Checkmk git commits

checkmk-commits@lists.checkmk.com

1 participants
64361 discussions

Check_MK Git: check_mk: checks/megaraid_bbu: The check for BBU status now silences while a battery learn cycle is running

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: 8b1f650c5bb673ab1e6502922c3a3bc5ac67d216 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=8b1f650c5bb673… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Mon Aug 20 17:24:17 2012 +0200 checks/megaraid_bbu: The check for BBU status now silences while a battery learn cycle is running --- ChangeLog | 1 + checkman/megaraid_bbu | 21 ++++++++++++++++----- checks/megaraid_bbu | 22 ++++++++++++++-------- 3 files changed, 31 insertions(+), 13 deletions(-) diff --git a/ChangeLog b/ChangeLog index e34dad1..e704d88 100644 --- a/ChangeLog +++ b/ChangeLog @@ -9,6 +9,7 @@ * New Checks for Siemens Blades (BX600) * New Checks for Fortigate Firewalls * FIX: megaraid_pdisks: handle case where no enclosure device exists + * FIX: megaraid_bbu: handle the controller's learn cycle. No errors in that period. * mysql_capacity: cleaned up check, levels are in MB now * jolokia_info, jolokia_metrics: new rewritten checks for jolokia (formerly jmx4perl). You need the new plugin mk_jokokia for using them diff --git a/checkman/megaraid_bbu b/checkman/megaraid_bbu index e4ea82f..0e7f83e 100644 --- a/checkman/megaraid_bbu +++ b/checkman/megaraid_bbu @@ -4,14 +4,25 @@ author: Florian Heigl <fh(a)mathias-kettner.de> license: GPL distribution: check_mk description: - This check monitors the existance and status of battery backup units on controllers that are based on the mid- and highend LSI Megaraid chipsets. The entry chipsets do not support BBUs. The Linux agent will try find any existing BBUs - if {MegaCli} is found in your search path. - The BBUs might come in various types {(iBBU, BBU)} and also some other vendors are using this RAID chip. It is tested against Intel, Dell, IBM and FSC models. + This check monitors the existance and status of battery backup units on controllers + that are based on the mid- and highend LSI Megaraid chipsets. The entry chipsets do + not support BBUs. The Linux agent will try find any existing BBUs - if {MegaCli} is + found in your search path. + The BBUs might come in various types {(iBBU, BBU)} and also some other vendors are + using this RAID chip. It is tested against Intel, Dell, IBM and FSC models. - The check works by matching the agent output against a dictionary of expected values. If you have MegaCli installed and some values are not detected, it might be neccessary to update your version of MegaCli. + The check works by matching the agent output against a dictionary of expected values. + If you have MegaCli installed and some values are not detected, it might be neccessary + to update your version of MegaCli. - {MegaCli} can be downloaded from LSI at the following URL {http://www.lsi.com/downloads/Public/MegaRAID%20Common%20Files/8.02.16_MegaCLI.zip} + {MegaCli} can be downloaded from LSI at the following URL + {http://www.lsi.com/downloads/Public/MegaRAID%20Common%20Files/8.02.16_MegaCLI.zip} - It would be possible to make the warning / critical levels user specifiable. See the check source for this if you have a need to influence those parameters. + It would be possible to make the warning / critical levels user specifiable. + See the check source for this if you have a need to influence those parameters. + Most controllers run a "battery learn cycle" periodically or on user request. + The check detects this learn cycle and suppresses all errors while this cycle is active. + This affects all models that do not have a flash / capacitor based BBU system. item: A string "RAID Adapter/BBU" followed by the ID of the adapter as reported by MegaCli. diff --git a/checks/megaraid_bbu b/checks/megaraid_bbu index 1e0066b..be2f9b2 100644 --- a/checks/megaraid_bbu +++ b/checks/megaraid_bbu @@ -31,18 +31,19 @@ # Load a fake controller with known good values for the most # important parameters only and try to define their importance megaraid_bbu_refvalues = { - 'Remaining Capacity Low' : ('No', 1), - 'I2c Errors Detected' : ('No', 1), + 'Remaining Capacity Low' : ('No', 1), # nolearn + 'I2c Errors Detected' : ('No', 1), 'Temperature' : ('OK', 2), 'Pack is about to fail & should be replaced': ('No', 1), - 'Charging Status' : ('None', 1), - 'Battery State' : ('Operational', 2), + 'Charging Status' : ('None', 1), # nolearn + 'Battery State' : ('Operational', 2), # nolearn 'Learn Cycle Status' : ('OK', 1), + 'Learn Cycle Active' : ('Yes', 0), 'Battery Pack Missing' : ('No', 2), 'Battery Replacement required' : ('No', 1), 'Over Temperature' : ('No', 2), 'Over Charged' : ('No', 1), - 'Voltage' : ('OK', 2), + 'Voltage' : ('OK', 2), # nolearn } @@ -80,19 +81,23 @@ def check_megaraid_bbu(item, _no_params, info): # get current charge level charge = (", Charge is %s" % controller['Relative State of Charge']) + # verify defined important parameters to current level for varname, (refvalue, refstate) in megaraid_bbu_refvalues.items(): + # the try/except should handle controller types that don't have certain values + # if your bbu chipset fails and you still get a partial response this will lead + # to a false result. but people asked for it :> try: - value = controller[varname] - # build a list of all errors if controller[varname] != refvalue: broken.append("%s is %s, but should be %s(%s)" % (varname, value, refvalue, "!" * refstate)) state = max(state, refstate) except: pass + if controller["Learn Cycle Active"] == "Yes": + return (0, "OK - no states to check (controller is in learn cycle)" + charge) # return assembled info - if broken: + elif broken: return (state, nagios_state_names[state] + " - " + ", ".join(broken) + charge) else: return (0, "OK - all states as expected" + charge) @@ -100,4 +105,5 @@ def check_megaraid_bbu(item, _no_params, info): return (3, "UNKNOWN - Check not implemented") + check_info["megaraid_bbu"] = (check_megaraid_bbu, "RAID Adapter/BBU %s", 0, inventory_megaraid_bbu)

