You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ambari.apache.org by al...@apache.org on 2017/06/28 00:24:38 UTC
[40/51] [partial] ambari git commit: AMBARI-21349. Create BigInsights
Stack Skeleton in Ambari 2.5 (alejandro)
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HBASE/widgets.json
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HBASE/widgets.json b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HBASE/widgets.json
new file mode 100755
index 0000000..a0f5ba9
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HBASE/widgets.json
@@ -0,0 +1,510 @@
+{
+ "layouts": [
+ {
+ "layout_name": "default_hbase_dashboard",
+ "display_name": "Standard HBase Dashboard",
+ "section_name": "HBASE_SUMMARY",
+ "widgetLayoutInfo": [
+ {
+ "widget_name": "Reads and Writes",
+ "description": "Count of read and write requests on all regions in the cluster.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.Server.Get_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/Get_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.ScanNext_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/ScanNext_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Append_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/Append_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Delete_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/Delete_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Increment_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/Increment_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Mutate_num_ops._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/Mutate_num_ops._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Read Requests",
+ "value": "${regionserver.Server.Get_num_ops._sum + regionserver.Server.ScanNext_num_ops._sum}"
+ },
+ {
+ "name": "Write Requests",
+ "value": "${regionserver.Server.Append_num_ops._sum + regionserver.Server.Delete_num_ops._sum + regionserver.Server.Increment_num_ops._sum + regionserver.Server.Mutate_num_ops._sum}"
+ }
+ ],
+ "properties": {
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Read Latency",
+ "description": "maximum of 95% read latency.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.Server.Get_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/Get_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.ScanNext_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/ScanNext_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Cluster wide maximum of 95% Get Latency",
+ "value": "${regionserver.Server.Get_95th_percentile._max}"
+ },
+ {
+ "name": "Cluster wide maximum of 95% ScanNext Latency",
+ "value": "${regionserver.Server.ScanNext_95th_percentile._max}"
+ }
+ ],
+ "properties": {
+ "display_unit": "ms",
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Write Latency",
+ "description": "maximum of 95% write latency.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.Server.Mutate_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/Mutate_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Increment_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/Increment_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Append_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/Append_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.Server.Delete_95th_percentile._max",
+ "metric_path": "metrics/hbase/regionserver/Server/Delete_95th_percentile._max",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Cluster wide maximum of 95% Mutate Latency",
+ "value": "${regionserver.Server.Mutate_95th_percentile._max}"
+ },
+ {
+ "name": "Cluster wide maximum of 95% Increment Latency",
+ "value": "${regionserver.Server.Increment_95th_percentile._max}"
+ },
+ {
+ "name": "Cluster wide maximum of 95% Append Latency",
+ "value": "${regionserver.Server.Append_95th_percentile._max}"
+ },
+ {
+ "name": "Cluster wide maximum of 95% Delete Latency",
+ "value": "${regionserver.Server.Delete_95th_percentile._max}"
+ }
+ ],
+ "properties": {
+ "display_unit": "ms",
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Open Connections",
+ "description": "Count of open connections across all RegionServer. This is indicative of RegionServer load in the cluster.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.RegionServer.numOpenConnections._sum",
+ "metric_path": "metrics/hbase/ipc/IPC/numOpenConnections._sum",
+ "category": "",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Open Connections",
+ "value": "${regionserver.RegionServer.numOpenConnections._sum}"
+ }
+ ],
+ "properties": {
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Request Handlers",
+ "description": "Count of Active handlers vs count of calls waiting in the general queue.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.RegionServer.numActiveHandler._sum",
+ "metric_path": "metrics/hbase/ipc/IPC/numActiveHandler._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "regionserver.RegionServer.numCallsInGeneralQueue._sum",
+ "metric_path": "metrics/hbase/ipc/IPC/numCallsInGeneralQueue._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Active Handlers",
+ "value": "${regionserver.RegionServer.numActiveHandler._sum}"
+ },
+ {
+ "name": "Calls in General Queue",
+ "value": "${regionserver.RegionServer.numCallsInGeneralQueue._sum}"
+ }
+ ],
+ "properties": {
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Files Local",
+ "description": "Average percentage of local files to RegionServer in the cluster.",
+ "widget_type": "NUMBER",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.Server.percentFilesLocal",
+ "metric_path": "metrics/hbase/regionserver/Server/percentFilesLocal",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Files Local",
+ "value": "${regionserver.Server.percentFilesLocal}"
+ }
+ ],
