diff options
Diffstat (limited to 'templates/app/hadoop_http/template_app_hadoop_http.yaml')
| -rw-r--r-- | templates/app/hadoop_http/template_app_hadoop_http.yaml | 85 |
1 files changed, 84 insertions, 1 deletions
diff --git a/templates/app/hadoop_http/template_app_hadoop_http.yaml b/templates/app/hadoop_http/template_app_hadoop_http.yaml index 5d02c82b2f9..d732450d099 100644 --- a/templates/app/hadoop_http/template_app_hadoop_http.yaml +++ b/templates/app/hadoop_http/template_app_hadoop_http.yaml @@ -1,11 +1,13 @@ zabbix_export: version: '5.4' - date: '2021-05-09T00:00:00Z' + date: '2021-05-10T19:41:40Z' groups: - + uuid: a571c0d144b14fd4a87a9d9b2aa9fcd6 name: Templates/Applications templates: - + uuid: e129aeba7c814bf189772cf5919b4bbb template: 'Hadoop by HTTP' name: 'Hadoop by HTTP' description: | @@ -19,6 +21,7 @@ zabbix_export: name: Templates/Applications items: - + uuid: d2d19ac9d1eb434c98a55cbf76c27850 name: 'Get DataNodes states' type: HTTP_AGENT key: hadoop.datanodes.get @@ -61,6 +64,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: 2cb55b7ed9cd41878dc985497f45e084 name: 'NameNode: Total blocks' type: DEPENDENT key: hadoop.namenode.blocks_total @@ -79,6 +83,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 1d098dc6fa134053b6c6be0e7618092e name: 'NameNode: Blocks allocable' type: DEPENDENT key: hadoop.namenode.block_capacity @@ -97,6 +102,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 26ca0bbd18e04b49b9eb8d2a74f4fd15 name: 'NameNode: Capacity remaining' type: DEPENDENT key: hadoop.namenode.capacity_remaining @@ -116,6 +122,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: c73c2b6c24b846e49bdb68c3f5a01419 name: 'NameNode: Corrupt blocks' type: DEPENDENT key: hadoop.namenode.corrupt_blocks @@ -134,6 +141,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 82198b21427a4e39a173369db42d9de3 name: 'NameNode: Total files' type: DEPENDENT key: hadoop.namenode.files_total @@ -152,6 +160,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 687406d06ce94a8291b2e72bb2f8bec4 name: 'Get NameNode stats' type: HTTP_AGENT key: hadoop.namenode.get @@ -164,6 +173,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: 30ee7e09067e4f00a4f26ad6c00454b2 name: 'NameNode: Missing blocks' type: DEPENDENT key: hadoop.namenode.missing_blocks @@ -183,11 +193,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: f462d6bb12104a058161918f18b97bb2 expression: 'min(/Hadoop by HTTP/hadoop.namenode.missing_blocks,15m)>0' name: 'NameNode: Cluster has missing blocks' priority: AVERAGE description: 'A missing block is far worse than a corrupt block, because a missing block cannot be recovered by copying a replica.' - + uuid: 3473bad0a7c94c8b9fd35cd4398e6215 name: 'NameNode: Dead DataNodes' type: DEPENDENT key: hadoop.namenode.num_dead_data_nodes @@ -211,11 +223,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: d13c06cca55345269ccce63de5bf94ca expression: 'min(/Hadoop by HTTP/hadoop.namenode.num_dead_data_nodes,5m)>0' name: 'NameNode: Cluster has DataNodes in Dead state' priority: AVERAGE description: 'The death of a DataNode causes a flurry of network activity, as the NameNode initiates replication of blocks lost on the dead nodes.' - + uuid: 398a8c95db3248b684f222fe7b912fe3 name: 'NameNode: Alive DataNodes' type: DEPENDENT key: hadoop.namenode.num_live_data_nodes @@ -238,6 +252,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 