Merging integration into clmcservice

src/test/clmctest/inputs/conftest.py

@@ -39,7 +39,7 @@ def telegraf_agent_config(request):
     :return: the python object representing the read YAML file
     """
     rspec = pkg_resources.resource_filename('clmctest', 'rspec.json')
-    print("rspec file: {0}".format(rspec))
+    print("\nrspec file: {0}".format(rspec))
     with open(rspec, 'r') as stream:
         data_loaded = json.load(stream)
     return data_loaded

src/test/clmctest/inputs/test_telegraf_agents.py

@@ -63,8 +63,9 @@ def test_ping(telegraf_agent_config):
     ('net', 'SELECT mean("bytes_sent") AS "mean" FROM "CLMCMetrics"."autogen"."net"', 0),
     ('disk', 'SELECT mean("free") AS "mean" FROM "CLMCMetrics"."autogen"."disk"', 0),
     ('mem', 'SELECT mean("free") AS "mean" FROM "CLMCMetrics"."autogen"."mem"', 0),
+    ('service_config_state', 'SELECT mean("loaded.active.running_count") AS "mean" FROM "CLMCMetrics"."autogen"."service_config_state" WHERE "resource"=\'nginx.service\'', 0),
     # Report MINIO's HTTP request response time (as a rolling difference of the sum total)
-    ('minio_http_requests_duration_seconds', 'SELECT difference(max("sum")) AS "mean" FROM "CLMCMetrics"."autogen"."minio_http_requests_duration_seconds" WHERE time > now() - 1h GROUP BY time(10s)',0),              
+    ('minio_http_requests_duration_seconds', 'SELECT difference(max("sum")) AS "mean" FROM "CLMCMetrics"."autogen"."minio_http_requests_duration_seconds" WHERE time > now() - 1h GROUP BY time(10s)',0),      
     # Report the average change in difference of MINIO's HTTP response time (the inner query determines a rolling difference between sampling periods [respTimeDiff])
     ('minio_http_requests_duration_seconds', 'SELECT mean("respTimeDiff") AS "mean" FROM (SELECT difference(max("sum")) AS "respTimeDiff" FROM "CLMCMetrics"."autogen"."minio_http_requests_duration_seconds" WHERE time > now() - 1h GROUP BY time(10s))',0)              
     ])

src/test/clmctest/monitoring/conftest.py

@@ -68,7 +68,7 @@ def simulator(streaming_sim_config):
     :return: an instance of the simulator
     """
 
-    influx_url     = "http://" + streaming_sim_config[0]['ip_address'] + ":8086"
+    influx_url = "http://" + streaming_sim_config[0]['ip_address'] + ":8086"
 
     for service in streaming_sim_config:
         if service['name'] == "ipendpoint1":

