Module: check_mk Branch: master Commit: 46582b9f5b243ae9d1ab521d415b78c7692a8762 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=46582b9f5b243a… Author: Mathias Kettner &lt;mk(a)mathias-kettner.de&gt; Date: Fri Aug 15 11:50:34 2014 +0200 #1008 Overall check timeout for Check_MK checks now defaults to CRIT state When using the Check_MK Micro Core as the core then the service status for Check_MK services that ran into an overal timeout (default is 60 seconds) was UNKNOWN. This has changed to CRIT. Furthermore this is configurable via a new <i>Timeout</i> option in the ruleset <i>Status of the Check_MK service</i>. --- .werks/1008 | 12 ++++++++++++ ChangeLog | 3 +++ modules/check_mk.py | 6 ++++-- web/plugins/wato/check_mk_configuration.py | 8 +++++++- 4 files changed, 26 insertions(+), 3 deletions(-) diff --git a/.werks/1008 b/.werks/1008 new file mode 100644 index 0000000..7627e27 --- /dev/null +++ b/.werks/1008 @@ -0,0 +1,12 @@ +Title: Overall check timeout for Check_MK checks now defaults to CRIT state +Level: 2 +Component: core +Compatible: compat +Version: 1.2.5i6 +Date: 1408096113 +Class: feature + +When using the Check_MK Micro Core as the core then the service status for Check_MK +services that ran into an overal timeout (default is 60 seconds) was UNKNOWN. This +has changed to CRIT. Furthermore this is configurable via a new <i>Timeout</i> +option in the ruleset <i>Status of the Check_MK service</i>. diff --git a/ChangeLog b/ChangeLog index 097f997..15e1a44 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,7 @@ 1.2.5i6: + Core & Setup: + * 1008 Overall check timeout for Check_MK checks now defaults to CRIT state... + Checks & Agents: * 0185 knuerr_rms_humidity, knuerr_rms_temp: Two new Checks to Monitor the Temperature and the Humidity on Knürr RMS Devices * 1065 heartbeat_crm / heartbeat_crm.resources: Rewrote checks / formalized parameters... diff --git a/modules/check_mk.py b/modules/check_mk.py index 8c03880..07e374e 100755 --- a/modules/check_mk.py +++ b/modules/check_mk.py @@ -5533,8 +5533,10 @@ def do_check_keepalive(): signal.alarm(0) except MKCheckTimeout: signal.signal(signal.SIGALRM, signal.SIG_IGN) # Prevent ALRM from CheckHelper.cc - status = 3 - total_check_output = "UNKNOWN - Check_MK timed out after %d seconds\n" % timeout + spec = exit_code_spec(hostname) + status = spec.get("timeout", 2) + total_check_output = "%s - Check_MK timed out after %d seconds\n" % ( + nagios_state_names[status], timeout) os.write(keepalive_fd, "%03d\n%08d\n%s" % (status, len(total_check_output), total_check_output)) diff --git a/web/plugins/wato/check_mk_configuration.py b/web/plugins/wato/check_mk_configuration.py index f6e8637..370efdb 100644 --- a/web/plugins/wato/check_mk_configuration.py +++ b/web/plugins/wato/check_mk_configuration.py @@ -2301,6 +2301,11 @@ register_rule(group, default_value = 2, title = _("State in case of connection problems")), ), + ( "timeout", + MonitoringState( + default_value = 2, + title = _("State in case of a overall timeout")), + ), ( "missing_sections", MonitoringState( default_value = 1, @@ -2328,7 +2333,8 @@ register_rule(group, help = _("This ruleset specifies the total status of the Check_MK service in " "case of various error situations. One use case is the monitoring " "of hosts that are not always up. You can have Check_MK an OK status " - "here if the host is not reachable."), + "here if the host is not reachable. Note: the <i>Timeout</i> setting only works " + "when using the Check_MK Micro Core."), match = "dict", )