+ "properties": {
+ "display_unit": "%",
+ "error_threshold":"25",
+ "warning_threshold": "75"
+ }
+ },
+ {
+ "widget_name": "Blocked Updates",
+ "description": "Number of milliseconds updates have been blocked so the memstore can be flushed.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "regionserver.Server.updatesBlockedTime._sum",
+ "metric_path": "metrics/hbase/regionserver/Server/updatesBlockedTime._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Updates Blocked Time",
+ "value": "${regionserver.Server.updatesBlockedTime._sum}"
+ }
+ ],
+ "properties": {
+ "display_unit": "ms",
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Cluster CPU",
+ "description": "Percentage of CPU utilized across all RegionServer hosts.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "cpu_system._sum",
+ "metric_path": "metrics/cpu/cpu_system._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "cpu_user._sum",
+ "metric_path": "metrics/cpu/cpu_user._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "cpu_nice._sum",
+ "metric_path": "metrics/cpu/cpu_nice._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "cpu_idle._sum",
+ "metric_path": "metrics/cpu/cpu_idle._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "cpu_wio._sum",
+ "metric_path": "metrics/cpu/cpu_wio._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "CPU utilization",
+ "value": "${((cpu_system._sum + cpu_user._sum + cpu_nice._sum)/(cpu_system._sum + cpu_user._sum + cpu_nice._sum + cpu_idle._sum + cpu_wio._sum)) * 100}"
+ }
+ ],
+ "properties": {
+ "graph_type": "LINE",
+ "time_range": "1",
+ "display_unit": "%"
+ }
+ },
+ {
+ "widget_name": "Cluster Network",
+ "description": "Average of Network IO utilized across all RegionServer hosts.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "pkts_in._avg",
+ "metric_path": "metrics/network/pkts_in._avg",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "pkts_out._avg",
+ "metric_path": "metrics/network/pkts_out._avg",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Packets In",
+ "value": "${pkts_in._avg}"
+ },
+ {
+ "name": "Packets Out",
+ "value": "${pkts_out._avg}"
+ }
+ ],
+ "properties": {
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ },
+ {
+ "widget_name": "Cluster Disk",
+ "description": "Sum of disk throughput for all RegionServer hosts.",
+ "widget_type": "GRAPH",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "read_bps._sum",
+ "metric_path": "metrics/disk/read_bps._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ },
+ {
+ "name": "write_bps._sum",
+ "metric_path": "metrics/disk/write_bps._sum",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "Read throughput",
+ "value": "${read_bps._sum/1048576}"
+ },
+ {
+ "name": "Write throughput",
+ "value": "${write_bps._sum/1048576}"
+ }
+ ],
+ "properties": {
+ "display_unit": "Mbps",
+ "graph_type": "LINE",
+ "time_range": "1"
+ }
+ }
+ ]
+ },
+ {
+ "layout_name": "default_hbase_heatmap",
+ "display_name": "HBase Heatmaps",
+ "section_name": "HBASE_HEATMAPS",
+ "widgetLayoutInfo": [
+ {
+ "widget_name": "HBase Compaction Queue Size",
+ "description": "",
+ "widget_type": "HEATMAP",
+ "is_visible": true,
+ "metrics": [
+ {
+ "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.compactionQueueLength",
+ "metric_path": "metrics/hbase/regionserver/compactionQueueSize",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "HBase Compaction Queue Size",
+ "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.compactionQueueLength} "
+ }
+ ],
+ "properties": {
+ "display_unit": "",
+ "max_limit": "10"
+ }
+ },
+ {
+ "widget_name": "HBase Memstore Sizes",
+ "description": "",
+ "widget_type": "HEATMAP",
+ "is_visible": false,
+ "metrics": [
+ {
+ "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.memStoreSize",
+ "metric_path": "metrics/hbase/regionserver/memstoreSize",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "HBase Memstore Sizes",
+ "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.memStoreSize}"
+ }
+ ],
+ "properties": {
+ "display_unit": "B",
+ "max_limit": "104857600"
+ }
+ },
+ {
+ "widget_name": "HBase Read Request Count",
+ "description": "",
+ "widget_type": "HEATMAP",
+ "is_visible": false,
+ "metrics": [
+ {
+ "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.readRequestCount",
+ "metric_path": "metrics/hbase/regionserver/readRequestsCount",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "HBase Read Request Count",
+ "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.readRequestCount}"
+ }
+ ],
+ "properties": {
+ "max_limit": "200"
+ }
+ },
+ {
+ "widget_name": "HBase Write Request Count",
+ "description": "",
+ "widget_type": "HEATMAP",
+ "is_visible": false,
+ "metrics": [
+ {
+ "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.writeRequestCount",
+ "metric_path": "metrics/hbase/regionserver/writeRequestsCount",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "HBase Write Request Count",
+ "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.writeRequestCount}"
+ }
+ ],
+ "properties": {
+ "max_limit": "200"
+ }
+ },
+ {
+ "widget_name": "HBase Regions",
+ "description": "",
+ "widget_type": "HEATMAP",
+ "is_visible": false,
+ "metrics": [
+ {
+ "name": "Hadoop:service=HBase,name=RegionServer,sub=Server.regionCount",
+ "metric_path": "metrics/hbase/regionserver/regions",
+ "service_name": "HBASE",
+ "component_name": "HBASE_REGIONSERVER"
+ }
+ ],
+ "values": [
+ {
+ "name": "HBase Regions",
+ "value": "${Hadoop:service=HBase,name=RegionServer,sub=Server.regionCount}"
+ }
+ ],
+ "properties": {
+ "max_limit": "10"
+ }
+ }
+ ]
+ }
+ ]
+}
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/alerts.json
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/alerts.json b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/alerts.json
