You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@uima.apache.org by ch...@apache.org on 2015/11/01 15:09:47 UTC
svn commit: r1711768 [1/2] - in /uima/sandbox/uima-ducc/trunk: ./
src/main/admin/ src/main/assembly/ src/main/resources/
uima-ducc-database/src/main/java/org/apache/uima/ducc/database/
uima-ducc-examples/src/main/scripts/ uima-ducc-parent/
Author: challngr
Date: Sun Nov 1 14:09:47 2015
New Revision: 1711768
URL: http://svn.apache.org/viewvc?rev=1711768&view=rev
Log:
UIMA-4577 Cassandra db support; packaging and scriptng.
Added:
uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh (with props)
uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep (with props)
uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbAlive.java
Modified:
uima/sandbox/uima-ducc/trunk/pom.xml
uima/sandbox/uima-ducc/trunk/src/main/admin/ducc.py
uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_post_install
uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_util.py
uima/sandbox/uima-ducc/trunk/src/main/admin/start_ducc
uima/sandbox/uima-ducc/trunk/src/main/assembly/bin.xml
uima/sandbox/uima-ducc/trunk/src/main/resources/default.ducc.properties
uima/sandbox/uima-ducc/trunk/src/main/resources/log4j.xml
uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbCreate.java
uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbManager.java
uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/HistoryManagerDb.java
uima/sandbox/uima-ducc/trunk/uima-ducc-examples/src/main/scripts/start_sim
uima/sandbox/uima-ducc/trunk/uima-ducc-examples/src/main/scripts/stop_sim
uima/sandbox/uima-ducc/trunk/uima-ducc-parent/pom.xml
Modified: uima/sandbox/uima-ducc/trunk/pom.xml
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/pom.xml?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/pom.xml (original)
+++ uima/sandbox/uima-ducc/trunk/pom.xml Sun Nov 1 14:09:47 2015
@@ -336,6 +336,27 @@
</configuration>
</execution>
+ <execution>
+ <!-- use the dependency:unpack goal to unpack the
+ base binary uima-as distribution -->
+ <id>unpack cassandra Bin</id>
+ <phase>prepare-package</phase>
+ <goals><goal>unpack</goal></goals>
+ <configuration>
+ <overWriteIfNewer>true</overWriteIfNewer>
+ <artifactItems>
+ <artifactItem>
+ <groupId>org.apache.cassandra</groupId>
+ <artifactId>apache-cassandra</artifactId>
+ <version>${cassandra.server.version}</version>
+ <type>tar.gz</type>
+ <classifier>bin</classifier>
+ <outputDirectory>${project.build.directory}/cassandra</outputDirectory>
+ </artifactItem>
+ </artifactItems>
+ </configuration>
+ </execution>
+
<execution>
<!-- use the dependency:unpack goal to unpack the Jetty release -->
Modified: uima/sandbox/uima-ducc/trunk/src/main/admin/ducc.py
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/admin/ducc.py?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/admin/ducc.py (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/admin/ducc.py Sun Nov 1 14:09:47 2015
@@ -27,7 +27,6 @@ import time
from ducc_util import DuccUtil
from local_hooks import verify_slave_node
-import database as db
from properties import Properties
from properties import Property
@@ -35,50 +34,43 @@ from properties import Property
class Ducc(DuccUtil):
- def run_db(self, background):
- # The dom gets loaded by the import above - or not
- if ( not db.domloaded ):
- print "Unable to read database configuration; insure the installed Python supports xml.dom.minidom"
- print "Note that Python must be at least version 2.6 but not 3.x. You are running version", sys.version_info
- return
-
- print '(re)Starting the database'
-
- # first write this out so it's easy to find in java without having to parse xml
- (jvm_parms, classpath, db_rt, dburl, dbrest, dbroot) = self.db_parms
- db_pw_file = Properties()
- comment = []
- comment.append('# Do not modify this file, it is auto-generated.')
