]|d[days] allowed)"
+        return 1
+        ;;
+esac
+
+print "${_DAYS}"
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_timestring_to_hours()
+# DOES: converts a specific timestring to hours (rounded to integer)
+# EXPECTS: time definition with a single s|m|h|d suffix [string]
+# OUTPUTS: time value in hours [string]
+# RETURNS: 0=conversion OK; 1=conversion failed
+# REQUIRES: n/a
+function data_timestring_to_hours
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _HOURS=""
+
+case "${1}" in
+    *s|*s)
+        _HOURS=$(( $(print "${1%*[sS]}") / 60 / 24 ))
+        ;;
+    *m|*M)
+        _HOURS=$(( $(print "${1%*[mM]}") / 60 ))
+        ;;
+    *h|*H)
+        _HOURS=$(print "${1%*[hH]}")
+        ;;
+    *d|*D)
+        _HOURS=$(( $(print "${1%*[dD]}") * 24 ))
+        ;;
+    *)
+        # invalid suffix specified
+        (( ARG_DEBUG > 0 )) && debug "invalid time suffix specified (only s[econds]|m[inutes]|h[ours]|d[days] allowed)"
+        return 1
+        ;;
+esac
+
+print "${_HOURS}"
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_timestring_to_mins()
+# DOES: converts a specific timestring to minutes (rounded to integer)
+# EXPECTS: time definition with a single s|m|h|d suffix [string]
+# OUTPUTS: time value in minutes [string]
+# RETURNS: 0=conversion OK; 1=conversion failed
+# REQUIRES: n/a
+function data_timestring_to_mins
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _MINUTES=""
+
+case "${1}" in
+    *s|*s)
+        _MINUTES=$(( $(print "${1%*[sS]}") / 60 ))
+        ;;
+    *m|*M)
+        _MINUTES=$(print "${1%*[mM]}")
+        ;;
+    *h|*H)
+        _MINUTES=$(( $(print "${1%*[hH]}") * 60 ))
+        ;;
+    *d|*D)
+        _MINUTES=$(( $(print "${1%*[dD]}") * 60 * 24 ))
+        ;;
+    *)
+        # invalid suffix specified
+        (( ARG_DEBUG > 0 )) && debug "invalid time suffix specified (only s[econds]|m[inutes]|h[ours]|d[days] allowed)"
+        return 1
+        ;;
+esac
+
+print "${_MINUTES}"
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: data_timestring_to_secs()
+# DOES: converts a specific timestring to seconds (rounded to integer)
+# EXPECTS: time definition with a single m|h|d suffix [string]
+# OUTPUTS: time value in seconds [string]
+# RETURNS: 0=conversion OK; 1=conversion failed
+# REQUIRES: n/a
+function data_timestring_to_secs
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _SECONDS=""
+
+case "${1}" in
+    *s|*s)
+        _SECONDS=$(print "${1%*[sS]}")
+        ;;
+    *m|*M)
+        _SECONDS=$(( $(print "${1%*[Mm]}") * 60 ))
+        ;;
+    *h|*H)
+        _SECONDS=$(( $(print "${1%*[hH]}") * 60 * 60 ))
+        ;;
+    *d|*D)
+        _SECONDS=$(( $(print "${1%*[dD]}") * 60 * 60 * 24 ))
+        ;;
+    *)
+        # invalid suffix specified
+        (( ARG_DEBUG > 0 )) && debug "invalid time suffix specified (only s[econds]|m[inutes]|h[ours]|d[days] allowed)"
+        return 1
+        ;;
+esac
+
+print "${_SECONDS}"
+
+return 0
+}
+
 #******************************************************************************
 # END of script
 #******************************************************************************

opt/hc/lib/core/include_os.sh

@@ -30,13 +30,107 @@
 # RETURNS: 0
 function version_include_os
 {
-typeset _VERSION="2019-03-16"                               # YYYY-MM-DD
+typeset _VERSION="2019-07-14"                               # YYYY-MM-DD
 
 print "INFO: $0: ${_VERSION#version_*}"
 
 return 0
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: linux_change_service()
+# DOES: restarts a specific service
+# EXPECTS: $1=name of service [string]; $2=action [stop/start/restart]
+# OUTPUTS: n/a
+# RETURNS: 0=success; 1=error
+# REQUIRES: linux_get_init(), linux_has_systemd_service()
+function linux_change_service
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _SERVICE="${1}"
+typeset _ACTION="${2}"
+
+# linux only
+check_platform 'Linux' || {
+    (( ARG_DEBUG > 0 )) && debug "may only run on platform(s): Linux"
+    return 1
+}
+
+# check action
+case "${_ACTION}" in
+    start|START|Start)
+        (( ARG_DEBUG > 0 )) && debug "requesting service start"
+        ;;
+    stop|STOP|Stop)
+        (( ARG_DEBUG > 0 )) && debug "requesting service stop"
+        ;;
+    restart|RESTART|Restart)
+        (( ARG_DEBUG > 0 )) && debug "requesting service restart"
+        ;;
+    *)
+        (( ARG_DEBUG > 0 )) && debug "requesting unknown service action"
+        return 1
+        ;;
+esac
+
+[[ -n "${LINUX_INIT}" ]] || linux_get_init
+case "${LINUX_INIT}" in
+    'systemd')
+        (( ARG_DEBUG > 0 )) && debug "is a systemd managed host"
+        _CHECK_SYSTEMD_SERVICE=$(linux_has_systemd_service "${_SERVICE}")
+        if (( _CHECK_SYSTEMD_SERVICE > 0 ))
+        then
+            systemctl --quiet ${_ACTION} ${_SERVICE} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+            return $?
+        else
+            warn "systemd unit file not found {${_SERVICE}}"
+            return 1
+        fi
+        ;;
+    'upstart')
+        (( ARG_DEBUG > 0 )) && debug "is an upstart managed host"
+        warn "code for upstart managed systems not implemented, NOOP"
+        return 1
+        ;;
+    'sysv')
+        (( ARG_DEBUG > 0 )) && debug "is a sysv managed host"
+        service ${_SERVICE} ${_ACTION} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+        return $?
+        ;;
+    *)
+        (( ARG_DEBUG > 0 )) && debug "unknown init system for this host?"
+        return 1
+        ;;
+esac
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: linux_exec_ssh()
+# DOES: execute a shell command remotely via SSH
+# EXPECTS: 1=options [string], 2=user [string], 3=host [string], 4=command [string]
+# RETURNS: exit code of remote command
+# OUTPUTS: STDOUT from SSH call
+# REQUIRES: ssh command-line utility
+function linux_exec_ssh
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+typeset _SSH_OPTS="${1}"
+typeset _SSH_USER="${2}"
+typeset _SSH_HOST="${3}"
+typeset _SSH_COMMAND="${4}"
+
+if [[ -z "${_SSH_USER}" || -z "${_SSH_HOST}" || -z "${_SSH_COMMAND}" ]]
+then
+    return 255
+fi
+# shellcheck disable=SC2086
+ssh ${_SSH_OPTS} -l ${_SSH_USER} ${_SSH_HOST} ${_SSH_COMMAND} 2>>${HC_STDERR_LOG} </dev/null
+
+return $?
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: linux_get_distro()
 # DOES: get Linux distribution name & version, sets $LINUX_DISTRO & $LINUX_RELEASE
@@ -118,12 +212,75 @@ elif [[ -r /usr/share/upstart ]]
 then
     # shellcheck disable=SC2034
     LINUX_INIT="upstart"
-
 fi
 
 return 0
 }
 
+# -----------------------------------------------------------------------------
+# @(#) FUNCTION: linux_has_service()
+# DOES: check if a specific service is present and/or enabled
+# EXPECTS: name of service [string]
+# OUTPUTS: 0=not present; 1=present (not enabled); 2=present (enabled)
+# RETURNS: 0=success; 1=error
+# REQUIRES: linux_get_init(), linux_has_systemd_service()
+function linux_has_service
+{
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _SERVICE="${1}"
+typeset _HAS_SERVICE=0
+
+# linux only
+check_platform 'Linux' || {
+    warn "may only run on platform(s): Linux"
+    return 1
+}
+
+[[ -n "${LINUX_INIT}" ]] || linux_get_init
+case "${LINUX_INIT}" in
+    'systemd')
+        (( ARG_DEBUG > 0 )) && debug "is a systemd managed host"
+        _CHECK_SYSTEMD_SERVICE=$(linux_has_systemd_service "${_SERVICE}")
+        if (( _CHECK_SYSTEMD_SERVICE > 0 ))
+        then
+            systemctl --quiet is-enabled ${_SERVICE} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+            if (( $? > 0 ))
+            then
+                _HAS_SERVICE=1
+            else
+                _HAS_SERVICE=2
+            fi
+        else
+            warn "systemd unit file not found {${_SERVICE}}"
+            return 1
+        fi
+        ;;
+    'upstart')
+        (( ARG_DEBUG > 0 )) && debug "is an upstart managed host"
+        warn "code for upstart managed systems not implemented, NOOP"
+        return 1
+        ;;
+    'sysv')
+        (( ARG_DEBUG > 0 )) && debug "is a sysv managed host"
+        chkconfig ${_SERVICE} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+        if (( $? > 0 ))
+        then
+            _HAS_SERVICE=2
+        else
+            _HAS_SERVICE=0
+        fi
+        ;;
+    *)
+        (( ARG_DEBUG > 0 )) && debug "unknown init system for this host?"
+        return 1
+        ;;
+esac
+
+print ${_HAS_SERVICE}
+
+return 0
+}
+
 # -----------------------------------------------------------------------------
 # @(#) FUNCTION: linux_has_crm()
 # DOES: check if Corosync (CRM version) is running
@@ -249,30 +406,70 @@ return ${_RC}
 }
 
 # -----------------------------------------------------------------------------
-# @(#) FUNCTION: linux_exec_ssh()
-# DOES: execute a shell command remotely via SSH
-# EXPECTS: 1=options [string], 2=user [string], 3=host [string], 4=command [string]
-# RETURNS: exit code of remote command
-# OUTPUTS: STDOUT from SSH call
-# REQUIRES: ssh command-line utility
-function linux_exec_ssh
+# @(#) FUNCTION: linux_runs_service()
+# DOES: check if a specific service is running (active)
+# EXPECTS: name of service [string]
+# OUTPUTS: 0=not running/not active; 1=running/active
+# RETURNS: 0=success; 1=error
+# REQUIRES: linux_get_init(), linux_has_systemd_service()
+function linux_runs_service
 {
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
-typeset _SSH_OPTS="${1}"
-typeset _SSH_USER="${2}"
-typeset _SSH_HOST="${3}"
-typeset _SSH_COMMAND="${4}"
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+typeset _SERVICE="${1}"
+typeset _RUNS_SERVICE=0
 
-if [[ -z "${_SSH_USER}" || -z "${_SSH_HOST}" || -z "${_SSH_COMMAND}" ]]
-then
-    return 255
-fi
-# shellcheck disable=SC2086
-ssh ${_SSH_OPTS} -l ${_SSH_USER} ${_SSH_HOST} ${_SSH_COMMAND} 2>>${HC_STDERR_LOG} </dev/null
-
-return $?
+# linux only
+check_platform 'Linux' || {
+    (( ARG_DEBUG > 0 )) && debug "may only run on platform(s): Linux"
+    return 1
 }
 
+[[ -n "${LINUX_INIT}" ]] || linux_get_init
+case "${LINUX_INIT}" in
+    'systemd')
+        (( ARG_DEBUG > 0 )) && debug "is a systemd managed host"
+        _CHECK_SYSTEMD_SERVICE=$(linux_has_systemd_service "${_SERVICE}")
+        if (( _CHECK_SYSTEMD_SERVICE > 0 ))
+        then
+            systemctl --quiet is-active ${_SERVICE} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+            if (( $? > 0 ))
+            then
+                _RUNS_SERVICE=0
+            else
+                _RUNS_SERVICE=1
+            fi
+        else
+            warn "systemd unit file not found {${_SERVICE}}"
+            return 1
+        fi
+        ;;
+    'upstart')
+        (( ARG_DEBUG > 0 )) && debug "is an upstart managed host"
+        warn "code for upstart managed systems not implemented, NOOP"
+        return 1
+        ;;
+    'sysv')
+        (( ARG_DEBUG > 0 )) && debug "is a sysv managed host"
+        service ${_SERVICE} status >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+        if (( $? > 0 ))
+        then
+            _RUNS_SERVICE=0
+        else
+            _RUNS_SERVICE=1
+        fi
+        ;;
+    *)
+        (( ARG_DEBUG > 0 )) && debug "unknown init system for this host?"
+        return 1
+        ;;
+esac
+
+print ${_RUNS_SERVICE}
+
+return 0
+}
+
+
 #******************************************************************************
 # END of script
 #******************************************************************************

opt/hc/lib/core/notify_mail.sh

@@ -30,7 +30,7 @@
 function notify_mail
 {
 # ------------------------- CONFIGURATION starts here -------------------------
-typeset _VERSION="2019-04-20"                               # YYYY-MM-DD
+typeset _VERSION="2022-02-16"                               # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="AIX,HP-UX,Linux"              # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -58,6 +58,7 @@ typeset _MAIL_ATTACH_BIT=""
 typeset _MAIL_METHOD=""
 typeset _MAIL_RC=0
 typeset _MAILX_BIN=""
+typeset _MAILX_ATTACH_SWITCH=""
 typeset _MUTT_BIN=""
 typeset _SENDMAIL_BIN=""
 typeset _UUENCODE_BIN=""
@@ -90,6 +91,17 @@ case "${OS_NAME}" in
             if [[ -x ${_MAILX_BIN} ]] && [[ -n "${_MAILX_BIN}" ]]
             then
                 _MAIL_METHOD="mailx"
+                # check which switch we need for attaching a file:
+                # Debian/Ubuntu: -A file
+                # Redhat (Heirloom version): -a file
+                ${_MAILX_BIN} -h 2>&1 | grep -q -e "-a FILE" >/dev/null 2>/dev/null
+                # shellcheck disable=SC2181
+                if (( $? == 0 ))
+                then
+                    _MAILX_ATTACH_SWITCH="-a "
+                else
+                    _MAILX_ATTACH_SWITCH="-A "
+                fi
             else
                 _MAIL_METHOD="sendmail"
             fi
@@ -122,18 +134,18 @@ then
     [[ -r "${_MAIL_INFO_TPL}" ]] || die "cannot read mail info template at ${_MAIL_INFO_TPL}"
     eval "cat << __EOT
 $(sed 's/[\$`]/\\&/g;s/<## @\([^ ]*\) ##>/${\1}/g' <${_MAIL_INFO_TPL})
-__EOT" >${_TMP1_MAIL_FILE}
+__EOT" >"${_TMP1_MAIL_FILE}"
 fi
 
 # create header part
 [[ -r "${_MAIL_HEADER_TPL}" ]] || die "cannot read mail header template at ${_MAIL_HEADER_TPL}"
 eval "cat << __EOT
 $(sed 's/[\$`]/\\&/g;s/<## @\([^ ]*\) ##>/${\1}/g' <${_MAIL_HEADER_TPL})
-__EOT" >>${_TMP1_MAIL_FILE}
-print "" >>${_TMP1_MAIL_FILE}
+__EOT" >>"${_TMP1_MAIL_FILE}"
+print "" >>"${_TMP1_MAIL_FILE}"
 
 # create body part (from $HC_MSG_VAR)
-print "${HC_MSG_VAR}" | while IFS=${MSG_SEP} read _MAIL_MSG_STC _ _MAIL_MSG_TEXT _MAIL_MSG_CUR_VAL _MAIL_MSG_EXP_VAL
+print "${HC_MSG_VAR}" | while IFS=${MSG_SEP} read -r _MAIL_MSG_STC _ _MAIL_MSG_TEXT _MAIL_MSG_CUR_VAL _MAIL_MSG_EXP_VAL
 do
     # magically unquote if needed
     if [[ -n "${_MAIL_MSG_TEXT}" ]]
@@ -175,8 +187,8 @@ done
 [[ -r "${_MAIL_BODY_TPL}" ]] || die "cannot read mail body template at ${_MAIL_BODY_TPL}"
 eval "cat << __EOT
 $(sed 's/[\$`]/\\&/g;s/<## @\([^ ]*\) ##>/${\1}/g' <${_MAIL_BODY_TPL})
-__EOT" >>${_TMP1_MAIL_FILE}
-print "" >>${_TMP1_MAIL_FILE}
+__EOT" >>"${_TMP1_MAIL_FILE}"
+print "" >>"${_TMP1_MAIL_FILE}"
 
 # HC STDOUT log? (drop the .$$ bit)
 _MAIL_STDOUT_LOG="${EVENTS_DIR}/${DIR_PREFIX}/${_MAIL_FAIL_ID}/${_HC_STDOUT_LOG_SHORT%.*}"
@@ -184,7 +196,14 @@ if [[ -s "${_MAIL_STDOUT_LOG}" ]]
 then
     # shellcheck disable=SC2034
     _MAIL_STDOUT_MSG="${_MAIL_STDOUT_LOG}"
+    case "${_MAIL_METHOD}" in
+        "mailx")
+            _MAIL_ATTACH_BIT="${_MAILX_ATTACH_SWITCH} ${_MAIL_STDOUT_LOG}"
+            ;;
+        *)
             _MAIL_ATTACH_BIT="-a ${_MAIL_STDOUT_LOG}"
+            ;;
+    esac
 else
     # shellcheck disable=SC2034
     _MAIL_STDOUT_MSG="no log file available"
@@ -195,7 +214,14 @@ if [[ -s "${_MAIL_STDERR_LOG}" ]]
 then
     # shellcheck disable=SC2034
     _MAIL_STDERR_MSG="${_MAIL_STDERR_LOG}"
+    case "${_MAIL_METHOD}" in
+        "mailx")
+            _MAIL_ATTACH_BIT="${_MAIL_ATTACH_BIT} ${_MAILX_ATTACH_SWITCH} ${_MAIL_STDERR_LOG}"
+            ;;
+        *)
             _MAIL_ATTACH_BIT="${_MAIL_ATTACH_BIT} -a ${_MAIL_STDERR_LOG}"
+            ;;
+    esac
 else
      # shellcheck disable=SC2034
     _MAIL_STDERR_MSG="no log file available"
@@ -205,28 +231,29 @@ fi
 [[ -r ${_MAIL_FOOTER_TPL} ]] || die "cannot read mail body template at ${_MAIL_FOOTER_TPL}"
 eval "cat << __EOT
 $(sed 's/[\$`]/\\&/g;s/<## @\([^ ]*\) ##>/${\1}/g' <${_MAIL_FOOTER_TPL})
-__EOT" >>${_TMP1_MAIL_FILE}
+__EOT" >>"${_TMP1_MAIL_FILE}"
 
 # combine and send message components
 case "${_MAIL_METHOD}" in
     "mailx")
         # remove non-ASCII characters to avoid Exchange ATT00001.bin
-        cat ${_TMP1_MAIL_FILE} | tr -cd '[:print:]\n' 2>/dev/null |\
+        # shellcheck disable=SC2086
+        tr -cd '[:print:]\n' < "${_TMP1_MAIL_FILE}" 2>/dev/null |\
             ${_MAILX_BIN} ${_MAIL_ATTACH_BIT} -s "${_SUBJ_MSG}" "${ARG_MAIL_TO}"
         _MAIL_RC=$?
         ;;
     "mutt")
         # attach bit goes at the end
-        cat ${_TMP1_MAIL_FILE} 2>/dev/null |\
-            ${_MUTT_BIN} -s "${_SUBJ_MSG}" "${ARG_MAIL_TO}" ${_MAIL_ATTACH_BIT}
+        # shellcheck disable=SC2086
+        ${_MUTT_BIN} -s "${_SUBJ_MSG}" "${ARG_MAIL_TO}" ${_MAIL_ATTACH_BIT} <"${_TMP1_MAIL_FILE}"
         _MAIL_RC=$?
         ;;
     "sendmail")
         [[ -s "${_MAIL_STDOUT_LOG}" ]] && \
-            uuencode ${_MAIL_STDOUT_LOG} stdout.log >>${_TMP2_MAIL_FILE} 2>/dev/null
+            uuencode "${_MAIL_STDOUT_LOG}" stdout.log >>"${_TMP2_MAIL_FILE}" 2>/dev/null
         [[ -s "${_MAIL_STDERR_LOG}" ]] && \
-            uuencode ${_MAIL_STDERR_LOG} stderr.log >>${_TMP2_MAIL_FILE} 2>/dev/null
-        cat ${_TMP1_MAIL_FILE} ${_TMP2_MAIL_FILE} 2>/dev/null | ${_SENDMAIL_BIN} -t
+            uuencode "${_MAIL_STDERR_LOG}" stderr.log >>"${_TMP2_MAIL_FILE}" 2>/dev/null
+        cat "${_TMP1_MAIL_FILE}" "${_TMP2_MAIL_FILE}" 2>/dev/null | ${_SENDMAIL_BIN} -t
         _MAIL_RC=$?
         ;;
     *)
@@ -242,8 +269,8 @@ else
 fi
 