12 years, 1 month

Check_MK Git: check_mk: output optimized

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: 1330d3623c6464076966de94e5374e7f2d38c26e URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=1330d3623c6464… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 19:19:03 2012 +0200 output optimized --- checks/cisco_hsrp | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/checks/cisco_hsrp b/checks/cisco_hsrp index 5593cb0..06181ad 100644 --- a/checks/cisco_hsrp +++ b/checks/cisco_hsrp @@ -90,7 +90,7 @@ def check_cisco_hsrp(item, params, info): # anything else must be a non-operative state already else: state = 2 - msgtxt = "Redundancy Group %s is %s" % ( hsrp_grp, hsrp_states[hsrp_state]) + msgtxt = "Redundancy Group %s has status %s" % ( hsrp_grp, hsrp_states[hsrp_state]) return (state, nagios_state_names[state] + " - " + msgtxt)

12 years, 1 month

Check_MK Git: check_mk: Add new Check for monitoring HSRP redundancy groups on Cisco routers

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: f2c5a46d4d466f79094dffa89c615453a1950d33 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=f2c5a46d4d466f… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 19:16:28 2012 +0200 Add new Check for monitoring HSRP redundancy groups on Cisco routers --- ChangeLog | 1 + checkman/cisco_hsrp | 37 ++++++++++++++++ checks/cisco_hsrp | 117 +++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 155 insertions(+), 0 deletions(-) diff --git a/ChangeLog b/ChangeLog index 0f12101..e34dad1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -45,6 +45,7 @@ * carel_uniflair_cooling: new check for monitoring datacenter air conditioning by "CAREL" * Added Agent for OpenBSD * Added Checks for MasterGuard UPS devices + * cisco_hsrp: New Check for monitoring HSRP groups on Cisco Routers. (SMIv2 version) WATO: * Added permission to control the "clone host" feature in WATO diff --git a/checkman/cisco_hsrp b/checkman/cisco_hsrp new file mode 100644 index 0000000..77457f5 --- /dev/null +++ b/checkman/cisco_hsrp @@ -0,0 +1,37 @@ +title: Cisco HSRP group status +agents: snmp +author: Florian Heigl <fh(a)mathias-kettner.de> +license: GPLv3 +distribution: check_mk +description: + Cisco routers support virtual redundant interfaces by using HSRP + (Hot Standby Router Protocol). + HSRP is configured by assigning IP interfaces to a group that has a + "floating" virtual IP. + If, for example, a router has an interface failure on either of the routed + interfaces, the protocol lowers the routers priority, and if that priority + drops too low, it will fail over the virtual IP. + + + The check returns {OK} if the HSRP status is a good one ("active", + "standby") and the same as during inventory. + If the states flip from "active" to "standby" or vice-versa, the check goes + to {WARN}, assuming that HSRP is doing it's job. + + Should the status ever be a different one that for example points to HSRP + still initializing, the check will return {CRIT} as HSRP is assumet to be + inoperable in these states. + +perfdata: + none + + +item: + The Virtual IP of the failover group. + +inventory: + The check reads the HSRP MIB and creates one service per virtual IP. It also + stores the HSRP state of + the IP as seen by the monitored device, normally either standby or active. + It also stores the ID of + the failover group. (For future use) diff --git a/checks/cisco_hsrp b/checks/cisco_hsrp new file mode 100644 index 0000000..5593cb0 --- /dev/null +++ b/checks/cisco_hsrp @@ -0,0 +1,117 @@ +#!/usr/bin/python + + + +# Good docs: +# http://www.cisco.com/en/US/tech/tk648/tk362/technologies_tech_note09186a008… +#.1.3.6.1.4.1.9.9.106.1.1.1.0 5 +# cHsrpGrpTable +########################### +#.1.3.6.1.4.1.9.9.106.1.2.1.1.2.1.192 "HSRP Secret key here" +#.1.3.6.1.4.1.9.9.106.1.2.1.1.2.7.193 "HSRP Secret key here" +#.1.3.6.1.4.1.9.9.106.1.2.1.1.3.1.192 100 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.3.7.193 100 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.4.1.192 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.4.7.193 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.5.1.192 300 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.5.7.193 300 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.6.1.192 2 