17522 New check plugin: Cisco UCS: Fault summary

Closes #756
CMK-20279

Change-Id: Ic526fc7069148c08980f09aed785c453a0c0a619

Author: nightwatcher74

.werks/17522.md

@@ -0,0 +1,14 @@
+[//]: # (werk v2)
+# New check plugin: Cisco UCS: Fault summary
+
+key        | value
+---------- | ---
+date       | 2025-02-11T07:32:03+00:00
+version    | 2.4.0b1
+class      | feature
+edition    | cre
+component  | checks
+level      | 1
+compatible | yes
+
+This adds a new check plugin monitoring all faults reported by the device.

cmk/plugins/cisco/agent_based/cisco_ucs_faults.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+# Copyright (C) 2019 Checkmk GmbH - License: GNU General Public License v2
+# This file is part of Checkmk (https://checkmk.com). It is subject to the terms and
+# conditions defined in the file COPYING, which is part of this source code package.
+
+from cmk.agent_based.v2 import (
+    CheckPlugin,
+    CheckResult,
+    DiscoveryResult,
+    Result,
+    Service,
+    State,
+)
+from cmk.plugins.collection.agent_based.cisco_ucs_fault_section import Section
+from cmk.plugins.lib.cisco_ucs import check_cisco_fault
+
+
+def discover_cisco_ucs_faults(section: Section) -> DiscoveryResult:
+    yield Service()
+
+
+def check_cisco_ucs_faults(section: Section) -> CheckResult:
+    if not section:
+        yield Result(state=State.OK, summary="No faults")
+        return
+
+    for fault in section.values():
+        yield from check_cisco_fault(fault)
+
+
+check_plugin_cisco_ucs_faults = CheckPlugin(
+    name="cisco_ucs_faults",
+    sections=["cisco_ucs_fault"],
+    service_name="Cisco UCS Faults",
+    discovery_function=discover_cisco_ucs_faults,
+    check_function=check_cisco_ucs_faults,
+)

cmk/plugins/cisco/checkman/cisco_ucs_faults

@@ -0,0 +1,14 @@
+title: Cisco UCS: Fault summary
+agents: snmp
+catalog: hw/network/cisco
+license: GPLv2
+distribution: check_mk
+
+description:
+ This check allows to monitor all faults reported by the device.
+ The check will report {OK} as long as no faults are reported.
+ In other cases, the check will report a status determined by the severity of the most severe issue:
+ "major" and "critical" are reported as {CRITICAL}, "warning" and "minor" as {WARNING} and "cleared" and "info" as {OK}.
+
+discovery:
+ One service is created.

cmk/plugins/collection/agent_based/cisco_ucs_fault_section.py

@@ -9,8 +9,10 @@
 from cmk.agent_based.v2 import SimpleSNMPSection, SNMPTree, StringTable
 from cmk.plugins.lib.cisco_ucs import DETECT, Fault, FaultSeverity
 
+type Section = dict[str, list[Fault]]  # FIXME
 
-def parse_cisco_ucs_fault(string_table: StringTable) -> dict[str, list[Fault]]:
+
+def parse_cisco_ucs_fault(string_table: StringTable) -> Section:
     faults = defaultdict(list)
     for fault_object_id, fault_ack, fault_code, fault_description, fault_severity in string_table:
         faults[fault_object_id].append(

tests/unit/cmk/plugins/cisco/agent_based/test_cisco_ucs_faults.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+# Copyright (C) 2024 Checkmk GmbH - License: GNU General Public License v2
+# This file is part of Checkmk (https://checkmk.com). It is subject to the terms and
+# conditions defined in the file COPYING, which is part of this source code package.
+
+from cmk.agent_based.v2 import Result, Service, State
+from cmk.plugins.cisco.agent_based.cisco_ucs_faults import (
+    check_cisco_ucs_faults,
+    discover_cisco_ucs_faults,
+)
+from cmk.plugins.collection.agent_based.cisco_ucs_fault_section import (
+    parse_cisco_ucs_fault,
+    Section,
+)
+
+
+def _section() -> Section:
+    return parse_cisco_ucs_fault(
+        [
+            [
+                "sys/rack-unit-1/psu-2",
+                "1",
+                "374",
+                "PSU2_STATUS: Power Supply 2 has lost input or input is out of range : Check input to PS or replace PS 2",
+                "5",
+            ]
+        ]
+    )
+
+
+def test_discover_cisco_ucs_faults_empty() -> None:
+    assert list(discover_cisco_ucs_faults({})) == [Service()]
+
+
+def test_discover_cisco_ucs_faults() -> None:
+    assert list(discover_cisco_ucs_faults(_section())) == [Service()]
+
+
+def test_check_cisco_ucs_faults_empty() -> None:
+    assert list(check_cisco_ucs_faults({})) == [Result(state=State.OK, summary="No faults")]
+
+
+def test_check_cisco_ucs_faults() -> None:
+    assert list(check_cisco_ucs_faults(_section())) == [
+        Result(
+            state=State.CRIT,
+            summary="Fault: 374 - PSU2_STATUS: Power Supply 2 has lost input or input is out of range : Check input to PS or replace PS 2",
+        ),
+    ]