 # clean up temporary files
-[[ -f ${_TMP1_MAIL_FILE} ]] && rm -f ${_TMP1_MAIL_FILE} >/dev/null 2>&1
-[[ -f ${_TMP2_MAIL_FILE} ]] && rm -f ${_TMP2_MAIL_FILE} >/dev/null 2>&1
+[[ -f ${_TMP1_MAIL_FILE} ]] && rm -f "${_TMP1_MAIL_FILE}" >/dev/null 2>&1
+[[ -f ${_TMP2_MAIL_FILE} ]] && rm -f "${_TMP2_MAIL_FILE}" >/dev/null 2>&1
 
 return 0
 }

opt/hc/lib/core/notify_slack.sh

@@ -0,0 +1,135 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) notify_slack.sh
+#******************************************************************************
+# @(#) Copyright (C) 2022 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: notify_slack
+# DOES: send message to slack app
+# EXPECTS: 1=HC name [string], 2=HC FAIL_ID [string]
+# RETURNS: 0
+# REQUIRES: data_contains_string(), data_get_lvalue_from_config(), data_magic_unquote(),
+#           init_hc(), log(), warn(), curl
+#
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function notify_slack
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/core/providers/$0.conf"
+typeset _VERSION="2022-10-14"                               # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="AIX,HP-UX,Linux"              # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+
+typeset _SLACK_HC="$1"
+typeset _SLACK_FAIL_ID="$2"
+
+typeset _SLACK_TEXT=""
+typeset _SLACK_MSG_STC=""
+typeset _SLACK_MSG_TEXT=""
+typeset _SLACK_MSG_CUR_VAL=""
+typeset _SLACK_MSG_EXP_VAL=""
+typeset _CURL_BIN=""
+typeset _SLACK_WEBHOOK=""
+
+# handle config file
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read required config values
+_SLACK_WEBHOOK=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'SLACK_WEBHOOK')
+if [[ -z "${_SLACK_WEBHOOK}" ]]
+then
+    warn "no value set for 'SLACK_WEBHOOK' in ${_CONFIG_FILE}"
+    return 1
+fi
+
+# create header part
+_SLACK_TEXT="${EXEC_USER}@${HOST_NAME}: HC ${_SLACK_HC} failed, FAIL_ID=${_SLACK_FAIL_ID}"
+
+# create body part (from $HC_MSG_VAR)
+print "${HC_MSG_VAR}" | while IFS=${MSG_SEP} read -r _SLACK_MSG_STC _ _SLACK_MSG_TEXT _SLACK_MSG_CUR_VAL _SLACK_MSG_EXP_VAL
+do
+    # magically unquote if needed
+    if [[ -n "${_SLACK_MSG_TEXT}" ]]
+    then
+        data_contains_string "${_SLACK_MSG_TEXT}" "${MAGIC_QUOTE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            _SLACK_MSG_TEXT=$(data_magic_unquote "${_SLACK_MSG_TEXT}")
+        fi
+    fi
+    if [[ -n "${_SLACK_MSG_CUR_VAL}" ]]
+    then
+        data_contains_string "${_SLACK_MSG_CUR_VAL}" "${MAGIC_QUOTE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            _SLACK_MSG_CUR_VAL=$(data_magic_unquote "${_SLACK_MSG_CUR_VAL}")
+        fi
+    fi
+    if [[ -n "${_SLACK_MSG_EXP_VAL}" ]]
+    then
+        data_contains_string "${_SLACK_MSG_EXP_VAL}" "${MAGIC_QUOTE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            _SLACK_MSG_EXP_VAL=$(data_magic_unquote "${_SLACK_MSG_EXP_VAL}")
+        fi
+    fi
+    if (( _SLACK_MSG_STC > 0 ))
+    then
+        # shellcheck disable=SC1117
+        _SLACK_BODY=$(printf "%s\n%s\n" "${_SLACK_BODY}" "${_SLACK_MSG_TEXT}")
+    fi
+done
+
+# send message
+# find 'curl'
+_CURL_BIN="$(command -v curl 2>/dev/null)"
+if [[ -x ${_CURL_BIN} ]] && [[ -n "${_CURL_BIN}" ]]
+then
+    if (( ARG_DEBUG == 0 ))
+    then
+        ${_CURL_BIN} --silent --data-urlencode \
+          "$(printf 'payload={"text": "%s\n\n%s" }' "${_SLACK_TEXT}" "${_SLACK_BODY}")" \
+          "${_SLACK_WEBHOOK}" >/dev/null 2>&1
+    else
+        ${_CURL_BIN} --data-urlencode \
+          "$(printf 'payload={"text": "%s\n\n%s" }' "${_SLACK_TEXT}" "${_SLACK_BODY}")" \
+          "${_SLACK_WEBHOOK}"
+    fi
+ else
+    die "unable to send message to Slack - curl is not installed here"
+fi
+
+log "Slack alert sent: ${_SLACK_HC} failed, FAIL_ID=${_SLACK_FAIL_ID}"
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/core/notify_sms.sh

@@ -20,7 +20,8 @@
 # DOES: send sms alert
 # EXPECTS: 1=HC name [string], 2=HC FAIL_ID [string]
 # RETURNS: 0
-# REQUIRES: data_get_lvalue_from_config(), init_hc(), log(), warn()
+# REQUIRES: data_encode_url(), data_get_lvalue_from_config(), init_hc(),
+#           log(), warn(), curl
 #
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
@@ -31,7 +32,7 @@ function notify_sms
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/core/providers/$0.conf"
-typeset _VERSION="2018-10-28"                               # YYYY-MM-DD
+typeset _VERSION="2022-10-14"                               # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="AIX,HP-UX,Linux"              # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 

opt/hc/lib/core/report_std.sh

@@ -30,7 +30,7 @@
 function report_std
 {
 # ------------------------- CONFIGURATION starts here -------------------------
-typeset _VERSION="2019-03-16"                               # YYYY-MM-DD
+typeset _VERSION="2020-04-08"                               # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="AIX,HP-UX,Linux"              # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -59,8 +59,14 @@ typeset _OLDER_MONTH=""
 typeset _OLDER_YEAR=""
 typeset _NEWER_MONTH=""
 typeset _NEWER_YEAR=""
+typeset _HC_REPORT_CACHE_LAST_STUB="${STATE_PERM_DIR}/cache.report-last"
+typeset _HC_REPORT_CACHE_LAST_FILE=""
+typeset _HC_REPORT_CACHE_TODAY_FILE="${STATE_PERM_DIR}/cache.report-today"
+typeset _USE_CACHE=0
+typeset _USE_ANY_CACHE=0
+typeset _CACHE_NOTE_BIT=""
 
-# set archive log stash
+# set archive log stash (never use cache files)
 if (( ARG_HISTORY > 0 )) || [[ -n "${ARG_OLDER}" ]] || [[ -n "${ARG_NEWER}" ]]
 then
     set +f  # file globbing must be on
@@ -148,10 +154,46 @@ then
         _HC_LAST_TIME=""
         _HC_LAST_STC=0
         _HC_LAST_FAIL_ID="-"
+        _USE_CACHE=0
+
+        # check for cache usage
+        if (( ARG_HISTORY == 0 ))
+        then
+            case "${HC_REPORT_CACHE_LAST}" in
+                Yes|yes|YES)
+                    _HC_REPORT_CACHE_LAST_FILE="${_HC_REPORT_CACHE_LAST_STUB}-${_HC_LAST}"
+                    # check if cache file exists
+                    if [[ -s "${_HC_REPORT_CACHE_LAST_FILE}" ]]
+                    then
+                        _LOG_STASH="${_HC_REPORT_CACHE_LAST_FILE}"
+                        _USE_CACHE=1
+                        _USE_ANY_CACHE=1
+                        (( ARG_DEBUG > 0 )) && debug "setting log stash to cache file at ${_HC_REPORT_CACHE_LAST_FILE}"
+                    else
+                        (( ARG_DEBUG > 0 )) && debug "HC_REPORT_CACHE_LAST is enabled but unable to find cache file at ${_HC_REPORT_CACHE_LAST_FILE}"
+                        # reset log stash to current log
+                        _LOG_STASH="${HC_LOG} ${_LOG_STASH}"
+                    fi
+                    ;;
+                *)
+                    # no caching: reset log stash to current log
+                    (( ARG_DEBUG > 0 )) && debug "HC_REPORT_CACHE_LAST is disabled"
+                    _LOG_STASH="${HC_LOG} ${_LOG_STASH}"
+                    ;;
+            esac
+        fi
+
+        # determine LAST_TIME from cache or log(s)
+        if (( ARG_HISTORY == 0 )) && (( _USE_CACHE > 1 ))
+        then
+            _HC_LAST_TIME="$(tail -n 1 ${_LOG_STASH} 2>/dev/null | cut -f1 -d${LOG_SEP} 2>/dev/null)"
+        else
             # find last event or block of events (same timestamp)
             # (but unfortunately this is only accurate to events within the SAME second!)
             # shellcheck disable=SC2086
             _HC_LAST_TIME="$(grep -h ${_HC_LAST} ${_LOG_STASH} 2>/dev/null | sort -n 2>/dev/null | cut -f1 -d${LOG_SEP} 2>/dev/null | uniq 2>/dev/null | tail -1 2>/dev/null)"
+        fi
+
         if [[ -z "${_HC_LAST_TIME}" ]]
         then
             _HC_LAST_TIME="-"
@@ -181,12 +223,26 @@ then
         fi
         # report on findings
         # shellcheck disable=SC1117
+        if (( _USE_CACHE > 0 ))
+        then
+            printf "| %-40s | %-20s | %-14s | %-4s (C)\n" \
+                "${_HC_LAST}" "${_HC_LAST_TIME}" "${_HC_LAST_FAIL_ID}" "${_HC_LAST_STC}"
+        else
             printf "| %-40s | %-20s | %-14s | %-4s\n" \
                 "${_HC_LAST}" "${_HC_LAST_TIME}" "${_HC_LAST_FAIL_ID}" "${_HC_LAST_STC}"
+        fi
     done
-    # disclaimer
-    print "NOTE: this report only shows the overall combined status of all events of each HC within exactly"
-    print "      the *same* time stamp (seconds precise). It may therefore fail to report certain FAIL IDs."
+    # spacer
+    print
+    # disclaimer & note(s)
+    if (( _USE_ANY_CACHE > 0 ))
+    then
+        print "NOTE: entries suffixed by (C) indicate results were retrieved from a cache file. If you wish to use "
+        print "      the real log files then disable HC_REPORT_CACHE_LAST in ${CONFIG_FILE}"
+    fi
+    (( ARG_HISTORY == 0 )) && _CACHE_NOTE_BIT="for non-cached entries: "
+    print "NOTE: ${_CACHE_NOTE_BIT}this report only shows the overall combined status of all events of each HC"
+    print "      within exactly the *same* time stamp (seconds precise). It may therefore fail to report certain FAIL IDs."
     print "      Use '--report' to get the exact list of failure events."
 # other reports
 else
@@ -198,7 +254,31 @@ else
         (( _IS_VALID_ID > 0 )) || die "invalid ID specified"
          _ID_NEEDLE="${ARG_FAIL_ID}"
     fi
-    (( ARG_TODAY > 0 )) && _ID_NEEDLE="$(date '+%Y%m%d')"    # refers to timestamp of HC FAIL_ID
+    # set today's needle and check cache usage
+    if (( ARG_TODAY > 0 ))
+    then
+        _ID_NEEDLE="$(date '+%Y%m%d')"    # refers to timestamp of HC FAIL_ID
+        # do not use a cache file when --with-history
+        if (( ARG_HISTORY == 0 ))
+        then
+            case "${HC_REPORT_CACHE_TODAY}" in
+                Yes|yes|YES)
+                    # check if cache file exists
+                    if [[ -s "${_HC_REPORT_CACHE_TODAY_FILE}" ]]
+                    then
+                        _LOG_STASH="${_HC_REPORT_CACHE_TODAY_FILE}"
+                        _USE_CACHE=1
+                        (( ARG_DEBUG > 0 )) && debug "setting log stash to today's cache file at ${_HC_REPORT_CACHE_TODAY_FILE}"
+                    else
+                        (( ARG_DEBUG > 0 )) && debug "HC_REPORT_CACHE_TODAY is enabled but unable to find cache file at ${_HC_REPORT_CACHE_TODAY_FILE}"
+                    fi
+                    ;;
+                *)
+                    (( ARG_DEBUG > 0 )) && debug "HC_REPORT_CACHE_TODAY is disabled"
+                    ;;
+            esac
+        fi
+    fi
 
     # reverse?
     if (( ARG_REVERSE == 0 ))
@@ -262,9 +342,9 @@ else
                         split (events[i], event, "|");
                         printf ("\n| %-20s | %-14s | %-40s | %-s", event[1], event[5], event[2], event[4]);
                     }
-                    printf ("\n\nSUMMARY: %s failed HC event(s) found.\n", event_count);
+                    printf ("\n\nSUMMARY: %s failed HC event(s) found.\n\n", event_count);
                 } else {
-                    printf ("\nSUMMARY: 0 failed HC events found.\n");
+                    printf ("\nSUMMARY: 0 failed HC events found.\n\n");
                 }
             }
             ' 2>/dev/null
@@ -316,17 +396,28 @@ else
         # shellcheck disable=SC2183,SC1117
         printf "%80s\n" | tr ' ' -
     fi
+
+    # add notes
+    # cache or not?
+    if (( _USE_CACHE > 0 ))
+    then
+        print "NOTE: results were retrieved from a cache file. If you wish to use the real log files then"
+        print "      remove ${_HC_REPORT_CACHE_TODAY_FILE} and/or disable HC_REPORT_CACHE_TODAY in ${CONFIG_FILE}"
+    fi
 fi
 
-# general note: history or not?
+# add general notes
+# history or not?
 if (( ARG_HISTORY > 0 ))
 then
     print "NOTE: showing results with all history (archive) included (--with-history)"
 else
-    print "NOTE: showing results only of current log entries (use --with-history to view all entries)"
+    print "NOTE: showing only results of current entries (use --with-history to view all entries)"
 fi
 
 # check consistency of log(s)
+# note: should no longer be necessary as of release 19/05/2019 but we keep the
+# check alive for now
 # shellcheck disable=SC2086
 find ${_LOG_STASH} -type f -print 2>/dev/null | while read -r _CHECK_FILE
 do

opt/hc/lib/platform/aix/check_aix_file_change.sh

@@ -29,6 +29,8 @@
 # @(#) 2019-01-24: arguments fix [Patrick Van der Veken]
 # @(#) 2019-03-09: added support for --log-healthy [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2020-09-05: fix log_hc call for failed checksum + quote fix [Patrick Van der Veken]
+# @(#) 2021-01-13: fix log_hc call (wrong logic) [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -38,7 +40,7 @@ function check_aix_file_change
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-03-16"                           # YYYY-MM-DD
+typeset _VERSION="2021-01-13"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -275,7 +277,7 @@ do
             openssl-sha256)
                 if (( _USE_OPENSSL == 1 ))
                 then
-                    _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
+                    _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
                     _FILE_TYPE="openssl-sha256"
                 else
                     _MSG="cannot compute checksum [${_FILE_TYPE}] for ${_FILE_TO_CHECK}"
@@ -285,7 +287,7 @@ do
             cksum-crc32)
                 if (( _USE_CKSUM == 1 ))
                 then
-                    _FILE_CKSUM=$(${_CKSUM_BIN} ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
+                    _FILE_CKSUM=$(${_CKSUM_BIN} "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
                     _FILE_TYPE="cksum-crc32"
                 else
                     _MSG="cannot compute checksum [${_FILE_TYPE}] for ${_FILE_TO_CHECK}"
@@ -301,11 +303,11 @@ do
         # new file
         if (( _USE_OPENSSL == 1 ))
         then
-            _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
+            _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
             _FILE_TYPE="openssl-sha256"
         elif (( _USE_CKSUM == 1 ))
         then
-            _FILE_CKSUM=$(${_CKSUM_BIN} ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
+            _FILE_CKSUM=$(${_CKSUM_BIN} "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
             _FILE_TYPE="cksum-crc32"
         else
             _MSG="cannot compute checksum (openssl/cksum) for ${_FILE_TO_CHECK}"
@@ -321,7 +323,7 @@ do
     fi
 
     # bounce failures back and jump to next file
-    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    if (( _LOG_HEALTHY > 0 && _STC > 0 ))
     then
         log_hc "$0" ${_STC} "${_MSG}"
         continue
@@ -347,7 +349,7 @@ do
     printf "%s|%s|%s\n" "${_FILE_TO_CHECK}" "${_FILE_TYPE}" "${_FILE_CKSUM}" >>${_TMP2_FILE}
 