15bcb22fdc7f4e2c8f24560ef641d63d name: 'NameNode: Stale DataNodes' type: DEPENDENT key: hadoop.namenode.num_stale_data_nodes @@ -260,6 +275,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: b72d54b849fc48fd8e7cdacd75943c23 name: 'NameNode: Block Pool Renaming' type: DEPENDENT key: hadoop.namenode.percent_block_pool_used @@ -278,6 +294,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 3cfbf084a31b479c91be356556d43c0d name: 'NameNode: Percent capacity remaining' type: DEPENDENT key: hadoop.namenode.percent_remaining @@ -303,11 +320,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: cc5850af8c6a4a0d9c89384eee9042c4 expression: 'max(/Hadoop by HTTP/hadoop.namenode.percent_remaining,15m)<{$HADOOP.CAPACITY_REMAINING.MIN.WARN}' name: 'NameNode: Cluster capacity remaining is low (below {$HADOOP.CAPACITY_REMAINING.MIN.WARN}% for 15m)' priority: WARNING description: 'A good practice is to ensure that disk use never exceeds 80 percent capacity.' - + uuid: a9e6c1e2f9544c71844785b4baa9c017 name: 'NameNode: RPC queue & processing time' type: DEPENDENT key: hadoop.namenode.rpc_processing_time_avg @@ -328,6 +347,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 9f00149ef0c2444ebbc9327b24acd7b9 name: 'NameNode: Total load' type: DEPENDENT key: hadoop.namenode.total_load @@ -346,6 +366,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 6abfe537a36646a0b10fe2c72586d249 name: 'NameNode: Transactions since last checkpoint' type: DEPENDENT key: hadoop.namenode.transactions_since_last_checkpoint @@ -364,6 +385,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 249098bbeb7a43cdac59f1297ca95104 name: 'NameNode: Under-replicated blocks' type: DEPENDENT key: hadoop.namenode.under_replicated_blocks @@ -382,6 +404,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 7e8769eb77304b6f9c6e1d5bbd420fd0 name: 'NameNode: Uptime' type: DEPENDENT key: hadoop.namenode.uptime @@ -406,6 +429,7 @@ zabbix_export: value: Hadoop triggers: - + uuid: be86e5a923f648b6b9e10cc8f8d6b7fd expression: 'nodata(/Hadoop by HTTP/hadoop.namenode.uptime,30m)=1' name: 'NameNode: Failed to fetch NameNode API page (or no data for 30m)' priority: WARNING @@ -416,12 +440,14 @@ zabbix_export: name: 'NameNode: Service is unavailable' expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"])=0' - + uuid: 84d866bc0dc3486d9c5dc9beefec8d31 expression: 'last(/Hadoop by HTTP/hadoop.namenode.uptime)<10m' name: 'NameNode: Service has been restarted (uptime < 10m)' priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' - + uuid: 396eb8f791d54254b08ddee553d3d944 name: 'NameNode: Failed volumes' type: DEPENDENT key: hadoop.namenode.volume_failures_total @@ -441,11 +467,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: 947ceff67480477eaf8ebc1d958a4bf3 expression: 'min(/Hadoop by HTTP/hadoop.namenode.volume_failures_total,15m)>0' name: 'NameNode: Cluster has volume failures' priority: AVERAGE description: 'HDFS now allows for disks to fail in place, without affecting DataNode operations, until a threshold value is reached. This is set on each DataNode via the dfs.datanode.failed.volumes.tolerated property; it defaults to 0, meaning that any volume failure will shut down the DataNode; on a production cluster where DataNodes typically have 6, 8, or 12 disks, setting this parameter to 1 or 2 is typically the best practice.' - + uuid: 6d7546c5d15d4e478b2e87e35d5306b0 name: 'Get