- comment.append('# This is extracted from the database configuration and written to this file on every boot of the db')
- p = Property('db_password', dbroot, comment)
- db_pw_file.put_property(p)
- db_pw_filename = self.DUCC_HOME + '/resources.private/db_password'
- db_pw_file.write(db_pw_filename)
- os.chmod(db_pw_filename, 0700)
+ def run_db(self):
- main = 'com.orientechnologies.orient.server.OServerMain'
-
- jp = ''
- for k in jvm_parms.keys():
- v = jvm_parms[k]
- if ( v == None ):
- jp = jp + k + ' '
- else:
- jp = jp + k + '=' + v + ' '
-
-
- if ( self.db_jvm_args != None ):
- jp = jp + ' ' + self.db_jvm_args
+ print '-------- starting the database'
+ if ( self.db_disabled ):
+ print 'Database is disabled; not starting it.'
+ print 'OK'
+ return
+
+ if ( not os.path.exists(self.DUCC_HOME + "/database/data" )):
+ print 'Database is missing. You must initialize the database with DbCreate.'
+ print 'NOTOK'
+ return
- cmd = ' '.join(['nohup', self.java(), jp, '-cp', classpath, main, '&'])
- print cmd
+ # check for the pid to see if the DB is running.
+ if ( self.db_process_alive() ) :
+ print 'Database is already running.'
+ print 'OK'
+ return
here = os.getcwd()
- os.chdir(db_rt)
- pid = self.spawn(cmd)
- os.chdir(here)
-
- print 'OK'
+ os.chdir(self.DUCC_HOME + "/cassandra-server")
+ pidfile = self.DUCC_HOME + '/state/cassandra.pid'
+ CMD = "bin/cassandra -p "+ pidfile + " > /dev/null 2>&1"
+ print '------- Running', CMD
+
+ os.system(CMD);
+ print "Database is started. Waiting for initialization";
+
+ # DB (cassandra) starts and take a moment before anything works. DbAlive retries for a while
+ # to (a) connect as (b) ducc with (c) initialized database
+ if ( self.db_alive() ):
+ print "OK"
+ else:
+ # The database MIGHT be started but not configured or otherwise faulty. db_alive() prints
+ # some useful hints. we indicate failure here though so you don't proceed too far before
+ # fixing it.
+ print "NOTOK"
def run_broker(self, component):
broker_port = self.ducc_properties.get('ducc.broker.port')
@@ -348,7 +340,7 @@ class Ducc(DuccUtil):
self.usage("Must specify component")
if ( component == 'db' ):
- self.run_db(background)
+ self.run_db()
return
if ( component == 'broker' ):
Modified: uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_post_install
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_post_install?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_post_install (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_post_install Sun Nov 1 14:09:47 2015
@@ -83,24 +83,78 @@ class PostInstall():
print 'WARNING'
print ''
- def configure_database(self):
- self.ducc_default_properties = Properties()
- self.ducc_default_properties.load(self.DUCC_HOME + '/resources/default.ducc.properties')
- self.ducc_default_properties.put('ducc.head', self.ducc_head)
-
- dburl = self.ducc_default_properties.get('ducc.database.url')
- dbconfig = self.DUCC_HOME + '/' + self.ducc_default_properties.get('ducc.database.config.file')
- print 'Configuring database at', dburl, 'from', dbconfig
- print ''
+ def addToCp(self, cp, lib):
+ return cp + ':' + self.DUCC_HOME + '/' + lib
- if ( self.database_pw == None ):
- self.database_pw = ''
- while ( self.database_pw == '' ):
- self.database_pw = raw_input('Enter password for database root:')
+ def execute(self, CMD):
+ print CMD
+ rc = os.system(CMD)
+ if ( rc != 0 ):
+ print 'Failure, cannot continue.'
+ sys.exit(1)
- print ''
- db.configure(dbconfig, self.ducc_head, self.database_pw)
+ def configure_database(self):
+ # for cassandra:
+ # in ducc_runtime/cassandra-server/conf we need to update cassandra.yaml to establish
+ # the data directories and db connection addresses
+
+ # Note this is a bootstrap routine and doesn't try to use common code that may depend on
+ # things being initialized correctly.
+
+ return
+ if ( os.path.exists(self.DUCC_HOME + "/database/data") ):
+ print 'Database is already defined. Not configuring'
+ return
+
+ db_pw = raw_input("Enter database password OR 'disable' to disable database support:")
+ if ( db_pw == '' ):
+ print "Must enter a DB password to continue."
