Added Node monitoring SR

See merge request nexedi/slapos!1312

software/monitor/buildout.hash.cfg

@@ -14,11 +14,7 @@
 # not need these here).
 [template]
 filename = instance.cfg
-md5sum = 072b276e0b0dd4b4a96a50348a04c7a7
-
-[template-monitor]
-_update_hash_filename_ = instance-monitor.cfg.jinja2
-md5sum = 5afba85a7aca9e716f61d59a524adc12
+md5sum = e1dd16a6f50468959b5c4572b8c82f23
 
 [json-test-template]
 _update_hash_filename_ = json-test-template.json.in.jinja2
@@ -26,7 +22,11 @@ md5sum = 2eb5596544d9c341acf653d4f7ce2680
 
 [template-monitor-edgetest-basic]
 _update_hash_filename_ = instance-monitor-edgetest-basic.cfg.jinja2
-md5sum = efc528296ddf7fade335d5f4241c1828
+md5sum = 6b933beb0744d97c7760e4601298e137
+
+[template-node-monitoring]
+_update_hash_filename_ = instance-node-monitoring.jinja2.cfg
+md5sum = 2d8bd1224472983e54f36770d3e3f969
 
 [network-bench-cfg]
 filename = network_bench.cfg.in

software/monitor/instance-default-input-schema.json

 {
-  "$schema": "http://json-schema.org/draft-04/schema#",
+  "$schema": "http://json-schema.org/draft-04/schema",
+  "title": "Input Parameters",
   "type": "object",
   "properties": {
-    "dummy": {
-      "title": "dummy",
-      "description": "Dummy",
-      "type": "string"
+    "promise_cpu_temperature_frequency": {
+      "default": "2",
+      "title": "Frequency at which CPU temperature promise will be run (unit: minutes)",
+      "description": "Frequency at which CPU temperature promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_cpu_temperature_threshold": {
+      "default": "90",
+      "title": "CPU temperature promise threshold (unit: Celsius)",
+      "description": "Temperature threshold above which CPU temperature promise will fail (unit: Celsius)",
+      "type": "number"
+    },
+    "promise_cpu_avg_temperature_threshold": {
+      "default": "80",
+      "title": "Average CPU temperature promise threshold (unit: Celsius)",
+      "description": "If average temperature over specified duration reaches this threshold, promise will fail (unit: Celsius)",
+      "type": "number"
+    },
+    "promise_cpu_avg_temperature_threshold_duration": {
+      "default": "600",
+      "title": "Average CPU temperature promise threshold duration (unit: secondes)",
+      "description": "Duration during which average temperature should not exceed specified threshold (unit: secondes)",
+      "type": "number"
+    },
+    "promise_ram_available_frequency": {
+      "default": "2",
+      "title": "Frequency at which RAM availalble promise will be run (unit: minutes)",
+      "description": "Frequency at which RAM availalble promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_ram_available_threshold": {
+      "default": "500",
+      "title": "Minimum available RAM promise threshold (unit: MB)",
+      "description": "Minimum available RAM threshold below which RAM available promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_ram_avg_available_threshold": {
+      "default": "1e3",
+      "title": "Minimum average available RAM promise threshold (unit: MB)",
+      "description": "If average available ram over specified duration reaches this threshold, promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_ram_avg_available_threshold_duration": {
+      "default": "600",
+      "title": "Minimum average available RAM promise threshold duration (unit: secondes)",
+      "description": "Duration during which average available RAM shall not be below specified threshold (unit: secondes)",
+      "type": "number"
+    },
+    "promise_network_errors_frequency": {
+      "default": "5",
+      "title": "Frequency at which network errors promise will be run (unit: minutes)",
+      "description": "Frequency at which network errors promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_network_errors_threshold": {