     # report with curr/exp values
-    if (( _LOG_HEALTHY > 0 ))
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
     then
         log_hc "$0" ${_STC} "${_MSG}" "${_FILE_CKSUM}" "${_STATE_FILE_CKSUM}"
         continue

opt/hc/lib/platform/aix/check_aix_uptime.sh

@@ -0,0 +1,349 @@
+#!/usr/bin/env ksh
+#------------------------------------------------------------------------------
+# @(#) check_aix_uptime
+#------------------------------------------------------------------------------
+# @(#) Copyright (C) 2020 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#------------------------------------------------------------------------------
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_aix_uptime
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_is_numeric(), data_timestring_to_mins(), data_comma2space(),
+#           init_hc(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2020-12-21: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#------------------------------------------------------------------------------
+
+# -----------------------------------------------------------------------------
+function check_aix_uptime
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _STATE_FILE="${STATE_PERM_DIR}/current.uptime"
+typeset _VERSION="2020-12-21"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="AIX"                      # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _LOG_HEALTHY=0
+typeset _CFG_HEALTHY=""
+typeset _CFG_CHECK_REBOOT=""
+typeset _CFG_REBOOT_TIME=""
+typeset _CFG_CHECK_OLD_AGE=""
+typeset _CFG_OLD_AGE_TIME=""
+typeset _CHECK_REBOOT=""
+typeset _REBOOT_TIME=""
+typeset _REBOOT_TIME_MINS=""
+typeset _CHECK_OLD_AGE=""
+typeset _OLD_AGE_TIME=""
+typeset _OLD_AGE_TIME_MINS=""
+typeset _CURRENT_UPTIME=""
+typeset _CURRENT_UPTIME_MINS=""
+typeset _INIT_TIME=""
+typeset _PREVIOUS_UPTIME=""
+typeset _PREVIOUS_UPTIME_MINS=""
+typeset _THRESHOLD_UPTIME_MINS=""
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
+            ;;
+    esac
+done
+
+# handle config file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read required config values
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+_CFG_CHECK_REBOOT=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_reboot')
+case "${_CFG_CHECK_REBOOT}" in
+    no|No|NO)
+        _CHECK_REBOOT=0
+        ;;
+    *)
+        _CHECK_REBOOT=1
+        ;;
+esac
+_CFG_REBOOT_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'reboot_time')
+if [[ -z "${_CFG_REBOOT_TIME}" ]]
+then
+    # default
+    _REBOOT_TIME="60m"
+else
+    _REBOOT_TIME="${_CFG_REBOOT_TIME}"
+fi
+_CFG_CHECK_OLD_AGE=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_old_age')
+case "${_CFG_CHECK_OLD_AGE}" in
+    yes|Yes|Yes)
+        _CHECK_OLD_AGE=1
+        ;;
+    *)
+        _CHECK_OLD_AGE=0
+        ;;
+esac
+_CFG_OLD_AGE_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'old_age_time')
+if [[ -z "${_CFG_OLD_AGE_TIME}" ]]
+then
+    # default
+    _OLD_AGE_TIME="365d"
+else
+    _OLD_AGE_TIME="${_CFG_OLD_AGE_TIME}"
+fi
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+#------------------------------------------------------------------------------
+# read uptime from init process
+# shellcheck disable=SC1007
+_INIT_TIME=$(UNIX95= ps -p 1 -o etime 2>/dev/null | tail -1)
+if [[ -n "${_INIT_TIME}" ]]
+then
+    # calculate exact uptime (seconds)
+    _CURRENT_UPTIME=$(print "${_INIT_TIME}" |\
+        awk '
+            BEGIN { days = 0; hours = 0; mins = 0; seconds = 0 };
+            {
+                gsub(/[ \t]/, "");
+                # get days
+                split ($0, day_str, "-");
+                if (2 in day_str) {
+                    # string has days
+                    days = day_str[1];
+                    split (day_str[2], hour_str, ":");
+                } else {
+                    split (day_str[1], hour_str, ":");
+                }
+                # get hours/minutes/seconds
+                hours = hour_str[1];
+                mins  = hour_str[2];
+                if (3 in hour_str) {
+                    # string has seconds
+                    secs  = hour_str[3];
+                }
+            }
+            END {
+                time = (days * 24 * 60 * 60) + (hours * 60 * 60) + (mins * 60) + secs;
+                print time;
+            }' 2>/dev/null)
+    data_is_numeric "${_CURRENT_UPTIME}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate uptime value (seconds)"
+        (( ARG_DEBUG )) && debug "_CURRENT_UPTIME=${_CURRENT_UPTIME}"
+        return 1
+    fi
+else
+    warn "uptime of INIT (1) process cannot be determined"
+    return 1
+fi
+
+#------------------------------------------------------------------------------
+# read state file
+if [[ -r ${_STATE_FILE} ]]
+then
+    _PREVIOUS_UPTIME=$(<"${_STATE_FILE}")
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "failed to read state file at ${_STATE_FILE}"
+        _PREVIOUS_UPTIME=""
+    fi
+fi
+
+#------------------------------------------------------------------------------
+# convert uptimes values
+_CURRENT_UPTIME_MINS=$(( _CURRENT_UPTIME / 60 ))
+data_is_numeric "${_CURRENT_UPTIME_MINS}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "unable to calculate current uptime value (minutes)"
+    (( ARG_DEBUG )) && debug "_CURRENT_UPTIME_MINS=${_CURRENT_UPTIME_MINS}"
+    return 1
+fi
+_PREVIOUS_UPTIME_MINS=$(( _PREVIOUS_UPTIME / 60 ))
+data_is_numeric "${_CURRENT_UPTIME_MINS}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "unable to calculate previous uptime value (minutes)"
+    (( ARG_DEBUG )) && debug "_PREVIOUS_UPTIME_MINS=${_PREVIOUS_UPTIME_MINS}"
+    return 1
+fi
+
+#------------------------------------------------------------------------------
+# check reboot event
+if (( _CHECK_REBOOT > 0 ))
+then
+    # convert _REBOOT_TIME to minutes
+    _REBOOT_TIME_MINS=$(data_timestring_to_mins "${_REBOOT_TIME}")
+    data_is_numeric "${_REBOOT_TIME_MINS}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate 'reboot_time' value from configuration file ${_CONFIG_FILE}"
+        (( ARG_DEBUG )) && debug "_REBOOT_TIME=${_REBOOT_TIME}"
+        return 1
+    fi
+
+    # previous uptime missing?
+    if [[ -z "${_PREVIOUS_UPTIME}" ]]
+    then
+        if (( ARG_LOG > 0 ))
+        then
+            print "${_CURRENT_UPTIME}" >"${_STATE_FILE}"
+            # shellcheck disable=SC2181
+            if (( $? > 0 ))
+            then
+                warn "failed to update state file at ${_STATE_FILE}"
+                return 1
+            else
+                log "unable to find previously recorded uptime, resetting to current uptime"
+                return 0
+            fi
+        else
+            log "unable to find previously recorded uptime, resetting to current uptime"
+        fi
+    else
+        # current uptime + reboot time is smaller than previous uptime?
+        _THRESHOLD_UPTIME_MINS=$(( _CURRENT_UPTIME_MINS + _REBOOT_TIME_MINS ))
+        if (( _THRESHOLD_UPTIME_MINS < _PREVIOUS_UPTIME_MINS ))
+        then
+            _MSG="reboot check: current uptime is NOK; check if reboot occurred"
+            _STC=1
+        else
+            _MSG="reboot check: current uptime is OK"
+            _STC=0
+        fi
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}" "${_THRESHOLD_UPTIME_MINS}" "${_PREVIOUS_UPTIME_MINS}"
+    fi
+
+    # update state file
+    if (( ARG_LOG > 0 ))
+    then
+        print "${_CURRENT_UPTIME}" >"${_STATE_FILE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            warn "failed to update state file at ${_STATE_FILE}"
+            return 1
+        fi
+    fi
+else
+    log "reboot check: not enabled"
+fi
+
+#------------------------------------------------------------------------------
+# check old age event
+if (( _CHECK_OLD_AGE > 0 ))
+then
+    # convert _OLD_AGE_TIME to minutes
+    _OLD_AGE_TIME_MINS=$(data_timestring_to_mins "${_OLD_AGE_TIME}")
+    data_is_numeric "${_OLD_AGE_TIME_MINS}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate 'old_age_time' value from configuration file ${_CONFIG_FILE}"
+        (( ARG_DEBUG )) && debug "_OLD_AGE_TIME=${_OLD_AGE_TIME}"
+        return 1
+    fi
+
+    # are we old age yet?
+    if (( _CURRENT_UPTIME_MINS > _OLD_AGE_TIME_MINS ))
+    then
+        _MSG="old_age check: current uptime is NOK; old age has arrived (>${_OLD_AGE_TIME})"
+        _STC=1
+    else
+        _MSG="old_age check: current uptime is OK"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}" "${_CURRENT_UPTIME_MINS}" "${_OLD_AGE_TIME_MINS}"
+    fi
+else
+    log "old age check: not enabled"
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with:
+               log_healthy=<yes|no>
+               check_reboot=<yes|no>
+               reboot_time=<timestring>
+               check_old_age=<yes|no>
+               old_age_time=<timestring>
+PURPOSE     : Checks for unexpected/unplanned reboot events based on uptime
+               values.
+              Checks whether the host has been up and running for too much time.
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+
+#------------------------------------------------------------------------------
+# END of script
+#------------------------------------------------------------------------------

opt/hc/lib/platform/exadata/check_exadata_cell_megaraid.sh

@@ -19,11 +19,15 @@
 # @(#) MAIN: check_exadata_cell_megaraid
 # DOES: see _show_usage()
 # EXPECTS: see _show_usage()
-# REQUIRES: data_comma2space(), data_comma2newline(), data_get_lvalue_from_config,
-#           dump_logs(), exadata_exec_dcli(), init_hc(), log_hc(), warn()
+# REQUIRES: data_comma2space(), data_comma2newline(), data_contains_string(),
+#           data_get_lvalue_from_config, dump_logs(), exadata_exec_dcli(),
+#           init_hc(), log_hc(), warn()
 #
 # @(#) HISTORY:
 # @(#) 2019-05-14: initial version [Patrick Van der Veken]
+# @(#) 2019-07-08: update _CELL_COMMAND [Patrick Van der Veken]
+# @(#) 2019-07-18: added supercap check, see Oracle bug 28564584 + exclusion
+#                  logic for components (cell_exclude) [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -33,10 +37,11 @@ function check_exadata_cell_megaraid
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2019-07-18"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # cell query command -- DO NOT CHANGE --
-typeset _CELL_COMMAND="/opt/MegaRAID/MegaCli/MegaCli64 -ShowSummary -aALL"
+typeset _CELL_COMMAND="/opt/MegaRAID/storcli/storcli64 -ShowSummary -aALL"
+typeset _SUPERCAP_COMMAND="/opt/MegaRAID/storcli/storcli64 /c0/cv show all"
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
@@ -55,15 +60,19 @@ typeset _CFG_CHECK_CONTROLLER=""
 typeset _CHECK_CONTROLLER=0
 typeset _CFG_CHECK_BBU=""
 typeset _CHECK_BBU=0
+typeset _CFG_CHECK_SUPERCAP=""
+typeset _CHECK_SUPERCAP=0
 typeset _CFG_CHECK_PHYSICAL=""
 typeset _CHECK_PHYSICAL=0
 typeset _CFG_CHECK_VIRTUAL=""
 typeset _CHECK_VIRTUAL=0
+typeset _CFG_EXCLUDES=""
 typeset _CELL_OUTPUT=""
 typeset _CELL_DATA=""
 typeset _RAID_DEVICE=""
 typeset _RAID_DEVICE_TYPE=""
 typeset _RAID_STATUS=""
+typeset _SUPERCAP_STATUS=""
 typeset _CELL_ALL_RC=0
 typeset _CELL_RC=0
 
@@ -126,7 +135,17 @@ case "${_CFG_CHECK_BBU}" in
         _CHECK_BBU=1
         ;;
 esac
-(( _CHECK_BBU > 0 )) || log "checking bbu has been disabled"
+(( _CHECK_BBU > 0 )) || log "checking bbu (battery) has been disabled"
+_CFG_CHECK_SUPERCAP=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_supercap')
+case "${_CFG_CHECK_SUPERCAP}" in
+    no|NO|No)
+        _CHECK_SUPERCAP=0
+        ;;
+    *)
+        _CHECK_SUPERCAP=1
+        ;;
+esac
+(( _CHECK_SUPERCAP > 0 )) || log "checking bbu (supercap) has been disabled"
 _CFG_CHECK_PHYSICAL=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_physical')
 case "${_CFG_CHECK_PHYSICAL}" in
     no|NO|No)
@@ -147,6 +166,7 @@ case "${_CFG_CHECK_VIRTUAL}" in
         ;;
 esac
 (( _CHECK_VIRTUAL > 0 )) || log "checking virtual has been disabled"
+_CFG_EXCLUDES=$(grep -i -E -e '^cell_exclude:' ${_CONFIG_FILE} 2>/dev/null)
 
 # log_healthy
 (( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
@@ -270,6 +290,10 @@ do
     case "${_RAID_DEVICE_TYPE}" in
         CONTROLLER)
             if (( _CHECK_CONTROLLER > 0 ))
+            then
+                # check for exclusion
+                $(data_contains_string "${_CFG_EXCLUDES}" "${_CELL_SERVER}:controller")
+                if (( $? == 0 ))
                 then
                     _TARGET_STATUS="Optimal"
                     if [[ "${_RAID_STATUS}" != "${_TARGET_STATUS}" ]]
@@ -285,19 +309,26 @@ do
                         log_hc "$0" ${_STC} "${_MSG}" "${_RAID_STATUS}" "${_TARGET_STATUS}"
                     fi
                 else
-                (( ARG_DEBUG > 0 )) && debug "skipping check for controller (disabled)"
+                    (( ARG_DEBUG > 0 )) && debug "excluded check for controller on ${_CELL_SERVER}"
+                fi
+            else
+                (( ARG_DEBUG > 0 )) && debug "skipping check for controller (disabled) [${_CELL_SERVER}]"
             fi
             ;;
         BBU)
             if (( _CHECK_BBU > 0 ))
+            then
+                # check for exclusion
+                $(data_contains_string "${_CFG_EXCLUDES}" "${_CELL_SERVER}:bbu")
+                if (( $? == 0 ))
                 then
                     _TARGET_STATUS="Healthy"
                     if [[ "${_RAID_STATUS}" != "${_TARGET_STATUS}" ]]
                     then
-                    _MSG="state of bbu on ${_CELL_SERVER} is NOK (${_RAID_STATUS}!=${_TARGET_STATUS})"
+                        _MSG="state of bbu (battery) on ${_CELL_SERVER} is NOK (${_RAID_STATUS}!=${_TARGET_STATUS})"
                         _STC=1
                     else
-                    _MSG="state of bbu on ${_CELL_SERVER} is OK (${_RAID_STATUS}==${_TARGET_STATUS})"
+                        _MSG="state of bbu (battery) on ${_CELL_SERVER} is OK (${_RAID_STATUS}==${_TARGET_STATUS})"
                         _STC=0
                     fi
                     if (( _LOG_HEALTHY > 0 || _STC > 0 ))
@@ -305,11 +336,18 @@ do
                         log_hc "$0" ${_STC} "${_MSG}" "${_RAID_STATUS}" "${_TARGET_STATUS}"
                     fi
                 else
-                (( ARG_DEBUG > 0 )) && debug "skipping check for bbu (disabled)"
+                    (( ARG_DEBUG > 0 )) && debug "excluded check for BBU (battery) on ${_CELL_SERVER}"
+                fi
+            else
+                (( ARG_DEBUG > 0 )) && debug "skipping check for bbu (battery) (disabled) [${_CELL_SERVER}]"
             fi
             ;;
         PHYSICAL)
             if (( _CHECK_PHYSICAL > 0 ))
+            then
+                # check for exclusion
+                $(data_contains_string "${_CFG_EXCLUDES}" "${_CELL_SERVER}:physical")
+                if (( $? == 0 ))
                 then
                     _TARGET_STATUS="Online"
                     if [[ "${_RAID_STATUS}" != "${_TARGET_STATUS}" ]]
@@ -324,12 +362,19 @@ do
                     then
                         log_hc "$0" ${_STC} "${_MSG}" "${_RAID_STATUS}" "${_TARGET_STATUS}"
                     fi
+                else
+                    (( ARG_DEBUG > 0 )) && debug "excluded check for physical devices on ${_CELL_SERVER}"
+                fi
             else
                 (( ARG_DEBUG > 0 )) && debug "skipping check for physical device [${_CELL_SERVER}:/${_RAID_DEVICE}] (disabled)"
             fi
             ;;
         VIRTUAL)
             if (( _CHECK_VIRTUAL > 0 ))
+            then
+                # check for exclusion
+                $(data_contains_string "${_CFG_EXCLUDES}" "${_CELL_SERVER}:virtual")
+                if (( $? == 0 ))
                 then
                     _TARGET_STATUS="Optimal"
                     if [[ "${_RAID_STATUS}" != "${_TARGET_STATUS}" ]]
@@ -344,6 +389,9 @@ do
                     then
                         log_hc "$0" ${_STC} "${_MSG}" "${_RAID_STATUS}" "${_TARGET_STATUS}"
                     fi
+                else
+                    (( ARG_DEBUG > 0 )) && debug "excluded check for virtual devices on ${_CELL_SERVER}"
+                fi
             else
                 (( ARG_DEBUG > 0 )) && debug "skipping check for virtual device [${_CELL_SERVER}:/${_RAID_DEVICE}] (disabled)"
             fi
@@ -352,9 +400,76 @@ do
 done
 
 # add dcli output to stdout log
-print "==== {dcli ${_CELL_COMMAND}} ====" >>${HC_STDOUT_LOG}
+print "==== {dcli ${_CELL_COMMAND} [${_CFG_CELL_SERVER}]} ====" >>${HC_STDOUT_LOG}
 print "${_CELL_DATA}" >>${HC_STDOUT_LOG}
 
+# check if we need to check the BBU (supercap). Use different storcli query
+# see Oracle Bug 28564584 : X5-2 Aspen w/storcli utility shows false bbu failed status
+if (( _CHECK_SUPERCAP > 0 ))
+then
+    _CELL_DATA=""
+    # gather cell data (serialized way to have better control of output & errors)
+    data_comma2newline "${_CFG_CELL_SERVERS}" | while read -r _CFG_CELL_SERVER
+    do
+        (( ARG_DEBUG > 0 )) && debug "executing remote cell script on ${_CFG_CELL_SERVER}"
+        _CELL_OUTPUT=$(exadata_exec_dcli "" "${_CFG_DCLI_USER}" "${_CFG_CELL_SERVER}" "" "${_SUPERCAP_COMMAND}" 2>>${HC_STDERR_LOG})
+        _CELL_RC=$?
+        if (( _CELL_RC > 0 )) || [[ -z "${_CELL_OUTPUT}" ]]
+        then
+            _CELL_ALL_RC=$(( _CELL_ALL_RC + _CELL_RC ))
+            warn "unable to discover cell data on ${_CFG_CELL_SERVER}"
+            (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+            continue
+        else
+        # _CELL_OUTPUT is always prefixed by cell server name, so no mangling needed
+        # shellcheck disable=SC1117
+        _CELL_DATA=$(printf "%s\n%s\n" "${_CELL_DATA}" "${_CELL_OUTPUT}")
+        fi
+    done
+
+    # validate cell data
+    if (( _CELL_ALL_RC > 0 )) || [[ -z "${_CELL_DATA}" ]]
+    then
+        _MSG="did not discover cell data or one of the discoveries failed"
+        _STC=2
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+        then
+            log_hc "$0" ${_STC} "${_MSG}"
+        fi
+        return 1
+    fi
+
+    # perform checks on cell data
+    _TARGET_STATUS="Optimal"
+    data_comma2newline "${_CFG_CELL_SERVERS}" | while read -r _CFG_CELL_SERVER
+    do
+        # check for exclusion
+        $(data_contains_string "${_CFG_EXCLUDES}" "${_CELL_SERVER}:supercap")
+        if (( $? == 0 ))
+        then
+            _SUPERCAP_STATUS=$(print -R "${_CELL_DATA}" | grep -c -E -e "^${_CFG_CELL_SERVER}: *State *${_TARGET_STATUS}" 2>/dev/null)
+            if (( _SUPERCAP_STATUS == 0 ))
+            then
+                _MSG="state of BBU (supercap) device on ${_CFG_CELL_SERVER} is NOK"
+                _STC=1
+            else
+                _MSG="state of BBU (supercap) device on ${_CFG_CELL_SERVER} is OK"
+                _STC=0
+            fi
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}" "Non-optimal" "${_TARGET_STATUS}"
+            fi
+        else
+            (( ARG_DEBUG > 0 )) && debug "excluded check for bbu (supercap) on ${_CELL_SERVER}"
+        fi
+    done
+
+    # add dcli output to stdout log
+    print "==== {dcli ${_SUPERCAP_COMMAND}} ====" >>${HC_STDOUT_LOG}
+    print "${_CELL_DATA}" >>${HC_STDOUT_LOG}
+fi
+
 return 0
 }
 