+ sys.exit(1);
+
+ if ( db_pw == 'disable' ):
+ print 'Database support will be disabled'
+ self.update_property('ducc.database.host', '--disabled--', '# Database support is disabled')
+ return;
+ else:
+ self.update_property('ducc.database.host', self.ducc_head, '# Database location')
+
+ config = self.DUCC_HOME + '/cassandra-server/conf/cassandra.yaml'
+ esc_home = self.DUCC_HOME.replace("/", "\/");
+ print "------ escaped home", esc_home
+
+ ch_head = "sed -i .bak s'/DUCC_HEAD/" + self.ducc_head + "'/ " + config
+ self.execute(ch_head)
+ ch_home = "sed -i .bak s'/DUCC_HOME/" + esc_home + "'/ " + config
+ self.execute(ch_home)
+
+ here = os.getcwd()
+ os.chdir(self.DUCC_HOME + "/cassandra-server")
+ pidfile = self.DUCC_HOME + '/state/cassandra.pid'
+ CMD = "bin/cassandra -p "+ pidfile + " > /dev/null 2>&1";
+ os.system(CMD);
+ print "Database is started. Waiting for initialization";
+
+ # Now start the db and create the schema
+ CLASSPATH = ''
+ CLASSPATH = self.addToCp(CLASSPATH, 'lib/cassandra/*')
+ CLASSPATH = self.addToCp(CLASSPATH, 'lib/guava/*')
+ CLASSPATH = self.addToCp(CLASSPATH, 'lib/apache-log4j/*')
+ CLASSPATH = self.addToCp(CLASSPATH, 'lib/uima-ducc/*')
+ CLASSPATH = self.addToCp(CLASSPATH, 'apache-uima/apache-activemq/lib/*')
+ os.environ['CLASSPATH'] = CLASSPATH
+
+ # First time - use built-in password and id. These get changed and then disabled with DbCreate.
+ CMD = [self.path_to_java, 'org.apache.uima.ducc.database.DbAlive', self.ducc_head, 'cassandra', 'cassandra']
+ CMD = ' '.join(CMD)
+ self.execute(CMD)
+ CMD = [self.path_to_java, '-DDUCC_HOME=' + self.DUCC_HOME, 'org.apache.uima.ducc.database.DbCreate', self.ducc_head, 'ducc', db_pw]
+ CMD = ' '.join(CMD)
+ self.execute(CMD)
+
+ CMD = ['kill', '-TERM', '`cat ' + pidfile + '`']
+ CMD = ' '.join(CMD)
+ self.execute(CMD)
def get_keystore_pw(self, prompt):
@@ -381,6 +435,10 @@ class PostInstall():
self.setup_ducc_head()
self.check_nodes()
+ # insure java is configured and installed
+ self.java_bindir = self.get_java_bindir()
+
+ # configure the database for local system and initialize the schema
self.configure_database()
# As of DUCC 2.0, always set here on installation
@@ -399,8 +457,6 @@ class PostInstall():
if ( not os.path.exists(historydir) ):
os.mkdir(historydir)
- # insure java is configured and installed
- self.java_bindir = self.get_java_bindir()
self.keytool = self.get_java_keytool(self.java_bindir)
print 'Java version:', self.get_java_version()
print 'Java is verified.'
