Changeset 935

Timestamp:

08/22/13 12:32:34 (11 years ago)

Author:

jripsl

Message:

• fix typo.

Location:

trunk/Monitoring

Files:

• Analyze/analyze (modified) (3 diffs)
• Watch/watch (modified) (4 diffs)
• doc/README (modified) (3 diffs)
• smon/repo_io.py (modified) (2 diffs)

trunk/Monitoring/Analyze/analyze

@@ -70 +70 @@
                 for simulation in repo_io.get_running_simulations():
 
-                        print "hhh"
-
-                        print "checking heartbeat ('%s')"%simulation.name
+                        print "\nchecking heartbeat ('%s')"%simulation.name
 
                         try:
@@ -94 +92 @@
                                 repo_io.update_simulation_status(simulation)
 
-                                print "heartbeat NOK - simulation status set to 'error' (%s)"%simulation.name
+                                print "heartbeat NOK - simulation status set to 'error'\n"
 
 
                         else:
-                                print "heartbeat OK (%s)"%simulation.name
+                                print "heartbeat OK\n"
 
 class Analyzer():
@@ -132 +130 @@
                 while True:
 
-                        print "checking simulations heartbeats"
+                        #print "checking simulations heartbeats"
 
                         CheckList.C0001()

trunk/Monitoring/Watch/watch

@@ -63 +63 @@
                         s=repo_io.retrieve_simulation(message.simuid)
 
+                        if s is None:
+                                raise Exception("WATCH-ERR102","simulation not found")
+
                         repo_io.create_message(message,s)
-
-                        sys.exit()
 
                 except:
@@ -102 +103 @@
         def crea_sim(cls,message):
 
-                #repo_io.retrieve_simulation(name)
-                #repo_io.delete_simulation(name)
-
-                simulation=smon.types.Simulation(name=message.simuid,status="running")
-
-                repo_io.create_simulation(simulation)
+                s=repo_io.retrieve_simulation(message.simuid)
+
+                if s is not None:
+                        #repo_io.delete_simulation(name)
+
+                        s.status="running"
+                        repo_io.update_simulation_status(s)
+
+                else:
+                        simulation=smon.types.Simulation(name=message.simuid,status="running")
+
+
+                        repo_io.create_simulation(simulation)
 
         @classmethod
@@ -125 +133 @@
 
                 print "%s %s %s %s\n"%(message.code,message.jobid,message.command,message.timestamp)
+                #pass
 
         @classmethod
@@ -291 +300 @@
 
                         except Exception,e:
-                                print "ERR019 - exception occurs (exception=%s,msg=%s)"%(str(e),base64_decoded_msg)
+                                print "ERR019 - exception occurs (exception=%s)"%(str(e))
+                                #print "ERR019 - exception occurs (exception=%s,msg=%s)"%(str(e),base64_decoded_msg)
 
                                 traceback.print_exc()

trunk/Monitoring/doc/README

@@ -1 +1 @@
 - installation instructions
-        - LibIGCM RabbitMQ agent installation
+        - LibIGCM AMQP agent installation
                 - see CNClient/README
         - Broker installation
                 - see Broker/README
         - Supervisor installation
+                - check if EPEL repository is configured, if not, do steps below
+                        - for CENTOS 6
+                          (from http://www.tecmint.com/how-to-enable-epel-repository-for-rhel-centos-6-5/)
+                                - wget http://download.fedoraproject.org/pub/epel/6/x86_64/epel-release-6-8.noarch.rpm
+                                - rpm -ivh epel-release-6-8.noarch.rpm
                 - Python installation
-                        - yum install python26
-                        - yum install python26-devel
+                        - if python version < 2.6, do
+                                - yum install python26
+                                - yum install python26-devel
+                        - yum install python-devel
                         - yum install sqlite
                         - yum install sqlite-devel
                         - yum install python-sqlite
                 - Virtualenv installation
+                        - mkdir /opt/src
                         - cd /opt/src/
-                        - wget http://pypi.python.org/packages/source/v/virtualenv/virtualenv-1.6.1.tar.gz
-                        - tar xzvf virtualenv-1.6.1.tar.gz
-                        - rm virtualenv-1.6.1.tar.gz
-                        - cd /opt/src/virtualenv-1.6.1
-                        - /usr/bin/python26 virtualenv.py --distribute --unzip-setuptools /opt/python2.6_ve
+                        - wget http://pypi.python.org/packages/source/v/virtualenv/virtualenv-1.10.1.tar.gz
+                        - tar xzvf virtualenv-1.10.1.tar.gz
+                        - rm virtualenv-1.10.1.tar.gz
+                        - cd /opt/src/virtualenv-1.10.1
+                        - check if python use the 2.6 version with
+                                - python -V
+                        - yum install python-pip
+                        - /usr/bin/python virtualenv.py --distribute --unzip-setuptools /opt/python2.6_ve
                         - source /opt/python2.6_ve/bin/activate
                 - Python PYPI libraries installation
@@ -33 +44 @@
                         - dependencies (PYPI packages)
                                 -
+                                        - yum install gcc
+                                        - yum install postgresql-devel
                                         - pip install psycopg2
                                                 - doesn't work (Error: pg_config executable not found)
@@ -52 +65 @@
                                                         - pip install SQLAlchemy==0.7.8
                         - Prodiguer package
+                                - mkdir -p /opt/supervisor/prodiguer_lib
+                                - cd /opt/supervisor/prodiguer_lib
                                 - svn co svn+ssh://<login here>@forge.ipsl.jussieu.fr/ipsl/forge/projets/prodiguer/svn/sw/src/python/trunk/prodiguer_shared/src
-                                - edit "watch" script and edit line below accordingly
-                                        - sys.path.append("/home/jripsl/snapshot/src") 
+                - Supervisor python script installation
+                        - svn co svn+ssh://<login here>@forge.ipsl.jussieu.fr/ipsl/forge/projets/libigcm/svn/trunk/Monitoring
+                        - edit "watch" script and edit line below accordingly
+                                - sys.path.append("/home/jripsl/snapshot/src") 
+                        - smon/repo_io.py
+                                - sys.path.append("/home/jripsl/snapshot/src") 
+        - test
+                - connectivity test
+                        - run command below on supervisor
+                                - telnet pp-db-dev.private.ipsl.fr 5432

trunk/Monitoring/smon/repo_io.py

@@ -250 +250 @@
 
                 if s is None:
-                        raise Exception("RG543534")
+                        #raise Exception("RG543534")
+                        return None
 
 
@@ -426 +427 @@
                 # ..
 
-                print "%s %s %s"%(simulation.name,message.code,"message.body")
+                # debug
+                #print "%s %s %s"%(simulation.name,message.code,"message.body")
 
                 # execute