@@ -370,15 +485,20 @@ CONFIG      : $3 with parameters:
                cell_servers=<list_of_cell_servers>
                check_controller=<yes|no>
                check_bbu=<yes|no>
+               check_supercap=<yes|no>
                check_physical=<yes|no>
                check_virtual=<yes|no>
-PURPOSE     : Checks the status of MegaRAID device(s) on cell servers (via dcli)
+              and formatted stanzas of:
+               cell_exclude:<cell_server>:<component>
+PURPOSE     : 1) Checks the status of MegaRAID device(s) on cell servers (via dcli)
                 dcli> /opt/MegaRAID/MegaCli/MegaCli64 -ShowSummary -aALL
               Target attributes:
                 * Controller: Optimal [optional]
-                * BBU: Healthy [optional]
+                * BBU (battery): Healthy [optional]
                 * Physical devices: Online [optional]
                 * Virtual devices: Optimal [optional]
+              2) Checks the status of the Supercap (battery):
+                dcli> /opt/MegaRAID/storcli/storcli64 /c0/cv show all
 CAVEAT      : Requires a working dcli setup for the root user
 LOG HEALTHY : Supported
 

opt/hc/lib/platform/exadata/check_exadata_ib_status.sh

@@ -0,0 +1,171 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_exadata_ib_status.sh
+#******************************************************************************
+# @(#) Copyright (C) 2020 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_exadata_ib_status
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_comma2space(), dump_logs(), init_hc(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2020-07-07: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_exadata_ib_status
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _VERSION="2020-07-07"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
+typeset _IBSTATUS_BIN="/usr/sbin/ibstatus"
+typeset _IBSWITCHES_BIN="/usr/sbin/ibswitches"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _LOG_HEALTHY=0
+typeset _IBSTATUS_OUTPUT=""
+typeset _IBSWITCHES_OUTPUT=""
+typeset _NUM_INACTIVE_PORTS=0
+typeset _NUM_SWITCHES=0
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            ;;
+    esac
+done
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+# check IB tools
+if [[ ! -x ${_IBSTATUS_BIN} || -z "${_IBSWITCHES_BIN}" ]]
+then
+    warn "IB tools are not installed here. This is not an Exadata compute node?"
+    return 1
+fi
+
+# gather infiniband status data
+(( ARG_DEBUG > 0 )) && debug "executing command {${_IBSTATUS_BIN}}"
+_IBSTATUS_OUTPUT=$(${_IBSTATUS_BIN} 2>>${HC_STDERR_LOG})
+# shellcheck disable=SC2181
+if (( $?> 0 )) || [[ -z "${_IBSTATUS_OUTPUT}" ]]
+then
+    _MSG="unable to run command {${_IBSTATUS_BIN}}"
+    _STC=2
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+    return 1
+fi
+(( ARG_DEBUG > 0 )) && debug "executing command {${_IBSWITCHES_BIN}}"
+_IBSWITCHES_OUTPUT=$(${_IBSWITCHES_BIN} 2>>${HC_STDERR_LOG})
+# shellcheck disable=SC2181
+if (( $?> 0 )) || [[ -z "${_IBSWITCHES_OUTPUT}" ]]
+then
+    _MSG="unable to run command {${_IBSWITCHES_BIN}}"
+    _STC=2
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+    return 1
+fi
+
+# perform checks on IB status data
+_NUM_INACTIVE_PORTS=$(print -R "${_IBSTATUS_OUTPUT}" | grep -E -e '^[[:space:]]+state:' 2>/dev/null | grep -c -v "ACTIVE" 2>/dev/null)
+if (( _HAS_OFFLINE_PORTS > 0 ))
+then
+    _MSG="${_NUM_INACTIVE_PORTS} IB port(s) are/is in state INACTIVE"
+    _STC=1
+else
+    _MSG="all IB port(s) are/is in ACTIVE state"
+    _STC=0
+fi
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
+
+# perform checks on IB switches data
+_NUM_SWITCHES=$(print -R "${_IBSWITCHES_OUTPUT}" | wc -l 2>/dev/null)
+if (( _NUM_SWITCHES != 2 ))
+then
+    _MSG="only ${_NUM_SWITCHES} IB switch(es) are/is reporting (${_NUM_SWITCHES}<>2)"
+    _STC=1
+else
+    _MSG="${_NUM_SWITCHES} IB switch(es) are/is reporting"
+    _STC=0
+fi
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
+
+# add IB output to stdout log
+print "==== {${_IBSTATUS_BIN}} ====" >>${HC_STDOUT_LOG}
+print "${_IBSTATUS_OUTPUT}" >>${HC_STDOUT_LOG}
+
+print "==== {${_IBSWITCHES_BIN}} ====" >>${HC_STDOUT_LOG}
+print "${_IBSWITCHES_OUTPUT}" >>${HC_STDOUT_LOG}
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+PURPOSE     : 1) Checks that (local) Infiniband ports are in active
+              2) Checks that Infiniband switches are present (should be 2)
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/exadata/check_exadata_megaraid.sh

@@ -19,11 +19,13 @@
 # @(#) MAIN: check_exadata_megaraid
 # DOES: see _show_usage()
 # EXPECTS: see _show_usage()
-# REQUIRES: data_comma2space(), data_comma2newline(), data_get_lvalue_from_config,
-#           dump_logs(), init_hc(), log_hc(), warn()
+# REQUIRES: data_comma2space(), data_comma2newline(), data_contains_string(),
+#           data_get_lvalue_from_config, dump_logs(), init_hc(), log_hc(), warn()
 #
 # @(#) HISTORY:
 # @(#) 2019-05-14: initial version [Patrick Van der Veken]
+# @(#) 2019-07-08: update _MEGACLI_BIN [Patrick Van der Veken]
+# @(#) 2019-07-18: added supercap check, see Oracle bug 28564584 [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -33,10 +35,11 @@ function check_exadata_megaraid
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2019-07-18"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
-typeset _MEGACLI_BIN="/opt/MegaRAID/MegaCli/MegaCli64"
+typeset _MEGACLI_BIN="/opt/MegaRAID/storcli/storcli64"
 typeset _MEGACLI_COMMAND="-ShowSummary -aALL"
+typeset _SUPERCAP_COMMAND="/c0/cv show all"
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
@@ -52,6 +55,8 @@ typeset _CFG_CHECK_CONTROLLER=""
 typeset _CHECK_CONTROLLER=0
 typeset _CFG_CHECK_BBU=""
 typeset _CHECK_BBU=0
+typeset _CFG_CHECK_SUPERCAP=""
+typeset _CHECK_SUPERCAP=0
 typeset _CFG_CHECK_PHYSICAL=""
 typeset _CHECK_PHYSICAL=0
 typeset _CFG_CHECK_VIRTUAL=""
@@ -61,6 +66,7 @@ typeset _CLI_DATA=""
 typeset _RAID_DEVICE=""
 typeset _RAID_DEVICE_TYPE=""
 typeset _RAID_STATUS=""
+typeset _SUPERCAP_STATUS=""
 
 # handle arguments (originally comma-separated)
 for _ARG in ${_ARGS}
@@ -110,6 +116,16 @@ case "${_CFG_CHECK_BBU}" in
         ;;
 esac
 (( _CHECK_BBU > 0 )) || log "checking bbu has been disabled"
+_CFG_CHECK_SUPERCAP=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_supercap')
+case "${_CFG_CHECK_SUPERCAP}" in
+    no|NO|No)
+        _CHECK_SUPERCAP=0
+        ;;
+    *)
+        _CHECK_SUPERCAP=1
+        ;;
+esac
+(( _CHECK_SUPERCAP > 0 )) || log "checking bbu (supercap) has been disabled"
 _CFG_CHECK_PHYSICAL=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_physical')
 case "${_CFG_CHECK_PHYSICAL}" in
     no|NO|No)
@@ -168,7 +184,7 @@ then
     return 1
 fi
 
-# perform checks on cell data
+# perform checks on MegaCLI data
 print -R "${_CLI_OUTPUT}" | awk '
 
     BEGIN { found_controller = 0; controller_status = "";
@@ -261,7 +277,7 @@ do
                     log_hc "$0" ${_STC} "${_MSG}" "${_RAID_STATUS}" "${_TARGET_STATUS}"
                 fi
             else
-                (( ARG_DEBUG > 0 )) && debug "skipping check for controller (disabled)"
+                (( ARG_DEBUG > 0 )) && debug "excluded check for controller"
             fi
             ;;
         BBU)
@@ -270,10 +286,10 @@ do
                 _TARGET_STATUS="Healthy"
                 if [[ "${_RAID_STATUS}" != "${_TARGET_STATUS}" ]]
                 then
-                    _MSG="state of bbu is NOK (${_RAID_STATUS}!=${_TARGET_STATUS})"
+                    _MSG="state of bbu (battery) is NOK (${_RAID_STATUS}!=${_TARGET_STATUS})"
                     _STC=1
                 else
-                    _MSG="state of bbu is OK (${_RAID_STATUS}==${_TARGET_STATUS})"
+                    _MSG="state of bbu (battery) is OK (${_RAID_STATUS}==${_TARGET_STATUS})"
                     _STC=0
                 fi
                 if (( _LOG_HEALTHY > 0 || _STC > 0 ))
@@ -331,6 +347,49 @@ done
 print "==== {${_MEGACLI_COMMAND}} ====" >>${HC_STDOUT_LOG}
 print "${_CLI_DATA}" >>${HC_STDOUT_LOG}
 
+# check if we need to check the BBU (supercap). Use different storcli query
+# see Oracle Bug 28564584 : X5-2 Aspen w/storcli utility shows false bbu failed status
+if (( _CHECK_SUPERCAP > 0 ))
+then
+    # gather MegaCLI data
+    (( ARG_DEBUG > 0 )) && debug "executing Supercap command"
+    _CLI_OUTPUT=$(${_MEGACLI_BIN} "${_SUPERCAP_COMMAND}" 2>>${HC_STDERR_LOG})
+    # shellcheck disable=SC2181
+    if (( $?> 0 )) || [[ -z "${_CLI_OUTPUT}" ]]
+    then
+        _MSG="unable to query MegaRAID controller"
+        _STC=2
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+        then
+            log_hc "$0" ${_STC} "${_MSG}"
+        fi
+        (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+        return 1
+    fi
+
+    # perform checks on MegaCLI data
+    _TARGET_STATUS="Optimal"
+    _SUPERCAP_STATUS=$(print -R "${_CLI_OUTPUT}" | grep -c -E -e "^State *${_TARGET_STATUS}" 2>/dev/null)
+    if (( _SUPERCAP_STATUS == 0 ))
+    then
+        _MSG="state of BBU (supercap) device is NOK"
+        _STC=1
+    else
+        _MSG="state of BBU (supercap) device is OK"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}" "Non-optimal" "${_TARGET_STATUS}"
+    fi
+
+    # add dcli output to stdout log
+    print "==== {dcli ${_SUPERCAP_COMMAND}} ====" >>${HC_STDOUT_LOG}
+    print "${_CELL_DATA}" >>${HC_STDOUT_LOG}
+else
+    (( ARG_DEBUG > 0 )) && debug "excluded check for bbu (supercap) on ${_CELL_SERVER}"
+fi
+
 return 0
 }
 
@@ -344,15 +403,18 @@ CONFIG      : $3 with parameters:
                log_healthy=<yes|no>
                check_controller=<yes|no>
                check_bbu=<yes|no>
+               check_supercap=<yes|no>
                check_physical=<yes|no>
                check_virtual=<yes|no>
-PURPOSE     : Checks the status of MegaRAID device(s)
+PURPOSE     : 1) Checks the status of MegaRAID device(s)
                 # /opt/MegaRAID/MegaCli/MegaCli64 -ShowSummary -aALL
               Target attributes:
                 * Controller: Optimal [optional]
-                * BBU: Healthy [optional]
+                * BBU (battery): Healthy [optional]
                 * Physical devices: Online [optional]
                 * Virtual devices: Optimal [optional]
+              2) Checks the status of the Supercap (battery):
+                dcli> /opt/MegaRAID/storcli/storcli64 /c0/cv show all
 LOG HEALTHY : Supported
 
 EOT

opt/hc/lib/platform/exadata/check_exadata_zfs_cluster.sh

@@ -0,0 +1,264 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_exadata_zfs_cluster.sh
+#******************************************************************************
+# @(#) Copyright (C) 2019 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_exadata_zfs_cluster
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_comma2space(), data_get_lvalue_from_config, dump_logs(),
+#           data_strip_outer_space(), init_hc(), linux_exec_ssh(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2019-07-05: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_exadata_zfs_cluster
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2019-07-05"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
+# cluster query script -- DO NOT CHANGE --
+# state=AKCS_CLUSTERED
+# link=clustron3_ng3:0/clustron_uart:0 = AKCIOS_ACTIVE
+# link=clustron3_ng3:0/clustron_uart:1 = AKCIOS_ACTIVE
+# link=clustron3_ng3:0/dlpi:0 = AKCIOS_ACTIVE
+typeset _ZFS_SCRIPT="
+    script
+        run('configuration cluster');
+        printf('state=%s\n', get('state'));
+        var links = run('links');
+        var links_array = links.split('\n');
+        for (var i = 0; i < links_array.length; ++i) {
+            if (links_array[i] != '') {
+                printf('link=%s\n', links_array[i].replace(/^\s+|\s+$/g,''));
+            }
+        }"
+# target state of the cluster
+typeset _CLUSTER_TARGET="AKCS_CLUSTERED"
+# target state of the cluster links
+typeset _LINK_TARGET="AKCIOS_ACTIVE"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _CFG_HEALTHY=""
+typeset _LOG_HEALTHY=0
+typeset _CFG_SSH_KEY_FILE=""
+typeset _CFG_SSH_OPTS=""
+typeset _CFG_SSH_USER=""
+typeset _CFG_SPACE_THRESHOLD=""
+typeset _CFG_ZFS_HOSTS=""
+typeset _CFG_ZFS_HOST=""
+typeset _CFG_ZFS_LINE=""
+typeset _SSH_BIN=""
+typeset _SSH_OUTPUT=""
+typeset _ZFS_DATA=""
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            ;;
+    esac
+done
+
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read configuration values
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+_CFG_SSH_USER=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'ssh_user')
+if [[ -z "${_CFG_SSH_USER}" ]]
+then
+    _CFG_SSH_USER="root"
+fi
+_CFG_SSH_KEY_FILE=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'ssh_key_file')
+_CFG_SSH_OPTS=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'ssh_opts')
+# add quiet mode
+_CFG_SSH_OPTS="${_CFG_SSH_OPTS} -q"
+if [[ -n "${_CFG_SSH_KEY_FILE}" ]]
+then
+    if [[ -r "${_CFG_SSH_KEY_FILE}" ]]
+    then
+        log "will use SSH key ${_CFG_SSH_KEY_FILE}"
+        _CFG_SSH_OPTS="${_CFG_SSH_OPTS} -i ${_CFG_SSH_KEY_FILE}"
+    else
+        warn "will use SSH key ${_CFG_SSH_KEY_FILE}, but file does not exist"
+        return 1
+    fi
+fi
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+# check ssh
+_SSH_BIN="$(command -v ssh 2>>${HC_STDERR_LOG})"
+if [[ ! -x ${_SSH_BIN} || -z "${_SSH_BIN}" ]]
+then
+    warn "SSH is not installed here"
+    return 1
+fi
+
+# gather ZFS hostnames (for this we need at least one data line, possibly with wildcards)
+_CFG_ZFS_HOSTS=$(grep -i -E -e '^zfs:' ${_CONFIG_FILE} 2>/dev/null | cut -f2 -d':' 2>/dev/null | sort -u 2>/dev/null)
+if [[ -z "${_CFG_ZFS_HOSTS}" ]]
+then
+    warn "no monitoring rules defined in ${_CONFIG_FILE}"
+    return 1
+fi
+
+# gather ZFS usage data
+print "${_CFG_ZFS_HOSTS}" | while read -r _CFG_ZFS_HOST
+do
+    (( ARG_DEBUG > 0 )) && debug "executing remote ZFS script on ${_CFG_ZFS_HOST}"
+    _SSH_OUTPUT=$(linux_exec_ssh "${_CFG_SSH_OPTS}" "${_CFG_SSH_USER}" "${_CFG_ZFS_HOST}" "${_ZFS_SCRIPT}" 2>>${HC_STDERR_LOG})
+    # shellcheck disable=SC2181
+    if (( $? > 0 )) || [[ -z "${_SSH_OUTPUT}" ]]
+    then
+        warn "unable to discover usage data on ${_CFG_ZFS_HOST}"
+        (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+        continue
+    else
+        # mangle SSH output by prefixing with hostname
+        print "${_SSH_OUTPUT}" | while read -r _SSH_LINE
+        do
+            if [[ -z "${_ZFS_DATA}" ]]
+            then
+                _ZFS_DATA="${_CFG_ZFS_HOST}#${_SSH_LINE}"
+            else
+                # shellcheck disable=SC1117
+                _ZFS_DATA=$(printf "%s\n%s#%s" "${_ZFS_DATA}" "${_CFG_ZFS_HOST}" "${_SSH_LINE}")
+            fi
+        done
+    fi
+done
+
+# process usage status data
+if [[ -z "${_ZFS_DATA}" ]]
+then
+    _MSG="did not discover any ZFS share data"
+    _STC=2
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    return 1
+fi
+print "${_ZFS_DATA}" | while IFS='#' read -r _ZFS_HOST _CLUSTER_LINE
+do
+    (( ARG_DEBUG > 0 )) && debug "parsing cluster data for appliance: ${_ZFS_HOST}"
+
+    # split up cluster data & perform checks
+    case "${_CLUSTER_LINE}" in
+        link=*)
+            _LINK_STATE=$(data_strip_outer_space "$(print "${_CLUSTER_LINE}" | cut -f3 -d'=' 2>/dev/null)")
+
+            if [[ "${_LINK_STATE}" != "${_LINK_TARGET}" ]]
+            then
+                _MSG="${_ZFS_HOST} cluster link state is NOK ([${_LINK_STATE}!=${_LINK_TARGET})"
+                _STC=1
+            else
+                _MSG="${_ZFS_HOST} cluster link state is OK (${_LINK_STATE}==${_LINK_TARGET})"
+                _STC=0
+            fi
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}" "${_LINK_STATE}" "${_LINK_TARGET}"
+            fi
+            ;;
+        state=*)
+            _CLUSTER_STATE=$(print "${_CLUSTER_LINE##state=}")
+
+            if [[ "${_CLUSTER_STATE}" != "${_CLUSTER_TARGET}" ]]
+            then
+                _MSG="${_ZFS_HOST} cluster state is NOK (${_CLUSTER_STATE}!=${_CLUSTER_TARGET})"
+                _STC=1
+            else
+                _MSG="${_ZFS_HOST} cluster state is OK (${_CLUSTER_STATE}==${_CLUSTER_TARGET})"
+                _STC=0
+            fi
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}" "${_CLUSTER_STATE}" "${_CLUSTER_TARGET}"
+            fi
+            ;;
+    esac
+done
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with parameters:
+               log_healthy=<yes|no>
+               ssh_user=<ssh_user_account>
+               ssh_key_file=<ssh_private_key_file>
+               ssh_opts=<ssh_options>
+              and formatted stanzas of:
+               zfs:<host_name>
+PURPOSE     : Checks the state of the cluster and its links
+              CLI: zfs > configuration > cluster > show
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/exadata/check_exadata_zfs_logs.sh

