Module: check_mk Branch: master Commit: a04bee7734dbed6888cb6bf6d2a5d3d78af44ef9 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=a04bee7734dbed… Author: Goetz Golla &lt;gg(a)mathias-kettner.de&gt; Date: Wed Jun 4 10:30:28 2014 +0200 apc_symmetra: check now also monitors the battery replacement status --- .werks/615 | 8 ++++++++ ChangeLog | 1 + checkman/apc_symmetra | 31 +++++++++++++++++++------------ checks/apc_symmetra | 39 ++++++++++++++++++++++++++++----------- 4 files changed, 56 insertions(+), 23 deletions(-) diff --git a/.werks/615 b/.werks/615 new file mode 100644 index 0000000..86cc707 --- /dev/null +++ b/.werks/615 @@ -0,0 +1,8 @@ +Title: apc_symmetra: check now also monitors the battery replacement status +Level: 1 +Component: checks +Version: 1.2.5i3 +Date: 1401870579 +Class: feature + + diff --git a/ChangeLog b/ChangeLog index 8e4e1b2..4fc1d94 100644 --- a/ChangeLog +++ b/ChangeLog @@ -64,6 +64,7 @@ * 0926 windows agent: local / plugin scripts now get the REMOTE_HOST as environment variable * 0163 kaspersky_av_quarantine,kaspersky_av_tasks,kaspersky_av_updates: New checks for kaspersky anti virus on linux * 0164 symantec_av_progstate,symantec_av_quarantine, symantec_av_updates: New checks for Symantec Anti Virus on Linux + * 0615 apc_symmetra: check now also monitors the battery replacement status * 0777 FIX: special agent emcvnx: did not work with security file authentication... * 0786 FIX: zfsget: fixed compatibility with older Solaris agents... * 0809 FIX: brocade_fcport: Fixed recently introduced problem with port speed detection diff --git a/checkman/apc_symmetra b/checkman/apc_symmetra index a04a997..a05c1d6 100644 --- a/checkman/apc_symmetra +++ b/checkman/apc_symmetra @@ -4,20 +4,27 @@ catalog: hw/power/apc license: GPL distribution: check_mk description: - This check monitors eight aspects of an APC Symmetra UPS: {(1)} the battery status, - {(2)} the output status, {(3)} the battery capacity, {(4)} the battery - temperature, {(5)} the battery current, {(6)} the output voltage and - {(7)} the output current, {(8)} the remaing run time. The output current and - remaining run time are not checked against a level but are just displayed, {(9)} the current - load in percent. + + This check monitors ten aspects of an APC Symmetra UPS: {(1)} the + battery status, {(2)} the battery replacement status including the number + of batteries to be replaced, {(3)} the output status, {(4)} the battery + capacity, {(5)} the battery temperature, {(6)} the battery current, {(7)} + the output voltage, {(8)} the output current, {(9)} the remaing run time, + and {(10)} the current load in percent. + + The output current and remaining run time are not checked against a level, + but just displayed. {(2)} is only displayed if a problem is found, the level + is {WARN} if one battery needs to be replaced and {CRIT} if more than one + battery needs to be replaced. {(1)} is not displayed if the state is normal + but a problem in {(2)} was found. The check output includes the calibration status of the UPS. During a - calibration the check result in section {(2)} is OK even though the UPS is running - on battery. - The check reads the date of the last calibration and optionally applies an alternative - level for the battery capacity on the day of the calibration. This is because the battery - capacity is reduced after calibration and may cause an unwanted critical condition - with the standard level. In addition a time span after the day of the calibration + calibration the check result in section {(2)} is OK even though the UPS is + running on battery. The check reads the date of the last calibration and + optionally applies an alternative level for the battery capacity on the + day of the calibration. This is because the battery capacity is reduced + after calibration and may cause an unwanted critical condition with the + standard level. In addition a time span after the day of the calibration can be configured during which the post-calibration phase still persists. examples: diff --git a/checks/apc_symmetra b/checks/apc_symmetra index f7a32d3..dda0fcd 100644 --- a/checks/apc_symmetra +++ b/checks/apc_symmetra @@ -29,6 +29,8 @@ # PowerNet-MIB::upsBasicOutputStatus.0 .1.3.6.1.4.1.318.1.1.1.4.1.1.0 # PowerNet-MIB::upsAdvBatteryCapacity.0 .1.3.6.1.4.1.318.1.1.1.2.2.1.0 # PowerNet-MIB::upsAdvBatteryTemperature.0 .1.3.6.1.4.1.318.1.1.1.2.2.2.0 +# PowerNet-MIB::upsAdvBatteryReplaceIndicator.0 .1.3.6.1.4.1.318.1.1.1.2.2.4.0 +# PowerNet-MIB::upsAdvBatteryNumOfBadBattPacks.0 .1.3.6.1.4.1.318.1.1.1.2.2.6.0 # PowerNet-MIB::upsAdvBatteryCurrent.0 .1.3.6.1.4.1.318.1.1.1.2.2.9.0 # PowerNet-MIB::upsAdvOutputVoltage.0 .1.3.6.1.4.1.318.1.1.1.4.2.1.0 # PowerNet-MIB::upsAdvOutputCurrent.0 .1.3.6.1.4.1.318.1.1.1.4.2.4.0 @@ -78,9 +80,10 @@ factory_settings["apc_default_levels"] = { def check_apc(item, params, info): BasicBatteryStatus, BasicOutputStatus, AdvBatteryCapacity, \ - AdvBatteryTemperature, AdvBatteryCurrent, AdvInputVoltage, AdvOutputVoltage, \ + AdvBatteryTemperature, AdvBatteryReplaceIndicator, AdvBatteryNumOfBadBattPacks, \ + AdvBatteryCurrent, AdvInputVoltage, AdvOutputVoltage, \ AdvOutputCurrent, AdvBatteryRunTimeRemaining, AdvTestCalibrationResults, AdvOutputLoad \ - = [ saveint(x) for x in info[0][:11] ] + = [ saveint(x) for x in info[0][:13] ] LastDiagnosticsDate = info[0][-1] RunTimeRemaining = AdvBatteryRunTimeRemaining / 100 @@ -110,11 +113,23 @@ def check_apc(item, params, info): if BasicBatteryStatus != 2: state = 2 infotxt += "(!!)" + single_states.append( (state, infotxt, None) ) else: state = 0 - single_states.append( (state, infotxt, None) ) - # 2. Check basic output status + # 2. Check battery replacement status + if AdvBatteryReplaceIndicator == 2: + if AdvBatteryNumOfBadBattPacks == 1: + infotxt = "one battery needs replacement(!)" + state = 1 + else: + infotxt = "%i batteries need replacement(!!)" % AdvBatteryNumOfBadBattPacks + state = 2 + single_states.append( (state, infotxt, None) ) + elif state == 0: # if normal only print when replacement status is also OK, to save on service output text + single_states.append( (state, infotxt, None) ) + + # 3. Check basic output status status_text = { 1:"unknown", 2:"online", 3:"on battery", 4:"on smart boost", 5:"timed sleeping", 6:"software bypass", 7:"off", 8:"rebooting", 9:"switched bypass", 10:"hardware failure bypass", 11:"sleeping until power return", @@ -129,7 +144,7 @@ def check_apc(item, params, info): state = 0 single_states.append( (state, infotxt, None) ) - # 3. Check battery capacity + # 4. Check battery capacity state = 0 infotxt = "capacity %d%% (crit at " % AdvBatteryCapacity @@ -146,7 +161,7 @@ def check_apc(item, params, info): single_states.append( (state, infotxt, ("capacity", AdvBatteryCapacity, "", crit_capacity, 0, 100)) ) - # 4. Check System temperature + # 5. Check System temperature # The Name AdvBatteryTemperature is a wrong naming in the vendor mib. infotxt = "sys. temp. %dC" % AdvBatteryTemperature if AdvBatteryTemperature >= crit_sys_temp: @@ -156,7 +171,7 @@ def check_apc(item, params, info): state = 0 single_states.append( (state, infotxt, ("systemp", AdvBatteryTemperature, "", crit_sys_temp) ) ) - # 5. Check battery current + # 6. Check battery current infotxt = "bat. curr. %dA" % AdvBatteryCurrent if AdvBatteryCurrent >= crit_batt_curr: state = 2 @@ -168,7 +183,7 @@ def check_apc(item, params, info): # 6a. Simply show input voltage (no performance data) single_states.append( (0, "input voltage %dV" % AdvInputVoltage, None) ) - # 6. Check output voltage + # 7. Check output voltage infotxt = "output voltage %dV" % AdvOutputVoltage if AdvOutputVoltage <= crit_voltage: state = 2 @@ -177,17 +192,17 @@ def check_apc(item, params, info): state = 0 single_states.append( (state, infotxt, ("voltage", AdvOutputVoltage, "", crit_voltage, 0) ) ) - # 7. Simply add output current as perfdata + # 8. Simply add output current as perfdata single_states.append( (0, "output current %dA" % AdvOutputCurrent, ("current", AdvOutputCurrent)) ) - # 8. run time remaining + # 9. run time remaining # RunTimeRemaining formatiert == "26:00.00" hrs = int(RunTimeRemaining) / 3600 mins, secs = divmod(int(RunTimeRemaining) % 3600, 60) single_states.append( (0, "run time remaining: %02d:%02d:%02d" % (hrs, mins, secs), ("runtime", RunTimeRemaining/60)) ) - # 9. Adv Output load (load in percent) + # 10. Adv Output load (load in percent) load_state = 0 loadwarn, loadcrit = None, None label = "" @@ -227,6 +242,8 @@ check_info['apc_symmetra'] = { "4.1.1.0", # BasicOutputStatus, "2.2.1.0", # AdvBatteryCapacity, "2.2.2.0", # AdvBatteryTemperature, + "2.2.4.0", # AdvBatteryReplaceIndicator, + "2.2.6.0", # AdvBatteryNumOfBadBattPacks, "2.2.9.0", # AdvBatteryCurrent, "3.2.1.0", # AdvInputVoltage, "4.2.1.0", # AdvOutputVoltage,