Modified: uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_util.py
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_util.py?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_util.py (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/admin/ducc_util.py Sun Nov 1 14:09:47 2015
@@ -34,8 +34,6 @@ from threading import *
import traceback
import Queue
-import database as db
-
from stat import *
from local_hooks import find_other_processes
@@ -138,7 +136,6 @@ class DuccUtil(DuccBase):
self.pm_jvm_args = self.ducc_properties.get('ducc.pm.jvm.args')
self.rm_jvm_args = self.ducc_properties.get('ducc.rm.jvm.args')
self.sm_jvm_args = self.ducc_properties.get('ducc.sm.jvm.args')
- self.db_jvm_args = self.ducc_properties.get('ducc.db.jvm.args')
self.or_jvm_args = self.ducc_properties.get('ducc.orchestrator.jvm.args')
@@ -162,113 +159,86 @@ class DuccUtil(DuccBase):
print 'Merging', base_props, 'with', site_props, 'into', run_props
os.system(CMD)
- def db_read_parms(self):
- #
- # common setup for orientdb management
- #
- dbhost = self.ducc_properties.get('ducc.database.host')
+ def db_configure(self):
+ dbhost = self.ducc_properties.get('ducc.database.host')
if ( dbhost == self.db_disabled ):
- self.db_parms = self.db_disabled
- return self.db_parms
-
- dburl = self.ducc_properties.get('ducc.database.url')
- dbrest = self.ducc_properties.get('ducc.database.rest.url')
- dbconfig = self.ducc_properties.get('ducc.database.config.file')
- dbroot = db.get_db_password(DUCC_HOME, dbconfig)
- if ( dbroot == None ):
- print 'Cannot find database passord in', dbconfig
- sys.exit(1)
-
- rt = self.DUCC_HOME # (ducc runtime)
- db_rt = rt + '/database' # ORIENTDB_HOME - the database "home" place
+ self.db_disabled = True
+ else:
+ self.db_disabled = False
+ dbprops = Properties()
+ dbprops.load(self.DUCC_HOME + '/resources.private/database.password')
+ self.db_password = dbprops.get('db_password')
- jvm_parms = {
- '-Dfile.encoding' : 'UTF8',
- '-Drhino.opt.level' : '9',
- '-Dprofile.enabled' : 'true',
- '-Djna.nosys' : 'true',
- '-Djava.awt.headless' : 'true',
- '-Dorientdb.config.file' : rt + '/' + dbconfig,
- '-Dorientdb.www.path' : db_rt + '/www',
- '-Djava.util.logging.config.file' : rt + '/resources/database.log.config',
- '-Dcom.sun.management.jmxremote' : None,
- '-Dcom.sun.management.jmxremote.ssl' : 'false',
- '-Dcom.sun.management.jmxremote.authenticate': 'false',
- '-Dcom.sun.management.jmxremote.port': '1098',
- }
- classpath = '"' + rt + '/lib/orientdb/*'
- classpath = classpath + ':' + rt + '/lib/jna/*' + '"'
+ # does the database process exist?
+ def db_process_alive(self):
+ pidfile = self.DUCC_HOME + '/state/cassandra.pid'
- os.environ['DUCC_HOME'] = self.DUCC_HOME
- os.environ['ORIENTDB_HOME'] = db_rt
+ if ( not os.path.exists(pidfile) ):
+ return False
- self.db_parms = (jvm_parms, classpath, db_rt, dburl, dbrest, dbroot)
+ f = open(self.DUCC_HOME + '/state/cassandra.pid')
+ pid = f.read();
+ f.close()
+ answer = []
+ if ( self.system == 'Darwin'):
+ ps = 'ps -eo user,pid,comm,args ' + pid
+ else:
+ ps = 'ps -eo user:14,pid,comm,args ' + pkd
+ lines = self.popen(ps)
+
+ for line in lines:
+ line = line.strip()
+ if (pid in line):
+ return True
+ return False
+ # contact the database and see how useful it seems to be
def db_alive(self):
- if ( self.db_parms == self.db_disabled ):
+ if ( self.db_disabled == True ):
return True
- (jvm_parms, classpath, db_rt, dburl, dbrest, dbroot) = self.db_parms
+ dbnode = self.ducc_properties.get('ducc.state.database.url')
+ if ( dbnode == None ):
+ print 'No database location defined.'
+ return False
+ # get our log4j config into the path to shut up noisy logging
+ os.environ['CLASSPATH'] = os.environ['CLASSPATH'] + ':' + self.DUCC_HOME + '/resources'
+
+ CMD = [self.java(), 'org.apache.uima.ducc.database.DbAlive', dbnode, 'ducc', self.db_password]
- try:
- conn = httplib.HTTPConnection(dbrest)
- conn.request('GET', '/listDatabases')
- except Exception, (e):
- print " Checking connection: ", e
+ CMD = ' '.join(CMD)
+ rc = os.system(CMD)
+ if ( rc == 0 ):
+ return True
+ else:
return False
-
- resp = conn.getresponse()
- print 'response code', resp.status, resp.reason
- data = resp.read()
- print 'Data:', data
-
- if ( resp.status == 200 ):
- # it will be simple json that Python will see as lists and maps so we can just eval it
- data = eval(data)
- dblist = data['databases']
- if ( len(dblist) == 0 ):
- print ' Connection succeeded, no databases found.'