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.6.7.193 2 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.7.1.192 0 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.7.7.193 0 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.8.1.192 0 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.8.7.193 0 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.9.1.192 3000 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.9.7.193 3000 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.10.1.192 10000 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.10.7.193 10000 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.11.1.192 192.168.10.4 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.11.7.193 172.20.10.20 <- hsrp ip +#.1.3.6.1.4.1.9.9.106.1.2.1.1.12.1.192 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.12.7.193 1 +# HSRP Monitored IP interfaces. If any of those go down, the priority of +# the router will be lowered. +#.1.3.6.1.4.1.9.9.106.1.2.1.1.13.1.192 192.168.10.5 <- ip Router 1 int 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.13.7.193 172.20.10.21 <- ip Router 2 int 7 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.14.1.192 192.168.10.6 <- ip Router 1 int 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.14.7.193 172.20.10.22 <- ip Router 2 int 7 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.15.1.192 6 <- group #1 "standby" state +#.1.3.6.1.4.1.9.9.106.1.2.1.1.15.7.193 6 <- group #2 "standby" state +#.1.3.6.1.4.1.9.9.106.1.2.1.1.16.1.192 "00 00 0C 07 AC C0 " +#.1.3.6.1.4.1.9.9.106.1.2.1.1.16.7.193 "00 00 0C 07 AC C1 " +#.1.3.6.1.4.1.9.9.106.1.2.1.1.17.1.192 1 +#.1.3.6.1.4.1.9.9.106.1.2.1.1.17.7.193 1 + + +# we'll be alerting if the state is not either 5 or 6. +# We could also not inventorize if the state isn't 5/6 but +# since you have to configure a group, to even show up in the +# MIB it's supposedly ok to alert if something isn't right there. +# otherwise modify the inventory. +hsrp_states = { 1: "initial", 2: "learn", 3: "listen", 4: "speak", 5: "standby", 6: "active" } + + +def inventory_cisco_hsrp(info): + + inventory = [] + for line in info: + hsrp_grp_entry, vip, actrouter, sbrouter, hsrp_state, vmac = line + interface_index, hsrp_grp = hsrp_grp_entry.split(".") + # inventorize HSRP group name+IP and the standby state as seen from "this" box. + inventory.append( (vip, (hsrp_grp, int(hsrp_state))) ) + + return inventory + + +def check_cisco_hsrp(item, params, info): + + hsrp_grp_wanted, hsrp_state_wanted = params + + for line in info: + hsrp_grp_entry, vip, actrouter, sbrouter, hsrp_state, vmac = line + interface_index, hsrp_grp = hsrp_grp_entry.split(".") + hsrp_state = int(hsrp_state) + + if vip == item: + # FIXME: This should be shorter. + # Validate that we the inventorized state is a "good one" + # if it's also the one we have now, then we're fine. + + if hsrp_state_wanted == 5 and hsrp_state == hsrp_state_wanted: + state = 0 + msgtxt = "Redundancy Group %s is OK" % hsrp_grp + elif hsrp_state_wanted == 6 and hsrp_state == hsrp_state_wanted: + state = 0 + msgtxt = "Redundancy Group %s is OK" % hsrp_grp + # otherwise if it's a good one, but flipped, then we are in a failover + elif hsrp_state == 5 or hsrp_state == 6: + state = 1 + msgtxt = "Redundancy Group %s has failed over" % hsrp_grp + # anything else must be a non-operative state already + else: + state = 2 + msgtxt = "Redundancy Group %s is %s" % ( hsrp_grp, hsrp_states[hsrp_state]) + + return (state, nagios_state_names[state] + " - " + msgtxt) + + return (3, "UNKNOWN - HSRP Group %s not found in Agent output" % hsrp_grp_wanted ) + + + +# FIXME: Outdated format. Fix after discussing WATO options. +check_info["cisco_hsrp"] = (check_cisco_hsrp, "HSRP Group %s", 0, inventory_cisco_hsrp) + +snmp_info["cisco_hsrp"] = \ + ( ".1.3.6.1.4.1.9.9.106.1.2.1.1", [ + OID_END, + "11", # cHsrpGrpVirtualIpAddr + "13", # cHsrpGrpActiveRouter + "14", # cHsrpGrpStandbyRouter + "15", # cHsrpGrpStandbyState + "16", # cHsrpGrpVirtualMacAddr + ]) + +# We can't scan for the HSRP table since the entries are indexed +# based on information we dont have without fetching all of it +# Instead we use the HSRP timeout +snmp_scan_functions["cisco_hsrp"] = lambda oid: "cisco" in oid(".1.3.6.1.2.1.1.1.0").lower() and oid(".1.3.6.1.4.1.9.9.106.1.1.1.0")