@@ -26,6 +26,7 @@
 # @(#) 2019-02-18: initial version [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
 # @(#) 2019-05-14: _STC fix [Patrick Van der Veken]
+# @(#) 2019-07-05: help fix [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -35,7 +36,7 @@ function check_exadata_zfs_logs
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2019-07-05"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -454,6 +455,7 @@ CONFIG      : $3 with parameters:
                log_healthy=<yes|no>
                ssh_user=<ssh_user_account>
                ssh_key_file=<ssh_private_key_file>
+               ssh_opts=<ssh_options>
               and formatted stanzas of:
                zfs:<host_name>:<alert|fltlog|scrk|system>:<filters>
 PURPOSE     : Checks the ZFS logs for (new) entries with particular alert level(s)

opt/hc/lib/platform/exadata/check_exadata_zfs_pool_usage.sh

@@ -25,6 +25,7 @@
 # @(#) HISTORY:
 # @(#) 2019-04-12: initial version [Patrick Van der Veken]
 # @(#) 2019-05-14: small fixes [Patrick Van der Veken]
+# @(#) 2019-07-05: help fix [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -34,7 +35,7 @@ function check_exadata_zfs_pool_usage
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2019-07-05"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # usage query script -- DO NOT CHANGE --
 # prj1:share1:16
@@ -277,6 +278,7 @@ CONFIG      : $3 with parameters:
                log_healthy=<yes|no>
                ssh_user=<ssh_user_account>
                ssh_key_file=<ssh_private_key_file>
+               ssh_opts=<ssh_options>
                max_space_usage=<general_max_space_treshold>
               and formatted stanzas of:
                zfs:<host_name>:<pool_name>:<max_space_threshold>

opt/hc/lib/platform/exadata/check_exadata_zfs_services.sh

@@ -26,6 +26,7 @@
 # @(#) 2019-02-18: initial version [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
 # @(#) 2019-05-14: small fixes [Patrick Van der Veken]
+# @(#) 2019-07-05: help fix [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -35,7 +36,7 @@ function check_exadata_zfs_services
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2019-07-05"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # usage query script -- DO NOT CHANGE --
 # svc1:online
@@ -244,6 +245,7 @@ CONFIG      : $3 with parameters:
                log_healthy=<yes|no>
                ssh_user=<ssh_user_account>
                ssh_key_file=<ssh_private_key_file>
+               ssh_opts=<ssh_options>
               and formatted stanzas of:
                zfs:<host_name>:<service_name>:<service_state>
 PURPOSE     : Checks the state of services for the configured ZFS hosts/shares

opt/hc/lib/platform/exadata/check_exadata_zfs_share_replication.sh

@@ -19,8 +19,10 @@
 # @(#) MAIN: check_exadata_zfs_share_replication
 # DOES: see _show_usage()
 # EXPECTS: see _show_usage()
-# REQUIRES: data_comma2space(), data_contains_string(), data_get_lvalue_from_config(),
-#           dump_logs(), init_hc(), linux_exec_ssh(), log_hc(), warn()
+# REQUIRES: data_comma2space(), data_contains_string(), data_expand_numerical_range(),
+#           data_get_lvalue_from_config(), data_has_newline(), data_is_numeric(),
+#           data_lc(), data_strip_space(), dump_logs(), init_hc(), linux_exec_ssh(),
+#           log_hc(), warn()
 #
 # @(#) HISTORY:
 # @(#) 2019-02-18: initial version [Patrick Van der Veken]
@@ -28,6 +30,10 @@
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
 # @(#) 2019-04-12: small fixes [Patrick Van der Veken]
 # @(#) 2019-05-14: small fixes [Patrick Van der Veken]
+# @(#) 2020-01-27: addition of day check option +
+# @(#)             newline config value check [Patrick Van der Veken]
+# @(#) 2020-03-05: addition of hour check option + fix
+# @(#) 2020-03-26: fix for expanding numerical range
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -37,7 +43,7 @@ function check_exadata_zfs_share_replication
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2020-03-26"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # replication query script -- DO NOT CHANGE --
 # prj1/share1:true:idle:success:111
@@ -74,12 +80,17 @@ typeset _CFG_SSH_USER=""
 typeset _CFG_ZFS_HOSTS=""
 typeset _CFG_ZFS_HOST=""
 typeset _CFG_ZFS_LINE=""
+typeset _CFG_REPLICATION_DAYS=""
+typeset _CFG_REPLICATION_HOURS=""
 typeset _REPLICATION_ENABLED=""
+typeset _REPLICATION_HOURS=""
 typeset _REPLICATION_LAG=""
 typeset _REPLICATION_RESULT=""
 typeset _SSH_BIN=""
 typeset _SSH_OUTPUT=""
 typeset _ZFS_DATA=""
+typeset _WEEKDAY=$(data_lc "$(date '+%a' 2>/dev/null)")  # Sun
+typeset _HOUR=$(data_strip_space "$(date '+%H' 2>/dev/null)") # 7,23 etc
 
 # handle arguments (originally comma-separated)
 for _ARG in ${_ARGS}
@@ -209,6 +220,8 @@ do
     _CFG_REPLICATION_ENABLED=""
     _CFG_REPLICATION_RESULT=""
     _CFG_REPLICATION_LAG=""
+    _CFG_REPLICATION_DAYS=""
+    _CFG_REPLICATION_HOURS=""
 
     # which values to use (general or custom?), keep in mind wildcards (custom will overrule wildcard entry)
     _CFG_ZFS_LINE=$(grep -E -e "^zfs:${_ZFS_HOST}:[*]:" ${_CONFIG_FILE} 2>/dev/null)
@@ -218,6 +231,8 @@ do
         _CFG_REPLICATION_ENABLED=$(print "${_CFG_ZFS_LINE}" | cut -f4 -d':' 2>/dev/null)
         _CFG_REPLICATION_RESULT=$(print "${_CFG_ZFS_LINE}" | cut -f5 -d':' 2>/dev/null)
         _CFG_REPLICATION_LAG=$(print "${_CFG_ZFS_LINE}" | cut -f6 -d':' 2>/dev/null)
+        _CFG_REPLICATION_DAYS=$(print "${_CFG_ZFS_LINE}" | cut -f7 -d':' 2>/dev/null)
+        _CFG_REPLICATION_HOURS=$(print "${_CFG_ZFS_LINE}" | cut -f8 -d':' 2>/dev/null)
         # null value means general threshold
         if [[ -z "${_CFG_REPLICATION_LAG}" ]]
         then
@@ -228,10 +243,19 @@ do
     _CFG_ZFS_LINE=$(grep -E -e "^zfs:${_ZFS_HOST}:${_REPLICATION_NAME}:" ${_CONFIG_FILE} 2>/dev/null)
     if [[ -n "${_CFG_ZFS_LINE}" ]]
     then
+        data_has_newline "${_CFG_ZFS_LINE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            warn "ignoring ${_ZFS_HOST}:${_REPLICATION_NAME} because it parses to multiple results in ${_CONFIG_FILE}"
+            continue
+        fi
         (( ARG_DEBUG > 0 )) && debug "found custom definition for ${_ZFS_HOST}:${_REPLICATION_NAME} in configuration file ${_CONFIG_FILE}"
         _CFG_REPLICATION_ENABLED=$(print "${_CFG_ZFS_LINE}" | cut -f4 -d':' 2>/dev/null)
         _CFG_REPLICATION_RESULT=$(print "${_CFG_ZFS_LINE}" | cut -f5 -d':' 2>/dev/null)
         _CFG_REPLICATION_LAG=$(print "${_CFG_ZFS_LINE}" | cut -f6 -d':' 2>/dev/null)
+        _CFG_REPLICATION_DAYS=$(print "${_CFG_ZFS_LINE}" | cut -f7 -d':' 2>/dev/null)
+        _CFG_REPLICATION_HOURS=$(print "${_CFG_ZFS_LINE}" | cut -f8 -d':' 2>/dev/null)
         # null value means general threshold
         if [[ -z "${_CFG_REPLICATION_LAG}" ]]
         then
@@ -261,8 +285,25 @@ do
     # fixed defaults if missing
     [[ -z "${_CFG_REPLICATION_ENABLED}" || "${_CFG_REPLICATION_ENABLED}" = '*' ]] && _CFG_REPLICATION_ENABLED="true"
     [[ -z "${_CFG_REPLICATION_RESULT}" || "${_CFG_REPLICATION_RESULT}" = '*' ]] && _CFG_REPLICATION_RESULT="success"
+    _CFG_REPLICATION_DAYS=$(data_lc "${_CFG_REPLICATION_DAYS}")
+    [[ -z "${_CFG_REPLICATION_DAYS}" || "${_CFG_REPLICATION_DAYS}" = '*' ]] && _CFG_REPLICATION_DAYS="${_WEEKDAY}"
+    if [[ -z "${_CFG_REPLICATION_HOURS}" || "${_CFG_REPLICATION_HOURS}" = '*' ]]
+    then
+        _REPLICATION_HOURS="${_HOUR}"
+    else
+        # expand range with leading zeroes
+        _REPLICATION_HOURS=$(data_expand_numerical_range "${_CFG_REPLICATION_HOURS}" 1)
+    fi
 
     # perform checks
+    # do we need to perform the check today?
+    data_contains_string "${_CFG_REPLICATION_DAYS}" "${_WEEKDAY}"
+    if (( $? > 0 ))
+    then
+        # do we need to perform the check this hour?
+        data_contains_string "${_REPLICATION_HOURS}" "${_HOUR}"
+        if (( $? > 0 ))
+        then
             # check replication enabled state (active or not?)
             if [[ $(data_lc "${_REPLICATION_ENABLED}") != $(data_lc "${_CFG_REPLICATION_ENABLED}") ]]
             then
@@ -312,6 +353,12 @@ do
             then
                 log_hc "$0" ${_STC} "${_MSG}" "${_REPLICATION_LAG}" "${_CFG_REPLICATION_LAG}"
             fi
+        else
+            warn "check of ${_ZFS_HOST}:${_REPLICATION_NAME} is only configured for this/these hour(s): ${_REPLICATION_HOURS}"
+        fi
+    else
+        warn "check of ${_ZFS_HOST}:${_REPLICATION_NAME} is not configured for today"
+    fi
 done
 
 return 0
@@ -329,8 +376,8 @@ CONFIG      : $3 with parameters:
                ssh_key_file=<ssh_private_key_file>
                max_replication_lag=<general_max_replication>
               and formatted stanzas of:
-               zfs:<host_name>:<replication_name>:<replication_enabled>:<replication_result>:<max_replication_lag>
-PURPOSE     : Checks the replication state, sync status and maximum lag of the configured ZFS hosts/shares
+               zfs:<host_name>:<replication_name>:<replication_enabled>:<replication_result>:<max_replication_lag>:<day1,day2>:<start_hour>-<end_hour>
+PURPOSE     : Checks the replication state, sync status and maximum lag of the configured ZFS hosts/shares on certain days
               CLI: zfs > shares > replications > packages > select (action) > show
 LOG HEALTHY : Supported
 

opt/hc/lib/platform/exadata/check_exadata_zfs_share_usage.sh

@@ -19,8 +19,8 @@
 # @(#) MAIN: check_exadata_zfs_share_usage
 # DOES: see _show_usage()
 # EXPECTS: see _show_usage()
-# REQUIRES: data_comma2space(), data_get_lvalue_from_config, dump_logs(),
-#           init_hc(), linux_exec_ssh(), log_hc(), warn()
+# REQUIRES: data_comma2space(), data_get_lvalue_from_config, data_has_newline(),
+#           dump_logs(), init_hc(), linux_exec_ssh(), log_hc(), warn()
 #
 # @(#) HISTORY:
 # @(#) 2019-02-18: initial version [Patrick Van der Veken]
@@ -28,6 +28,7 @@
 # @(#) 2019-04-09: fix bad math in ZFS script & HC message [Patrick Van der Veken]
 # @(#) 2019-04-12: small fixes [Patrick Van der Veken]
 # @(#) 2019-05-14: small fixes [Patrick Van der Veken]
+# @(#) 2020-01-27: newline config value check [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -37,7 +38,7 @@ function check_exadata_zfs_share_usage
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-05-14"                           # YYYY-MM-DD
+typeset _VERSION="2020-01-27"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # usage query script -- DO NOT CHANGE --
 # prj1:share1:16
@@ -232,6 +233,13 @@ do
     _CFG_ZFS_LINE=$(grep -E -e "^zfs:${_ZFS_HOST}:${_PROJECT_NAME}:${_SHARE_NAME}:" ${_CONFIG_FILE} 2>/dev/null)
     if [[ -n "${_CFG_ZFS_LINE}" ]]
     then
+        data_has_newline "${_CFG_ZFS_LINE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            warn "ignoring ${_ZFS_HOST}:${_PROJECT_NAME}:${_SHARE_NAME} because it parses to multiple results in ${_CONFIG_FILE}"
+            continue
+        fi
         (( ARG_DEBUG > 0 )) && debug "found custom definition for ${_ZFS_HOST}:${_PROJECT_NAME}/${_SHARE_NAME} in configuration file ${_CONFIG_FILE}"
         _CFG_SPACE_THRESHOLD=$(print "${_CFG_ZFS_LINE}" | cut -f5 -d':' 2>/dev/null)
         # null value means general threshold

opt/hc/lib/platform/hp-ux/check_hpux_autofs.sh

@@ -0,0 +1,257 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_hpux_autofs.sh
+#******************************************************************************
+# @(#) Copyright (C) 2019 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_hpux_autofs
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_comma2space(), data_is_numeric(), dump_logs(), init_hc(),
+#           log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2019-07-14: original version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_hpux_autofs
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2019-07-14"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
+# shellcheck disable=SC2034
+typeset _HC_CAN_FIX=1                                   # plugin has fix/healing logic?
+typeset _CHRC_BIN="/usr/bin/ch_rc"
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _CFG_HEALTHY=""
+typeset _LOG_HEALTHY=0
+typeset _CFG_FIX_AUTOFS=""
+typeset _FIX_AUTOFS=0
+typeset _IS_ACTIVE=0
+typeset _IS_ENABLED=0
+typeset _RETRY_START=3
+typeset _SLEEP_TIME=5
+typeset _RETRY_COUNT=1
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            ;;
+    esac
+done
+
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+_CFG_FIX_AUTOFS=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'fix_autofs')
+case "${_CFG_FIX_AUTOFS}" in
+    yes|YES|Yes)
+        _FIX_AUTOFS=1
+        ;;
+    *)
+        _FIX_AUTOFS=0
+        ;;
+esac
+_CFG_RETRY_START=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'retry_start')
+data_is_numeric "${_CFG_RETRY_START}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "value for parameter 'retry_count' in configuration file ${_CONFIG_FILE} is invalid"
+    return 1
+else
+    _RETRY_START=${_CFG_RETRY_START}
+fi
+_CFG_SLEEP_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'sleep_time')
+data_is_numeric "${_CFG_SLEEP_TIME}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "value for parameter 'sleep_time' in configuration file ${_CONFIG_FILE} is invalid"
+    return 1
+else
+    _SLEEP_TIME=${_CFG_SLEEP_TIME}
+fi
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+
+# log_healthy/--log-healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+# --no-fix
+if (( ARG_NO_FIX > 0 ))
+then
+    _FIX_AUTOFS=0
+    log "fix/healing logic has been disabled"
+fi
+
+# check required tools
+if [[ ! -x ${_CHRC_BIN} ]]
+then
+    warn "${_CHRC_BIN} is not installed here"
+    return 1
+fi
+
+# check if autofs is enabled
+log "checking if autofs daemon is enabled"
+_IS_ENABLED=$(ch_rc -l -p AUTOFS /etc/rc.config.d/nfsconf 2>${HC_STDERR_LOG})
+if (( _IS_ENABLED > 0 ))
+then
+    _MSG="autofs service is enabled"
+    _STC=0
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    # check if autofs is running
+    log "checking if autofs daemon is active"
+    _is_autofs_active
+    _IS_ACTIVE=$?
+    if (( _IS_ACTIVE > 0 ))
+    then
+        _MSG="autofs daemon is running"
+        _STC=0
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+        then
+            log_hc "$0" ${_STC} "${_MSG}"
+        fi
+    else
+        warn "autofs daemon is not running"
+        # try restart if healing is desired
+        if (( _FIX_AUTOFS > 0 ))
+        then
+            while (( _RETRY_COUNT <= _RETRY_START && _IS_ACTIVE == 0 ))
+            do
+                log "restarting autofs (attempt #${_RETRY_COUNT})"
+                /sbin/init.d/autofs stop >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+                # dump debug info
+                (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+                /sbin/init.d/autofs start >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+                # dump debug info
+                (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+                log "sleeping for ${_SLEEP_TIME} seconds"
+                sleep ${_SLEEP_TIME}
+                _RETRY_COUNT=$(( _RETRY_COUNT + 1 ))
+                _is_autofs_active
+                _IS_ACTIVE=$?
+            done
+            # check again if autofs is running
+            _is_autofs_active
+            _IS_ACTIVE=$?
+            if (( _IS_ACTIVE > 0 ))
+            then
+                _MSG="autofs daemon is running"
+                _STC=0
+                if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+                then
+                    log_hc "$0" ${_STC} "${_MSG}"
+                fi
+            else
+                _MSG="autofs daemon is not running"
+                _STC=1
+                if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+                then
+                    log_hc "$0" ${_STC} "${_MSG}"
+                fi
+            fi
+        else
+            _MSG="autofs daemon is not running"
+            _STC=1
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}"
+            fi
+        fi
+    fi
+else
+    _MSG="autofs service is disabled"
+    _STC=1
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _is_autofs_active
+{
+typeset _IS_ACTIVE=$(pgrep -u root automountd 2>>${HC_STDERR_LOG} | wc -l 2>/dev/null)
+
+return ${_IS_ACTIVE}
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with parameters:
+                log_healthy=<yes|no>
+                fix_autofs=<yes|no>
+                retry_start=<amount_of_start_retries>
+                sleep_time=<seconds_to_sleep_during_restart_attempts>
+PURPOSE     : Check/fix AutoFS service
+LOG HEALTHY : Supported
+CAN FIX?    : Yes
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/hp-ux/check_hpux_cron_status.sh

@@ -19,12 +19,13 @@
 # @(#) MAIN: check_hpux_cron_status
 # DOES: see _show_usage()
 # EXPECTS: n/a
-# REQUIRES: data_comma2space(), init_hc(), log_hc()
+# REQUIRES: data_is_numeric(), data_comma2space(), init_hc(), log_hc()
 #
 # @(#) HISTORY:
 # @(#) 2018-02-08: initial version [Patrick Van der Veken]µ
 # @(#) 2018-02-13: fix to avoid log check if cron is not active [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2021-03-25: make _WAIT_TIME & _CRON_LOG_FILE configurable [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -33,20 +34,25 @@
 function check_hpux_cron_status
 {
 # ------------------------- CONFIGURATION starts here -------------------------
-typeset _CRON_LOG_FILE="/var/adm/cron/log"
-typeset _WAIT_TIME=10
-typeset _VERSION="2019-02-16"                           # YYYY-MM-DD
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2021-03-25"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
 typeset _ARGS=$(data_comma2space "$*")
 typeset _ARG=""
 typeset _MSG=""
 typeset _STC=0
+typeset _CFG_HEALTHY=""
 typeset _LOG_HEALTHY=0
+typeset _CFG_CRON_LOG_FILE=""
+typeset _CFG_WAIT_TIME=""
+typeset _LOG_HEALTHY=0
+typeset _CRON_LOG_FILE=""
+typeset _WAIT_TIME=""
 typeset _JOB_ID=""
 typeset _AT_BIN=""
 
@@ -55,11 +61,56 @@ for _ARG in ${_ARGS}
 do
     case "${_ARG}" in
         help)
-            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            _show_usage "${0}" "${_VERSION}" "${_CONFIG_FILE}" && return 0
             ;;
     esac
 done
 
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+_CFG_WAIT_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'wait_time')
+if [[ -z "${_CFG_WAIT_TIME}" ]]
+then
+    # default
+    _WAIT_TIME=10
+    log "setting value for parameter wait_time to its default (${_WAIT_TIME})"
+else
+    data_is_numeric "${_CFG_WAIT_TIME}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "wait time parameter is not numeric in configuration file ${_CONFIG_FILE}"
+        return 1
+    else
+        _WAIT_TIME=${_CFG_WAIT_TIME}
+    fi
+fi
+_CFG_CRON_LOG_FILE=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'cron_log')
+if [[ -z "${_CFG_CRON_LOG_FILE}" ]]
+then
+    # default
+    _CRON_LOG_FILE="/var/adm/cron/log"
+    log "setting value for parameter cron_log to its default (${_CRON_LOG_FILE})"
+else
+    _CRON_LOG_FILE="${_CFG_CRON_LOG_FILE}"
+    log "setting value for parameter cron_log (${_CRON_LOG_FILE})"
+fi
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+
 # log_healthy
 (( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
 if (( _LOG_HEALTHY > 0 ))
@@ -74,10 +125,20 @@ else
     log "not logging/showing passed health checks"
 fi
 
+# check timeout (_WAIT_TIME must be at least 30 secs smaller than health check timeout)
+if (( _WAIT_TIME > 0 ))
+then
+    if (( (_WAIT_TIME + 30) > HC_TIME_OUT ))
+    then
+        warn "wait time value will conflict with health check timeout. Specify a (larger) --timeout value"
+    return 1
+    fi
+fi
+
 # ---- process state ----
 # try the pgrep way (note: old pgreps do not support '-c')
 (( ARG_DEBUG > 0 )) && debug "checking cron service via pgrep"
-(( $(pgrep -u root cron 2>>${HC_STDERR_LOG} | wc -l 2>/dev/null) == 0 )) && _STC=1
+(( $(pgrep -u root cron 2>>"${HC_STDERR_LOG}" | wc -l 2>/dev/null) == 0 )) && _STC=1
 