- pass
- else:
- print 'Found these databases:'
- for d in data['databases']:
- print ' ', d
- return True
+
def db_start(self):
- return True
# bypass all of this for the initial delivery
- if ( self.db_parms == self.db_disabled ):
+ if ( self.db_disabled == True) :
print ' (Bypass database start because ducc.database.host =', self.db_disabled + ')'
return True
print 'Starting database'
-
- self.sync_db_config() # insure db is running on head node, in case the head changed in ducc.properties
- node = self.ducc_properties.get('ducc.head')
-
- if ( node == 'local' ):
- node = self.localhost
-
- if ( self.db_alive() ):
- print 'Database is already started.'
- return True
+ dbnode = self.ducc_properties.get('ducc.state.database.url')
max_attempts = 5
attempt = 0
while attempt < max_attempts:
- lines = self.ssh(node, True, "'", self.DUCC_HOME + '/admin/ducc.py', '-c', 'db', '--nodup', "'")
+ lines = self.ssh(dbnode, True, "'", self.DUCC_HOME + '/admin/ducc.py', '-c', 'db', '--nodup', "'")
# we'll capture anything that the python shell spews because it may be useful, and then drop the
# pipe when we see a PID message
+
while True:
try:
line = lines.readline().strip()
except:
break
- print '[]', line
+ # print '[]', line
if ( not line ):
break
@@ -279,7 +249,6 @@ class DuccUtil(DuccBase):
lines.close();
print 'waiting for database to start'
- time.sleep(5)
if ( self.db_alive() ):
return True
@@ -288,70 +257,18 @@ class DuccUtil(DuccBase):
return False
- def db_init(self):
- return True
- # bypass all of this for the initial delivery
- if ( self.db_parms == self.db_disabled ):
- return True
-
- print 'Initializing database.'
- main = 'org.apache.uima.ducc.database.DbCreate'
- (jvm_parms, classpath, db_rt, dburl, dbrest, dbroot) = self.db_parms
-
- classpath = self.DUCC_HOME + '/lib/uima-ducc/*:' + classpath
- dburl = self.ducc_properties.get('ducc.state.database.url')
- cmd = ' '.join([self.java(), '-DDUCC_HOME=' + self.DUCC_HOME, '-cp', classpath, main, dburl])
- print cmd
- self.spawn(cmd)
-
def db_stop(self):
- return True
- # bypass all of this for the initial delivery
- if ( self.db_parms == self.db_disabled ):
- return True
-
-
- cfgfile = 'ducc.database.config.file'
- dbconfig = self.ducc_properties.get(cfgfile)
- if ( dbconfig == None ):
- print 'Database is not configured:', cfgfile, 'is not found in ducc.properties'
- return
-
- rt = self.DUCC_HOME # (ducc runtime)
- db_rt = rt + '/database' # ORIENTDB_HOME - the database "home" place
-
- jvm_parms = {
- '-Djava.awt.headless' : 'true',
- '-Dorientdb.config.file' : rt + '/' + dbconfig,
- }
- classpath = '"' + rt + '/lib/orientdb/*' + '"'
-
- main = 'com.orientechnologies.orient.server.OServerShutdownMain'
-
- jp = ''
- for k in jvm_parms.keys():
- v = jvm_parms[k]
- if ( v == None ):
- jp = jp + k + ' '
- else:
- jp = jp + k + '=' + v + ' '
+ if ( self.db_disabled == True) :
+ print ' (Bypass database start because ducc.database.host =', self.db_disabled + ')'
+ return True
- os.environ['ORIENTDB_HOME'] = db_rt
- cmd = ' '.join([self.java(), jp, '-cp', classpath, main])
- print cmd
+ pidfile = self.DUCC_HOME + '/state/cassandra.pid'
- here = os.getcwd()
- os.chdir(db_rt)
- self.spawn(cmd)
- os.chdir(here)
-
- def sync_db_config(self):
- dbconfig = self.DUCC_HOME + '/' + self.ducc_properties.get('ducc.database.config.file')
- head = self.ducc_properties.get('ducc.head')
- print 'Sync database node with head node on', head
- dom = db.update_head(dbconfig, head)
- db.write_config(dbconfig, dom)
+ # for cassandra, just send it a terminate signal. a pidfile is written on startup
+ CMD = ['kill', '-TERM', '`cat ' + pidfile + '`']
+ CMD = ' '.join(CMD)
+ os.system(CMD)
def find_netstat(self):