+      "default": "100",
+      "title": "Maximum errors on Network per MB (unit: N/A)",
+      "description": "Maximum network errors threshold(per MB) above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_network_lost_packets_threshold": {
+      "default": "100",
+      "title": "Maximum lost packets on Network per MB (unit: N/A)",
+      "description": "Maximum network lost packets threshold(per MB) above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_network_transit_frequency": {
+      "default": "1",
+      "title": "Frequency at which network transit promise will be run (unit: minutes)",
+      "description": "Frequency at which network transit promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_network_transit_max_data_threshold": {
+      "default": "1e6",
+      "title": "Maximum data amount on network (unit: MB)",
+      "description": "Maximum data amount on network below which the promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_network_transit_min_data_threshold": {
+      "default": "0",
+      "title": "Minimum data amount on network (unit: MB)",
+      "description": "Minimum data amount on network below which the promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_network_transit_duration": {
+      "default": "600",
+      "title": "Duration to check thresholds (unit: secondes)",
+      "description": "Duration during which data amount on network shall not be above maximum and below minimum (unit: secondes)",
+      "type": "number"
+    },
+    "promise_cpu_load_frequency": {
+      "default": "3",
+      "title": "Frequency at which CPU load promise will be run (unit: minutes)",
+      "description": "Frequency at which CPU load promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_cpu_load_threshold": {
+      "default": "1.5",
+      "title": "Maximum CPU load ratio threshold (unit: N/A)",
+      "description": "Maximum CPU load ratio threshold above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_monitor_space_frequency": {
+      "default": "60",
+      "title": "Frequency at which monitor space promise will be run (unit: minutes)",
+      "description": "Frequency at which monitor space promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_partition_space_threshold": {
+      "default": "0.08",
+      "title": "Minimum partition space ratio threshold (unit: N/A)",
+      "description": "Minimum partition space ratio threshold below which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_free_disk_space_frequency": {
+      "default": "60",
+      "title": "Frequency at which free disk space promise will be run (unit: minutes)",
+      "description": "Frequency at which free disk space promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_free_disk_space_threshold": {
+      "default": "0.08",
+      "title": "Minimum partition space ratio threshold (unit: N/A)",
+      "description": "Minimum partition space ratio threshold below which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_free_disk_space_nb_days_predicted": {
+      "default": "10",
+      "title": "Number of days for prediction (unit: Days)",
+      "description": "Number of days (unit: Days) that will be take into account for prediction calculation",
+      "type": "number"
+    },
+    "promise_free_disk_space_display_partition": {
+      "default": true,
+      "title": "Boolean to display partition (unit: N/A)",
+      "description": "Enable partition display by setting boolean to True (unit: N/A)",
+      "type": "boolean"
+    },
+    "promise_free_disk_space_display_prediction": {
+      "default": true,
+      "title": "Boolean to display prediction (unit: N/A)",
+      "description": "Enable prediction display by setting boolean to True (unit: N/A)",
+      "type": "boolean"
     }
   }
 }

