diff --git a/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/alerts.json b/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/alerts.json old mode 100755 new mode 100644 index 8ccfa47b5ec..194d80b497e --- a/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/alerts.json +++ b/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/alerts.json @@ -213,7 +213,7 @@ "warning": { "text": "Total Blocks:[{1}], Missing Blocks:[{0}]", "value": 1 - }, + }, "critical": { "text": "Total Blocks:[{1}], Missing Blocks:[{0}]", "value": 1 @@ -275,6 +275,52 @@ } } }, + { + "name": "namenode_hdfs_volume_failures", + "label": "Datanode Volume Failures", + "description": "This service-level alert is triggered if the number of volume failures exceeds the configured critical threshold. The threshold values are in volumes.", + "interval": 2, + "scope": "ANY", + "enabled": true, + "source": { + "type": "METRIC", + "uri": { + "http": "{{hdfs-site/dfs.namenode.http-address}}", + "https": "{{hdfs-site/dfs.namenode.https-address}}", + "kerberos_keytab": "{{hdfs-site/dfs.web.authentication.kerberos.keytab}}", + "kerberos_principal": "{{hdfs-site/dfs.web.authentication.kerberos.principal}}", + "https_property": "{{hdfs-site/dfs.http.policy}}", + "https_property_value": "HTTPS_ONLY", + "connection_timeout": 5.0, + "high_availability": { + "nameservice": "{{hdfs-site/dfs.internal.nameservices}}", + "alias_key" : "{{hdfs-site/dfs.ha.namenodes.{{ha-nameservice}}}}", + "http_pattern" : "{{hdfs-site/dfs.namenode.http-address.{{ha-nameservice}}.{{alias}}}}", + "https_pattern" : "{{hdfs-site/dfs.namenode.https-address.{{ha-nameservice}}.{{alias}}}}" + } + }, + "reporting": { + "ok": { + "text": "Failed Volumes:[{0}]" + }, + "warning": { + "text": "Failed Volumes:[{0}]", + "value": 1 + }, + "critical": { + "text": "Failed Volumes:[{0}]", + "value": 1 + }, + "units" : "Volumes" + }, + "jmx": { + "property_list": [ + "Hadoop:service=NameNode,name=FSNamesystem/VolumeFailuresTotal" + ], + "value": "{0}" + } + } + }, { "name": "namenode_hdfs_capacity_utilization", "label": "HDFS Capacity Utilization", @@ -354,7 +400,7 @@ "warning": { "text": "Average Queue Time:[{0}], Average Processing Time:[{1}]", "value": 3000 - }, + }, "critical": { "text": "Average Queue Time:[{0}], Average Processing Time:[{1}]", "value": 5000 @@ -1598,7 +1644,7 @@ } } } - ], + ], "DATANODE": [ { "name": "datanode_process", diff --git a/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/widgets.json b/ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/widgets.json old mode 100755 new mode 100644