Merge pull request #142 from Helene/prometheus

Prometheus exporter initial version

Author: Helene

README.md

@@ -20,7 +20,7 @@ Grafana Bridge is a standalone Python application. It translates the IBM Storage
 * [Run the grafana bridge in a docker container](https://github.com/IBM/ibm-spectrum-scale-bridge-for-grafana/wiki/Running-the-IBM-Spectrum-Scale-Performance-Monitoring-Bridge-in-a-docker-container)
 * [Setup a Grafana environment for monitoring performance data of a CNSA cluster in a k8s OCP environment](https://github.com/IBM/ibm-spectrum-scale-bridge-for-grafana/wiki/Setup-Grafana-for-monitoring-a-CNSA-cluster--in-a-k8s-OCP-environment)
 
-The ***latest article***:
+The ***latest*** article:
 * [How to setup Grafana instance to monitor multiple IBM Storage Scale clusters running in a cloud or mixed environment](https://github.com/IBM/ibm-spectrum-scale-bridge-for-grafana/wiki/How-to-setup-Grafana-instance-to-monitor-multiple-IBM-Storage-Scale-clusters-running-in-a-cloud-or-mixed-environment)
 
 Find more helpful information about the bridge usage in the project [Wiki](https://github.com/IBM/ibm-spectrum-scale-bridge-for-grafana/wiki)

docs/AvailableDashboards.PNG

@@ -0,0 +1,126 @@
+# my global config
+global:
+  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+  query_log_file: /var/log/prometheus/query.log
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          # - alertmanager:9093
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+  # - "first_rules.yml"
+  # - "second_rules.yml"
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
+  - job_name: 'prometheus'
+
+    # metrics_path defaults to '/metrics'
+    # scheme defaults to 'http'.
+
+    static_configs:
+      - targets: ["<prometheus_server_ip>:9090"]
+
+  - job_name: 'CPU'
+    scrape_interval: 1s
+    honor_timestamps: true
+    metrics_path: '/metrics_cpu'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'Load'
+    scrape_interval: 1s
+    honor_timestamps: true
+    metrics_path: '/metrics_load'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250'] 
+
+  - job_name: 'Memory'
+    scrape_interval: 1s
+    honor_timestamps: true
+    metrics_path: '/metrics_memory'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'Network'
+    scrape_interval: 1s
+    honor_timestamps: true
+    metrics_path: '/metrics_network'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'Netstat'
+    scrape_interval: 1s
+    honor_timestamps: true
+    metrics_path: '/metrics_netstat'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'DiskFree'
+    scrape_interval: 600s
+    honor_timestamps: true
+    metrics_path: '/metrics_diskfree'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'GPFSFileset'
+    scrape_interval: 300s
+    honor_timestamps: true
+    metrics_path: '/metrics_gpfs_fileset'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']
+
+  - job_name: 'GPFSPool'
+    scrape_interval: 300s
+    honor_timestamps: true
+    metrics_path: '/metrics_gpfs_pool'
+    scheme: https
+    tls_config:
+      cert_file: /etc/prometheus/certs/cert.pem
+      key_file: /etc/prometheus/certs/privkey.pem
+      insecure_skip_verify: true
+    static_configs:
+    - targets: ['<grafana_bridge_ip>:9250']

docs/bridge_connect_grafana_ocp.png

@@ -23,6 +23,7 @@
 import argparse
 import os
 from messages import MSG
+from metaclasses import Singleton
 import configparser
 import getpass
 
@@ -35,18 +36,28 @@ def checkFileExists(path, filename):
 
 
 def checkTLSsettings(args):
-    if args.get('protocol') == "https" and (not args.get('tlsKeyPath') or not args.get('tlsKeyFile') or not args.get('tlsCertFile')):
+    if args.get('prometheus') and (not args.get('tlsKeyPath') or not
+                                   args.get('tlsKeyFile') or not
+                                   args.get('tlsCertFile')):
+        return False, MSG['MissingSSLCert']
+    elif args.get('protocol') == "https" and (not args.get('tlsKeyPath') or not
+                                              args.get('tlsKeyFile') or not
+                                              args.get('tlsCertFile')
+                                              ):
         return False, MSG['MissingParm']
     elif args.get('protocol') == "https" and not os.path.exists(args.get('tlsKeyPath')):
         return False, MSG['KeyPathError']
     elif args.get('protocol') == "https":
-        if (not checkFileExists(args.get('tlsKeyPath'), args.get('tlsCertFile'))) or (not checkFileExists(args.get('tlsKeyPath'), args.get('tlsKeyFile'))):
+        if (not checkFileExists(
+            args.get('tlsKeyPath'), args.get('tlsCertFile'))
+            ) or (not checkFileExists(
+                args.get('tlsKeyPath'), args.get('tlsKeyFile'))):
             return False, MSG['CertError']
     return True, ''
 
 
 def checkApplicationPort(args):
-    if not args.get('port') or not args.get('apiKeyValue'):
+    if not args.get('port', None) and not args.get('prometheus', None):
         return False, MSG['MissingParm']
     return True, ''
 