src/test/clmctest/services/host/telegraf_host.conf

-## © University of Southampton IT Innovation Centre, 2018
-##
-## Copyright in this software belongs to University of Southampton
-## IT Innovation Centre of Gamma House, Enterprise Road, 
-## Chilworth Science Park, Southampton, SO16 7NS, UK.
-##
-## This software may not be used, sold, licensed, transferred, copied
-## or reproduced in whole or in part in any manner or form or in or
-## on any media by any person other than in accordance with the terms
-## of the Licence Agreement supplied with the software, or otherwise
-## without the prior written consent of the copyright owners.
-##
-## This software is distributed WITHOUT ANY WARRANTY, without even the
-## implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
-## PURPOSE, except where stated in the Licence Agreement supplied with
-## the software.
-##
-##      Created By :            Michael Boniface
-##      Created Date :          20-03-2018
-##      Created for Project :   FLAME
-
-###############################################################################
-#                                  INPUTS                                     #
-###############################################################################
-# # Read metrics about network interface usage
- [[inputs.net]]
-#   ## By default, telegraf gathers stats from any up interface (excluding loopback)
-#   ## Setting interfaces will tell it to gather these explicit interfaces,
-#   ## regardless of status.
-#   ##
-#   # interfaces = ["eth0"]
-
-# Read metrics about cpu usage
 [[inputs.cpu]]
   ## Whether to report per-cpu stats or not
   percpu = true
@@ -39,26 +6,18 @@
   ## If true, collect raw CPU time metrics.
   collect_cpu_time = false
   ## If true, compute and report the sum of all non-idle CPU states.
- #report_active = false
-
-
-# Read metrics about disk usage by mount point
+  report_active = false
 [[inputs.disk]]
-  ## By default, telegraf gather stats for all mountpoints.
-  ## Setting mountpoints will restrict the stats to the specified mountpoints.
+  ## By default stats will be gathered for all mount points.
+  ## Set mount_points will restrict the stats to only the specified mount points.
   # mount_points = ["/"]
-
-  ## Ignore some mountpoints by filesystem type. For example (dev)tmpfs (usually
-  ## present on /run, /var/run, /dev/shm or /dev).
+  ## Ignore mount points by filesystem type.
   ignore_fs = ["tmpfs", "devtmpfs", "devfs"]
-
-
-# Read metrics about disk IO by device
 [[inputs.diskio]]
   ## By default, telegraf will gather stats for all devices including
   ## disk partitions.
   ## Setting devices will restrict the stats to the specified devices.
-  # devices = ["sda", "sdb"]
+  devices = ["sda1"]
   ## Uncomment the following line if you need disk serial numbers.
   # skip_serial_number = false
   #
@@ -78,23 +37,21 @@
   ## The typical use case is for LVM volumes, to get the VG/LV name instead of
   ## the near-meaningless DM-0 name.
   # name_templates = ["$ID_FS_LABEL","$DM_VG_NAME/$DM_LV_NAME"]
-
-# Read metrics about memory usage
+[[inputs.kernel]]
+  # no configuration
 [[inputs.mem]]
   # no configuration
+[[inputs.processes]]
+  # no configuration
+[[inputs.swap]]
+  # no configuration
+[[inputs.system]]
+  # no configuration
+[[inputs.net]]
+[[inputs.netstat]]
+  # no configuration
 
-# # Influx HTTP write listener
-[[inputs.http_listener]]
-  ## Address and port to host HTTP listener on
-  service_address = ":8186"
-
-  ## timeouts
-  read_timeout = "10s"
-  write_timeout = "10s"
-
-  ## HTTPS
-  #tls_cert= "/etc/telegraf/cert.pem"
-  #tls_key = "/etc/telegraf/key.pem"
-
-  ## MTLS
-  #tls_allowed_cacerts = ["/etc/telegraf/clientca.pem"]
\ No newline at end of file
+# Influx HTTP write listener
+# [[inputs.http_listener]]
+#   ## Address and port to host HTTP listener on
+#   service_address = ":8186"

src/test/clmctest/services/minio/telegraf_minio.conf

@@ -20,4 +20,18 @@
 ##      Created for Project :   FLAME
 
 [[inputs.prometheus]]
-    urls = ["http://localhost:9000/minio/prometheus/metrics"]
\ No newline at end of file
+    urls = ["http://localhost:9000/minio/prometheus/metrics"]
+
+[[inputs.procstat]]
+  #pid_file = "/var/run/nginx.pid"
+  exe = "minio"
+
+# [[inputs.systemctl]]
+#   ## Service array
+#   services = [
+#     "minio.service"
+#   ]
+
+#   ## Sample rate for sampling state of service.
+#   ## Must be greter that the collection_interval/2
+#   #sample_rate = 2
\ No newline at end of file

src/test/clmctest/services/nginx/telegraf_nginx.conf

@@ -23,11 +23,21 @@
 [[inputs.nginx]]
   ## An array of Nginx stub_status URI to gather stats.
   urls = ["http://localhost:80/nginx_status"]
-
   ## HTTP response timeout (default: 5s)
-#  response_timeout = "5s"
+  #  response_timeout = "5s"
+
+[[inputs.procstat]]
+  #pid_file = "/var/run/nginx.pid"
+  exe = "nginx"
 
-# # Influx HTTP write listener
-[[inputs.http_listener]]
-  ## Address and port to host HTTP listener on
-  service_address = ":8186"
\ No newline at end of file
+[[inputs.systemctl]]
+	services = [
+	  "nginx.service",
+	]
+	## Sample rate for sampling state of service.
+	## Must be greter that the collection_interval/2 
+	sample_rate = 2
+	
+	## Logging level for this plugin according to logrus log levels
+	## "debug", "info", "warning", "error", "fatal", "panic"
+	log_level = "debug"