software/monitor/instance-default-output-schema.json

 {
-  "$schema": "http://json-schema.org/draft-04/schema#",
-  "description": "Values returned by Re6st Master instanciation",
+  "$schema": "http://json-schema.org/draft-04/schema",
+  "title": "Values returned by node-monitoring instanciation",
+  "type": "object",
   "properties": {
-    "re6stry-url": {
-      "description": "ipv6 url to access your re6st registry service",
-      "type": "string"
+    "promise_cpu_temperature_frequency": {
+      "description": "Frequency at which CPU temperature promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_cpu_temperature_threshold": {
+      "description": "Temperature threshold above which CPU temperature promise will fail (unit: Celsius)",
+      "type": "number"
+    },
+    "promise_cpu_avg_temperature_threshold": {
+      "description": "If average temperature over specified duration reaches this threshold, promise will fail (unit: Celsius)",
+      "type": "number"
+    },
+    "promise_cpu_avg_temperature_threshold_duration": {
+      "description": "Duration during which average temperature should not exceed specified threshold (unit: secondes)",
+      "type": "number"
+    },
+    "promise_ram_available_frequency": {
+      "description": "Frequency at which RAM availalble promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_ram_available_threshold": {
+      "description": "Minimum available RAM threshold below which RAM available promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_ram_avg_available_threshold": {
+      "description": "If average available ram over specified duration reaches this threshold, promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_ram_avg_available_threshold_duration": {
+      "description": "Duration during which average available RAM shall not be below specified threshold (unit: secondes)",
+      "type": "number"
+    },
+    "promise_network_errors_frequency": {
+      "description": "Frequency at which network errors promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_network_errors_threshold": {
+      "description": "Maximum network errors threshold(per MB) above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_network_lost_packets_threshold": {
+      "description": "Maximum network lost packets threshold(per MB) above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_network_transit_frequency": {
+      "description": "Frequency at which network transit promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_network_transit_max_data_threshold": {
+      "description": "Maximum data amount on network below which the promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_network_transit_min_data_threshold": {
+      "description": "Minimum data amount on network below which the promise will fail (unit: MB)",
+      "type": "number"
+    },
+    "promise_network_transit_duration": {
+      "description": "Duration during which data amount on network shall not be above maximum and below minimum (unit: secondes)",
+      "type": "number"
+    },
+    "promise_cpu_load_frequency": {
+      "description": "Frequency at which CPU load promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_cpu_load_threshold": {
+      "description": "Maximum CPU load ratio threshold above which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_monitor_space_frequency": {
+      "description": "Frequency at which monitor space promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_partition_space_threshold": {
+      "description": "Minimum partition space ratio threshold below which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_free_disk_space_frequency": {
+      "description": "Frequency at which free disk space promise will be run (unit: minutes)",
+      "type": "number"
+    },
+    "promise_free_disk_space_threshold": {
+      "description": "Minimum partition space ratio threshold below which the promise will fail (unit: N/A)",
+      "type": "number"
+    },
+    "promise_free_disk_space_nb_days_predicted": {
+      "description": "Number of days (unit: Days) that will be take into account for prediction calculation",
+      "type": "number"
+    },
+    "promise_free_disk_space_display_partition": {
+      "description": "Enable partition display by setting boolean to True (unit: N/A)",
+      "type": "boolean"
+    },
+    "promise_free_disk_space_display_prediction": {
+      "description": "Enable prediction display by setting boolean to True (unit: N/A)",
+      "type": "boolean"
     }
-  },
-  "type": "object"
+  }
 }

software/monitor/instance-edgetest-basic-output-schema.json

+{
+  "$schema": "http://json-schema.org/draft-04/schema#",
+  "description": "Values returned by Re6st Master instanciation",
+  "properties": {
+    "re6stry-url": {
+      "description": "ipv6 url to access your re6st registry service",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

software/monitor/instance-monitor-edgetest-basic.cfg.jinja2

@@ -135,8 +135,43 @@ command = ${surykatka-status-json-{{ class }}:output}
 {%- endfor %} {#- for class, class_check_list in CHECK_DICT.items() #}
 