NodeManagers states' type: HTTP_AGENT key: hadoop.nodemanagers.get @@ -463,6 +491,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: e693cff98ec74cc198ec6b5e973f116c name: 'Get ResourceManager stats' type: HTTP_AGENT key: hadoop.resourcemanager.get @@ -475,6 +504,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: 63d4fe7384044027b08b99698355fd8b name: 'ResourceManager: Active NMs' type: DEPENDENT key: hadoop.resourcemanager.num_active_nm @@ -498,11 +528,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: 27043b687b5e41c78e95a313414b3022 expression: 'max(/Hadoop by HTTP/hadoop.resourcemanager.num_active_nm,5m)=0' name: 'ResourceManager: Cluster has no active NodeManagers' priority: HIGH description: 'Cluster is unable to execute any jobs without at least one NodeManager.' - + uuid: 3fccfdd8738544ca8969ade842430fc8 name: 'ResourceManager: Decommissioned NMs' type: DEPENDENT key: hadoop.resourcemanager.num_decommissioned_nm @@ -521,6 +553,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 9aad193a9e074575878e44aa96ff4237 name: 'ResourceManager: Decommissioning NMs' type: DEPENDENT key: hadoop.resourcemanager.num_decommissioning_nm @@ -543,6 +576,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: c4bbf5295b2a44619e2b641468071f9b name: 'ResourceManager: Lost NMs' type: DEPENDENT key: hadoop.resourcemanager.num_lost_nm @@ -565,6 +599,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: b7791ce30e8f4aa7b5eea2ee7ca7eef9 name: 'ResourceManager: Rebooted NMs' type: DEPENDENT key: hadoop.resourcemanager.num_rebooted_nm @@ -583,6 +618,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 666152b3bf544a29b9e58a9f417c0ab8 name: 'ResourceManager: Shutdown NMs' type: DEPENDENT key: hadoop.resourcemanager.num_shutdown_nm @@ -601,6 +637,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: e6aa4b4b29414f2fb1f06bd536552c1c name: 'ResourceManager: Unhealthy NMs' type: DEPENDENT key: hadoop.resourcemanager.num_unhealthy_nm @@ -620,11 +657,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: f2bacdf44c6c4ab78557b65d8c9a2b6a expression: 'min(/Hadoop by HTTP/hadoop.resourcemanager.num_unhealthy_nm,15m)>0' name: 'ResourceManager: Cluster has unhealthy NodeManagers' priority: AVERAGE description: 'YARN considers any node with disk utilization exceeding the value specified under the property yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage (in yarn-site.xml) to be unhealthy. Ample disk space is critical to ensure uninterrupted operation of a Hadoop cluster, and large numbers of unhealthyNodes (the number to alert on depends on the size of your cluster) should be quickly investigated and resolved.' - + uuid: c4c3195326e34ebcb57e5039beffce7c name: 'ResourceManager: RPC queue & processing time' type: DEPENDENT key: hadoop.resourcemanager.rpc_processing_time_avg @@ -645,6 +684,7 @@ zabbix_export: tag: Application value: Hadoop - + uuid: 4e74ca69a84d441e95e2c20afd25fada name: 'ResourceManager: Uptime' type: DEPENDENT key: hadoop.resourcemanager.uptime @@ -669,6 +709,7 @@ zabbix_export: value: Hadoop triggers: - + uuid: a9a1b10830bf4e5fa34c81e040cceca9 expression: 'nodata(/Hadoop by HTTP/hadoop.resourcemanager.uptime,30m)=1' name: 'ResourceManager: Failed to fetch ResourceManager API page (or no data for 30m)' priority: WARNING @@ -679,12 +720,14 @@ zabbix_export: name: 'ResourceManager: Service is