Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ADHL-425: add Datanode Volume Failures alert #190

Open
wants to merge 2 commits into
base: branch-adh-1.6
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 49 additions & 3 deletions ambari-server/src/main/resources/stacks/ADH/1.0/services/HDFS/alerts.json
100755 → 100644
Original file line number Diff line number Diff line change
Expand Up @@ -213,7 +213,7 @@
"warning": {
"text": "Total Blocks:[{1}], Missing Blocks:[{0}]",
"value": 1
},
},
"critical": {
"text": "Total Blocks:[{1}], Missing Blocks:[{0}]",
"value": 1
Expand Down Expand Up @@ -275,6 +275,52 @@
}
}
},
{
"name": "namenode_hdfs_volume_failures",
"label": "Datanode Volume Failures",
"description": "This service-level alert is triggered if the number of volume failures exceeds the configured critical threshold. The threshold values are in volumes.",
"interval": 2,
"scope": "ANY",
"enabled": true,
"source": {
"type": "METRIC",
"uri": {
"http": "{{hdfs-site/dfs.namenode.http-address}}",
"https": "{{hdfs-site/dfs.namenode.https-address}}",
"kerberos_keytab": "{{hdfs-site/dfs.web.authentication.kerberos.keytab}}",
"kerberos_principal": "{{hdfs-site/dfs.web.authentication.kerberos.principal}}",
"https_property": "{{hdfs-site/dfs.http.policy}}",
"https_property_value": "HTTPS_ONLY",
"connection_timeout": 5.0,
"high_availability": {
"nameservice": "{{hdfs-site/dfs.internal.nameservices}}",
"alias_key" : "{{hdfs-site/dfs.ha.namenodes.{{ha-nameservice}}}}",
"http_pattern" : "{{hdfs-site/dfs.namenode.http-address.{{ha-nameservice}}.{{alias}}}}",
"https_pattern" : "{{hdfs-site/dfs.namenode.https-address.{{ha-nameservice}}.{{alias}}}}"
}
},
"reporting": {
"ok": {
"text": "Failed Volumes:[{0}]"
},
"warning": {
"text": "Failed Volumes:[{0}]",
"value": 1
},
"critical": {
"text": "Failed Volumes:[{0}]",
"value": 1
},
"units" : "Volumes"
},
"jmx": {
"property_list": [
"Hadoop:service=NameNode,name=FSNamesystem/VolumeFailuresTotal"
],
"value": "{0}"
}
}
},
{
"name": "namenode_hdfs_capacity_utilization",
"label": "HDFS Capacity Utilization",
Expand Down Expand Up @@ -354,7 +400,7 @@
"warning": {
"text": "Average Queue Time:[{0}], Average Processing Time:[{1}]",
"value": 3000
},
},
"critical": {
"text": "Average Queue Time:[{0}], Average Processing Time:[{1}]",
"value": 5000
Expand Down Expand Up @@ -1598,7 +1644,7 @@
}
}
}
],
],
"DATANODE": [
{
"name": "datanode_process",
Expand Down
Empty file.