 # evaluate results
 case ${_STC} in
@@ -99,18 +160,30 @@ then
 fi
 
 # ---- log state ----
-_AT_BIN="$(command -v at 2>>${HC_STDERR_LOG})"
+# check cron log file
+if [[ ! -r ${_CRON_LOG_FILE} ]]
+then
+    _MSG="cron log does not exist (${_CRON_LOG_FILE})"
+    _STC=1
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" 1 "${_MSG}"
+    fi
+    return 0
+fi
+# create test event
+_AT_BIN=$(command -v at 2>>"${HC_STDERR_LOG}")
 if [[ -x ${_AT_BIN} && -n "${_AT_BIN}" ]]
 then
     # start test job
     (( ARG_DEBUG > 0 )) && debug "checking cron log via {${_AT_BIN}}"
-    (echo "*** CHECK LOG ***" >/dev/null | ${_AT_BIN} now) >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
-    sleep ${_WAIT_TIME}
-    if (( $(grep -c 'cron may not be running' ${HC_STDERR_LOG} 2>/dev/null) == 0 ))
+    (echo "*** CHECK LOG ***" >/dev/null | ${_AT_BIN} now) >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
+    sleep "${_WAIT_TIME}"
+    if (( $(grep -c 'cron may not be running' "${HC_STDERR_LOG}" 2>/dev/null) == 0 ))
     then
         # find job results
-        _JOB_ID=$(grep -E -e '^job' ${HC_STDERR_LOG} 2>/dev/null | awk '{ print $2}' 2>/dev/null)
-        if [[ -n "${_JOB_ID}" ]] && (( $(grep -c "${_JOB_ID}" ${_CRON_LOG_FILE} 2>/dev/null) > 0 ))
+        _JOB_ID=$(grep -E -e '^job' "${HC_STDERR_LOG}" 2>/dev/null | awk '{ print $2}' 2>/dev/null)
+        if [[ -n "${_JOB_ID}" ]] && (( $(grep -c "${_JOB_ID}" "${_CRON_LOG_FILE}" 2>/dev/null) > 0 ))
         then
             _MSG="cron is logging correctly, schedule via {${_AT_BIN}} OK"
             _STC=0
@@ -125,7 +198,7 @@ then
 else
     # check cron log itself
     (( ARG_DEBUG > 0 )) && debug "checking cron log via file check"
-    if [[ -r ${_CRON_LOG_FILE} ]] && [[ -s ${_CRON_LOG_FILE} ]]
+    if [[ -s ${_CRON_LOG_FILE} ]]
     then
         _MSG="cron is logging correctly (${_CRON_LOG_FILE})"
         _STC=0
@@ -148,9 +221,12 @@ function _show_usage
 cat <<- EOT
 NAME        : $1
 VERSION     : $2
-CONFIG      : $3
+CONFIG      : $3 with parameters:
+                log_healthy=<yes|no>
+                wait_time=<seconds>
+                cron_log=<file_path>
 PURPOSE     : Checks whether cron (CRON) service is running and whether cron is
-              actually logging to ${_CRON_LOG_FILE}.
+              actually logging to the cron log file.
 LOG HEALTHY : Supported
 
 EOT

opt/hc/lib/platform/hp-ux/check_hpux_defunct_processes.sh

@@ -0,0 +1,212 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_hpux_defunct_processes.sh
+#******************************************************************************
+# @(#) Copyright (C) 2021 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_hpux_defunct_processes
+# DOES: see _show_usage()
+# EXPECTS: n/a
+# REQUIRES: data_comma2space(), data_is_numeric(), init_hc(), log_hc()
+#
+# @(#) HISTORY:
+# @(#) 2021-04-07: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_hpux_defunct_processes
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2021-04-07"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _CFG_GROUP_BY_PPID=""
+typeset _GROUP_BY_PPID=""
+typeset _CFG_PROCESS_THRESHOLD=""
+typeset _PROCESS_THRESHOLD=""
+typeset _CFG_HEALTHY=""
+typeset _LOG_HEALTHY=0
+typeset _DEFUNCT_PROCS=""
+typeset _NUM_DEFUNCT_PROCS=""
+typeset _PPID=""
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage "${0}" "${_VERSION}" "${_CONFIG_FILE}" && return 0
+            ;;
+    esac
+done
+
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read required configuration values
+_CFG_PROCESS_THRESHOLD=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'process_threshold')
+if [[ -z "${_CFG_PROCESS_THRESHOLD}" ]]
+then
+    # default
+    _PROCESS_THRESHOLD=10
+    log "setting value for parameter process_threshold to its default (10)"
+else
+    data_is_numeric "${_CFG_PROCESS_THRESHOLD}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "value for parameter process_threshold in configuration file ${_CONFIG_FILE} is invalid"
+        return 1
+    else
+        _PROCESS_THRESHOLD=${_CFG_PROCESS_THRESHOLD}
+        log "setting value for parameter collect_interval (${_PROCESS_THRESHOLD})"
+    fi
+fi
+_CFG_GROUP_BY_PPID=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'group_by_ppid')
+case "${_CFG_GROUP_BY_PPID}" in
+    no|NO|No)
+        _GROUP_BY_PPID=0
+        log "setting value for parameter group_by_ppid (No)"
+        ;;
+    *)
+        # default
+        _GROUP_BY_PPID=1
+        log "setting value for parameter group_by_ppid to its default (Yes)"
+        ;;
+esac
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+# collect defunct processes
+# shellcheck disable=SC2009
+_DEFUNCT_PROCS=$(UNIX95=1 ps -eo ppid,pid,comm,etime 2>"${HC_STDERR_LOG}" | tee -a "${HC_STDOUT_LOG}" 2>/dev/null | grep '[d]efunct' 2>/dev/null)
+
+# check defunct processes
+if [[ -z "${_DEFUNCT_PROCS}" ]]
+then
+    _MSG="no defunct process(es) detected"
+    _STC=0
+    if (( _LOG_HEALTHY > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    return 0
+else
+    if (( _GROUP_BY_PPID > 0 ))
+    then
+        # per by PPID
+        print -R "${_DEFUNCT_PROCS}" | awk '
+
+            {
+                # count PIDs per PPID
+                counts[$1]++;
+            }
+
+            END {
+                for (i in counts) print i ":" counts[i]
+            }' 2>/dev/null | while IFS=":" read -r _PPID _NUM_DEFUNCT_PROCS
+        do
+            (( ARG_DEBUG > 0 )) && debug "awk found PPID: ${_PPID} with # procs: ${_NUM_DEFUNCT_PROCS}"
+            if (( _NUM_DEFUNCT_PROCS <= _PROCESS_THRESHOLD ))
+            then
+                _MSG="defunct process(es) detected for PPID (${_PPID}) but are still under threshold (${_NUM_DEFUNCT_PROCS}<=${_PROCESS_THRESHOLD})"
+                _STC=0
+            else
+                _MSG="defunct process(es) detected for PPID (${_PPID}) and are over threshold (${_NUM_DEFUNCT_PROCS}>${_PROCESS_THRESHOLD})"
+                _STC=1
+            fi
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}" "${_NUM_DEFUNCT_PROCS}" "${_PROCESS_THRESHOLD}"
+            fi
+        done
+    else
+        _NUM_DEFUNCT_PROCS=$(print -R "${_DEFUNCT_PROCS}" | wc -l 2>/dev/null)
+        if (( _NUM_DEFUNCT_PROCS <= _PROCESS_THRESHOLD ))
+        then
+            _MSG="defunct process(es) detected but are still under threshold (${_NUM_DEFUNCT_PROCS}<=${_PROCESS_THRESHOLD})"
+            _STC=0
+        else
+            _MSG="defunct process(es) detected and are over threshold (${_NUM_DEFUNCT_PROCS}>${_PROCESS_THRESHOLD})"
+            _STC=1
+        fi
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+        then
+            log_hc "$0" ${_STC} "${_MSG}" "${_NUM_DEFUNCT_PROCS}" "${_PROCESS_THRESHOLD}"
+        fi
+    fi
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with parameters:
+                log_healthy=<yes|no>
+                process_threshold=<#_of_processes>
+                group_by_ppid=<yes|no>
+PURPOSE     : Checks whether there are (too many) defunct processes on the host.
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/hp-ux/check_hpux_file_change.sh

@@ -29,6 +29,8 @@
 # @(#) 2019-01-24: arguments fix [Patrick Van der Veken]
 # @(#) 2019-03-09: added support for --log-healthy [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2020-09-05: fix log_hc call for failed checksum + quote fix [Patrick Van der Veken]
+# @(#) 2021-01-13: fix log_hc call (wrong logic) [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -38,7 +40,7 @@ function check_hpux_file_change
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-03-16"                           # YYYY-MM-DD
+typeset _VERSION="2021-01-13"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -275,7 +277,7 @@ do
             openssl-sha256)
                 if (( _USE_OPENSSL == 1 ))
                 then
-                    _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
+                    _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
                     _FILE_TYPE="openssl-sha256"
                 else
                     _MSG="cannot compute checksum [${_FILE_TYPE}] for ${_FILE_TO_CHECK}"
@@ -285,7 +287,7 @@ do
             cksum-crc32)
                 if (( _USE_CKSUM == 1 ))
                 then
-                    _FILE_CKSUM=$(${_CKSUM_BIN} ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
+                    _FILE_CKSUM=$(${_CKSUM_BIN} "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
                     _FILE_TYPE="cksum-crc32"
                 else
                     _MSG="cannot compute checksum [${_FILE_TYPE}] for ${_FILE_TO_CHECK}"
@@ -301,11 +303,11 @@ do
         # new file
         if (( _USE_OPENSSL == 1 ))
         then
-            _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
+            _FILE_CKSUM=$(${_OPENSSL_BIN} dgst -sha256 "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f2 -d'=' | tr -d ' ')
             _FILE_TYPE="openssl-sha256"
         elif (( _USE_CKSUM == 1 ))
         then
-            _FILE_CKSUM=$(${_CKSUM_BIN} ${_FILE_TO_CHECK} 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
+            _FILE_CKSUM=$(${_CKSUM_BIN} "${_FILE_TO_CHECK}" 2>>${HC_STDERR_LOG} | cut -f1 -d' ')
             _FILE_TYPE="cksum-crc32"
         else
             _MSG="cannot compute checksum (openssl/cksum) for ${_FILE_TO_CHECK}"
@@ -321,7 +323,7 @@ do
     fi
 
     # bounce failures back and jump to next file
-    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    if (( _LOG_HEALTHY > 0 && _STC > 0 ))
     then
         log_hc "$0" ${_STC} "${_MSG}"
         continue
@@ -347,7 +349,7 @@ do
     printf "%s|%s|%s\n" "${_FILE_TO_CHECK}" "${_FILE_TYPE}" "${_FILE_CKSUM}" >>${_TMP2_FILE}
 
     # report with curr/exp values
-    if (( _LOG_HEALTHY > 0 ))
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
     then
         log_hc "$0" ${_STC} "${_MSG}" "${_FILE_CKSUM}" "${_STATE_FILE_CKSUM}"
         continue

opt/hc/lib/platform/hp-ux/check_hpux_ioscan.sh

@@ -32,6 +32,7 @@
 # @(#) 2018-10-28: fixed (linter) errors [Patrick Van der Veken]
 # @(#) 2019-01-24: arguments fix [Patrick Van der Veken]
 # @(#) 2019-03-09: added support for --log-healthy [Patrick Van der Veken]
+# @(#) 2021-04-07: quotes & shellcheck fixes [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -43,13 +44,13 @@ function check_hpux_ioscan
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
 typeset _IOSCAN_BIN="/usr/sbin/ioscan"
 typeset _IOSCAN_OPTS="-Fn"
-typeset _VERSION="2019-03-09"                           # YYYY-MM-DD
+typeset _VERSION="2021-04-07"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
-init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "${0}" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
 typeset _ARGS=$(data_comma2space "$*")
 typeset _ARG=""
 typeset _MSG=""
@@ -71,7 +72,7 @@ for _ARG in ${_ARGS}
 do
     case "${_ARG}" in
         help)
-            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            _show_usage "${0}" "${_VERSION}" "${_CONFIG_FILE}" && return 0
             ;;
     esac
 done
@@ -154,7 +155,8 @@ else
         _IOSCAN_OPTS="${_IOSCAN_OPTS}u"
     fi
     log "executing ioscan with options: ${_IOSCAN_OPTS}"
-    ${_IOSCAN_BIN} ${_IOSCAN_OPTS} >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+    ${_IOSCAN_BIN} ${_IOSCAN_OPTS} >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
+    # shellcheck disable=SC2181
     if (( $? > 0 ))
     then
         _MSG="unable to run command: {${_IOSCAN_BIN}}"
@@ -166,13 +168,13 @@ else
 fi
 
 # check for requested device classes
-grep -E -e ".*:.*:.*:.*:.*:.*:.*:.*:${_IOSCAN_CLASSES}:.*" ${HC_STDOUT_LOG} 2>/dev/null |\
-    while read _IOSCAN_LINE
+grep -E -e ".*:.*:.*:.*:.*:.*:.*:.*:${_IOSCAN_CLASSES}:.*" "${HC_STDOUT_LOG}" 2>/dev/null |\
+    while read -r _IOSCAN_LINE
 do
     # possible states are: CLAIMED, UNCLAIMED, DIFF_HW, NO_HW, ERROR, SCAN
-    _HW_CLASS="$(print ${_IOSCAN_LINE} | cut -f9 -d':')"
-    _HW_PATH="$(print ${_IOSCAN_LINE} | cut -f11 -d':')"
-    _HW_STATE="$(print ${_IOSCAN_LINE} | cut -f16 -d':')"
+    _HW_CLASS=$(print "${_IOSCAN_LINE}" | cut -f9 -d':')
+    _HW_PATH=$(print "${_IOSCAN_LINE}" | cut -f11 -d':')
+    _HW_STATE=$(print "${_IOSCAN_LINE}" | cut -f16 -d':')
 
     case "${_HW_STATE}" in
         NO_HW)
@@ -214,7 +216,6 @@ function _show_usage
 cat <<- EOT
 NAME        : $1
 VERSION     : $2
-CONFIG      : $3 with:
 CONFIG      : $3 with parameters:
                 log_healthy=<yes|no>
                 ioscan_classes=<list_of_device_classes_to_check>

opt/hc/lib/platform/hp-ux/check_hpux_ntp_status.sh

@@ -30,6 +30,7 @@
 # @(#)             with offset calculation [Patrick Van der Veken]
 # @(#) 2019-01-24: arguments fix [Patrick Van der Veken]
 # @(#) 2019-03-09: Text updates [Patrick Van der Veken]
+# @(#) 2020-12-21: fixes for --log-healthy [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #------------------------------------------------------------------------------
@@ -39,14 +40,14 @@ function check_hpux_ntp_status
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-03-09"                           # YYYY-MM-DD
+typeset _VERSION="2020-12-21"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 typeset _NTPQ_BIN="/usr/sbin/ntpq"
 typeset _NTPQ_OPTS="-pn"
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
 typeset _ARGS=$(data_comma2space "$*")
 typeset _ARG=""
@@ -65,7 +66,7 @@ for _ARG in ${_ARGS}
 do
     case "${_ARG}" in
         help)
-            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
             ;;
     esac
 done
@@ -148,7 +149,10 @@ case "${_NTP_PEER}" in
         _MSG="NTP is synchronizing against ${_NTP_PEER##*\*}"
         ;;
 esac
-log_hc "$0" ${_STC} "${_MSG}"
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
 
 # 2) offset value
 if (( _STC == 0 ))
@@ -165,7 +169,10 @@ then
             else
                 _MSG="NTP offset of ${_CURR_OFFSET} is within the acceptable range"
             fi
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
                 log_hc "$0" ${_STC} "${_MSG}"
+            fi
             ;;
         *)
             # not numeric

opt/hc/lib/platform/hp-ux/check_hpux_postfix_status.sh

@@ -26,6 +26,7 @@
 # @(#) 2019-01-24: arguments fix [Patrick Van der Veken]
 # @(#) 2019-03-09: added support for --log-healthy [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2020-12-27: add configuration check + quoting fixes [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -34,16 +35,17 @@
 function check_hpux_postfix_status
 {
 # ------------------------- CONFIGURATION starts here -------------------------
-typeset _VERSION="2019-03-09"                           # YYYY-MM-DD
+typeset _VERSION="2020-12-27"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
 typeset _ARGS=$(data_comma2space "$*")
 typeset _ARG=""
 typeset _POSTFIX_BIN=""
+typeset _POSTFIX_CHECKER=""
 typeset _MSG=""
 typeset _STC=0
 typeset _LOG_HEALTHY=0
@@ -53,7 +55,7 @@ for _ARG in ${_ARGS}
 do
     case "${_ARG}" in
         help)
-            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
             ;;
     esac
 done
@@ -72,10 +74,14 @@ else
     log "not logging/showing passed health checks"
 fi
 
+#-------------------------------------------------------------------------------
+# process state
+
 _POSTFIX_BIN="$(command -v postfix 2>>${HC_STDERR_LOG})"
 if [[ -x ${_POSTFIX_BIN} && -n "${_POSTFIX_BIN}" ]]
 then
-    ${_POSTFIX_BIN} status >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+    ${_POSTFIX_BIN} status >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
+    # shellcheck disable=SC2181
     if (( $? == 0 ))
     then
         _MSG="postfix is running"
@@ -87,13 +93,35 @@ else
     warn "postfix is not installed here"
     return 1
 fi
-
-# report result
 if (( _LOG_HEALTHY > 0 || _STC > 0 ))
 then
     log_hc "$0" ${_STC} "${_MSG}"
 fi
 
+#-------------------------------------------------------------------------------
+# configuration state
+_POSTFIX_CHECKER="$(command -v postconf 2>>${HC_STDERR_LOG})"
+if [[ -x ${_POSTFIX_CHECKER} && -n "${_POSTFIX_CHECKER}" ]]
+then
+    # dump configuration
+    ${_POSTFIX_CHECKER} -n >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        _MSG="postfix configuration files have syntax error(s) {${_POSTFIX_CHECKER} -n}"
+        _STC=1
+    else
+        _MSG="postfix configuration files are syntactically correct"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+else
+    warn "skipping syntax check (unable to find syntax check tool)"
+fi
+
 return 0
 }
 
@@ -103,7 +131,8 @@ function _show_usage
 cat <<- EOT
 NAME        : $1
 VERSION     : $2
-PURPOSE     : Checks whether postfix (mail system) is running
+PURPOSE     : Checks whether postfix (mail system) is running and whether the
+              postfix configuration files are syntactically correct
 LOG HEALTHY : Supported
 
 EOT

opt/hc/lib/platform/hp-ux/check_hpux_syslogd_status.sh

@@ -26,6 +26,7 @@
 # @(#) 2018-02-13: fix to avoid log check if syslogd is not active [Patrick Van der Veken]
 # @(#) 2019-03-09: text updates [Patrick Van der Veken]
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2019-10-07: fixed syslog.log checking [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -35,8 +36,8 @@ function check_hpux_syslogd_status
 {
 # ------------------------- CONFIGURATION starts here -------------------------
 typeset _SYSLOGD_PID_FILE="/var/run/syslog.pid"
-typeset _SYSLOGD_LOG_FILE="/var/adm/syslog.log"
-typeset _VERSION="2019-03-16"                           # YYYY-MM-DD
+typeset _SYSLOGD_LOG_FILE="/var/adm/syslog/syslog.log"
+typeset _VERSION="2019-10-07"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
@@ -121,9 +122,26 @@ then
 fi
 