unavailable' expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"])=0' - + uuid: ade7cc30a4184ef89ed896bae56e0b18 expression: 'last(/Hadoop by HTTP/hadoop.resourcemanager.uptime)<10m' name: 'ResourceManager: Service has been restarted (uptime < 10m)' priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' - + uuid: 66a87b21d32c436bb2d2eb23ec328f91 name: 'NameNode: Service response time' type: SIMPLE key: 'net.tcp.service.perf["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"]' @@ -698,6 +741,7 @@ zabbix_export: value: Hadoop triggers: - + uuid: 5c54acfc4c2447bf98e75ff77b20f0b5 expression: 'min(/Hadoop by HTTP/net.tcp.service.perf["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"],5m)>{$HADOOP.NAMENODE.RESPONSE_TIME.MAX.WARN}' name: 'NameNode: Service response time is too high (over {$HADOOP.NAMENODE.RESPONSE_TIME.MAX.WARN} for 5m)' priority: WARNING @@ -707,6 +751,7 @@ zabbix_export: name: 'NameNode: Service is unavailable' expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"])=0' - + uuid: 98b11f1156dc472fbce27ca053e01d4e name: 'ResourceManager: Service response time' type: SIMPLE key: 'net.tcp.service.perf["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"]' @@ -720,6 +765,7 @@ zabbix_export: value: Hadoop triggers: - + uuid: 6b445006a38945a5a5ca6d1a9024a5fc expression: 'min(/Hadoop by HTTP/net.tcp.service.perf["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"],5m)>{$HADOOP.RESOURCEMANAGER.RESPONSE_TIME.MAX.WARN}' name: 'ResourceManager: Service response time is too high (over {$HADOOP.RESOURCEMANAGER.RESPONSE_TIME.MAX.WARN} for 5m)' priority: WARNING @@ -729,6 +775,7 @@ zabbix_export: name: 'ResourceManager: Service is unavailable' expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"])=0' - + uuid: 2c52d856e07e4524abf3c2ae4b47c6b6 name: 'NameNode: Service status' type: SIMPLE key: 'net.tcp.service["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"]' @@ -747,11 +794,13 @@ zabbix_export: value: Hadoop triggers: - + uuid: f7e16c4ec91e4c04b13b73ee817c71d7 expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.NAMENODE.HOST}","{$HADOOP.NAMENODE.PORT}"])=0' name: 'NameNode: Service is unavailable' priority: AVERAGE manual_close: 'YES' - + uuid: 615b75c42ebe471da798a0613667d499 name: 'ResourceManager: Service status' type: SIMPLE key: 'net.tcp.service["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"]' @@ -770,18 +819,21 @@ zabbix_export: value: Hadoop triggers: - + uuid: a9ac7ede0c004fe18ab9f1fee36ad2b2 expression: 'last(/Hadoop by HTTP/net.tcp.service["tcp","{$HADOOP.RESOURCEMANAGER.HOST}","{$HADOOP.RESOURCEMANAGER.PORT}"])=0' name: 'ResourceManager: Service is unavailable' priority: AVERAGE manual_close: 'YES' discovery_rules: - + uuid: 0f05e90a6fc547d18f291ae2264db9d1 name: 'Data node discovery' type: HTTP_AGENT key: hadoop.datanode.discovery delay: 1h item_prototypes: - + uuid: ef570f8b37c545bd880b7df20bd19f06 name: '{#HOSTNAME}: Admin state' type: DEPENDENT key: 'hadoop.datanode.admin_state[{#HOSTNAME}]' @@ -806,6 +858,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: 14904ca75991456784d2082c14b7ec88 name: '{#HOSTNAME}: Used' type: DEPENDENT key: 'hadoop.datanode.dfs_used[{#HOSTNAME}]' @@ -825,6 +878,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: 6d2d030b3ddb41a394faede737329bbb name: 'Hadoop DataNode {#HOSTNAME}: Get stats' type: HTTP_AGENT key: 'hadoop.datanode.get[{#HOSTNAME}]' @@ -837,6 +891,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: 01bc20e53e314089a55b270961062c00 name: '{#HOSTNAME}: JVM Garbage collection time' type: DEPENDENT key: 'hadoop.datanode.jvm.gc_time[{#HOSTNAME}]' @@ -856,6 +911,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: 4cae9eef95f24810a6607de5348b7b54 name: '{#HOSTNAME}: JVM Heap usage' type: DEPENDENT key: 'hadoop.datanode.jvm.mem_heap_used[{#HOSTNAME}]' @@ -876,6 +932,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: dc30742dba2e4e5d99ca237615ffaef3 name: '{#HOSTNAME}: JVM Threads' type: DEPENDENT key: 'hadoop.datanode.jvm.threads[{#HOSTNAME}]' @@ -894,6 +951,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: 57c00b46aef94c018806cdae43adfab5 name: '{#HOSTNAME}: Number of failed volumes' type: DEPENDENT key: 'hadoop.datanode.numfailedvolumes[{#HOSTNAME}]' @@ -912,6 +970,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: a6541492d4f7426b8016d1a8932b87ce name: '{#HOSTNAME}: Oper state' type: DEPENDENT key: 'hadoop.datanode.oper_state[{#HOSTNAME}]' @@ -937,11 +996,13 @@ zabbix_export: value: 'Hadoop DataNode {#HOSTNAME}' trigger_prototypes: - + uuid: 9f657289a04041e5bcaa1947f62f607d expression: 'last(/Hadoop by HTTP/hadoop.datanode.oper_state[{#HOSTNAME}])<>"Live"' name: '{#HOSTNAME}: DataNode has state {ITEM.VALUE}.' priority: AVERAGE description: 'The state is different from normal.' - + uuid: 5a46ec3c89eb40d4ad57cec2080c66f8 name: '{#HOSTNAME}: Remaining' type: DEPENDENT key: 'hadoop.datanode.remaining[{#HOSTNAME}]' @@ -961,6 +1022,7 @@ zabbix_export: tag: Application value: 'Hadoop DataNode {#HOSTNAME}' - + uuid: 2ac19ff8ee7f480f9974be56ab06eaaf name: '{#HOSTNAME}: Uptime' type: DEPENDENT key: 'hadoop.datanode.uptime[{#HOSTNAME}]' @@ -985,6 +1047,7 @@ zabbix_export: value: 'Hadoop DataNode {#HOSTNAME}' trigger_prototypes: - + uuid: 19762d7bc50e4de291e821c82d2250b2 expression: 'nodata(/Hadoop by HTTP/hadoop.datanode.uptime[{#HOSTNAME}],30m)=1' name: '{#HOSTNAME}: Failed to fetch DataNode API page (or no data for 30m)' priority: WARNING @@ -995,12 +1058,14 @@ zabbix_export: name: '{#HOSTNAME}: DataNode has state {ITEM.VALUE}.' expression: 'last(/Hadoop by HTTP/hadoop.datanode.oper_state[{#HOSTNAME}])<>"Live"' - + uuid: e40298d300764251abcf93d5df3d9a67 expression: 'last(/Hadoop by HTTP/hadoop.datanode.uptime[{#HOSTNAME}])<10m' name: '{#HOSTNAME}: Service has been restarted (uptime < 10m)' priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' - + uuid: 62b4ca9b1e8a43aa89fbeb78ac16c8cf name: '{#HOSTNAME}: Version' type: DEPENDENT key: 'hadoop.datanode.version[{#HOSTNAME}]' @@ -1026,6 +1091,7 @@ zabbix_export: value: 'Hadoop DataNode {#HOSTNAME}' graph_prototypes: - + uuid: c497416bcce1416ebcede7fc491ccdba name: '{#HOSTNAME}: DataNode {#HOSTNAME} DFS size' type: STACKED graph_items: @@ -1072,12 +1138,14 @@ zabbix_export: throw 'Failed to process response received from Hadoop.'; } - + uuid: de2d5f97843345668bc0b8c8336b9c14 name: 'Node manager discovery' type: HTTP_AGENT key: hadoop.nodemanager.discovery delay: 1h item_prototypes: - + uuid: ffa4704e099a4f1a8b49add245938501 name: '{#HOSTNAME}: Available memory' type: DEPENDENT key: 'hadoop.nodemanager.availablememory[{#HOSTNAME}]' @@ -1096,6 +1164,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: e8d0ea2c96b643f899e370ab73c5c262 name: '{#HOSTNAME}: Container launch avg duration' type: DEPENDENT key: 