12 years, 1 month

Check_MK Git: check_mk: checks/cbl_airlaser: Add oid's for attenuation/ margin

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: 42bf15a997a4c810c1397cfc9f0b86c65ae2514a URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=42bf15a997a4c8… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 13:22:45 2012 +0200 checks/cbl_airlaser: Add oid's for attenuation/margin --- checks/cbl_airlaser | 4 ++++ 1 files changed, 4 insertions(+), 0 deletions(-) diff --git a/checks/cbl_airlaser b/checks/cbl_airlaser index 33966bf..8fef745 100644 --- a/checks/cbl_airlaser +++ b/checks/cbl_airlaser @@ -82,6 +82,10 @@ def parse_cbl_airlaser(info): "optrxStatusTemp" : (None, "2.5.3.0", 2), # this is mislabeled "optrxValueTemp" "optrxTempValue" : (None, "2.5.4.0", 3), + #"optrxOptValue" + # .1.3.6.1.4.1.2800.2.2.5.8.0 -10 + #"optrxOptMargin" + # .1.3.6.1.4.1.2800.2.2.5.9.0 22 }, }

12 years, 1 month

Check_MK Git: check_mk: Add new bug entry

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: b5cd92e7311b27dfe9e3e045e04580a9e253ff88 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=b5cd92e7311b27… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 12:57:56 2012 +0200 Add new bug entry --- .bugs/723 | 12 ++++++++++++ checks/megaraid_pdisks | 2 +- 2 files changed, 13 insertions(+), 1 deletions(-) diff --git a/.bugs/723 b/.bugs/723 new file mode 100644 index 0000000..eecd7ef --- /dev/null +++ b/.bugs/723 @@ -0,0 +1,12 @@ +Title: Simulation mode overrides usewalk_hosts +Component: core +State: open +Date: 2012-08-16 12:55:42 +Targetversion: 1.2.0 +Class: nastiness + +If you have some hosts defined as usewalk hosts so that they'll check based on their already +recorded snmpwalks and then enable simulation_mode, it breaks usewalk for some reason. +The result is that the snmp devices are checked against 127.0.0.1. + +This is a big problem if you simulate a customer site. diff --git a/checks/megaraid_pdisks b/checks/megaraid_pdisks index bb2f843..8b94aec 100644 --- a/checks/megaraid_pdisks +++ b/checks/megaraid_pdisks @@ -72,7 +72,7 @@ def megaraid_pdisks_parse(info): try: enclosure_devid = int(line[-1]) # this should fix inventory problems. - #adapters[adapter][enclosure_devid] = enclosure_devid + adapters[adapter][enclosure_devid] = enclosure_devid except: # no enclosure device enclosure_devid = 0