 # ---- log state ----
-_LOGGER_BIN="$(command -v logger 2>>${HC_STDERR_LOG})"
-if [[ -x ${_LOGGER_BIN} && -n "${_LOGGER_BIN}" ]]
+# check syslog.log
+(( ARG_DEBUG > 0 )) && debug "checking syslogd log via file check"
+if [[ -r ${_SYSLOGD_LOG_FILE} ]] && [[ -s ${_SYSLOGD_LOG_FILE} ]]
 then
+    _MSG="syslog.log is present (${_SYSLOGD_LOG_FILE})"
+    _STC=0
+else
+    _MSG="syslog.log is not present or empty (${_SYSLOGD_LOG_FILE})"
+    _STC=1
+fi
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
+# check logger if syslog.log check did not fail
+if (( _STC == 0 ))
+then
+    _LOGGER_BIN="$(command -v logger 2>>${HC_STDERR_LOG})"
+    if [[ -x ${_LOGGER_BIN} && -n "${_LOGGER_BIN}" ]]
+    then
         # write test entry
         (( ARG_DEBUG > 0 )) && debug "checking syslogd log via {${_LOGGER_BIN}}"
         ${_LOGGER_BIN} -i -t "check_health" "*** LOG CHECK ***" >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
@@ -135,21 +153,13 @@ then
             _MSG="syslogd is not logging (correctly), write via {${_LOGGER_BIN}} NOK"
             _STC=1
         fi
-else
-    # check the syslog itself
-    (( ARG_DEBUG > 0 )) && debug "checking syslogd log via file check"
-    if [[ -r ${_SYSLOGD_LOG_FILE} ]] && [[ -s ${_SYSLOGD_LOG_FILE} ]]
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
         then
-        _MSG="syslogd is logging correctly (${_CRON_LOG_FILE})"
-        _STC=0
-    else
-        _MSG="syslogd is not logging (correctly) (${_SYSLOGD_LOG_FILE})"
-        _STC=1
-    fi
-fi
-if (( _LOG_HEALTHY > 0 || _STC > 0 ))
-then
             log_hc "$0" ${_STC} "${_MSG}"
+        fi
+    else
+        (( ARG_DEBUG > 0 )) && debug "no logger facility found, skipping logger check"
+    fi
 fi
 
 return 0

opt/hc/lib/platform/hp-ux/check_hpux_uptime.sh

@@ -0,0 +1,349 @@
+#!/usr/bin/env ksh
+#------------------------------------------------------------------------------
+# @(#) check_hpux_uptime
+#------------------------------------------------------------------------------
+# @(#) Copyright (C) 2020 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#------------------------------------------------------------------------------
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_hpux_uptime
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_is_numeric(), data_timestring_to_mins(), data_comma2space(),
+#           init_hc(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2020-12-21: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#------------------------------------------------------------------------------
+
+# -----------------------------------------------------------------------------
+function check_hpux_uptime
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _STATE_FILE="${STATE_PERM_DIR}/current.uptime"
+typeset _VERSION="2020-12-21"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="HP-UX"                    # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _LOG_HEALTHY=0
+typeset _CFG_HEALTHY=""
+typeset _CFG_CHECK_REBOOT=""
+typeset _CFG_REBOOT_TIME=""
+typeset _CFG_CHECK_OLD_AGE=""
+typeset _CFG_OLD_AGE_TIME=""
+typeset _CHECK_REBOOT=""
+typeset _REBOOT_TIME=""
+typeset _REBOOT_TIME_MINS=""
+typeset _CHECK_OLD_AGE=""
+typeset _OLD_AGE_TIME=""
+typeset _OLD_AGE_TIME_MINS=""
+typeset _CURRENT_UPTIME=""
+typeset _CURRENT_UPTIME_MINS=""
+typeset _INIT_TIME=""
+typeset _PREVIOUS_UPTIME=""
+typeset _PREVIOUS_UPTIME_MINS=""
+typeset _THRESHOLD_UPTIME_MINS=""
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
+            ;;
+    esac
+done
+
+# handle config file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read required config values
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+_CFG_CHECK_REBOOT=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_reboot')
+case "${_CFG_CHECK_REBOOT}" in
+    no|No|NO)
+        _CHECK_REBOOT=0
+        ;;
+    *)
+        _CHECK_REBOOT=1
+        ;;
+esac
+_CFG_REBOOT_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'reboot_time')
+if [[ -z "${_CFG_REBOOT_TIME}" ]]
+then
+    # default
+    _REBOOT_TIME="60m"
+else
+    _REBOOT_TIME="${_CFG_REBOOT_TIME}"
+fi
+_CFG_CHECK_OLD_AGE=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_old_age')
+case "${_CFG_CHECK_OLD_AGE}" in
+    yes|Yes|Yes)
+        _CHECK_OLD_AGE=1
+        ;;
+    *)
+        _CHECK_OLD_AGE=0
+        ;;
+esac
+_CFG_OLD_AGE_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'old_age_time')
+if [[ -z "${_CFG_OLD_AGE_TIME}" ]]
+then
+    # default
+    _OLD_AGE_TIME="365d"
+else
+    _OLD_AGE_TIME="${_CFG_OLD_AGE_TIME}"
+fi
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+#------------------------------------------------------------------------------
+# read uptime from init process
+# shellcheck disable=SC1007
+_INIT_TIME=$(UNIX95= ps -p 1 -o etime 2>/dev/null | tail -1)
+if [[ -n "${_INIT_TIME}" ]]
+then
+    # calculate exact uptime (seconds)
+    _CURRENT_UPTIME=$(print "${_INIT_TIME}" |\
+        awk '
+            BEGIN { days = 0; hours = 0; mins = 0; seconds = 0 };
+            {
+                gsub(/[ \t]/, "");
+                # get days
+                split ($0, day_str, "-");
+                if (2 in day_str) {
+                    # string has days
+                    days = day_str[1];
+                    split (day_str[2], hour_str, ":");
+                } else {
+                    split (day_str[1], hour_str, ":");
+                }
+                # get hours/minutes/seconds
+                hours = hour_str[1];
+                mins  = hour_str[2];
+                if (3 in hour_str) {
+                    # string has seconds
+                    secs  = hour_str[3];
+                }
+            }
+            END {
+                time = (days * 24 * 60 * 60) + (hours * 60 * 60) + (mins * 60) + secs;
+                print time;
+            }' 2>/dev/null)
+    data_is_numeric "${_CURRENT_UPTIME}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate uptime value (seconds)"
+        (( ARG_DEBUG )) && debug "_CURRENT_UPTIME=${_CURRENT_UPTIME}"
+        return 1
+    fi
+else
+    warn "uptime of INIT (1) process cannot be determined"
+    return 1
+fi
+
+#------------------------------------------------------------------------------
+# read state file
+if [[ -r ${_STATE_FILE} ]]
+then
+    _PREVIOUS_UPTIME=$(<"${_STATE_FILE}")
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "failed to read state file at ${_STATE_FILE}"
+        _PREVIOUS_UPTIME=""
+    fi
+fi
+
+#------------------------------------------------------------------------------
+# convert uptimes values
+_CURRENT_UPTIME_MINS=$(( _CURRENT_UPTIME / 60 ))
+data_is_numeric "${_CURRENT_UPTIME_MINS}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "unable to calculate current uptime value (minutes)"
+    (( ARG_DEBUG )) && debug "_CURRENT_UPTIME_MINS=${_CURRENT_UPTIME_MINS}"
+    return 1
+fi
+_PREVIOUS_UPTIME_MINS=$(( _PREVIOUS_UPTIME / 60 ))
+data_is_numeric "${_CURRENT_UPTIME_MINS}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "unable to calculate previous uptime value (minutes)"
+    (( ARG_DEBUG )) && debug "_PREVIOUS_UPTIME_MINS=${_PREVIOUS_UPTIME_MINS}"
+    return 1
+fi
+
+#------------------------------------------------------------------------------
+# check reboot event
+if (( _CHECK_REBOOT > 0 ))
+then
+    # convert _REBOOT_TIME to minutes
+    _REBOOT_TIME_MINS=$(data_timestring_to_mins "${_REBOOT_TIME}")
+    data_is_numeric "${_REBOOT_TIME_MINS}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate 'reboot_time' value from configuration file ${_CONFIG_FILE}"
+        (( ARG_DEBUG )) && debug "_REBOOT_TIME=${_REBOOT_TIME}"
+        return 1
+    fi
+
+    # previous uptime missing?
+    if [[ -z "${_PREVIOUS_UPTIME}" ]]
+    then
+        if (( ARG_LOG > 0 ))
+        then
+            print "${_CURRENT_UPTIME}" >"${_STATE_FILE}"
+            # shellcheck disable=SC2181
+            if (( $? > 0 ))
+            then
+                warn "failed to update state file at ${_STATE_FILE}"
+                return 1
+            else
+                log "unable to find previously recorded uptime, resetting to current uptime"
+                return 0
+            fi
+        else
+            log "unable to find previously recorded uptime, resetting to current uptime"
+        fi
+    else
+        # current uptime + reboot time is smaller than previous uptime?
+        _THRESHOLD_UPTIME_MINS=$(( _CURRENT_UPTIME_MINS + _REBOOT_TIME_MINS ))
+        if (( _THRESHOLD_UPTIME_MINS < _PREVIOUS_UPTIME_MINS ))
+        then
+            _MSG="reboot check: current uptime is NOK; check if reboot occurred"
+            _STC=1
+        else
+            _MSG="reboot check: current uptime is OK"
+            _STC=0
+        fi
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}" "${_THRESHOLD_UPTIME_MINS}" "${_PREVIOUS_UPTIME_MINS}"
+    fi
+
+    # update state file
+    if (( ARG_LOG > 0 ))
+    then
+        print "${_CURRENT_UPTIME}" >"${_STATE_FILE}"
+        # shellcheck disable=SC2181
+        if (( $? > 0 ))
+        then
+            warn "failed to update state file at ${_STATE_FILE}"
+            return 1
+        fi
+    fi
+else
+    log "reboot check: not enabled"
+fi
+
+#------------------------------------------------------------------------------
+# check old age event
+if (( _CHECK_OLD_AGE > 0 ))
+then
+    # convert _OLD_AGE_TIME to minutes
+    _OLD_AGE_TIME_MINS=$(data_timestring_to_mins "${_OLD_AGE_TIME}")
+    data_is_numeric "${_OLD_AGE_TIME_MINS}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        warn "unable to calculate 'old_age_time' value from configuration file ${_CONFIG_FILE}"
+        (( ARG_DEBUG )) && debug "_OLD_AGE_TIME=${_OLD_AGE_TIME}"
+        return 1
+    fi
+
+    # are we old age yet?
+    if (( _CURRENT_UPTIME_MINS > _OLD_AGE_TIME_MINS ))
+    then
+        _MSG="old_age check: current uptime is NOK; old age has arrived (>${_OLD_AGE_TIME})"
+        _STC=1
+    else
+        _MSG="old_age check: current uptime is OK"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}" "${_CURRENT_UPTIME_MINS}" "${_OLD_AGE_TIME_MINS}"
+    fi
+else
+    log "old age check: not enabled"
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with:
+               log_healthy=<yes|no>
+               check_reboot=<yes|no>
+               reboot_time=<timestring>
+               check_old_age=<yes|no>
+               old_age_time=<timestring>
+PURPOSE     : Checks for unexpected/unplanned reboot events based on uptime
+               values.
+              Checks whether the host has been up and running for too much time.
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+
+#------------------------------------------------------------------------------
+# END of script
+#------------------------------------------------------------------------------

opt/hc/lib/platform/linux/check_linux_autofs.sh

@@ -0,0 +1,263 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_linux_autofs.sh
+#******************************************************************************
+# @(#) Copyright (C) 2019 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_linux_autofs
+# DOES: see _show_usage()
+# EXPECTS: see _show_usage()
+# REQUIRES: data_comma2space(), data_is_numeric(), dump_logs(), init_hc(),
+#           linux_change_service(), linux_has_service(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2019-07-14: original version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_linux_autofs
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2019-10-24"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
+# shellcheck disable=SC2034
+typeset _HC_CAN_FIX=1                                   # plugin has fix/healing logic?
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _CFG_HEALTHY=""
+typeset _LOG_HEALTHY=0
+typeset _CFG_FIX_AUTOFS=""
+typeset _FIX_AUTOFS=0
+typeset _IS_ACTIVE=0
+typeset _HAS_SERVICE=0
+typeset _RETRY_START=3
+typeset _SLEEP_TIME=5
+typeset _RETRY_COUNT=1
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            ;;
+    esac
+done
+
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+_CFG_FIX_AUTOFS=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'fix_autofs')
+case "${_CFG_FIX_AUTOFS}" in
+    yes|YES|Yes)
+        _FIX_AUTOFS=1
+        ;;
+    *)
+        _FIX_AUTOFS=0
+        ;;
+esac
+_CFG_RETRY_START=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'retry_start')
+data_is_numeric "${_CFG_RETRY_START}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "value for parameter 'retry_count' in configuration file ${_CONFIG_FILE} is invalid"
+    return 1
+else
+    _RETRY_START=${_CFG_RETRY_START}
+fi
+_CFG_SLEEP_TIME=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'sleep_time')
+data_is_numeric "${_CFG_SLEEP_TIME}"
+# shellcheck disable=SC2181
+if (( $? > 0 ))
+then
+    warn "value for parameter 'sleep_time' in configuration file ${_CONFIG_FILE} is invalid"
+    return 1
+else
+    _SLEEP_TIME=${_CFG_SLEEP_TIME}
+fi
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+
+# log_healthy/--log-healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+# --no-fix
+if (( ARG_NO_FIX > 0 ))
+then
+    _FIX_AUTOFS=0
+    log "fix/healing logic has been disabled"
+fi
+
+# check if autofs is enabled
+log "checking if autofs daemon is enabled"
+_HAS_SERVICE=$(linux_has_service "autofs")
+(( $? > 0)) && {
+    _MSG="error in function {linux_has_service}"
+    log_hc "$0" 1 "${_MSG}"
+    # dump debug info
+    (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+    return 1
+}
+if (( _HAS_SERVICE == 2 ))
+then
+    _MSG="autofs service is enabled"
+    _STC=0
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+    # check if autofs is running
+    log "checking if autofs daemon is active"
+    _IS_ACTIVE=$(linux_runs_service autofs)
+    (( $? > 0)) && {
+        _MSG="error in function {linux_runs_service }"
+        log_hc "$0" 1 "${_MSG}"
+        # dump debug info
+        (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+        return 1
+    }
+    if (( _IS_ACTIVE > 0 ))
+    then
+        _MSG="autofs daemon is running"
+        _STC=0
+        if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+        then
+            log_hc "$0" ${_STC} "${_MSG}"
+        fi
+    else
+        warn "autofs daemon is not running"
+        # try restart if healing is desired
+        if (( _FIX_AUTOFS > 0 ))
+        then
+            while (( _RETRY_COUNT <= _RETRY_START && _IS_ACTIVE == 0 ))
+            do
+                log "restarting autofs (attempt #${_RETRY_COUNT})"
+                linux_change_service "autofs" "restart" >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+                # dump debug info
+                (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+                log "sleeping for ${_SLEEP_TIME} seconds"
+                sleep ${_SLEEP_TIME}
+                _RETRY_COUNT=$(( _RETRY_COUNT + 1 ))
+                _IS_ACTIVE=$(linux_runs_service "autofs")
+                (( $? > 0)) && {
+                    _MSG="error in function {linux_runs_service }"
+                    log_hc "$0" 1 "${_MSG}"
+                    # dump debug info
+                    (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+                    return 1
+                }
+            done
+            # check again if autofs is running
+            _IS_ACTIVE=$(linux_runs_service "autofs")
+            (( $? > 0)) && {
+                _MSG="error in function {linux_runs_service }"
+                log_hc "$0" 1 "${_MSG}"
+                # dump debug info
+                (( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && dump_logs
+                return 1
+            }
+            if (( _IS_ACTIVE > 0 ))
+            then
+                _MSG="autofs daemon is running"
+                _STC=0
+                if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+                then
+                    log_hc "$0" ${_STC} "${_MSG}"
+                fi
+            else
+                _MSG="autofs daemon is not running"
+                _STC=1
+                if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+                then
+                    log_hc "$0" ${_STC} "${_MSG}"
+                fi
+            fi
+        else
+            _MSG="autofs daemon is not running"
+            _STC=1
+            if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+            then
+                log_hc "$0" ${_STC} "${_MSG}"
+            fi
+        fi
+    fi
+else
+    _MSG="autofs service is disabled"
+    _STC=1
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with parameters:
+                log_healthy=<yes|no>
+                fix_autofs=<yes|no>
+                retry_start=<amount_of_start_retries>
+                sleep_time=<seconds_to_sleep_during_restart_attempts>
+PURPOSE     : Check/fix AutoFS service
+LOG HEALTHY : Supported
+CAN FIX?    : Yes
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/linux/check_linux_burp_backup.sh

@@ -34,6 +34,8 @@
 # @(#)             added support for --log-healthy [Patrick Van der Veken]
 # @(#) 2019-03-10: fix for burp v2
 # @(#) 2019-03-16: replace 'which' [Patrick Van der Veken]
+# @(#) 2021-03-28: updated code for changing 'burp -v' option as of burp v2.2 +
+#                  quote fixes [Patrick Van der Veken]
 # -----------------------------------------------------------------------------
 # DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
 #******************************************************************************
@@ -45,12 +47,12 @@ function check_linux_burp_backup
 typeset _BURP_SERVER_CONFIG_FILE="/etc/burp/burp-server.conf"
 typeset _BURP_CLIENT_CONFIG_FILE="/etc/burp/burp.conf"
 typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
-typeset _VERSION="2019-03-16"                           # YYYY-MM-DD
+typeset _VERSION="2021-03-28"                           # YYYY-MM-DD
 typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
 # ------------------------- CONFIGURATION ends here ---------------------------
 
 # set defaults
-(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
 init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
 typeset _ARGS=$(data_comma2space "$*")
 typeset _ARG=""
@@ -64,6 +66,7 @@ typeset _BURP_BACKUP_DIR=""
 typeset _BURP_CLIENTCONF_DIR=""
 typeset _BURP_CLIENT=""
 typeset _BURP_VERSION=""
+typeset _BURP_V_OUTPUT=""
 typeset _BURP_WARNINGS=""
 typeset _GNU_DATE=""
 typeset _COUNT=1
@@ -75,7 +78,7 @@ for _ARG in ${_ARGS}
 do
     case "${_ARG}" in
         help)
-            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
             ;;
     esac
 done
@@ -99,7 +102,7 @@ case "${_CFG_HEALTHY}" in
 esac
 
 # check for old-style configuration file (non-prefixed stanzas)
-_IS_OLD_STYLE=$(grep -c -E -e "^client:" ${_CONFIG_FILE} 2>/dev/null)
+_IS_OLD_STYLE=$(grep -c -E -e "^client:" "${_CONFIG_FILE}" 2>/dev/null)
 if (( _IS_OLD_STYLE == 0 ))
 then
     warn "no 'client:' stanza(s) found in ${_CONFIG_FILE}; possibly an old-style configuration?"
@@ -123,6 +126,7 @@ fi
 # check for capable GNU date
 _GNU_DATE=$(date --date="1 day ago" '+%s' 2>/dev/null)
 data_is_numeric "${_GNU_DATE}"
+# shellcheck disable=SC2181
 if (( $? > 0 ))
 then
     warn "no capable GNU date found here"
@@ -137,8 +141,20 @@ then
     return 1
 fi
 
-# burp v1 or v2?
-_BURP_VERSION="$(${_BURP_BIN} -v 2>/dev/null)"
+# burp v1 or v2? (up to v2.1 burp -v; as of burp v2.2 use burp -V but we can still use burp -v with a workaround)
+_BURP_V_OUTPUT="$(${_BURP_BIN} -v 2>/dev/null)"
+# check if the output contains 'server version'
+case "${_BURP_V_OUTPUT}" in
+    *Server\ version*)
+        # burp 2.2 and above
+        _BURP_VERSION=$(print "${_BURP_V_OUTPUT}" | grep "Server version" | awk -F":" '{ print $NF}')
+        _BURP_VERSION="burp-"$(data_strip_outer_space "${_BURP_VERSION}")
+        ;;
+    *)
+        # burp 2.1 and below
+        _BURP_VERSION="${_BURP_V_OUTPUT}"
+        ;;
+esac
 (( ARG_DEBUG > 0 )) && debug "burp version: ${_BURP_VERSION}"
 case "${_BURP_VERSION}" in
     burp-2*)
@@ -183,8 +199,8 @@ case "${_BURP_VERSION}" in
 esac
 
