summaryrefslogtreecommitdiffstats
path: root/src/go/collectors/go.d.plugin/modules/hdfs/metadata.yaml
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--src/go/collectors/go.d.plugin/modules/hdfs/metadata.yaml388
1 files changed, 388 insertions, 0 deletions
diff --git a/src/go/collectors/go.d.plugin/modules/hdfs/metadata.yaml b/src/go/collectors/go.d.plugin/modules/hdfs/metadata.yaml
new file mode 100644
index 000000000..694868e01
--- /dev/null
+++ b/src/go/collectors/go.d.plugin/modules/hdfs/metadata.yaml
@@ -0,0 +1,388 @@
+plugin_name: go.d.plugin
+modules:
+ - meta:
+ id: collector-go.d.plugin-hfs
+ plugin_name: go.d.plugin
+ module_name: hfs
+ monitored_instance:
+ name: Hadoop Distributed File System (HDFS)
+ link: https://hadoop.apache.org/docs/r1.2.1/hdfs_design.html
+ icon_filename: hadoop.svg
+ categories:
+ - data-collection.storage-mount-points-and-filesystems
+ keywords:
+ - hdfs
+ - hadoop
+ related_resources:
+ integrations:
+ list: []
+ info_provided_to_referring_integrations:
+ description: ""
+ most_popular: true
+ overview:
+ data_collection:
+ metrics_description: |
+ This collector monitors HDFS nodes.
+
+ Netdata accesses HDFS metrics over `Java Management Extensions` (JMX) through the web interface of an HDFS daemon.
+ method_description: ""
+ supported_platforms:
+ include: []
+ exclude: []
+ multi_instance: true
+ additional_permissions:
+ description: ""
+ default_behavior:
+ auto_detection:
+ description: ""
+ limits:
+ description: ""
+ performance_impact:
+ description: ""
+ setup:
+ prerequisites:
+ list: []
+ configuration:
+ file:
+ name: go.d/hdfs.conf
+ options:
+ description: |
+ The following options can be defined globally: update_every, autodetection_retry.
+ folding:
+ title: Config options
+ enabled: true
+ list:
+ - name: update_every
+ description: Data collection frequency.
+ default_value: 1
+ required: false
+ - name: autodetection_retry
+ description: Recheck interval in seconds. Zero means no recheck will be scheduled.
+ default_value: 0
+ required: false
+ - name: url
+ description: Server URL.
+ default_value: http://127.0.0.1:9870/jmx
+ required: true
+ - name: timeout
+ description: HTTP request timeout.
+ default_value: 1
+ required: false
+ - name: username
+ description: Username for basic HTTP authentication.
+ default_value: ""
+ required: false
+ - name: password
+ description: Password for basic HTTP authentication.
+ default_value: ""
+ required: false
+ - name: proxy_url
+ description: Proxy URL.
+ default_value: ""
+ required: false
+ - name: proxy_username
+ description: Username for proxy basic HTTP authentication.
+ default_value: ""
+ required: false
+ - name: proxy_password
+ description: Password for proxy basic HTTP authentication.
+ default_value: ""
+ required: false
+ - name: method
+ description: HTTP request method.
+ default_value: "GET"
+ required: false
+ - name: body
+ description: HTTP request body.
+ default_value: ""
+ required: false
+ - name: headers
+ description: HTTP request headers.
+ default_value: ""
+ required: false
+ - name: not_follow_redirects
+ description: Redirect handling policy. Controls whether the client follows redirects.
+ default_value: no
+ required: false
+ - name: tls_skip_verify
+ description: Server certificate chain and hostname validation policy. Controls whether the client performs this check.
+ default_value: no
+ required: false
+ - name: tls_ca
+ description: Certification authority that the client uses when verifying the server's certificates.
+ default_value: ""
+ required: false
+ - name: tls_cert
+ description: Client TLS certificate.
+ default_value: ""
+ required: false
+ - name: tls_key
+ description: Client TLS key.
+ default_value: ""
+ required: false
+ examples:
+ folding:
+ title: Config
+ enabled: true
+ list:
+ - name: Basic
+ folding:
+ enabled: false
+ description: A basic example configuration.
+ config: |
+ jobs:
+ - name: local
+ url: http://127.0.0.1:9870/jmx
+ - name: HTTP authentication
+ description: Basic HTTP authentication.
+ config: |
+ jobs:
+ - name: local
+ url: http://127.0.0.1:9870/jmx
+ username: username
+ password: password
+ - name: HTTPS with self-signed certificate
+ description: |
+ Do not validate server certificate chain and hostname.
+ config: |
+ jobs:
+ - name: local
+ url: https://127.0.0.1:9870/jmx
+ tls_skip_verify: yes
+ - name: Multi-instance
+ description: |
+ > **Note**: When you define multiple jobs, their names must be unique.
+
+ Collecting metrics from local and remote instances.
+ config: |
+ jobs:
+ - name: local
+ url: http://127.0.0.1:9870/jmx
+
+ - name: remote
+ url: http://192.0.2.1:9870/jmx
+ troubleshooting:
+ problems:
+ list: []
+ alerts:
+ - name: hdfs_capacity_usage
+ metric: hdfs.capacity
+ info: summary datanodes space capacity utilization
+ link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf
+ - name: hdfs_missing_blocks
+ metric: hdfs.blocks
+ info: number of missing blocks
+ link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf
+ - name: hdfs_stale_nodes
+ metric: hdfs.data_nodes
+ info: number of datanodes marked stale due to delayed heartbeat
+ link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf
+ - name: hdfs_dead_nodes
+ metric: hdfs.data_nodes
+ info: number of datanodes which are currently dead
+ link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf
+ - name: hdfs_num_failed_volumes
+ metric: hdfs.num_failed_volumes
+ info: number of failed volumes
+ link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf
+ metrics:
+ folding:
+ title: Metrics
+ enabled: false
+ description: ""
+ availability:
+ - DataNode
+ - NameNode
+ scopes:
+ - name: global
+ description: These metrics refer to the entire monitored application.