new file mode 100755
index 0000000..6888a18
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/alerts.json
@@ -0,0 +1,657 @@
+{
+ "HDFS":{
+ "service": [
+ {
+ "name": "datanode_process_percent",
+ "label": "Percent DataNodes Available",
+ "description": "This alert is triggered if the number of down DataNodes in the cluster is greater than the configured critical threshold. It aggregates the results of DataNode process checks.",
+ "interval": 1,
+ "scope": "SERVICE",
+ "enabled": true,
+ "source": {
+ "type": "AGGREGATE",
+ "alert_name": "datanode_process",
+ "reporting": {
+ "ok": {
+ "text": "affected: [{1}], total: [{0}]"
+ },
+ "warning": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.1
+ },
+ "critical": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.3
+ }
+ }
+ }
+ },
+ {
+ "name": "datanode_storage_percent",
+ "label": "Percent DataNodes With Available Space",
+ "description": "This service-level alert is triggered if the storage on a certain percentage of DataNodes exceeds either the warning or critical threshold values.",
+ "interval": 1,
+ "scope": "SERVICE",
+ "enabled": true,
+ "source": {
+ "type": "AGGREGATE",
+ "alert_name": "datanode_storage",
+ "reporting": {
+ "ok": {
+ "text": "affected: [{1}], total: [{0}]"
+ },
+ "warning": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.1
+ },
+ "critical": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.3
+ }
+ }
+ }
+ },
+ {
+ "name": "journalnode_process_percent",
+ "label": "Percent JournalNodes Available",
+ "description": "This alert is triggered if the number of down JournalNodes in the cluster is greater than the configured critical threshold. It aggregates the results of JournalNode process checks.",
+ "interval": 1,
+ "scope": "SERVICE",
+ "enabled": true,
+ "source": {
+ "type": "AGGREGATE",
+ "alert_name": "journalnode_process",
+ "reporting": {
+ "ok": {
+ "text": "affected: [{1}], total: [{0}]"
+ },
+ "warning": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.33
+ },
+ "critical": {
+ "text": "affected: [{1}], total: [{0}]",
+ "value": 0.50
+ }
+ }
+ }
+ }
+ ],
+ "NAMENODE": [
+ {
+ "name": "namenode_webui",
+ "label": "NameNode Web UI",
+ "description": "This host-level alert is triggered if the NameNode Web UI is unreachable.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "WEB",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "kerberos_keytab": "{{hdfs-site/dfs.web.authentication.kerberos.keytab}}",
+ "kerberos_principal": "{{hdfs-site/dfs.web.authentication.kerberos.principal}}",
+ "connection_timeout": 5.0,
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "HTTP {0} response in {2:.3f}s"
+ },
+ "warning":{
+ "text": "HTTP {0} response from {1} in {2:.3f}s ({3})"
+ },
+ "critical": {
+ "text": "Connection failed to {1} ({3})"
+ }
+ }
+ }
+ },
+ {
+ "name": "namenode_cpu",
+ "label": "NameNode Host CPU Utilization",
+ "description": "This host-level alert is triggered if CPU utilization of the NameNode exceeds certain warning and critical thresholds. It checks the NameNode JMX Servlet for the SystemCPULoad property. The threshold values are in percent.",
+ "interval": 5,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "{1} CPU, load {0:.1%}"
+ },
+ "warning": {
+ "text": "{1} CPU, load {0:.1%}",
+ "value": 200
+ },
+ "critical": {
+ "text": "{1} CPU, load {0:.1%}",
+ "value": 250
+ },
+ "units" : "%"
+ },
+ "jmx": {
+ "property_list": [
+ "java.lang:type=OperatingSystem/SystemCpuLoad",
+ "java.lang:type=OperatingSystem/AvailableProcessors"
+ ],
+ "value": "{0} * 100"
+ }
+ }
+ },
+ {
+ "name": "namenode_hdfs_blocks_health",
+ "label": "NameNode Blocks Health",
+ "description": "This service-level alert is triggered if the number of corrupt or missing blocks exceeds the configured critical threshold. The threshold values are in blocks.",
+ "interval": 2,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "Total Blocks:[{1}], Missing Blocks:[{0}]"
+ },
+ "warning": {
+ "text": "Total Blocks:[{1}], Missing Blocks:[{0}]",
+ "value": 1
+ },
+ "critical": {
+ "text": "Total Blocks:[{1}], Missing Blocks:[{0}]",
+ "value": 1
+ },
+ "units" : "Blocks"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=NameNode,name=FSNamesystem/MissingBlocks",
+ "Hadoop:service=NameNode,name=FSNamesystem/BlocksTotal"
+ ],
+ "value": "{0}"
+ }
+ }
+ },
+ {
+ "name": "namenode_hdfs_capacity_utilization",
+ "label": "HDFS Capacity Utilization",
+ "description": "This service-level alert is triggered if the HDFS capacity utilization exceeds the configured warning and critical thresholds. It checks the NameNode JMX Servlet for the CapacityUsed and CapacityRemaining properties. The threshold values are in percent.",
+ "interval": 2,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "Capacity Used:[{2:.0f}%, {0}], Capacity Remaining:[{1}]"
+ },
+ "warning": {
+ "text": "Capacity Used:[{2:.0f}%, {0}], Capacity Remaining:[{1}]",
+ "value": 80
+ },
+ "critical": {
+ "text": "Capacity Used:[{2:.0f}%, {0}], Capacity Remaining:[{1}]",
+ "value": 90
+ },
+ "units" : "%"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=NameNode,name=FSNamesystemState/CapacityUsed",
+ "Hadoop:service=NameNode,name=FSNamesystemState/CapacityRemaining"
+ ],
+ "value": "{0}/({0} + {1}) * 100.0"
+ }
+ }
+ },
+ {
+ "name": "namenode_rpc_latency",
+ "label": "NameNode RPC Latency",
+ "description": "This host-level alert is triggered if the NameNode RPC latency exceeds the configured critical threshold. Typically an increase in the RPC processing time increases the RPC queue length, causing the average queue wait time to increase for NameNode operations. The threshold values are in milliseconds.",
+ "interval": 2,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "Average Queue Time:[{0}], Average Processing Time:[{1}]"