 [buildout]
-extends = {{ instance_base_monitor }}
-parts +=
+extends = {{ monitor_template }}
+parts =
+  publish-connection-information
 {% for part_id in sorted(PART_LIST) %}
   {{ part_id }}
 {% endfor %}
+
+[publish-connection-information]
+recipe = slapos.cookbook:publish
+monitor-setup-url = https://monitor.app.officejs.com/#page=settings_configurator&url=${monitor-publish-parameters:monitor-url}&username=${monitor-publish-parameters:monitor-user}&password=${monitor-publish-parameters:monitor-password}
+server_log_url = ${monitor-publish-parameters:monitor-base-url}/${slap-configuration:private-hash}/
+
+[monitor-directory]
+service = ${buildout:directory}/etc/service
+var = ${buildout:directory}/var
+srv = ${buildout:directory}/srv
+server-log = ${:private}/server-log
+monitor-log = ${:private}/monitor-log
+system-log = ${:private}/system-log
+consumption = ${:log}/consumption
+
+[pwgen]
+recipe = slapos.cookbook:generate.password
+user = admin
+bytes = 16
+
+[pwgen32]
+recipe = slapos.cookbook:generate.password
+user = admin
+bytes = 16
+
+[slap-configuration]
+recipe = slapos.cookbook:slapconfiguration.serialised
+computer = ${slap-connection:computer-id}
+partition = ${slap-connection:partition-id}
+url = ${slap-connection:server-url}
+key = ${slap-connection:key-file}
+cert = ${slap-connection:cert-file}
+private-hash = ${pwgen:passwd}${pwgen32:passwd}
+frontend-domain = 

software/monitor/instance-monitor.cfg.jinja2

-[buildout]
-
-extends = {{ monitor_template_output }}
-
-parts =
-  cron
-  cron-network-bench
-  symlink-re6st-logs
-  symlink-collected-logs
-  python-symlink
-  monitor-collect-csv-wrapper
-  monitor-base
-  monitor-check-memory-usage
-  monitor-check-cpu-usage
-  publish-connection-information
-
-
-eggs-directory = {{ eggs_directory }}
-develop-eggs-directory = {{ develop_eggs_directory }}
-offline = true
-
-[cron-network-bench]
-<= cron
-recipe = slapos.cookbook:cron.d
-name = network-bench-test
-frequency = */10 * * * *
-# skip to not fill cron log file.
-# command = {{ buildout_bin }}/networkbench ${network-bench-configuration:output} ${monitor-directory:monitor-log}
-command = true
-
-
-[symlink-re6st-logs]
-recipe = cns.recipe.symlink
-symlink = /var/log/re6stnet = ${monitor-directory:system-log}/re6stnet
-autocreate = true
-
-[symlink-collected-logs]
-recipe = cns.recipe.symlink
-symlink = /srv/slapgrid/var/data-log = ${monitor-directory:server-log}/data-log
-autocreate = true
-
-[network-bench-configuration]
-recipe = slapos.recipe.template:jinja2
-url = {{ network_benck_cfg_output }}
