[ https://issues.apache.org/jira/browse/AMBARI-15533?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15209306#comment-15209306 ]
Hudson commented on AMBARI-15533: --------------------------------- SUCCESS: Integrated in Ambari-branch-2.2 #548 (See [https://builds.apache.org/job/Ambari-branch-2.2/548/]) AMBARI-15533 - HDFS Alerts for AMS Throw 'invalid literal for int() with (jhurley: [http://git-wip-us.apache.org/repos/asf?p=ambari.git&a=commit&h=f1efa3a5e1b64fa3eb66815ce3d40e9bd54aa4b0]) * ambari-server/src/main/resources/common-services/HDFS/2.1.0.2.0/package/alerts/alert_metrics_deviation.py > HDFS Alerts for AMS Throw 'invalid literal for int() with base 10: '50.0'' > -------------------------------------------------------------------------- > > Key: AMBARI-15533 > URL: https://issues.apache.org/jira/browse/AMBARI-15533 > Project: Ambari > Issue Type: Bug > Components: ambari-agent > Affects Versions: 2.2.2 > Reporter: Jonathan Hurley > Assignee: Jonathan Hurley > Priority: Critical > Fix For: 2.2.2 > > Attachments: AMBARI-15533.patch > > > SCRIPT alerts stuck in UNKNWN status with response message 'invalid literal > for int() with base 10: '50.0''. > It is noticed that the error is thrown only after a PUT alertDefinition call > to update few parameters of alert definition since the numeric values are > changed into strings. > The scripts need to safely cast their parameters; the fix is in the script > here. > E.g PUT Request : > {noformat} > PUT http://172.22.114.20:8080/api/v1/clusters/cl1/alert_definitions/38 > { > "AlertDefinition" : { > "cluster_name" : "cl1", > "component_name" : "NAMENODE", > "description" : "This service-level alert is triggered if the NN heap > usage deviation has grown beyond the specified threshold within a given time > interval.", > "enabled" : true, > "id" : 38, > "ignore_host" : false, > "interval" : 2, > "label" : "NameNode Heap Usage (Daily)", > "name" : "increase_nn_heap_usage_daily", > "scope" : "ANY", > "service_name" : "HDFS", > "source" : { > "parameters" : [ > { > "name" : "mergeHaMetrics", > "display_name" : "Whether active and stanby NameNodes metrics > should be merged", > "value" : "false", > "description" : "Whether active and stanby NameNodes metrics should > be merged.", > "type" : "STRING" > }, > { > "name" : "interval", > "display_name" : "Time interval in minutes", > "value" : 1441.0, > "description" : "Time interval in minutes.", > "type" : "NUMERIC" > }, > { > "name" : "appId", > "display_name" : "AMS application id", > "value" : "NAMENODE", > "description" : "The application id used to retrieve the metric.", > "type" : "STRING" > }, > { > "name" : "metricName", > "display_name" : "Metric Name", > "value" : "jvm.JvmMetrics.MemHeapUsedM", > "description" : "The metric to monitor.", > "type" : "STRING" > }, > { > "name" : "metric.deviation.warning.threshold", > "display_name" : "The standard deviation threshold above which a > warning is produced.", > "units" : "%", > "value" : 20.0, > "type" : "PERCENT", > "threshold" : "WARNING" > }, > { > "name" : "metric.deviation.critical.threshold", > "display_name" : "The standard deviation threshold above which a > critical alert is produced.", > "units" : "%", > "value" : 50.0, > "type" : "PERCENT", > "threshold" : "CRITICAL" > } > ], > "path" : "HDFS/2.1.0.2.0/package/alerts/alert_metrics_deviation.py", > "type" : "SCRIPT" > } > } > } > {noformat} > Response :200OK > {noformat} > GET http://172.22.114.20:8080/api/v1/clusters/cl1/alert_definitions/38 > { > "href" : > "http://172.22.114.20:8080/api/v1/clusters/cl1/alert_definitions/38", > "AlertDefinition" : { > "cluster_name" : "cl1", > "component_name" : "NAMENODE", > "description" : "This service-level alert is triggered if the NN heap > usage deviation has grown beyond the specified threshold within a given time > interval.", > "enabled" : true, > "id" : 38, > "ignore_host" : false, > "interval" : 2, > "label" : "NameNode Heap Usage (Daily)", > "name" : "increase_nn_heap_usage_daily", > "scope" : "ANY", > "service_name" : "HDFS", > "source" : { > "parameters" : [ > { > "display_name" : "Whether active and stanby NameNodes metrics > should be merged", > "description" : "Whether active and stanby NameNodes metrics should > be merged.", > "name" : "mergeHaMetrics", > "value" : "false", > "type" : "STRING" > }, > { > "display_name" : "Time interval in minutes", > "description" : "Time interval in minutes.", > "name" : "interval", > "value" : "1441.0", > "type" : "NUMERIC" > }, > { > "display_name" : "AMS application id", > "description" : "The application id used to retrieve the metric.", > "name" : "appId", > "value" : "NAMENODE", > "type" : "STRING" > }, > { > "display_name" : "Metric Name", > "description" : "The metric to monitor.", > "name" : "metricName", > "value" : "jvm.JvmMetrics.MemHeapUsedM", > "type" : "STRING" > }, > { > "display_name" : "The standard deviation threshold above which a > warning is produced.", > "name" : "metric.deviation.warning.threshold", > "value" : "20.0", > "type" : "PERCENT", > "units" : "%", > "threshold" : "WARNING" > }, > { > "display_name" : "The standard deviation threshold above which a > critical alert is produced.", > "name" : "metric.deviation.critical.threshold", > "value" : "50.0", > "type" : "PERCENT", > "units" : "%", > "threshold" : "CRITICAL" > } > ], > "path" : "HDFS/2.1.0.2.0/package/alerts/alert_metrics_deviation.py", > "type" : "SCRIPT" > } > } > } > {noformat} -- This message was sent by Atlassian JIRA (v6.3.4#6332)