+ },
+ "warning": {
+ "text": "Average Queue Time:[{0}], Average Processing Time:[{1}]",
+ "value": 3000
+ },
+ "critical": {
+ "text": "Average Queue Time:[{0}], Average Processing Time:[{1}]",
+ "value": 5000
+ },
+ "units" : "ms"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=NameNode,name=RpcActivityForPort*/RpcQueueTimeAvgTime",
+ "Hadoop:service=NameNode,name=RpcActivityForPort*/RpcProcessingTimeAvgTime"
+ ],
+ "value": "{0}"
+ }
+ }
+ },
+ {
+ "name": "namenode_directory_status",
+ "label": "NameNode Directory Status",
+ "description": "This host-level alert is triggered if the NameNode NameDirStatuses metric (name=NameNodeInfo/NameDirStatuses) reports a failed directory. The threshold values are in the number of directories that are not healthy.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "Directories are healthy"
+ },
+ "warning": {
+ "text": "Failed directory count: {1}",
+ "value": 1
+ },
+ "critical": {
+ "text": "Failed directory count: {1}",
+ "value": 1
+ },
+ "units" : "Dirs"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=NameNode,name=NameNodeInfo/NameDirStatuses"
+ ],
+ "value": "calculate(args)\ndef calculate(args):\n import json\n json_statuses = json.loads({0})\n return len(json_statuses['failed']) if 'failed' in json_statuses else 0"
+ }
+ }
+ },
+ {
+ "name": "datanode_health_summary",
+ "label": "DataNode Health Summary",
+ "description": "This service-level alert is triggered if there are unhealthy DataNodes",
+ "interval": 1,
+ "scope": "SERVICE",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.namenode.http-address}}",
+ "https": "{{hdfs-site/dfs.namenode.https-address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "high_availability": {
+ "nameservice": "{{hdfs-site/dfs.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": "All {2} DataNode(s) are healthy"
+ },
+ "warning": {
+ "text": "DataNode Health: [Live={2}, Stale={1}, Dead={0}]",
+ "value": 1
+ },
+ "critical": {
+ "text": "DataNode Health: [Live={2}, Stale={1}, Dead={0}]",
+ "value": 1
+ },
+ "units" : "DNs"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=NameNode,name=FSNamesystemState/NumDeadDataNodes",
+ "Hadoop:service=NameNode,name=FSNamesystemState/NumStaleDataNodes",
+ "Hadoop:service=NameNode,name=FSNamesystemState/NumLiveDataNodes"
+ ],
+ "value": "{0} + {1}"
+ }
+ }
+ },
+ {
+ "name": "namenode_last_checkpoint",
+ "label": "NameNode Last Checkpoint",
+ "description": "This service-level alert will trigger if the last time that the NameNode performed a checkpoint was too long ago. It will also trigger if the number of uncommitted transactions is beyond a certain threshold.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "SCRIPT",
+ "path": "HDFS/2.7.1.4.1/package/alerts/alert_checkpoint_time.py",
+ "parameters": [
+ {
+ "name": "connection.timeout",
+ "display_name": "Connection Timeout",
+ "value": 5.0,
+ "type": "NUMERIC",
+ "description": "The maximum time before this alert is considered to be CRITICAL",
+ "units": "seconds",
+ "threshold": "CRITICAL"
+ },
+ {
+ "name": "checkpoint.time.warning.threshold",
+ "display_name": "Checkpoint Warning",
+ "value": 2.0,
+ "type": "PERCENT",
+ "description": "The percentage of the last checkpoint time greater than the interval in order to trigger a warning alert.",
+ "units": "%",
+ "threshold": "WARNING"
+ },
+ {
+ "name": "checkpoint.time.critical.threshold",
+ "display_name": "Checkpoint Critical",
+ "value": 2.0,
+ "type": "PERCENT",
+ "description": "The percentage of the last checkpoint time greater than the interval in order to trigger a critical alert.",
+ "units": "%",
+ "threshold": "CRITICAL"
+ }
+ ]
+ }
+ },
+ {
+ "name": "namenode_ha_health",
+ "label": "NameNode High Availability Health",
+ "description": "This service-level alert is triggered if either the Active NameNode or Standby NameNode are not running.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "ignore_host": true,
+ "source": {
+ "type": "SCRIPT",
+ "path": "HDFS/2.7.1.4.1/package/alerts/alert_ha_namenode_health.py",
+ "parameters": [
+ {
+ "name": "connection.timeout",
+ "display_name": "Connection Timeout",
+ "value": 5.0,
+ "type": "NUMERIC",
+ "description": "The maximum time before this alert is considered to be CRITICAL",
+ "units": "seconds",
+ "threshold": "CRITICAL"
+ }
+ ]
+ }
+ }
+ ],
+ "SECONDARY_NAMENODE": [
+ {
+ "name": "secondary_namenode_process",
+ "label": "Secondary NameNode Process",
+ "description": "This host-level alert is triggered if the Secondary NameNode process cannot be confirmed to be up and listening on the network.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "PORT",
+ "uri": "{{hdfs-site/dfs.namenode.secondary.http-address}}",
+ "default_port": 50071,
+ "reporting": {
+ "ok": {
+ "text": "TCP OK - {0:.3f}s response on port {1}"
+ },
+ "warning": {
+ "text": "TCP OK - {0:.3f}s response on port {1}",
+ "value": 1.5
+ },
+ "critical": {
+ "text": "Connection failed: {0} to {1}:{2}",
+ "value": 5.0
+ }
+ }
+ }
+ }
+ ],
+ "NFS_GATEWAY": [
+ {
+ "name": "nfsgateway_process",
+ "label": "NFS Gateway Process",
+ "description": "This host-level alert is triggered if the NFS Gateway process cannot be confirmed to be up and listening on the network.",
+ "interval": 1,
+ "scope": "HOST",
+ "enabled": true,
+ "source": {
+ "type": "PORT",
+ "uri": "{{hdfs-site/nfs.server.port}}",
+ "default_port": 2049,
+ "reporting": {
+ "ok": {
+ "text": "TCP OK - {0:.3f}s response on port {1}"
+ },
+ "warning": {
+ "text": "TCP OK - {0:.3f}s response on port {1}",
+ "value": 1.5
+ },
+ "critical": {
+ "text": "Connection failed: {0} to {1}:{2}",
+ "value": 5.0
+ }
+ }
+ }
+ }
+ ],
+ "JOURNALNODE": [
+ {
+ "name": "journalnode_process",
+ "label": "JournalNode Process",