-output = ${monitor-directory:etc}/network_bench.cfg
-context =
-  key slapparameter_dict slap-configuration:configuration
-
-[pwgen]
-recipe = slapos.cookbook:generate.password
-user = admin
-bytes = 16
-
-[pwgen32]
-recipe = slapos.cookbook:generate.password
-user = admin
-bytes = 16
-
-[monitor-instance-parameter]
-monitor-httpd-port = {{ slap_configuration['configuration.monitor-base-port'] }}
-
-[monitor-directory]
-service = ${buildout:directory}/etc/service
-var = ${buildout:directory}/var
-srv = ${buildout:directory}/srv
-server-log = ${:private}/server-log
-monitor-log = ${:private}/monitor-log
-system-log = ${:private}/system-log
-consumption = ${:log}/consumption
-
-[python-symlink]
-recipe = plone.recipe.command
-command = ln -sf {{ buildout_bin }}/pythonwitheggs ${monitor-directory:bin}/python
-update-command = ${:command}
-
-[monitor-collect-csv-wrapper]
-recipe = slapos.cookbook:wrapper
-command-line = 
-  ${monitor-directory:bin}/python {{ monitor_collect_csv_dump }} --output_folder ${monitor-directory:consumption}
-wrapper-path = ${monitor-directory:bin}/monitor-collect-csv-dump  
-
-[monitor-check-memory-usage]
-<= monitor-promise-base
-promise = check_command_execute
-name = check-computer-memory-usage.py
-config-command = {{ buildout_bin}}/check-computer-memory -db ${monitor-instance-parameter:collector-db} --threshold ${slap-parameter:memory-percent-threshold} --unit percent
-
-[monitor-check-cpu-usage]
-recipe = slapos.cookbook:promise.plugin
-eggs =
-  slapos.toolbox
-module = slapos.promise.plugin.check_server_cpu_load
-output = ${directory:plugins}/system-CPU-load-check.py
-config-cpu-load-threshold = ${slap-parameter:cpu-load-threshold}
-
-[publish-connection-information]
-recipe = slapos.cookbook:publish
-monitor-setup-url = https://monitor.app.officejs.com/#page=settings_configurator&url=${monitor-publish-parameters:monitor-url}&username=${monitor-publish-parameters:monitor-user}&password=${monitor-publish-parameters:monitor-password}
-server_log_url = ${monitor-publish-parameters:monitor-base-url}/${slap-configuration:private-hash}/ 
-
-[slap-configuration]
-recipe = slapos.cookbook:slapconfiguration.serialised
-computer = ${slap-connection:computer-id}
-partition = ${slap-connection:partition-id}
-url = ${slap-connection:server-url}
-key = ${slap-connection:key-file}
-cert = ${slap-connection:cert-file}
-private-hash = ${pwgen:passwd}${pwgen32:passwd}
-frontend-domain = 
-
-[slap-parameter]
-# Max cpu load for one core on server
-cpu-load-threshold = 3.0
-memory-percent-threshold = 96

