From b485aab7e71c1625cfc27e0f92c9509f42378458 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Sun, 5 May 2024 13:19:16 +0200
Subject: Adding upstream version 1.45.3+dfsg.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 src/health/health.d/hdfs.conf | 81 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 src/health/health.d/hdfs.conf

(limited to 'src/health/health.d/hdfs.conf')

diff --git a/src/health/health.d/hdfs.conf b/src/health/health.d/hdfs.conf
new file mode 100644
index 000000000..566e815aa
--- /dev/null
+++ b/src/health/health.d/hdfs.conf
@@ -0,0 +1,81 @@
+
+# Common
+
+ template: hdfs_capacity_usage
+       on: hdfs.capacity
+    class: Utilization
+     type: Storage
+component: HDFS
+     calc: ($used) * 100 / ($used + $remaining)
+    units: %
+    every: 10s
+     warn: $this > (($status >= $WARNING)  ? (70) : (80))
+     crit: $this > (($status == $CRITICAL) ? (80) : (98))
+    delay: down 15m multiplier 1.5 max 1h
+  summary: HDFS datanodes space utilization
+     info: summary datanodes space capacity utilization
+       to: sysadmin
+
+
+# NameNode
+
+ template: hdfs_missing_blocks
+       on: hdfs.blocks
+    class: Errors
+     type: Storage
+component: HDFS
+     calc: $missing
+    units: missing blocks
+    every: 10s
+     warn: $this > 0
+    delay: down 15m multiplier 1.5 max 1h
+  summary: HDFS missing blocks
+     info: number of missing blocks
+       to: sysadmin
+
+
+ template: hdfs_stale_nodes
+       on: hdfs.data_nodes
+    class: Errors
+     type: Storage
+component: HDFS
+     calc: $stale
+    units: dead nodes
+    every: 10s
+     warn: $this > 0
+    delay: down 15m multiplier 1.5 max 1h
+  summary: HDFS stale datanodes
+     info: number of datanodes marked stale due to delayed heartbeat
+       to: sysadmin
+
+
+ template: hdfs_dead_nodes
+       on: hdfs.data_nodes
+    class: Errors
+     type: Storage
+component: HDFS
+     calc: $dead
+    units: dead nodes
+    every: 10s
+     crit: $this > 0
+    delay: down 15m multiplier 1.5 max 1h
+  summary: HDFS dead datanodes
+     info: number of datanodes which are currently dead
+       to: sysadmin
+
+
+# DataNode
+
+ template: hdfs_num_failed_volumes
+       on: hdfs.num_failed_volumes
+    class: Errors
+     type: Storage
+component: HDFS
+     calc: $fsds_num_failed_volumes
+    units: failed volumes
+    every: 10s
+     warn: $this > 0
+    delay: down 15m multiplier 1.5 max 1h
+  summary: HDFS failed volumes
+     info: number of failed volumes
+       to: sysadmin
-- 
cgit v1.2.3