+ "description": "This host-level alert is triggered if the JournalNode process cannot be confirmed to be up and listening on the network.",
+ "interval": 1,
+ "scope": "HOST",
+ "enabled": true,
+ "source": {
+ "type": "PORT",
+ "uri": "{{hdfs-site/dfs.journalnode.http-address}}",
+ "default_port": 8480,
+ "reporting": {
+ "ok": {
+ "text": "TCP OK - {0:.3f}s response on port {1}"
+ },
+ "warning": {
+ "text": "TCP OK - {0:.3f}s response on port {1}",
+ "value": 1.5
+ },
+ "critical": {
+ "text": "Connection failed: {0} to {1}:{2}",
+ "value": 5.0
+ }
+ }
+ }
+ }
+ ],
+ "DATANODE": [
+ {
+ "name": "datanode_process",
+ "label": "DataNode Process",
+ "description": "This host-level alert is triggered if the individual DataNode processes cannot be established to be up and listening on the network.",
+ "interval": 1,
+ "scope": "HOST",
+ "enabled": true,
+ "source": {
+ "type": "PORT",
+ "uri": "{{hdfs-site/dfs.datanode.address}}",
+ "default_port": 50010,
+ "reporting": {
+ "ok": {
+ "text": "TCP OK - {0:.3f}s response on port {1}"
+ },
+ "warning": {
+ "text": "TCP OK - {0:.3f}s response on port {1}",
+ "value": 1.5
+ },
+ "critical": {
+ "text": "Connection failed: {0} to {1}:{2}",
+ "value": 5.0
+ }
+ }
+ }
+ },
+ {
+ "name": "datanode_webui",
+ "label": "DataNode Web UI",
+ "description": "This host-level alert is triggered if the DataNode Web UI is unreachable.",
+ "interval": 1,
+ "scope": "HOST",
+ "enabled": true,
+ "source": {
+ "type": "WEB",
+ "uri": {
+ "http": "{{hdfs-site/dfs.datanode.http.address}}",
+ "https": "{{hdfs-site/dfs.datanode.https.address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY",
+ "kerberos_keytab": "{{hdfs-site/dfs.web.authentication.kerberos.keytab}}",
+ "kerberos_principal": "{{hdfs-site/dfs.web.authentication.kerberos.principal}}"
+ },
+ "reporting": {
+ "ok": {
+ "text": "HTTP {0} response in {2:.3f}s"
+ },
+ "warning":{
+ "text": "HTTP {0} response from {1} in {2:.3f}s ({3})"
+ },
+ "critical": {
+ "text": "Connection failed to {1} ({3})"
+ }
+ }
+ }
+ },
+ {
+ "name": "datanode_storage",
+ "label": "DataNode Storage",
+ "description": "This host-level alert is triggered if storage capacity if full on the DataNode. It checks the DataNode JMX Servlet for the Capacity and Remaining properties. The threshold values are in percent.",
+ "interval": 2,
+ "scope": "HOST",
+ "enabled": true,
+ "source": {
+ "type": "METRIC",
+ "uri": {
+ "http": "{{hdfs-site/dfs.datanode.http.address}}",
+ "https": "{{hdfs-site/dfs.datanode.https.address}}",
+ "https_property": "{{hdfs-site/dfs.http.policy}}",
+ "https_property_value": "HTTPS_ONLY"
+ },
+ "reporting": {
+ "ok": {
+ "text": "Remaining Capacity:[{0}], Total Capacity:[{2:.0f}% Used, {1}]"
+ },
+ "warning": {
+ "text": "Remaining Capacity:[{0}], Total Capacity:[{2:.0f}% Used, {1}]",
+ "value": 80
+ },
+ "critical": {
+ "text": "Remaining Capacity:[{0}], Total Capacity:[{2:.0f}% Used, {1}]",
+ "value": 90
+ },
+ "units" : "%"
+ },
+ "jmx": {
+ "property_list": [
+ "Hadoop:service=DataNode,name=FSDatasetState-*/Remaining",
+ "Hadoop:service=DataNode,name=FSDatasetState-*/Capacity"
+ ],
+ "value": "({1} - {0})/{1} * 100.0"
+ }
+ }
+ }
+ ],
+ "ZKFC": [
+ {
+ "name": "hdfs_zookeeper_failover_controller_process",
+ "label": "ZooKeeper Failover Controller Process",
+ "description": "This host-level alert is triggered if the ZooKeeper Failover Controller process cannot be confirmed to be up and listening on the network.",
+ "interval": 1,
+ "scope": "ANY",
+ "enabled": true,
+ "source": {
+ "type": "PORT",
+ "uri": "{{core-site/ha.zookeeper.quorum}}",
+ "default_port": 2181,
+ "reporting": {
+ "ok": {
+ "text": "TCP OK - {0:.3f}s response on port {1}"
+ },
+ "warning": {
+ "text": "TCP OK - {0:.3f}s response on port {1}",
+ "value": 1.5
+ },
+ "critical": {
+ "text": "Connection failed: {0} to {1}:{2}",
+ "value": 5.0
+ }
+ }
+ }
+ }
+ ]
+ }
+}
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/core-site.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/core-site.xml b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/core-site.xml
new file mode 100755
index 0000000..f833896
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/core-site.xml
@@ -0,0 +1,189 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+ <!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+ -->
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration supports_final="true" xmlns:xi="http://www.w3.org/2001/XInclude">
+
+<!-- i/o properties -->
+
+ <property>
+ <name>io.file.buffer.size</name>
+ <value>131072</value>
+ <description>The size of buffer for use in sequence files.
+ The size of this buffer should probably be a multiple of hardware
+ page size (4096 on Intel x86), and it determines how much data is
+ buffered during read and write operations.</description>
+ </property>
+
+ <property>
+ <name>io.serializations</name>
+ <value>org.apache.hadoop.io.serializer.WritableSerialization</value>
+ <description> A list of comma-delimited serialization classes that can be used for obtaining serializers and deserializers.
+ </description>
+ </property>
+
+ <property>
+ <name>io.compression.codecs</name>
+ <value>org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.SnappyCodec</value>
+ <description>A list of the compression codec classes that can be used
+ for compression/decompression.</description>
+ </property>
+
+<!-- file system properties -->
+
+ <property>
+ <name>fs.defaultFS</name>
+ <!-- cluster variant -->
+ <value>hdfs://localhost:8020</value>
+ <description>The name of the default file system. Either the
+ literal string "local" or a host:port for NDFS.</description>
+ <final>true</final>
+ </property>
+
+ <property>
+ <name>fs.trash.interval</name>
+ <value>360</value>
+ <description>Number of minutes between trash checkpoints.