software/monitor/instance-node-monitoring.jinja2.cfg

+[buildout]
+parts =
+  directory
+  check-disk-space.py
+  check-partition-space.py
+  check-cpu-temperature.py
+  check-ram-usage.py
+  check-network-errors.py
+  check-network-transit.py
+  check-cpu-load.py
+  publish-connection-information
+
+extends = {{ monitor_template }}
+
+eggs-directory = {{ eggs_directory }}
+develop-eggs-directory = {{ develop_eggs_directory }}
+offline = true
+
+[slap-configuration]
+recipe = slapos.cookbook:slapconfiguration.serialised
+computer = {{ slap_connection['computer-id'] }}
+partition = {{ slap_connection['partition-id'] }}
+url = {{ slap_connection['server-url'] }}
+key = {{ slap_connection['key-file'] }}
+cert = {{ slap_connection['cert-file'] }}
+
+[directory]
+recipe = slapos.cookbook:mkdirectory
+software = {{ buildout_directory }}
+home = ${buildout:directory}
+etc = ${:home}/etc
+var = ${:home}/var
+etc = ${:home}/etc
+bin = ${:home}/bin
+run = ${:var}/run
+script = ${:etc}/run
+service = ${:etc}/service
+promise = ${:etc}/promise
+log = ${:var}/log
+
+[publish-connection-information]
+recipe = slapos.cookbook:publish.serialised
+<= monitor-publish
+
+[macro.promise]
+<= monitor-promise-base
+name = ${:_buildout_section_name_}
+
+[check-disk-space.py]
+<= macro.promise
+eggs = slapos.toolbox[prediction]
+promise = check_free_disk_space
+config-collectordb = ${monitor-instance-parameter:collector-db}
+config-frequency = {{ slapparameter_dict.get("promise_free_disk_space_frequency", 60) }}
+config-threshold = {{ slapparameter_dict.get("promise_free_disk_space_threshold", 0.08) }}
+config-nb-days-predicted = {{ slapparameter_dict.get("promise_free_disk_space_nb_days_predicted", 10) }}
+config-display-partition = {{ int(slapparameter_dict.get("promise_free_disk_space_display_partition", 1)) }}
+config-display-prediction = {{ int(slapparameter_dict.get("promise_free_disk_space_display_prediction", 1)) }}
+
+[check-partition-space.py]
+<= macro.promise
+eggs = slapos.toolbox[pandas]
+promise = monitor_partition_space
+config-collectordb = ${monitor-instance-parameter:collector-db}
+config-frequency = {{ slapparameter_dict.get("promise_monitor_space_frequency", 60) }}
+config-threshold-ratio = {{ slapparameter_dict.get("promise_partition_space_threshold", 0.08) }}
+
+[check-cpu-temperature.py]
+<= macro.promise
+promise = check_cpu_temperature
+config-testing = false
+config-frequency = {{ slapparameter_dict.get("promise_cpu_temperature_frequency", 5) }}
+config-max-spot-temp = {{ slapparameter_dict.get("promise_cpu_temperature_threshold", 90) }}
+config-max-avg-temp = {{ slapparameter_dict.get("promise_cpu_avg_temperature_threshold", 80) }}
+config-avg-temp-duration = {{ slapparameter_dict.get("promise_cpu_avg_temperature_threshold_duration", 600) }}
+config-last-avg-computation-file = ${directory:var}/promise_cpu_temperature_last_avg_file
+
+[check-ram-usage.py]
+<= macro.promise
+promise = check_ram_usage
+config-frequency = {{ slapparameter_dict.get("promise_ram_available_frequency", 2) }}
+config-min-threshold-ram = {{ slapparameter_dict.get("promise_ram_available_threshold", 500) }}
+config-min-avg-ram = {{ slapparameter_dict.get("promise_ram_avg_available_threshold", 1e3) }}
+config-avg-ram-period = {{ slapparameter_dict.get("promise_ram_avg_available_threshold_duration", 600) }}
+config-last-avg-ram-file = ${directory:var}/promise_ram_space_last_avg_file
+
+[check-network-errors.py]
+<= macro.promise
+promise = check_network_errors_packets
+config-frequency = {{ slapparameter_dict.get("promise_network_errors_frequency", 5) }}
+config-max-error-messages-per-MB = {{ slapparameter_dict.get("promise_network_errors_threshold", 100) }}
+config-max-lost-packets-per-MB = {{ slapparameter_dict.get("promise_network_lost_packets_threshold", 100) }}
+
+[check-network-transit.py]
+<= macro.promise
+promise = check_network_transit
+config-frequency = {{ slapparameter_dict.get("promise_network_transit_frequency", 5) }}
+config-max-data-amount = {{ slapparameter_dict.get("promise_network_transit_max_data_threshold", 1e6) }}
+config-min-data-amount = {{ slapparameter_dict.get("promise_network_transit_min_data_threshold", 0) }}
+config-transit-period = {{ slapparameter_dict.get("promise_network_transit_duration", 600) }}
+config-last-transit-file = ${directory:var}/promise_network_last_transit_file
+
+[check-cpu-load.py]
+<= macro.promise
+promise = check_server_cpu_load
+config-frequency = {{ slapparameter_dict.get("promise_cpu_load_frequency", 3) }}
+config-cpu-load-threshold = {{ slapparameter_dict.get("promise_cpu_load_threshold", 1.5) }}

software/monitor/instance.cfg

@@ -7,24 +7,10 @@ develop-eggs-directory = ${buildout:develop-eggs-directory}
 
 [switch_softwaretype]
 recipe = slapos.cookbook:switch-softwaretype
-default = instance-base-monitor:output
+default = instance-node-monitoring:output
 edgetest-basic = instance-edgetest-basic:output
 RootSoftwareInstance = $${:default}
 
-[instance-base-monitor]
-recipe = slapos.recipe.template:jinja2
-url = ${template-monitor:target}
-output = $${buildout:directory}/template-base-monitor.cfg
-extensions = jinja2.ext.do
-context = key develop_eggs_directory buildout:develop-eggs-directory
-          key eggs_directory buildout:eggs-directory
-          key slapparameter_dict slap-configuration:configuration
-          section slap_configuration slap-configuration
-          raw buildout_bin ${buildout:bin-directory}
-          raw monitor_template_output ${monitor-template:output}
-          raw network_benck_cfg_output ${network-bench-cfg:output}
-          raw monitor_collect_csv_dump ${monitor-collect-csv-dump:target}
-
 [instance-template]
 recipe = slapos.recipe.template:jinja2
 extensions = jinja2.ext.do
@@ -36,13 +22,16 @@ context =
   key eggs_directory buildout:eggs-directory
   key slapparameter_dict slap-configuration:configuration
   key slap_software_type slap-configuration:slap-software-type
-  key instance_base_monitor instance-base-monitor:output
   raw buildout_bin ${buildout:bin-directory}
+  raw monitor_template ${monitor2-template:output}
   $${:extra-context}
 
-[surykatka]
-binary = ${buildout:bin-directory}/${surykatka:script-name}
-ini = ${template-surykatka-ini:target}
+[instance-node-monitoring]
+<= instance-template
+url = ${template-node-monitoring:target}
+extra-context =
+    raw buildout_directory ${buildout:directory}
+    section slap_connection slap-connection
 
 [instance-edgetest-basic]
 <= instance-template
@@ -52,6 +41,10 @@ extra-context =
   key template_surykatka_ini surykatka:ini
   key surykatka_binary surykatka:binary
 
+[surykatka]
+binary = ${buildout:bin-directory}/${surykatka:script-name}
+ini = ${template-surykatka-ini:target}
+
 [slap-configuration]
 recipe = slapos.cookbook:slapconfiguration.serialised
 computer = $${slap-connection:computer-id}

software/monitor/software.cfg

@@ -4,31 +4,35 @@ extends =
   buildout.hash.cfg
   ../../component/pycurl/buildout.cfg
   ../../component/python-cryptography/buildout.cfg
+  ../../component/python3/buildout.cfg
+  ../../component/pandas/buildout.cfg
+  ../../component/scipy/buildout.cfg
+  ../../component/statsmodels/buildout.cfg
+  ../../component/defaults.cfg
   ../../stack/monitor/buildout.cfg
   ../../stack/slapos.cfg
-  ../../component/python3/buildout.cfg
+
 
 parts =
   slapos-cookbook
   network-bench-cfg
   json-test-template
   template
-  template-monitor
 
 [template]
 recipe = slapos.recipe.template
 url = ${:_profile_base_location_}/${:filename}
 output = ${buildout:directory}/template.cfg
 
-[template-monitor]
+[template-monitor-edgetest-basic]
 recipe = slapos.recipe.build:download
 url = ${:_profile_base_location_}/${:_update_hash_filename_}
 
-[template-monitor-edgetest-basic]
+[template-surykatka-ini]
 recipe = slapos.recipe.build:download
 url = ${:_profile_base_location_}/${:_update_hash_filename_}
 
-[template-surykatka-ini]
+[template-node-monitoring]
 recipe = slapos.recipe.build:download
 url = ${:_profile_base_location_}/${:_update_hash_filename_}
 
@@ -68,3 +72,14 @@ miniupnpc = 2.0.2
 peewee = 3.14.4
 python-whois = 0.7.3
 future = 0.18.2
+
+# Build GCC with Fortran for OpenBLAS (scipy & numpy)
+[gcc]
+max_version = 0
+
+[slapos-toolbox-dependencies]
+eggs +=
+  ${pandas:egg}
+  ${statsmodels:egg}
+  ${scipy:egg}
+

software/monitor/software.cfg.json

 {
   "name": "Monitor",
   "description": "Software release for Monitoring purpose",
-  "serialisation": "xml",
+  "serialisation": "json-in-xml",
   "software-type": {
     "default": {
       "title": "Default",
@@ -14,7 +14,7 @@
       "title": "Edge Test Basic",
       "description": "Basic URL monitoring configuration",
       "request": "instance-edgetest-basic-input-schema.json",
-      "response": "instance-default-output-schema.json",
+      "response": "instance-edgetest-basic-output-schema.json",
       "serialisation": "json-in-xml",
       "index": 1
     }