 # check backup runs of clients
-grep -E -e "^client:" ${_CONFIG_FILE} 2>/dev/null |\
-    while IFS=':' read _ _BURP_CLIENT _BURP_WARNINGS _BURP_AGE
+grep -E -e "^client:" "${_CONFIG_FILE}" 2>/dev/null |\
+    while IFS=':' read -r _ _BURP_CLIENT _BURP_WARNINGS _BURP_AGE
 do
     typeset _BACKUP_AGING=""
     typeset _BACKUP_DATE=""
@@ -222,10 +238,10 @@ do
         # ex.:
         #   Backup: 0000078 2016-11-27 03:39:03 (deletable)
         #   Backup: 0000079 2016-12-04 03:59:04
-        _BACKUP_STATS="$(${_BURP_BIN} -a l -C ${_BURP_CLIENT} 2>>${HC_STDERR_LOG} | grep '^Backup' | tail -n 1 | cut -f2- -d':')"
+        _BACKUP_STATS="$(${_BURP_BIN} -a l -C "${_BURP_CLIENT}" 2>>"${HC_STDERR_LOG}" | grep '^Backup' | tail -n 1 | cut -f2- -d':')"
         if [[ -n "${_BACKUP_STATS}" ]]
         then
-            _BACKUP_RUN="$(print ${_BACKUP_STATS} | awk '{print $1}')"
+            _BACKUP_RUN="$(print "${_BACKUP_STATS}" | awk '{print $1}')"
             # output format: YYYYMMDD HHMM
             _BACKUP_DATE=$(print "${_BACKUP_STATS}" | awk '{gsub(/-/,"",$2); gsub(/:/,"",$3); print $2" "substr($3,0,4)}' 2>/dev/null)
             # convert to UNIX seconds
@@ -267,16 +283,16 @@ do
                         continue
                     fi
                 fi
-                if [[ -r ${_BURP_BACKUP_DIR}/${_BURP_CLIENT}/current/log.gz ]]
+                if [[ -r "${_BURP_BACKUP_DIR}"/"${_BURP_CLIENT}"/current/log.gz ]]
                 then
-                    _BACKUP_WARNINGS=$(zcat ${_BURP_BACKUP_DIR}/${_BURP_CLIENT}/current/log.gz 2>/dev/null | grep -c "WARNING:" 2>/dev/null)
+                    _BACKUP_WARNINGS=$(zcat "${_BURP_BACKUP_DIR}"/"${_BURP_CLIENT}"/current/log.gz 2>/dev/null | grep -c "WARNING:" 2>/dev/null)
                 else
                     warn "could not find ${_BURP_BACKUP_DIR}/${_BURP_CLIENT}/current/log.gz"
                     continue
                 fi
                 ;;
             burp-1*)
-                _BACKUP_WARNINGS=$(${_BURP_BIN} -c ${_BURP_SERVER_CONFIG_FILE} -a S -C ${_BURP_CLIENT} -b ${_BACKUP_RUN} -z backup_stats 2>>${HC_STDERR_LOG} |\
+                _BACKUP_WARNINGS=$(${_BURP_BIN} -c ${_BURP_SERVER_CONFIG_FILE} -a S -C "${_BURP_CLIENT}" -b "${_BACKUP_RUN}" -z backup_stats 2>>"${HC_STDERR_LOG}" |\
                                     grep '^warnings' 2>/dev/null | cut -f2 -d':' 2>/dev/null)
                 ;;
         esac
@@ -325,16 +341,16 @@ do
         # save STDOUT
         if (( _STC > 0 ))
         then
-            print "=== ${_BURP_CLIENT}: ${_BACKUP_RUN} ===" >>${HC_STDOUT_LOG}
+            print "=== ${_BURP_CLIENT}: ${_BACKUP_RUN} ===" >>"${HC_STDOUT_LOG}"
             case "${_BURP_VERSION}" in
                 burp-2*)
-                    if [[ -r ${_BURP_BACKUP_DIR}/${_BURP_CLIENT}/current/log.gz ]]
+                    if [[ -r "${_BURP_BACKUP_DIR}"/"${_BURP_CLIENT}"/current/log.gz ]]
                     then
-                        zcat ${_BURP_BACKUP_DIR}/${_BURP_CLIENT}/current/log.gz >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+                        zcat "${_BURP_BACKUP_DIR}"/"${_BURP_CLIENT}"/current/log.gz >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
                     fi
                     ;;
                 burp-1*)
-                    ${_BURP_BIN} -c ${_BURP_SERVER_CONFIG_FILE} -a S -C ${_BURP_CLIENT} -b ${_BACKUP_RUN} -z log.gz >>${HC_STDOUT_LOG} 2>>${HC_STDERR_LOG}
+                    ${_BURP_BIN} -c ${_BURP_SERVER_CONFIG_FILE} -a S -C "${_BURP_CLIENT}" -b "${_BACKUP_RUN}" -z log.gz >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
                     ;;
             esac
         fi

opt/hc/lib/platform/linux/check_linux_dovecot_status.sh

@@ -0,0 +1,209 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_linux_dovecot_status.sh
+#******************************************************************************
+# @(#) Copyright (C) 2020 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_linux_dovecot_status
+# DOES: see _show_usage()
+# EXPECTS: n/a
+# REQUIRES: data_comma2space(), linux_get_init(), init_hc(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2020-12-27: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_linux_dovecot_status
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _DOVECOT_INIT_SCRIPT="/etc/init.d/dovecot"
+typeset _DOVECOT_SYSTEMD_SERVICE="dovecot.service"
+typeset _VERSION="2020-12-27"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set "${DEBUG_OPTS}"
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _DOVECOT_BIN=""
+typeset _DOVECOT_CHECKER=""
+typeset _MSG=""
+typeset _STC=0
+typeset _LOG_HEALTHY=0
+typeset _RC=0
+typeset _CHECK_SYSTEMD_SERVICE=0
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage "$0" "${_VERSION}" "${_CONFIG_FILE}" && return 0
+            ;;
+    esac
+done
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+#-------------------------------------------------------------------------------
+# process state
+
+# 1) try using the init ways
+linux_get_init
+case "${LINUX_INIT}" in
+    'systemd')
+        # Debian8/Ubuntu16 do not correctly report a unit file for dovecot,
+        # do not check for it and instead just query systemd service
+        linux_get_distro
+        if [[ "${LINUX_DISTRO}" = "Debian" ]] && (( ${LINUX_RELEASE%%.*} < 9 ))
+        then
+            _CHECK_SYSTEMD_SERVICE=1
+        elif [[ "${LINUX_DISTRO}" = "Ubuntu" ]] && (( ${LINUX_RELEASE%%.*} < 17 ))
+        then
+            _CHECK_SYSTEMD_SERVICE=1
+        else
+            _CHECK_SYSTEMD_SERVICE=$(linux_has_systemd_service "${_DOVECOT_SYSTEMD_SERVICE}")
+        fi
+        if (( _CHECK_SYSTEMD_SERVICE > 0 ))
+        then
+            systemctl --quiet is-active ${_DOVECOT_SYSTEMD_SERVICE} 2>>"${HC_STDERR_LOG}" || _STC=1
+        else
+            warn "systemd unit file not found {${_DOVECOT_SYSTEMD_SERVICE}}"
+            _RC=1
+        fi
+        ;;
+    'upstart')
+        warn "code for upstart managed systems not implemented, NOOP"
+        _RC=1
+        ;;
+    'sysv')
+        # check running SysV
+        if [[ -x ${_DOVECOT_INIT_SCRIPT} ]]
+        then
+            if (( $(${_DOVECOT_INIT_SCRIPT} status 2>>"${HC_STDERR_LOG}" | grep -c -i 'is running' 2>/dev/null) == 0 ))
+            then
+                _STC=1
+            fi
+        else
+            warn "sysv init script not found {${_DOVECOT_INIT_SCRIPT}}"
+            _RC=1
+        fi
+        ;;
+    *)
+        _RC=1
+        ;;
+esac
+
+# 2) try the dovecot way
+if (( _RC > 0 ))
+then
+    _DOVECOT_BIN="$(command -v dovecot 2>>${HC_STDERR_LOG})"
+    if [[ -x ${_DOVECOT_BIN} && -n "${_DOVECOT_BIN}" ]]
+    then
+        if (( $(${_DOVECOT_BIN} status 2>>"${HC_STDERR_LOG}" | grep -c -i 'is running' 2>/dev/null) == 0 ))
+        then
+            _RC=1
+        fi
+    else
+        warn "dovecot is not installed here"
+        return 1
+    fi
+fi
+
+# 3) try the pgrep way (note: old pgreps do not support '-c')
+if (( _RC > 0 ))
+then
+    (( $(pgrep -u dovecot 2>>"${HC_STDERR_LOG}" | wc -l 2>/dev/null) == 0 )) && _STC=1
+fi
+
+# evaluate results
+case ${_STC} in
+    0)
+        _MSG="dovecot is running"
+        ;;
+    1)
+        _MSG="dovecot is not running"
+        ;;
+    *)
+        _MSG="could not determine status of dovecot"
+        ;;
+esac
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
+
+#-------------------------------------------------------------------------------
+# configuration state
+_DOVECOT_CHECKER="$(command -v doveconf 2>>${HC_STDERR_LOG})"
+if [[ -x ${_DOVECOT_CHECKER} && -n "${_DOVECOT_CHECKER}" ]]
+then
+    # dump configuration
+    ${_DOVECOT_CHECKER} -n >>"${HC_STDOUT_LOG}" 2>>"${HC_STDERR_LOG}"
+    # shellcheck disable=SC2181
+    if (( $? > 0 ))
+    then
+        _MSG="dovecot configuration files have syntax error(s) {${_DOVECOT_CHECKER} -n}"
+        _STC=1
+    else
+        _MSG="dovecot configuration files are syntactically correct"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        log_hc "$0" ${_STC} "${_MSG}"
+    fi
+else
+    warn "skipping syntax check (unable to find syntax check tool)"
+fi
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+PURPOSE     : Checks whether dovecot (mail system) is running and whether the
+              dovecot configuration files are syntactically correct
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************

opt/hc/lib/platform/linux/check_linux_fail2ban_status.sh

@@ -0,0 +1,266 @@
+#!/usr/bin/env ksh
+#******************************************************************************
+# @(#) check_linux_fail2ban_status.sh
+#******************************************************************************
+# @(#) Copyright (C) 2020 by KUDOS BVBA (info@kudos.be).  All rights reserved.
+#
+# This program is a free software; you can redistribute it and/or modify
+# it under the same terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#******************************************************************************
+#
+# DOCUMENTATION (MAIN)
+# -----------------------------------------------------------------------------
+# @(#) MAIN: check_linux_fail2ban_status
+# DOES: see _show_usage()
+# EXPECTS: n/a
+# REQUIRES: data_comma2newline(), data_comma2space(), linux_get_init(), init_hc(),
+#           log(), log_hc(), warn()
+#
+# @(#) HISTORY:
+# @(#) 2020-10-18: initial version [Patrick Van der Veken]
+# -----------------------------------------------------------------------------
+# DO NOT CHANGE THIS FILE UNLESS YOU KNOW WHAT YOU ARE DOING!
+#******************************************************************************
+
+# -----------------------------------------------------------------------------
+function check_linux_fail2ban_status
+{
+# ------------------------- CONFIGURATION starts here -------------------------
+typeset _FAIL2BAN_INIT_SCRIPT="/etc/init.d/fail2ban"
+typeset _FAIL2BAN_SYSTEMD_SERVICE="fail2ban.service"
+typeset _CONFIG_FILE="${CONFIG_DIR}/$0.conf"
+typeset _VERSION="2020-10-18"                           # YYYY-MM-DD
+typeset _SUPPORTED_PLATFORMS="Linux"                    # uname -s match
+# ------------------------- CONFIGURATION ends here ---------------------------
+
+# set defaults
+(( ARG_DEBUG > 0 && ARG_DEBUG_LEVEL > 0 )) && set ${DEBUG_OPTS}
+init_hc "$0" "${_SUPPORTED_PLATFORMS}" "${_VERSION}"
+typeset _ARGS=$(data_comma2space "$*")
+typeset _ARG=""
+typeset _MSG=""
+typeset _STC=0
+typeset _CHECK_SYSTEMD_SERVICE=0
+typeset _CFG_HEALTHY=""
+typeset _LOG_HEALTHY=0
+typeset _CFG_CHECK_JAILS=""
+typeset _CFG_CHECK_TYPE=""
+typeset _DO_PGREP=0
+typeset _DO_CHECK_JAIL=1
+typeset _CHECK_JAIL=""
+typeset _JAIL_OUTPUT=""
+typeset _FAILED_NUM=0
+typeset _BANNED_NUM=0
+typeset _RC=0
+
+# handle arguments (originally comma-separated)
+for _ARG in ${_ARGS}
+do
+    case "${_ARG}" in
+        help)
+            _show_usage $0 ${_VERSION} ${_CONFIG_FILE} && return 0
+            ;;
+    esac
+done
+
+# handle configuration file
+[[ -n "${ARG_CONFIG_FILE}" ]] && _CONFIG_FILE="${ARG_CONFIG_FILE}"
+if [[ ! -r ${_CONFIG_FILE} ]]
+then
+    warn "unable to read configuration file at ${_CONFIG_FILE}"
+    return 1
+fi
+# read configuration values
+_CFG_CHECK_TYPE=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_type')
+case "${_CFG_CHECK_TYPE}" in
+    pgrep|Pgrep|PGREP)
+        _DO_PGREP=1
+        log "using pgrep process check (config override)"
+        ;;
+    sysv|Sysv|SYSV)
+        LINUX_INIT="sysv"
+        log "using init based process check (config override)"
+        ;;
+    systemd|Systemd|SYSTEMD)
+        LINUX_INIT="systemd"
+        log "using systemd based process check (config override)"
+        ;;
+    *)
+        # no overrides
+        :
+        ;;
+esac
+_CFG_CHECK_JAILS=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'check_jails')
+if [[ -n "${_CFG_CHECK_JAILS}" ]]
+then
+    log "setting jail list to ${_CFG_CHECK_JAILS}"
+fi
+_CFG_HEALTHY=$(_CONFIG_FILE="${_CONFIG_FILE}" data_get_lvalue_from_config 'log_healthy')
+case "${_CFG_HEALTHY}" in
+    yes|YES|Yes)
+        _LOG_HEALTHY=1
+        ;;
+    *)
+        # do not override hc_arg
+        (( _LOG_HEALTHY > 0 )) || _LOG_HEALTHY=0
+        ;;
+esac
+
+# log_healthy
+(( ARG_LOG_HEALTHY > 0 )) && _LOG_HEALTHY=1
+if (( _LOG_HEALTHY > 0 ))
+then
+    if (( ARG_LOG > 0 ))
+    then
+        log "logging/showing passed health checks"
+    else
+        log "showing passed health checks (but not logging)"
+    fi
+else
+    log "not logging/showing passed health checks"
+fi
+
+# check fail2ban-server
+_FAIL2BAN_BIN="$(command -v fail2ban-server 2>>${HC_STDERR_LOG})"
+if [[ -x ${_FAIL2BAN_BIN} && -n "${_FAIL2BAN_BIN}" ]]
+then
+    log "fail2ban (server) is installed at {${_FAIL2BAN_BIN}}"
+else
+    warn "fail2ban (server) is not installed here"
+    return 1
+fi
+
+# ---- process state ----
+# 1) try using the init ways
+if (( _DO_PGREP == 0 ))
+then
+    [[ -n "${LINUX_INIT}" ]] || linux_get_init
+    case "${LINUX_INIT}" in
+        'systemd')
+            _CHECK_SYSTEMD_SERVICE=$(linux_has_systemd_service "${_FAIL2BAN_SYSTEMD_SERVICE}")
+            if (( _CHECK_SYSTEMD_SERVICE > 0 ))
+            then
+                systemctl --quiet is-active ${_FAIL2BAN_SYSTEMD_SERVICE} 2>>${HC_STDERR_LOG} || _STC=1
+            else
+                warn "systemd unit file not found {${_FAIL2BAN_SYSTEMD_SERVICE}}"
+                _RC=1
+            fi
+            ;;
+        'upstart')
+            warn "code for upstart managed systems not implemented, NOOP"
+            _RC=1
+            ;;
+        'sysv')
+            # check running SysV
+            if [[ -x ${_FAIL2BAN_INIT_SCRIPT} ]]
+            then
+                if (( $(${_FAIL2BAN_INIT_SCRIPT} status 2>>${HC_STDERR_LOG} | grep -c -i 'is running' 2>/dev/null) == 0 ))
+                then
+                    _STC=1
+                fi
+            else
+                warn "sysv init script not found {${_FAIL2BAN_INIT_SCRIPT}}"
+                _RC=1
+            fi
+            ;;
+        *)
+            _RC=1
+            ;;
+    esac
+fi
+
+# 2) try the pgrep way (note: old pgreps do not support '-c')
+if (( _DO_PGREP > 0 || _RC > 0 ))
+then
+    (( $(pgrep --full -u root "python.*${_FAIL2BAN_BIN}" 2>>${HC_STDERR_LOG} | wc -l 2>/dev/null) == 0 )) && _STC=1
+fi
+
+# evaluate results
+case ${_STC} in
+    0)
+        _MSG="${_FAIL2BAN_BIN} is running"
+        ;;
+    1)
+        _MSG="${_FAIL2BAN_BIN} is not running"
+        _DO_CHECK_JAIL=0
+        ;;
+    *)
+        _MSG="could not determine status of ${_FAIL2BAN_BIN}"
+        _DO_CHECK_JAIL=0
+        ;;
+esac
+if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+then
+    log_hc "$0" ${_STC} "${_MSG}"
+fi
+
+# ---- jail states ----
+if (( _DO_CHECK_JAIL == 0 ))
+then
+    warn "fail2ban (server) is not running, skipping jail checks"
+    return 0
+fi
+_FAIL2BAN_BIN="$(command -v fail2ban-client 2>>${HC_STDERR_LOG})"
+if [[ -x ${_FAIL2BAN_BIN} && -n "${_FAIL2BAN_BIN}" ]]
+then
+    log "fail2ban (client) is installed at {${_FAIL2BAN_BIN}}"
+else
+    warn "fail2ban (client) is not installed here, skipping jail checks"
+    return 1
+fi
+print "$(data_comma2newline ${_CFG_CHECK_JAILS})" | while read -r _CHECK_JAIL
+do
+    _FAILED_NUM=0
+    _BANNED_NUM=0
+    _JAIL_OUTPUT=$(${_FAIL2BAN_BIN} status ${_CHECK_JAIL} 2>>${HC_STDERR_LOG})
+    if (( $? > 0 ))
+    then
+        _MSG="state of jail ${_CHECK_JAIL} is NOK"
+        _STC=1
+    else
+        _FAILED_NUM=$(print "${_JAIL_OUTPUT}" | grep -i 'currently failed' 2>/dev/null | awk -F':' '{ gsub(/[[:space:]]/,"",$2); print $2 }')
+        _BANNED_NUM=$(print "${_JAIL_OUTPUT}" | grep -i 'currently banned' 2>/dev/null | awk -F':' '{ gsub(/[[:space:]]/,"",$2); print $2 }')
+        _MSG="state of jail ${_CHECK_JAIL} is OK [failed=${_FAILED_NUM}/banned=${_BANNED_NUM}]"
+        _STC=0
+    fi
+    if (( _LOG_HEALTHY > 0 || _STC > 0 ))
+    then
+        # report only number of banned if OK
+        log_hc "$0" ${_STC} "${_MSG}" ${_BANNED_NUM} ${_BANNED_NUM}
+    fi
+    # add jail output to STDOUT
+    print "==== {${_FAIL2BAN_BIN} status ${_CHECK_JAIL}} ====" >>${HC_STDOUT_LOG}
+    print "${_JAIL_OUTPUT}" >>${HC_STDOUT_LOG}
+done
+
+return 0
+}
+
+# -----------------------------------------------------------------------------
+function _show_usage
+{
+cat <<- EOT
+NAME        : $1
+VERSION     : $2
+CONFIG      : $3 with parameters:
+               log_healthy=<yes|no>
+               check_type=<auto|pgrep|sysv|systemd>
+               check_jails=<list_of_jails>
+PURPOSE     : Checks whether fail2ban (server service) is running and the state
+              of the configured jails.
+LOG HEALTHY : Supported
+
+EOT
+
+return 0
+}
+
+#******************************************************************************
+# END of script
+#******************************************************************************