+ If zero, the trash feature is disabled.
+ </description>
+ </property>
+
+ <!-- ipc properties: copied from kryptonite configuration -->
+ <property>
+ <name>ipc.client.idlethreshold</name>
+ <value>8000</value>
+ <description>Defines the threshold number of connections after which
+ connections will be inspected for idleness.
+ </description>
+ </property>
+
+ <property>
+ <name>ipc.client.connection.maxidletime</name>
+ <value>30000</value>
+ <description>The maximum time after which a client will bring down the
+ connection to the server.
+ </description>
+ </property>
+
+ <property>
+ <name>ipc.client.connect.max.retries</name>
+ <value>50</value>
+ <description>Defines the maximum number of retries for IPC connections.</description>
+ </property>
+
+ <property>
+ <name>ipc.server.tcpnodelay</name>
+ <value>true</value>
+ <description>Turn on/off Nagle's algorithm for the TCP socket
+ connection on
+ the server. Setting to true disables the algorithm and may
+ decrease latency
+ with a cost of more/smaller packets.
+ </description>
+ </property>
+
+ <!-- Web Interface Configuration -->
+ <property>
+ <name>mapreduce.jobtracker.webinterface.trusted</name>
+ <value>false</value>
+ <description> If set to true, the web interfaces of JT and NN may contain
+ actions, such as kill job, delete file, etc., that should
+ not be exposed to public. Enable this option if the interfaces
+ are only reachable by those who have the right authorization.
+ </description>
+ </property>
+
+ <property>
+ <name>hadoop.security.authentication</name>
+ <value>simple</value>
+ <description>
+ Set the authentication for the cluster. Valid values are: simple or
+ kerberos.
+ </description>
+ </property>
+<property>
+ <name>hadoop.security.authorization</name>
+ <value>false</value>
+ <description>
+ Enable authorization for different protocols.
+ </description>
+</property>
+
+ <property>
+ <name>hadoop.security.auth_to_local</name>
+ <value>
+ RULE:[2:$1@$0]([rn]m@.*)s/.*/yarn/
+ RULE:[2:$1@$0](jhs@.*)s/.*/mapred/
+ RULE:[2:$1@$0]([nd]n@.*)s/.*/hdfs/
+ RULE:[2:$1@$0](hm@.*)s/.*/hbase/
+ RULE:[2:$1@$0](rs@.*)s/.*/hbase/
+ DEFAULT
+ </value>
+<description>The mapping from kerberos principal names to local OS mapreduce.job.user.names.
+ So the default rule is just "DEFAULT" which takes all principals in your default domain to their first component.
+ "omalley@APACHE.ORG" and "omalley/admin@APACHE.ORG" to "omalley", if your default domain is APACHE.ORG.
+The translations rules have 3 sections:
+ base filter substitution
+The base consists of a number that represents the number of components in the principal name excluding the realm and the pattern for building the name from the sections of the principal name. The base uses $0 to mean the realm, $1 to mean the first component and $2 to mean the second component.
+
+[1:$1@$0] translates "omalley@APACHE.ORG" to "omalley@APACHE.ORG"
+[2:$1] translates "omalley/admin@APACHE.ORG" to "omalley"
+[2:$1%$2] translates "omalley/admin@APACHE.ORG" to "omalley%admin"
+
+The filter is a regex in parens that must the generated string for the rule to apply.
+
+"(.*%admin)" will take any string that ends in "%admin"
+"(.*@ACME.COM)" will take any string that ends in "@ACME.COM"
+
+Finally, the substitution is a sed rule to translate a regex into a fixed string.
+
+"s/@ACME\.COM//" removes the first instance of "@ACME.COM".
+"s/@[A-Z]*\.COM//" removes the first instance of "@" followed by a name followed by ".COM".
+"s/X/Y/g" replaces all of the "X" in the name with "Y"
+
+So, if your default realm was APACHE.ORG, but you also wanted to take all principals from ACME.COM that had a single component "joe@ACME.COM", you'd do:
+
+RULE:[1:$1@$0](.@ACME.ORG)s/@.//
+DEFAULT
+
+To also translate the names with a second component, you'd make the rules:
+
+RULE:[1:$1@$0](.@ACME.ORG)s/@.//
+RULE:[2:$1@$0](.@ACME.ORG)s/@.//
+DEFAULT
+
+If you want to treat all principals from APACHE.ORG with /admin as "admin", your rules would look like:
+
+RULE[2:$1%$2@$0](.%admin@APACHE.ORG)s/./admin/
+DEFAULT
+ </description>
+ <value-attributes>
+ <type>multiLine</type>
+ </value-attributes>
+ </property>
+ <property>
+ <name>net.topology.script.file.name</name>
+ <value>/etc/hadoop/conf/topology_script.py</value>
+ <description>
+ Location of topology script used by Hadoop to determine the rack location of nodes.