12 years, 1 month

Check_MK Git: check_mk: livedump: extend documentation to cover recent questions

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: e7e56b3932f1944b67d008ad870d786ab401f011 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=e7e56b3932f194… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 12:32:21 2012 +0200 livedump: extend documentation to cover recent questions --- doc/treasures/README.livedump | 12 ++++++++---- 1 files changed, 8 insertions(+), 4 deletions(-) diff --git a/doc/treasures/README.livedump b/doc/treasures/README.livedump index 8946f4f..797adb2 100644 --- a/doc/treasures/README.livedump +++ b/doc/treasures/README.livedump @@ -17,7 +17,7 @@ Disadvantages: How to setup livedump --------------------- -Copy the file livedump to a conveniant place. Make sure that +Copy the file livedump to a convenient place. Make sure that ../livestatus/api/python/livestatus.py is either in the same directory as livedump or somewhere in the Python path. @@ -41,14 +41,15 @@ and be in pending state. Now create a cronjob that does the following every 1 or 5 minutes: -1. ./livedump > cgagaga +1. ./livedump > ca1b2c3 2. copy that file to the target system into the checkresults directory (in OMD this is ~/tmp/nagios/checkresults) -3. After a correct copy touch the file cgagaga.ok in that +3. After a correct copy touch the file ca1b2c3.ok in that directory Nagios will now read in that file (which is containing all current -host and service states). +host and service states). The filename is arbitrary, but has to be +7 characters in length, starting with a "c". Filtering --------- @@ -63,3 +64,6 @@ all hosts that are needed by the dumped services are also dumped: Note: The -H headers will also be added to the service queries. Make sure that all columns are prefixed with host_ in these. +If you are using this is in conjunction with NSCA transport and do not +wish to transfer the templated configuration, you can use the filter +to only export services that have "obsess_over_service = 1" set.

12 years, 1 month

Check_MK Git: check_mk: Check cbl_airlaser.hardware: add nicer PNP Template

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: ddfc7a8f5cc9c6f970792d3dd696ee5ad5fad4f3 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=ddfc7a8f5cc9c6… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 11:32:11 2012 +0200 Check cbl_airlaser.hardware: add nicer PNP Template --- pnp-templates/check_mk-cbl_airlaser.hardware.php | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/pnp-templates/check_mk-cbl_airlaser.hardware.php b/pnp-templates/check_mk-cbl_airlaser.hardware.php new file mode 120000 index 0000000..a7f1e24 --- /dev/null +++ b/pnp-templates/check_mk-cbl_airlaser.hardware.php @@ -0,0 +1 @@ +check_mk-cmctc.temp.php \ No newline at end of file

12 years, 1 month

Check_MK Git: check_mk: Add manual page for cbl_airlaser.hardware. Cant add config example.

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: 9131d055c588a8ccf7029078b4ce6abd86937294 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=9131d055c588a8… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 11:28:20 2012 +0200 Add manual page for cbl_airlaser.hardware. Cant add config example. --- checkman/cbl_airlaser.hardware | 26 ++++++++++++++++++++++++++ 1 files changed, 26 insertions(+), 0 deletions(-) diff --git a/checkman/cbl_airlaser.hardware b/checkman/cbl_airlaser.hardware new file mode 100644 index 0000000..83f9c82 --- /dev/null +++ b/checkman/cbl_airlaser.hardware @@ -0,0 +1,26 @@ +title: Check of runtime Status CBL Airlaser +agents: snmp +author: Florian Heigl <fh(a)mathias-kettner.de> +license: GPL +distribution: check_mk +description: + The CBL Airlaser is a device to transparently transport Gigabit Ethernet + over an optical link with optional microwave fallback. + + The check queries a list containing all known power and temperature "status" + information from the device. + If one of the status OIDs indicates an error, the check will go to {WARN} or + {CRIT} according to the error reported. + For the temperature sensors, default values are included and can be adjusted. + If these are exceeded, the check will also alert. + + Note: Monitoring rx/tx attentuation will be added after more testing. + +inventory: + A service will be generated if the CBL-AIRLASOR-IP1000 MIB is supported by + the remote device. + +perfdata: + the check automatically generates performance data for all sensors that + monitor a temperature. +