'hadoop.nodemanager.container_launch_duration_avg[{#HOSTNAME}]' @@ -1114,6 +1183,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: 23c89dfb26a34b77bf34fcf543f719f2 name: 'Hadoop NodeManager {#HOSTNAME}: Get stats' type: HTTP_AGENT key: 'hadoop.nodemanager.get[{#HOSTNAME}]' @@ -1126,6 +1196,7 @@ zabbix_export: tag: Application value: 'Zabbix raw items' - + uuid: 82e289c999a246a6bd1feb85349d0348 name: '{#HOSTNAME}: JVM Garbage collection time' type: DEPENDENT key: 'hadoop.nodemanager.jvm.gc_time[{#HOSTNAME}]' @@ -1145,6 +1216,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: 4032f0a266c44b34896e8179bbed2419 name: '{#HOSTNAME}: JVM Heap usage' type: DEPENDENT key: 'hadoop.nodemanager.jvm.mem_heap_used[{#HOSTNAME}]' @@ -1165,6 +1237,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: d7485913b2db4e31a8f02f63f8c18913 name: '{#HOSTNAME}: JVM Threads' type: DEPENDENT key: 'hadoop.nodemanager.jvm.threads[{#HOSTNAME}]' @@ -1183,6 +1256,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: 662cafd31e194db8808c75789bf712eb name: '{#HOSTNAME}: Number of containers' type: DEPENDENT key: 'hadoop.nodemanager.numcontainers[{#HOSTNAME}]' @@ -1202,6 +1276,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: 01a5bcdbfc1c4a84a471738998aed372 name: '{#HOSTNAME}: RPC queue & processing time' type: DEPENDENT key: 'hadoop.nodemanager.rpc_processing_time_avg[{#HOSTNAME}]' @@ -1221,6 +1296,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: bab9c705d31e42ce9af65b396e18504b name: '{#HOSTNAME}: State' type: DEPENDENT key: 'hadoop.nodemanager.state[{#HOSTNAME}]' @@ -1246,11 +1322,13 @@ zabbix_export: value: 'Hadoop NodeManager {#HOSTNAME}' trigger_prototypes: - + uuid: 8752a292093347fcb16d3f06dd97c5c3 expression: 'last(/Hadoop by HTTP/hadoop.nodemanager.state[{#HOSTNAME}])<>"RUNNING"' name: '{#HOSTNAME}: NodeManager has state {ITEM.VALUE}.' priority: AVERAGE description: 'The state is different from normal.' - + uuid: f8f6799130d34848a7dfb65815939c48 name: '{#HOSTNAME}: Uptime' type: DEPENDENT key: 'hadoop.nodemanager.uptime[{#HOSTNAME}]' @@ -1275,6 +1353,7 @@ zabbix_export: value: 'Hadoop NodeManager {#HOSTNAME}' trigger_prototypes: - + uuid: 78114571ad4647d3ae52ac99b625ef02 expression: 'nodata(/Hadoop by HTTP/hadoop.nodemanager.uptime[{#HOSTNAME}],30m)=1' name: '{#HOSTNAME}: Failed to fetch NodeManager API page (or no data for 30m)' priority: WARNING @@ -1285,12 +1364,14 @@ zabbix_export: name: '{#HOSTNAME}: NodeManager has state {ITEM.VALUE}.' expression: 'last(/Hadoop by HTTP/hadoop.nodemanager.state[{#HOSTNAME}])<>"RUNNING"' - + uuid: 05f3cf8ed34f4a708df508f0e50e119d expression: 'last(/Hadoop by HTTP/hadoop.nodemanager.uptime[{#HOSTNAME}])<10m' name: '{#HOSTNAME}: Service has been restarted (uptime < 10m)' priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' - + uuid: d92b66e61a5244a995693ab8aedee96e name: '{#HOSTNAME}: Used memory' type: DEPENDENT key: 'hadoop.nodemanager.usedmemory[{#HOSTNAME}]' @@ -1309,6 +1390,7 @@ zabbix_export: tag: Application value: 'Hadoop NodeManager {#HOSTNAME}' - + uuid: c4d46de2d6d341f5a2c1826236f94e5e name: '{#HOSTNAME}: Version' type: DEPENDENT key: 'hadoop.nodemanager.version[{#HOSTNAME}]' @@ -1388,6 +1470,7 @@ zabbix_export: description: 'The Hadoop ResourceManager API page maximum response time in seconds for trigger expression.' valuemaps: - + uuid: 6c967c4df18d4c7ebb0fd4be17df292a name: 'Service state' mappings: - |