+ </description>
+ </property>
+</configuration>
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-env.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-env.xml b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-env.xml
new file mode 100755
index 0000000..ba575b0
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-env.xml
@@ -0,0 +1,308 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+-->
+
+<configuration>
+ <property>
+ <name>hdfs_log_dir_prefix</name>
+ <display-name>Hadoop Log Dir Prefix</display-name>
+ <value>/var/log/hadoop</value>
+ <description>Hadoop Log Dir Prefix</description>
+ <value-attributes>
+ <type>directory</type>
+ <overridable>false</overridable>
+ <editable-only-at-install>true</editable-only-at-install>
+ </value-attributes>
+ </property>
+ <property>
+ <name>hadoop_pid_dir_prefix</name>
+ <display-name>Hadoop PID Dir Prefix</display-name>
+ <value>/var/run/hadoop</value>
+ <description>Hadoop PID Dir Prefix</description>
+ <value-attributes>
+ <type>directory</type>
+ <overridable>false</overridable>
+ <editable-only-at-install>true</editable-only-at-install>
+ </value-attributes>
+ </property>
+ <property>
+ <name>hadoop_root_logger</name>
+ <value>INFO,RFA</value>
+ <description>Hadoop Root Logger</description>
+ <display-name>Hadoop Root Logger</display-name>
+ <value-attributes>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>hadoop_heapsize</name>
+ <display-name>Hadoop maximum Java heap size</display-name>
+ <value>1024</value>
+ <description>Hadoop maximum Java heap size</description>
+ <value-attributes>
+ <type>int</type>
+ <unit>MB</unit>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>namenode_heapsize</name>
+ <value>1024</value>
+ <description>NameNode Java heap size</description>
+ <display-name>NameNode Java heap size</display-name>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>268435456</maximum>
+ <unit>MB</unit>
+ <increment-step>256</increment-step>
+ </value-attributes>
+ </property>
+ <property>
+ <name>namenode_opt_newsize</name>
+ <value>200</value>
+ <description>NameNode new generation size</description>
+ <display-name>NameNode new generation size</display-name>
+ <depends-on>
+ <property>
+ <type>hadoop-env</type>
+ <name>namenode_heapsize</name>
+ </property>
+ </depends-on>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>16384</maximum>
+ <unit>MB</unit>
+ <increment-step>256</increment-step>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>namenode_opt_maxnewsize</name>
+ <value>200</value>
+ <description>NameNode maximum new generation size</description>
+ <display-name>NameNode maximum new generation size</display-name>
+ <depends-on>
+ <property>
+ <type>hadoop-env</type>
+ <name>namenode_heapsize</name>
+ </property>
+ </depends-on>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>16384</maximum>
+ <unit>MB</unit>
+ <increment-step>256</increment-step>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>namenode_opt_permsize</name>
+ <value>128</value>
+ <description>NameNode permanent generation size</description>
+ <display-name>NameNode permanent generation size</display-name>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>2096</maximum>
+ <unit>MB</unit>
+ <increment-step>128</increment-step>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>namenode_opt_maxpermsize</name>
+ <value>256</value>
+ <description>NameNode maximum permanent generation size</description>
+ <display-name>NameNode maximum permanent generation size</display-name>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>2096</maximum>
+ <unit>MB</unit>
+ <increment-step>128</increment-step>
+ <overridable>false</overridable>
+ </value-attributes>
+ </property>
+ <property>
+ <name>dtnode_heapsize</name>
+ <value>1024</value>
+ <description>DataNode maximum Java heap size</description>
+ <display-name>DataNode maximum Java heap size</display-name>
+ <value-attributes>
+ <type>int</type>
+ <minimum>0</minimum>
+ <maximum>268435456</maximum>
+ <unit>MB</unit>
+ <increment-step>128</increment-step>
+ </value-attributes>
+ </property>
+ <property>
+ <name>proxyuser_group</name>
+ <value>users</value>
+ <property-type>GROUP</property-type>
+ <description>Proxy user group.</description>
+ </property>
+ <property>
+ <name>hdfs_user</name>
+ <value>hdfs</value>
+ <property-type>USER</property-type>
+ <description>User to run HDFS as</description>
+ </property>
+ <property>
+ <name>dfs.datanode.data.dir.mount.file</name>
+ <value>/etc/hadoop/conf/dfs_data_dir_mount.hist</value>
+ <description>
+ File path that contains the last known mount point for each data dir. This
+ file is used to avoid creating a DFS data dir on the root drive (and filling it up)
+ if a path was previously mounted on a drive.
+ </description>
+ <display-name>File that stores mount point for each data dir</display-name>
+ <value-attributes>
+ <type>directory</type>
+ <visible>true</visible>
+ </value-attributes>
+ </property>
+
+ <!-- hadoop-env.sh -->
+ <property>
+ <name>content</name>
+ <description>This is the jinja template for hadoop-env.sh file</description>
+ <value>
+# Set Hadoop-specific environment variables here.
+
+# The only required environment variable is JAVA_HOME. All others are
+# optional. When running a distributed configuration it is best to
+# set JAVA_HOME in this file, so that it is correctly defined on
+# remote nodes.
+
+# The java implementation to use. Required.
+export JAVA_HOME={{java_home}}
+export HADOOP_HOME_WARN_SUPPRESS=1
+
+# Hadoop home directory
+export HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}
+
+# Hadoop Configuration Directory
+#TODO: if env var set that can cause problems
+export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-{{hadoop_conf_dir}}}
+
+{# this is different for HDP1 #}
+# Path to jsvc required by secure HDP 2.0 datanode
+export JSVC_HOME={{jsvc_path}}
+
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+export HADOOP_HEAPSIZE="{{hadoop_heapsize}}"
+
+export HADOOP_NAMENODE_INIT_HEAPSIZE="-Xms{{namenode_heapsize}}"
+
+# Extra Java runtime options. Empty by default.
+export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}"
+
+# Command specific options appended to HADOOP_OPTS when specified
+export HADOOP_NAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_NAMENODE_OPTS}"
+HADOOP_JOBTRACKER_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx{{jtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}"
+
+HADOOP_TASKTRACKER_OPTS="-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}"
+export HADOOP_DATANODE_OPTS="-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS}"
+HADOOP_BALANCER_OPTS="-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}"
+
+export HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS
+
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+export HADOOP_CLIENT_OPTS="-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS"
+# On secure datanodes, user to run the datanode as after dropping privileges
+export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}
+
+# Extra ssh options. Empty by default.
+export HADOOP_SSH_OPTS="-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR"
+
+# Where log files are stored. $HADOOP_HOME/logs by default.
+export HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER
+
+# History server logs
+export HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER
+
+# Where log files are stored in the secure data environment.
+export HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER
+
+# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.
+# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
+
+# host:path where hadoop code should be rsync'd from. Unset by default.
+# export HADOOP_MASTER=master:/home/$USER/src/hadoop
+
+# Seconds to sleep between slave commands. Unset by default. This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HADOOP_SLAVE_SLEEP=0.1
+
+# The directory where pid files are stored. /tmp by default.
+export HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER
+export HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER
+
+# History server pid
+export HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER
+
+YARN_RESOURCEMANAGER_OPTS="-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY"
+
+# A string representing this instance of hadoop. $USER by default.
+export HADOOP_IDENT_STRING=$USER
+
+# The scheduling priority for daemon processes. See 'man nice'.
+
+# export HADOOP_NICENESS=10
+
+# Use libraries from standard classpath
+JAVA_JDBC_LIBS=""
+#Add libraries required by mysql connector
+for jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`
+do
+ JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile
+done
+#Add libraries required by oracle connector
+for jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`
+do
+ JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile
+done
+#Add libraries required by nodemanager
+MAPREDUCE_LIBS={{mapreduce_libs_path}}
+export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}
+
+#if [ -d "/usr/lib/tez" ]; then
+# export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:/usr/lib/tez/*:/usr/lib/tez/lib/*:/etc/tez/conf
+#fi
+
+# Setting path to hdfs command line
+export HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}
+
+#Mostly required for hadoop 2.0
+export JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:/usr/iop/current/hadoop-client/lib/native
+
+#Hadoop logging options. Modify and uncomment to change logging level
+#export HADOOP_ROOT_LOGGER={{hadoop_root_logger}}
+ </value>
+ </property>
+
+</configuration>
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-policy.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-policy.xml b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-policy.xml
new file mode 100755
index 0000000..41bde16
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hadoop-policy.xml
@@ -0,0 +1,134 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration supports_final="true">
+ <property>
+ <name>security.client.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for ClientProtocol, which is used by user code
+ via the DistributedFileSystem.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.client.datanode.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for ClientDatanodeProtocol, the client-to-datanode protocol
+ for block recovery.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.datanode.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for DatanodeProtocol, which is used by datanodes to
+ communicate with the namenode.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.inter.datanode.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for InterDatanodeProtocol, the inter-datanode protocol
+ for updating generation timestamp.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.namenode.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for NamenodeProtocol, the protocol used by the secondary
+ namenode to communicate with the namenode.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.inter.tracker.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for InterTrackerProtocol, used by the tasktrackers to
+ communicate with the jobtracker.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.job.client.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for JobSubmissionProtocol, used by job clients to
+ communciate with the jobtracker for job submission, querying job status etc.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.job.task.protocol.acl</name>
+ <value>*</value>
+ <description>ACL for TaskUmbilicalProtocol, used by the map and reduce
+ tasks to communicate with the parent tasktracker.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.admin.operations.protocol.acl</name>
+ <value>hadoop</value>
+ <description>ACL for AdminOperationsProtocol. Used for admin commands.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+ <property>
+ <name>security.refresh.usertogroups.mappings.protocol.acl</name>
+ <value>hadoop</value>
+ <description>ACL for RefreshUserMappingsProtocol. Used to refresh
+ users mappings. The ACL is a comma-separated list of user and
+ group names. The user and group list is separated by a blank. For
+ e.g. "alice,bob users,wheel". A special value of "*" means all
+ users are allowed.</description>
+ </property>
+
+<property>
+ <name>security.refresh.policy.protocol.acl</name>
+ <value>hadoop</value>
+ <description>ACL for RefreshAuthorizationPolicyProtocol, used by the
+ dfsadmin and mradmin commands to refresh the security policy in-effect.
+ The ACL is a comma-separated list of user and group names. The user and
+ group list is separated by a blank. For e.g. "alice,bob users,wheel".
+ A special value of "*" means all users are allowed.</description>
+ </property>
+
+
+</configuration>
http://git-wip-us.apache.org/repos/asf/ambari/blob/1863c3b9/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hdfs-log4j.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hdfs-log4j.xml b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hdfs-log4j.xml
new file mode 100755
index 0000000..08822eb
--- /dev/null
+++ b/ambari-server/src/main/resources/stacks/BigInsights/4.0/services/HDFS/configuration/hdfs-log4j.xml
@@ -0,0 +1,201 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+-->
+
+<configuration supports_final="false">
+
+ <property>
+ <name>content</name>
+ <description>Custom log4j.properties</description>
+ <value>
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+
+# Define some default values that can be overridden by system properties
+# To change daemon root logger use hadoop_root_logger in hadoop-env
+hadoop.root.logger=INFO,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshhold=ALL
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.iscleanup=false
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+#Security audit appender
+#
+hadoop.security.logger=INFO,console
+hadoop.security.log.maxfilesize=256MB
+hadoop.security.log.maxbackupindex=20
+log4j.category.SecurityLogger=${hadoop.security.logger}
+hadoop.security.log.file=SecurityAuth.audit
+log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
+
+log4j.appender.RFAS=org.apache.log4j.RollingFileAppender
+log4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.RFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}
+log4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}
+
+#
+# hdfs audit logging
+#
+hdfs.audit.logger=INFO,console
+log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
+log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
+log4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
+log4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd
+
+#
+# mapred audit logging
+#
+mapred.audit.logger=INFO,console
+log4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}
+log4j.additivity.org.apache.hadoop.mapred.AuditLogger=false
+log4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log
+log4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd
+
+#
+# Rolling File Appender
+#
+
+log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+log4j.appender.RFA.MaxFileSize=256MB
+log4j.appender.RFA.MaxBackupIndex=10
+
+log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+# Custom Logging levels
+
+hadoop.metrics.log.level=INFO
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+log4j.logger.org.apache.hadoop.metrics2=${hadoop.metrics.log.level}
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+#
+# Null Appender
+# Trap security logger on the hadoop client side
+#
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
+
+# Removes "deprecated" messages
+log4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN
+ </value>
+ </property>
+
+</configuration>