software/monitor/test/test.py

@@ -533,3 +533,41 @@ URL =
     self.assertSurykatkaPromises()
     self.assertSurykatkaCron()
     self.assertConnectionParameterDict()
+
+
+class TestNodeMonitoring(SlapOSInstanceTestCase):
+  """Test class for node monitoring instanciation"""
+  @classmethod
+  def getInstanceParameterDict(cls):
+    return {'_': json.dumps({
+      'promise_cpu_temperature_frequency': 2,
+      'promise_cpu_temperature_threshold': 90,
+      'promise_cpu_avg_temperature_threshold': 80,
+      'promise_cpu_avg_temperature_threshold_duration': 600,
+      'promise_ram_available_frequency': 2,
+      'promise_ram_available_threshold': 500,
+      'promise_ram_avg_available_threshold': 1e3,
+      'promise_ram_avg_available_threshold_duration': 600,
+      'promise_network_errors_frequency': 5,
+      'promise_network_errors_threshold': 100,
+      'promise_network_lost_packets_threshold': 100,
+      'promise_network_transit_frequency': 1,
+      'promise_network_transit_max_data_threshold': 1e6,
+      'promise_network_transit_min_data_threshold': 0,
+      'promise_network_transit_duration': 600,
+      'promise_cpu_load_threshold': 1.5,
+      'promise_monitor_space_frequency': 5,
+      'promise_partition_space_threshold': 0.08,
+      'promise_free_disk_space_frequency': 3,
+      'promise_free_disk_space_threshold': 0.08,
+      'promise_free_disk_space_nb_days_predicted': 10,
+      'promise_free_disk_space_display_partition': True,
+      'promise_free_disk_space_display_prediction': True,
+      })}
+
+  @classmethod
+  def getInstanceSoftwareType(cls):
+    return 'default'
+
+  def test_node_monitoring_instance(self):
+    pass

software/slapos-sr-testing/software.cfg

@@ -414,7 +414,7 @@ tests =
   matomo ${slapos.test.matomo-setup:setup}
   metabase ${slapos.test.metabase-setup:setup}
   monitor ${slapos.test.monitor-setup:setup}
-  mosquitto ${slapos.test.mosquitto-setup:setup}  
+  mosquitto ${slapos.test.mosquitto-setup:setup}
   nextcloud ${slapos.test.nextcloud-setup:setup}
   nginx-push-stream ${slapos.test.nginx-push-stream-setup:setup}
   ors-amarisoft ${slapos.test.ors-amarisoft-setup:setup}

software/slapos-testing/software.cfg

@@ -24,6 +24,9 @@ extends =
   ../../component/openvpn/buildout.cfg
   ../../component/babeld/buildout.cfg
   ../../component/bridge-utils/buildout.cfg
+  ../../component/pandas/buildout.cfg
+  ../../component/statsmodels/buildout.cfg
+  ../../component/scipy/buildout.cfg
   ../../stack/slapos.cfg
   ../../stack/caucase/buildout.cfg
   ../../stack/nxdtest.cfg
@@ -35,6 +38,10 @@ parts =
   phantomjs
   template
 
+[gcc]
+# Always build GCC for Fortran (see openblas).
+max_version = 0
+
 [bootstrap-slapos.recipe.cmmi]
 # install our develop version of slapos.recipe.cmmi before anything else,
 # otherwise it will be installed from pypi by dependencies.
@@ -153,6 +160,9 @@ eggs +=
   ${slapcache-setup:egg}
   ${slapos.rebootstrap-setup:egg}
   ${rubygemsrecipe-setup:egg}
+  ${pandas:egg}
+  ${statsmodels:egg}
+  ${scipy:egg}
   zope.testing
   supervisor
   ${extra-eggs:eggs}