From 10f2583794cc968e82aa8fe0b04ad9dc0f6e7e2c Mon Sep 17 00:00:00 2001
From: Deezzir <deezzir@gmail.com>
Date: Fri, 13 Dec 2024 22:45:35 -0500
Subject: [PATCH 1/2] Consider physical blocksize for SmartHealthStatusFail
 alert

---
 src/prometheus_alert_rules/smart.yaml       |  2 +-
 tests/unit/test_alert_rules/test_smart.yaml | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/src/prometheus_alert_rules/smart.yaml b/src/prometheus_alert_rules/smart.yaml
index d4a31df..563bf77 100644
--- a/src/prometheus_alert_rules/smart.yaml
+++ b/src/prometheus_alert_rules/smart.yaml
@@ -33,7 +33,7 @@ groups:
           LABELS = {{ $labels }}
 
   - alert: SmartHealthStatusFail
-    expr: smartctl_device_smart_status == 0
+    expr: (smartctl_device_smart_status == 0) and on(device, juju_unit) (smartctl_device_block_size{blocks_type="physical"} != 0)
     for: 2m
     labels:
       severity: critical
diff --git a/tests/unit/test_alert_rules/test_smart.yaml b/tests/unit/test_alert_rules/test_smart.yaml
index 5030e22..051f35e 100644
--- a/tests/unit/test_alert_rules/test_smart.yaml
+++ b/tests/unit/test_alert_rules/test_smart.yaml
@@ -68,6 +68,8 @@ tests:
     input_series:
       - series: 'smartctl_device_smart_status{device="sda", instance="ubuntu-1"}'
         values: '0x15'
+      - series: 'smartctl_device_block_size{device="sda", instance="ubuntu-1", blocks_type="physical"}'
+        values: '1x15'
 
     alert_rule_test:
       - eval_time: 10m
@@ -84,6 +86,18 @@ tests:
                   VALUE = 0
                   LABELS = map[__name__:smartctl_device_smart_status device:sda instance:ubuntu-1]
 
+  - interval: 1m
+    input_series:
+      - series: 'smartctl_device_smart_status{device="sda", instance="ubuntu-1"}'
+        values: '0x15'
+      - series: 'smartctl_device_block_size{device="sda", instance="ubuntu-1", blocks_type="physical"}'
+        values: '0x15'
+
+    alert_rule_test:
+      - eval_time: 10m
+        alertname: SmartHealthStatusFail
+        exp_alerts: # alerts shouldn't fire since block size is 0
+
   - interval: 1m
     input_series:
       - series: 'smartctl_device_smartctl_exit_status{device="sda", instance="ubuntu-2"}'

From f29248644856e40c04e16574d0cd955c73cbfa17 Mon Sep 17 00:00:00 2001
From: Deezzir <deezzir@gmail.com>
Date: Mon, 16 Dec 2024 18:59:12 -0500
Subject: [PATCH 2/2] Add comments

---
 src/prometheus_alert_rules/smart.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/prometheus_alert_rules/smart.yaml b/src/prometheus_alert_rules/smart.yaml
index 563bf77..d7edcdf 100644
--- a/src/prometheus_alert_rules/smart.yaml
+++ b/src/prometheus_alert_rules/smart.yaml
@@ -33,6 +33,9 @@ groups:
           LABELS = {{ $labels }}
 
   - alert: SmartHealthStatusFail
+    # We can check if the physical size of the drive is 0, meaning it's a logical device,
+    # and ignore the status 0, which is always returned for logical devices, like HW RAID,
+    # avoiding false positives.
     expr: (smartctl_device_smart_status == 0) and on(device, juju_unit) (smartctl_device_block_size{blocks_type="physical"} != 0)
     for: 2m
     labels: