From 16933f8333edaf09b4e58a16290452c51393be60 Mon Sep 17 00:00:00 2001
From: Hui Chen <hchenxa@cn.ibm.com>
Date: Mon, 22 Oct 2018 18:05:49 +0800
Subject: [PATCH] update the deployment file and use configmap

---
 README.md                                    |  4 +-
 deployment/node-problem-detector-config.yaml | 82 ++++++++++++++++++++
 deployment/node-problem-detector.yaml        |  9 ++-
 3 files changed, 91 insertions(+), 4 deletions(-)
 create mode 100644 deployment/node-problem-detector-config.yaml

diff --git a/README.md b/README.md
index 75790b1a..8e8e06f1 100644
--- a/README.md
+++ b/README.md
@@ -103,9 +103,9 @@ to another registry.
 
 ## Start DaemonSet
 * Edit [node-problem-detector.yaml](https://github.com/kubernetes/node-problem-detector/blob/master/deployment/node-problem-detector.yaml) to fit your environment: Set `log` volume to your system log directory. (Used by SystemLogMonitor). For **kubernetes <1.9** use [node-problem-detector-old.yaml](https://github.com/kubernetes/node-problem-detector/blob/master/deployment/node-problem-detector-old.yaml)
-* Create the DaemonSet with `kubectl create -f node-problem-detector.yaml`
 * If needed, you can use [ConfigMap](https://kubernetes.io/docs/tasks/configure-pod-container/configure-pod-configmap/)
-to overwrite the `config/`.
+to overwrite the `config/`, Edit [node-problem-detector-config.yaml](https://github.com/kubernetes/node-problem-detector/blob/master/deployment/node-problem-detector-config.yaml) to fit your environment. and create the ConfigMap with `kubectl create -f node-problem-detector-config.yaml`.
+* Create the DaemonSet with `kubectl create -f node-problem-detector.yaml`.
 
 ## Start Standalone
 To run node-problem-detector standalone, you should set `inClusterConfig` to `false` and
diff --git a/deployment/node-problem-detector-config.yaml b/deployment/node-problem-detector-config.yaml
new file mode 100644
index 00000000..84ac4e98
--- /dev/null
+++ b/deployment/node-problem-detector-config.yaml
@@ -0,0 +1,82 @@
+apiVersion: v1
+data:
+  kernel-monitor.json: |
+    {
+        "plugin": "journald",
+        "pluginConfig": {
+            "source": "kernel"
+        },
+        "logPath": "/var/log/journal",
+        "lookback": "5m",
+        "bufferSize": 10,
+        "source": "kernel-monitor",
+        "conditions": [
+            {
+                "type": "KernelDeadlock",
+                "reason": "KernelHasNoDeadlock",
+                "message": "kernel has no deadlock"
+            }
+        ],
+        "rules": [
+            {
+                "type": "temporary",
+                "reason": "OOMKilling",
+                "pattern": "Kill process \\d+ (.+) score \\d+ or sacrifice child\\nKilled process \\d+ (.+) total-vm:\\d+kB, anon-rss:\\d+kB, file-rss:\\d+kB.*"
+            },
+            {
+                "type": "temporary",
+                "reason": "TaskHung",
+                "pattern": "task \\S+:\\w+ blocked for more than \\w+ seconds\\."
+            },
+            {
+                "type": "temporary",
+                "reason": "UnregisterNetDevice",
+                "pattern": "unregister_netdevice: waiting for \\w+ to become free. Usage count = \\d+"
+            },
+            {
+                "type": "temporary",
+                "reason": "KernelOops",
+                "pattern": "BUG: unable to handle kernel NULL pointer dereference at .*"
+            },
+            {
+                "type": "temporary",
+                "reason": "KernelOops",
+                "pattern": "divide error: 0000 \\[#\\d+\\] SMP"
+            },
+            {
+                "type": "permanent",
+                "condition": "KernelDeadlock",
+                "reason": "AUFSUmountHung",
+                "pattern": "task umount\\.aufs:\\w+ blocked for more than \\w+ seconds\\."
+            },
+            {
+                "type": "permanent",
+                "condition": "KernelDeadlock",
+                "reason": "DockerHung",
+                "pattern": "task docker:\\w+ blocked for more than \\w+ seconds\\."
+            }
+        ]
+    }
+  docker-monitor.json: |
+    {
+        "plugin": "journald",
+        "pluginConfig": {
+            "source": "docker"
+        },
+        "logPath": "/var/log/journal",
+        "lookback": "5m",
+        "bufferSize": 10,
+        "source": "docker-monitor",
+        "conditions": [],
+        "rules": [
+            {
+                "type": "temporary",
+                "reason": "CorruptDockerImage",
+                "pattern": "Error trying v2 registry: failed to register layer: rename /var/lib/docker/image/(.+) /var/lib/docker/image/(.+): directory not empty.*"
+            }
+        ]
+    }
+kind: ConfigMap
+metadata:
+  name: node-problem-detector-config
+  namespace: default
diff --git a/deployment/node-problem-detector.yaml b/deployment/node-problem-detector.yaml
index 52634f18..300d5092 100644
--- a/deployment/node-problem-detector.yaml
+++ b/deployment/node-problem-detector.yaml
@@ -16,8 +16,8 @@ spec:
         command:
         - /node-problem-detector
         - --logtostderr
-        - --kernel-monitor=/config/kernel-monitor.json
-        image: k8s.gcr.io/node-problem-detector:v0.2
+        - --system-log-monitors=/config/kernel-monitor.json,/config/docker-monitor.json
+        image: k8s.gcr.io/node-problem-detector:v0.5.0
         imagePullPolicy: Always
         securityContext:
           privileged: true
@@ -55,3 +55,8 @@ spec:
       - name: config
         configMap:
           name: node-problem-detector-config
+          items:
+          - key: kernel-monitor.json
+            path: kernel-monitor.json
+          - key: docker-monitor.json
+            path: docker-monitor.json