12 years, 1 month

Check_MK Git: check_mk: New check: cbl_airlaser. hardware for status monitoring on CBL Airlaser IP1000

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: ec5d68349e9ae1c420b1a24e01275f9cd2e3ab4f URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=ec5d68349e9ae1… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Thu Aug 16 11:09:04 2012 +0200 New check: cbl_airlaser.hardware for status monitoring on CBL Airlaser IP1000 --- ChangeLog | 2 + checks/cbl_airlaser | 97 ++++++++++++++++++++++++++++---------------------- 2 files changed, 56 insertions(+), 43 deletions(-) diff --git a/ChangeLog b/ChangeLog index aae0f8b..0f12101 100644 --- a/ChangeLog +++ b/ChangeLog @@ -35,6 +35,8 @@ "Room temperature (external thermal sensors)" * cisco_asa_failover: New Check for clustered Cisco ASA Firewalls * cbl_airlaser.status: New Check for CBL Airlaser IP1000 laser bridge. + * cbl_airlaser.hardware: New Check for CBL Airlaser IP1000 laser bridge. + Check monitors the status info and allows alerting based on temperature. * df, hr_fs, etc.: Filesystem checks now support grouping (pools) Please refer to the check manpage of df for details * FIX: windows agent: try to fix crash in event log handling diff --git a/checks/cbl_airlaser b/checks/cbl_airlaser index 3916f21..33966bf 100644 --- a/checks/cbl_airlaser +++ b/checks/cbl_airlaser @@ -32,6 +32,15 @@ # .1.3.6.1.4.1.2800.2.1.3 < AirLaser Status +# Migrate to factory settings? +airlaser_default_levels = { + "opttxTempValue" : (60, 80), + "chassisTempValue" : (60, 70), + "chassisFrontScreenTempValue" : (40, 55), + "optrxTempValue" : (50, 60), + "apmodTempValue" : (60, 70), } + + def parse_cbl_airlaser(info): airlaser_status_names = { 0: 'undefined', 1: 'active', 2: 'standby', @@ -90,67 +99,71 @@ def parse_cbl_airlaser(info): # update values from one dict into the other by picking the "offsetted" values # (optimize at will, if we can make it one-dict-for-all then we 100% sanitized their MIB) - for section in airlaser_sensors.keys(): - for sensor in airlaser_sensors[section].keys(): + for hwclass in airlaser_sensors.keys(): + for sensor in airlaser_sensors[hwclass].keys(): # we could remove the offset hack by parsing our OID - sub_oid = airlaser_sensors[section][sensor][1] - offset = airlaser_sensors[section][sensor][2] + sub_oid = airlaser_sensors[hwclass][sensor][1] + offset = airlaser_sensors[hwclass][sensor][2] if "Status" in sensor: - value = airlaser_status_names[int(data[section][offset][0])] + value = airlaser_status_names[int(data[hwclass][offset][0])] else: - value = saveint(data[section][offset][0]) - airlaser_sensors[section][sensor] = ( value, sub_oid, offset) + value = saveint(data[hwclass][offset][0]) + airlaser_sensors[hwclass][sensor] = ( value, sub_oid, offset) return airlaser_sensors - -def check_cbl_airlaser_hw(item, _no_params, info): +def check_cbl_airlaser_hw(item, params, info): + + + airlaser_info = parse_cbl_airlaser(info) - #import pprint - #pprint.pprint(parse_cbl_airlaser(info)) state = 0 msgtxt = "" + perfdata = [] + + for hwclass in airlaser_info.keys(): + for sensor in airlaser_info[hwclass].keys(): + val = airlaser_info[hwclass][sensor][0] + if sensor.lower().endswith("value"): + val = saveint(val) + if sensor in params.keys(): + warn, crit = params[sensor] + perfdata.append(("%s" % sensor, "%d" % val, warn, crit, 0, 90)), + if val > crit: + state = max(state, 2) + elif val > warn: + state = max(state, 1) + else: + # if this sensor wasn't in the params, then we don't alert on it. + perfdata.append(("%s" % sensor, "%d" % val, '', '', 0, 90)), - - return (3, "UNKNOWN") - - for sensor in airlaser_info.keys(): - #print sensor - #print "1" - if sensor.lower().endswith("value"): - #print "1a" - # das geht noch nicht. - #perfdata += [ sensor, saveint(airlaser_info[sensor]), - #print saveint(airlaser_info[sensor]) - continue - - #print "2" - #print airlaser_info[sensor] - if airlaser_info[sensor] == "failure": - #print "2a" - state = 2 - elif airlaser_info[sensor] == "warning": - #print "2b" - state = max(state, 1) - # go here if no explicit error occured, - # no handling undefined and not_installed - else: - print "2c" - continue - msgtxt = msgtxt + "%s is %s" + state * "!" + " " + else: + if val == "failure": + state = 2 + elif val == "warning": + state = max(state, 1) + # go here if no explicit error occured, + # no handling undefined and not_installed + else: + continue + if state > 0: + msgtxt = msgtxt + "Sensor %s %s" % (sensor, val) + state * "!" + " " if state == 0: msgtxt = "All sensors OK" - return (state, nagios_state_names[state] + " - " + msgtxt) + return (state, nagios_state_names[state] + " - " + msgtxt, perfdata) def inventory_cbl_airlaser(info): - return [ (None, None) ] + # start passing parameters, but since we might also need some for optics + # this may change to using factory settings. + # Or we just hardcode the margins we got from the vendor. + return [ (None, "airlaser_default_levels") ] def check_cbl_airlaser_status(item, _no_params, info): @@ -186,12 +199,10 @@ check_info["cbl_airlaser.status"] = { } -def inventory_cbl_airlaser_off(): - return [] check_info["cbl_airlaser.hardware"] = { "check_function" : check_cbl_airlaser_hw, - "inventory_function" : inventory_cbl_airlaser_off, + "inventory_function" : inventory_cbl_airlaser, "service_description" : "CBL Airlaser Hardware", "has_perfdata" : True, }