@@ -107,15 +118,6 @@ def merge_defaults_and_args(defaults, args):
     return brConfig
 
 
-class Singleton(type):
-    _inst = {}
-
-    def __call__(clazz, *args, **kwargs):
-        if clazz not in clazz._inst:
-            clazz._inst[clazz] = super(Singleton, clazz).__call__(*args, **kwargs)
-        return clazz._inst[clazz]
-
-
 class ConfigManager(object, metaclass=Singleton):
     ''' A singleton class managing the application configuration defaults '''
 

docs/grafana_bridge_overview.png

@@ -1,6 +1,8 @@
-##################### Grafana Connection Defaults ############################
+##################### OpenTSDB API Connection Defaults ########################
 [connection]
-# port number the bridge listening on for Grafana data requests
+# Port number the bridge listening on for Grafana data requests over
+# OpentTSDB plugin
+# 
 # 4242 - for HTTP connections 
 # 8443 - for HTTPS connections 
 # (Default: 4242)
@@ -9,7 +11,13 @@ port = 4242
 # Protocol (http, https)
 protocol = http
 
-#################################### Grafana Generic OAuth ####################
+##################### Prometheus Exporter API Connection Defaults #############
+# Port number the bridge listening on for Prometheus server https requests;
+# ssl cert and key configuration required
+
+# prometheus = 9250
+
+#################################### API SSL OAuth ############################
 [tls]
 # Directory path of tls key and cert file location
 #tlsKeyPath = /etc/bridge_cert/certs
@@ -20,6 +28,8 @@ protocol = http
 # Name of tls certificate file
 #tlsCertFile = cert.pem
 
+
+
 #################################### GPFS Server ##############################
 [server]
 # The ip address to bind to, empty will bind to all interfaces
@@ -59,7 +69,8 @@ includeDiskData = no
 # Directory where the bridge can store logs
 logPath = /var/log/ibm_bridge_for_grafana
 
-# log level 10 (DEBUG), 15 (MOREINFO), 20 (INFO), 30 (WARN), 40 (ERROR) (Default: 15)
+# log level 5 (TRACE) 10 (DEBUG), 15 (MOREINFO), 20 (INFO), 30 (WARN), 
+# 40 (ERROR) (Default: 15)
 logLevel = 15
 
 # Log file name (Default: zserver.log)

docs/grafana_bridge_prometheus_overview.png

@@ -28,8 +28,9 @@
 MSG = {'IntError': 'Server internal error occurred. Reason: {}',
        'sysStart': 'Initial cherryPy server engine start have been invoked. Python version: {}, cherryPy version: {}.',
        'MissingParm': 'Missing mandatory parameters, quitting',
+       'MissingSSLCert': 'Missing ssl key and certificate configuration, quitting',
        'KeyPathError': 'KeyPath directory not found, quitting',
-       'CertError': 'Missing certificates in tht specified keyPath directory, quitting',
+       'CertError': 'Missing certificates in the specified keyPath directory, quitting',
        'CollectorErr': 'Failed to initialize connection to pmcollector: {}, quitting',
        'MetaError': 'Metadata could not be retrieved. Check log file for more details, quitting',
        'MetaSuccess': 'Successfully retrieved MetaData',

examples/prometheus_config_file/prometheus.yml

@@ -32,9 +32,10 @@
 class OpenTsdbApi(object):
     exposed = True
 
-    def __init__(self, logger, mdHandler):
+    def __init__(self, logger, mdHandler, port):
         self.logger = logger
         self.__md = mdHandler
+        self.port = port
 
     @property
     def md(self):
@@ -273,6 +274,10 @@ def GET(self, **params):
         """
         resp = []
 
+        conn = cherrypy.request.headers.get('Host').split(':')
+        if int(conn[1]) != int(self.port):
+            raise cherrypy.HTTPError(400, MSG[400])
+
         # /api/suggest
         if 'suggest' in cherrypy.request.script_name:
             resp = self.suggest(params)