Back merged

Author: dbshah12

debian/control

@@ -13,6 +13,6 @@ Standards-Version: 4.1.2
 
 Package: performance-diagnostics
 Architecture: any
-Depends: python3-bpfcc, python3-minimal, python3-psutil, telegraf, docker.io, influxdb2, curl
+Depends: python3-bpfcc, python3-minimal, python3-psutil, telegraf, docker-ce, influxdb2, curl
 Description: eBPF-based Performance Diagnostic Tools
   A collection of eBPF-based tools for diagnosing performance issues.

influxdb/delphix-influxdb-init

@@ -212,3 +212,7 @@ umask "$old_umask"
 
 rm -f "$INFLUXDB_SETUP_STATE_FILE"
 log "InfluxDB initialized successfully."
+
+# Restart Telegraf so it picks up the InfluxDB output stanza written above.
+# This is only reached on first boot (subsequent boots exit early at the top).
+systemctl restart delphix-telegraf 2>/dev/null || true

influxdb/perf_influxdb

@@ -32,7 +32,7 @@ function enable_influxdb() {
 function disable_influxdb() {
 	date
 	echo "Disabling InfluxDB Metric Output"
-	rm -rf $INFLUXDB_FLAG
+	rm -f $INFLUXDB_FLAG
 	systemctl restart delphix-telegraf
 }
 

telegraf/delphix-telegraf-service

@@ -51,7 +51,10 @@ else
 fi
 
 if influxdb_is_enabled && [[ -f $INFLUXDB_OUTPUT ]]; then
-	cat $STORAGE_IO_INPUTS $INFLUXDB_OUTPUT >> $TELEGRAF_CONFIG
+	if [[ -f $STORAGE_IO_INPUTS ]]; then
+		cat $STORAGE_IO_INPUTS >> $TELEGRAF_CONFIG
+	fi
+	cat $INFLUXDB_OUTPUT >> $TELEGRAF_CONFIG
 fi
 
 # Restrict permissions so the InfluxDB write token is not world-readable.

telegraf/telegraf.base

@@ -15,6 +15,10 @@
 # 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.
+#
+# Fallback: discard all metrics when InfluxDB output is not appended
+# (e.g. InfluxDB disabled). Telegraf requires at least one output to start.
+[[outputs.discard]]
 
 ###############################################################################
 #                            INPUT PLUGINS                                    #

telegraf/telegraf.inputs.playbook

@@ -1,7 +1,7 @@
 ##############################################################################
 # Performance Playbook (estat, nfs_threads) collection
 # Note: estat_nfs, estat_iscsi, and estat_backend-io live in
-# telegraf.inputs.nfs_iscsi and are always collected when InfluxDB is
+# telegraf.inputs.storage_io and are always collected when InfluxDB is
 # enabled, independent of playbook state.
 
 # Collect output from "estat zpl -jm 10"
@@ -89,7 +89,7 @@
 ###############################################################################
 # 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.
+# in telegraf.inputs.storage_io.
 [[processors.converter]]
   namepass = ["estat_zpl", "estat_zio", "estat_zvol", "estat_zio-queue", "estat_metaslab-alloc"]
   [processors.converter.fields]