12 years, 1 month

Check_MK Git: check_mk: cbl_airlaser: add new parser function for hardware checks. inventory/checks disabled

by git＠mathias-kettner.de

Module: check_mk Branch: master Commit: 537d490e6a6d6d02d0d0059b41a56c68b0834e6e URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=537d490e6a6d6d… Author: Florian Heigl <fh(a)mathias-kettner.de> Date: Tue Aug 14 19:18:21 2012 +0200 cbl_airlaser: add new parser function for hardware checks. inventory/checks disabled --- checks/cbl_airlaser | 142 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 files changed, 137 insertions(+), 5 deletions(-) diff --git a/checks/cbl_airlaser b/checks/cbl_airlaser index d38fdfd..3916f21 100644 --- a/checks/cbl_airlaser +++ b/checks/cbl_airlaser @@ -32,13 +32,131 @@ # .1.3.6.1.4.1.2800.2.1.3 < AirLaser Status +def parse_cbl_airlaser(info): + + airlaser_status_names = { 0: 'undefined', 1: 'active', 2: 'standby', + 3 : 'warning', 4: 'failure', 5: 'not_installed' } + + +# I have my own little MIB right here, their MIB is +# just a long list, not structured. + airlaser_sensors = { + "chassis" : { + # Name of OID, Value, specific OID (not used), Position in SNMP data + "chassisFrontScreenTempStatus" : ( None, "2.1.1.0", 0 ), + "chassisFrontScreenTempValue" : ( None, "2.1.2.0", 1 ), + "chassisHeatingStatus" : ( None, "2.1.7.0", 6 ), + "chassisTempStatus" : ( None, "2.1.8.0", 7 ), + "chassisTempValue" : ( None, "2.1.9.0", 8 ), + "chassisFan1Status" : ( None, "2.1.10.0", 9 ), + "chassisFan2Status" : ( None, "2.1.12.0", 11), + }, + "power" : { + "psStatus48V" : ( None, "2.2.2.0", 1), + "psStatus230V" : ( None, "2.2.3.0", 2), + "psStatus5V" : ( None, "2.2.4.0", 3), + "psStatus3V3" : ( None, "2.2.8.0", 7), + "psStatus2V5" : ( None, "2.2.12.0", 11), + }, + + "module" : { + "apmodTempStatus" : (None, "2.3.6.0", 5), + "apmodTempValue" : (None, "2.3.7.0", 6), + }, + + "opttx" : { + "opttxTempValue" : (None, "2.4.3.0", 2), + "opttxStatusTemp" : (None, "2.4.4.0", 3), + }, + + "optrx" : { + "optrxStatusTemp" : (None, "2.5.3.0", 2), + # this is mislabeled "optrxValueTemp" + "optrxTempValue" : (None, "2.5.4.0", 3), + }, + } + + + # load the info into a dict separated by the different MIB regions + # Selfest (info[0] is not handled here. + data = { + "chassis" : info[1], + "power" : info[2], + "module" : info[3], + "opttx" : info[4], + "optrx" : info[5], + } + + + # update values from one dict into the other by picking the "offsetted" values + # (optimize at will, if we can make it one-dict-for-all then we 100% sanitized their MIB) + for section in