DLPX-96312 Sending all data to influxDB now

Author: dbshah12

influxdb/delphix-influxdb-init

@@ -184,7 +184,6 @@ cat >"$INFLUXDB_OUTPUT" <<EOF
   token = "$WRITE_TOKEN"
   organization = "$INFLUXDB_ORG"
   bucket = "$INFLUXDB_BUCKET"
-  namepass = ["cpu", "disk", "diskio", "mem", "net", "procstat", "processes", "swap", "system", "zfs", "estat_nfs", "estat_iscsi"]
 EOF
 # Enforce restrictive permissions so the write token is not world-readable.
 chmod 640 "$INFLUXDB_OUTPUT"

telegraf/delphix-telegraf-service

@@ -50,12 +50,8 @@ else
 	fi
 fi
 
-if playbook_is_enabled || influxdb_is_enabled; then
-	cat $NFS_ISCSI_INPUTS >> $TELEGRAF_CONFIG
-fi
-
 if influxdb_is_enabled && [[ -f $INFLUXDB_OUTPUT ]]; then
-	cat $INFLUXDB_OUTPUT >> $TELEGRAF_CONFIG
+	cat $NFS_ISCSI_INPUTS $INFLUXDB_OUTPUT >> $TELEGRAF_CONFIG
 fi
 
 # Restrict permissions so the InfluxDB write token is not world-readable.

telegraf/telegraf.base

@@ -11,41 +11,9 @@
 ###############################################################################
 #                            OUTPUT PLUGINS                                   #
 ###############################################################################
-# Define the main metric output file, excluding aggregated stats and 
-# Performance Playbook (estat) data.
-[[outputs.file]]
-  files = ["/var/log/telegraf/metrics.json"]
-  rotation_max_size = "50MB"
-  rotation_max_archives = 9
-  data_format = "json"
-  namedrop = ["*estat_*", "agg_*", "zfs", "zpool*", "zcache*", "docker*"]
-
-# Define output file for ZFS related metrics
-[[outputs.file]]
-  files = ["/var/log/telegraf/metrics_zfs.json"]
-  rotation_max_size = "30MB"
-  rotation_max_archives = 5
-  data_format = "json"
-  namepass = ["zpool*", "zcache*", "zfs"]
-
-# Define output file for Performance Playbook (estat) metrics
-[[outputs.file]]
-  files = ["/var/log/telegraf/metrics_estat.json"]
-  rotation_max_size = "30MB"
-  rotation_max_archives = 5
-  data_format = "json"
-  namepass = ["*estat_*"]
-
-# Define output file for aggregate statistics
-[[outputs.file]]
-  files = ["/var/log/telegraf/metric_aggregates.json"]
-  rotation_max_size = "30MB"
-  rotation_max_archives = 5
-  data_format = "json"
-  namepass = ["agg_*"]
-
-# InfluxDB output is managed via /etc/telegraf/telegraf.outputs.influxdb (written by
-# delphix-influxdb-init) and the /etc/telegraf/INFLUXDB_ENABLED flag.
+# All metrics are ingested into InfluxDB. The output stanza is written by
+# delphix-influxdb-init to /etc/telegraf/telegraf.outputs.influxdb and
+# appended here by delphix-telegraf-service when InfluxDB is enabled.
 # Use 'perf_influxdb enable|disable' to toggle and restart Telegraf.
 
 ###############################################################################
@@ -64,15 +32,10 @@
 [[inputs.disk]]
   mount_points = ["/","/domain0"]
 
-# Get disk I/O stats
+# Get disk I/O stats, excluding ZFS zvol devices (zd*) which are internal
+# ZFS block devices not useful for performance diagnostics.
 [[inputs.diskio]]
-
-# Track stats for the current metric files
-[[inputs.filestat]]
-  files = ["/var/log/telegraf/metrics.json",
-  	   "/var/log/telegraf/metrics_estat.json",
-  	   "/var/log/telegraf/metrics_zfs.json",
-  	   "/var/log/telegraf/metric_aggregates.json"]
+  tagdrop = {name = ["zd*"]}
 
 # Get Memory stats
 [[inputs.mem]]

telegraf/telegraf.inputs.dct

@@ -11,12 +11,5 @@
   ]
   docker_label_exclude = ["com.docker.compose.*", "resty*"]
 
- [[outputs.file]]
-  files = ["/var/log/telegraf/metrics_docker.json"]
-  rotation_max_size = "30MB"
-  rotation_max_archives = 5
-  data_format = "json"
-  namepass = ["docker*"]
-
 ####################### End of Docker/DCT services Metrics #######################
 

telegraf/telegraf.inputs.nfs_iscsi

@@ -1,7 +1,8 @@
 ##############################################################################
-# NFS server I/O and iSCSI target I/O — included when InfluxDB is enabled
-# but Performance Playbook is not (playbook already contains these inputs).
+# NFS server I/O and iSCSI target I/O collection.
+# Always included when InfluxDB is enabled, independent of playbook state.
 
+# Collect output from "estat nfs -jm 10"
 [[inputs.execd]]
   command = ["estat", "nfs", "-jm", "10"]
   name_override = "estat_nfs"
@@ -14,6 +15,7 @@
   ]
   json_string_fields = ["iops(/s)", "avg latency(us)", "stddev(us)", "throughput(k/s)", "microseconds"]
 
+# Collect output from "estat iscsi -jm 10"
 [[inputs.execd]]
   command = ["estat", "iscsi", "-jm", "10"]
   name_override = "estat_iscsi"

telegraf/telegraf.inputs.playbook

@@ -1,7 +1,7 @@
 ##############################################################################
 # Performance Playbook (estat, nfs_threads) collection
-# Note: estat_nfs and estat_iscsi are in telegraf.inputs.nfs_iscsi so they
-# are also available when only InfluxDB is enabled (without the full playbook).
+# Note: estat_nfs and estat_iscsi live in telegraf.inputs.nfs_iscsi and are
+# always collected when InfluxDB is enabled, independent of playbook state.
 
 # Collect output from "estat zpl -jm 10"
 [[inputs.execd]]
@@ -99,8 +99,11 @@
 ###############################################################################
 #                         PROCESSOR PLUGINS                                   #
 ###############################################################################
-# Convert strings from estat into integer values so they don't get dropped
+# Convert strings from estat into integer values so they don't get dropped.
+# Scoped to playbook-only metrics; estat_nfs/iscsi have their own converter
+# in telegraf.inputs.nfs_iscsi.
 [[processors.converter]]
+  namepass = ["estat_zpl", "estat_zio", "estat_zvol", "estat_backend-io", "estat_zio-queue", "estat_metaslab-alloc"]
   [processors.converter.fields]
     integer = ["iops(/s)", "avg latency(us)", "stddev(us)", "throughput(k/s)"]