+ labels: []
+ metrics:
+ - name: hdfs.heap_memory
+ description: Heap Memory
+ unit: MiB
+ chart_type: area
+ dimensions:
+ - name: committed
+ - name: used
+ - name: hdfs.gc_count_total
+ description: GC Events
+ unit: events/s
+ chart_type: line
+ dimensions:
+ - name: gc
+ - name: hdfs.gc_time_total
+ description: GC Time
+ unit: ms
+ chart_type: line
+ dimensions:
+ - name: ms
+ - name: hdfs.gc_threshold
+ description: Number of Times That the GC Threshold is Exceeded
+ unit: events/s
+ chart_type: line
+ dimensions:
+ - name: info
+ - name: warn
+ - name: hdfs.threads
+ description: Number of Threads
+ unit: num
+ chart_type: stacked
+ dimensions:
+ - name: new
+ - name: runnable
+ - name: blocked
+ - name: waiting
+ - name: timed_waiting
+ - name: terminated
+ - name: hdfs.logs_total
+ description: Number of Logs
+ unit: logs/s
+ chart_type: stacked
+ dimensions:
+ - name: info
+ - name: error
+ - name: warn
+ - name: fatal
+ - name: hdfs.rpc_bandwidth
+ description: RPC Bandwidth
+ unit: kilobits/s
+ chart_type: area
+ dimensions:
+ - name: received
+ - name: sent
+ - name: hdfs.rpc_calls
+ description: RPC Calls
+ unit: calls/s
+ chart_type: line
+ dimensions:
+ - name: calls
+ - name: hdfs.open_connections
+ description: RPC Open Connections
+ unit: connections
+ chart_type: line
+ dimensions:
+ - name: open
+ - name: hdfs.call_queue_length
+ description: RPC Call Queue Length
+ unit: num
+ chart_type: line
+ dimensions:
+ - name: length
+ - name: hdfs.avg_queue_time
+ description: RPC Avg Queue Time
+ unit: ms
+ chart_type: line
+ dimensions:
+ - name: time
+ - name: hdfs.avg_processing_time
+ description: RPC Avg Processing Time
+ unit: ms
+ chart_type: line
+ dimensions:
+ - name: time
+ - name: hdfs.capacity
+ description: Capacity Across All Datanodes
+ unit: KiB
+ chart_type: stacked
+ availability:
+ - NameNode
+ dimensions:
+ - name: remaining
+ - name: used
+ - name: hdfs.used_capacity
+ description: Used Capacity Across All Datanodes
+ unit: KiB
+ chart_type: stacked
+ availability:
+ - NameNode
+ dimensions:
+ - name: dfs
+ - name: non_dfs
+ - name: hdfs.load
+ description: Number of Concurrent File Accesses (read/write) Across All DataNodes
+ unit: load
+ chart_type: line
+ availability:
+ - NameNode
+ dimensions:
+ - name: load
+ - name: hdfs.volume_failures_total
+ description: Number of Volume Failures Across All Datanodes
+ unit: events/s
+ chart_type: line
+ availability:
+ - NameNode
+ dimensions:
+ - name: failures
+ - name: hdfs.files_total
+ description: Number of Tracked Files
+ unit: num
+ chart_type: line
+ availability:
+ - NameNode
+ dimensions:
+ - name: files
+ - name: hdfs.blocks_total
+ description: Number of Allocated Blocks in the System
+ unit: num
+ chart_type: line
+ availability:
+ - NameNode
+ dimensions:
+ - name: blocks
+ - name: hdfs.blocks
+ description: Number of Problem Blocks (can point to an unhealthy cluster)
+ unit: num
+ chart_type: line
+ availability:
+ - NameNode
+ dimensions:
+ - name: corrupt
+ - name: missing
+ - name: under_replicated
+ - name: hdfs.data_nodes
+ description: Number of Data Nodes By Status
+ unit: num
+ chart_type: stacked
+ availability:
+ - NameNode
+ dimensions:
+ - name: live
+ - name: dead
+ - name: stale
+ - name: hdfs.datanode_capacity
+ description: Capacity
+ unit: KiB
+ chart_type: stacked
+ availability:
+ - DataNode
+ dimensions:
+ - name: remaining
+ - name: used
+ - name: hdfs.datanode_used_capacity
+ description: Used Capacity
+ unit: KiB
+ chart_type: stacked
+ availability:
+ - DataNode
+ dimensions:
+ - name: dfs
+ - name: non_dfs
+ - name: hdfs.datanode_failed_volumes
+ description: Number of Failed Volumes
+ unit: num
+ chart_type: line
+ availability:
+ - DataNode
+ dimensions:
+ - name: failed volumes
+ - name: hdfs.datanode_bandwidth
+ description: Bandwidth
+ unit: KiB/s
+ chart_type: area
+ availability:
+ - DataNode
+ dimensions:
+ - name: reads
+ - name: writes
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-17 00:24:00 +0000