airlaser_sensors.keys(): + for sensor in airlaser_sensors[section].keys(): + # we could remove the offset hack by parsing our OID + sub_oid = airlaser_sensors[section][sensor][1] + offset = airlaser_sensors[section][sensor][2] + + + if "Status" in sensor: + value = airlaser_status_names[int(data[section][offset][0])] + else: + value = saveint(data[section][offset][0]) + airlaser_sensors[section][sensor] = ( value, sub_oid, offset) + + return airlaser_sensors + + + + +def check_cbl_airlaser_hw(item, _no_params, info): + + #import pprint + #pprint.pprint(parse_cbl_airlaser(info)) + state = 0 + msgtxt = "" + + + return (3, "UNKNOWN") + + for sensor in airlaser_info.keys(): + #print sensor + #print "1" + if sensor.lower().endswith("value"): + #print "1a" + # das geht noch nicht. + #perfdata += [ sensor, saveint(airlaser_info[sensor]), + #print saveint(airlaser_info[sensor]) + continue + + #print "2" + #print airlaser_info[sensor] + if airlaser_info[sensor] == "failure": + #print "2a" + state = 2 + elif airlaser_info[sensor] == "warning": + #print "2b" + state = max(state, 1) + # go here if no explicit error occured, + # no handling undefined and not_installed + else: + print "2c" + continue + msgtxt = msgtxt + "%s is %s" + state * "!" + " " + + if state == 0: + msgtxt = "All sensors OK" + + return (state, nagios_state_names[state] + " - " + msgtxt) + def inventory_cbl_airlaser(info): - # Inventorize if the scan function fired return [ (None, None) ] + def check_cbl_airlaser_status(item, _no_params, info): - status = info[0][0] + selftest, chassis, power, module, optrx, opttx = info + status = selftest[0][0] + if status == "1": return (0, "OK - Airlaser: normal operation") @@ -59,7 +177,21 @@ check_info["cbl_airlaser.status"] = { "has_perfdata" : False, "snmp_scan_function" : lambda oid: "airlaser" in oid(".1.3.6.1.2.1.1.1.0").lower() \ and oid(".1.3.6.1.4.1.2800.2.1.1.0"), - "snmp_info" : (".1.3.6.1.4.1.2800.2.1", [ - "3", # AirLaser Status - ]), + "snmp_info" : [ (".1.3.6.1.4.1.2800.2", [ "1.3" ]), + (".1.3.6.1.4.1.2800.2.2", [ "1" ]), + (".1.3.6.1.4.1.2800.2.2", [ "2" ]), + (".1.3.6.1.4.1.2800.2.2", [ "3" ]), + (".1.3.6.1.4.1.2800.2.2", [ "4" ]), + (".1.3.6.1.4.1.2800.2.2", [ "5" ]), ], + +} + +def inventory_cbl_airlaser_off(): + return [] + +check_info["cbl_airlaser.hardware"] = { + "check_function" : check_cbl_airlaser_hw, + "inventory_function" : inventory_cbl_airlaser_off, + "service_description" : "CBL Airlaser Hardware", + "has_perfdata" : True, }

12 years, 1 month

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Checkmk git commits