# don't you wish people would get together on where stuff lives?
@@ -420,7 +337,6 @@ class DuccUtil(DuccBase):
def ssh(self, host, do_wait, *CMD):
cmd = ' '.join(CMD)
- # print 'ssh -o BatchMode=yes -o ConnectTimeout=10', host, cmd
if ( do_wait ):
return self.popen('ssh -q -o BatchMode=yes -o ConnectTimeout=10', host, cmd)
else:
@@ -452,6 +368,7 @@ class DuccUtil(DuccBase):
CLASSPATH = CLASSPATH + ':' + LIB + 'jna/*'
CLASSPATH = CLASSPATH + ':' + LIB + 'libpam4j/*'
CLASSPATH = CLASSPATH + ':' + LIB + 'uima-ducc/*'
+ CLASSPATH = CLASSPATH + ':' + LIB + 'cassandra/*'
# CLASSPATH = CLASSPATH + ':' + DH + 'resources' UIMA-4168 Use API, not classpath to configure log4j
@@ -978,7 +895,7 @@ class DuccUtil(DuccBase):
self.os_pagesize = self.get_os_pagesize()
self.update_properties()
- self.db_read_parms()
+ self.db_configure()
manage_broker = self.ducc_properties.get('ducc.broker.automanage')
Modified: uima/sandbox/uima-ducc/trunk/src/main/admin/start_ducc
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/admin/start_ducc?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/admin/start_ducc (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/admin/start_ducc Sun Nov 1 14:09:47 2015
@@ -312,9 +312,7 @@ class StartDucc(DuccUtil):
sys.exit(1)
try:
- if ( self.db_start() ):
- self.db_init()
-
+ self.db_start()
except Exception (e):
# print e
print sys.exc_info()[0], "Can't start the database."
Modified: uima/sandbox/uima-ducc/trunk/src/main/assembly/bin.xml
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/assembly/bin.xml?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/assembly/bin.xml (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/assembly/bin.xml Sun Nov 1 14:09:47 2015
@@ -298,6 +298,17 @@ under the License.
<directoryMode>755</directoryMode>
</fileSet>
+ <!-- CASSANDRA server -->
+ <fileSet>
+ <directory>target/cassandra/apache-cassandra-2.1.11</directory>
+ <outputDirectory>cassandra-server</outputDirectory>
+ <excludes>
+ <exclude>javadac/*</exclude>
+ </excludes>
+ <fileMode>755</fileMode>
+ <directoryMode>755</directoryMode>
+ </fileSet>
+
<!-- Unversioned CLI jar -->
<fileSet>
<directory>uima-ducc-cli/target</directory>
Added: uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh?rev=1711768&view=auto
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh (added)
+++ uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh Sun Nov 1 14:09:47 2015
@@ -0,0 +1,311 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+calculate_heap_sizes()
+{
+ case "`uname`" in
+ Linux)
+ system_memory_in_mb=`free -m | awk '/:/ {print $2;exit}'`
+ system_cpu_cores=`egrep -c 'processor([[:space:]]+):.*' /proc/cpuinfo`
+ ;;
+ FreeBSD)
+ system_memory_in_bytes=`sysctl hw.physmem | awk '{print $2}'`
+ system_memory_in_mb=`expr $system_memory_in_bytes / 1024 / 1024`
+ system_cpu_cores=`sysctl hw.ncpu | awk '{print $2}'`
+ ;;
+ SunOS)
+ system_memory_in_mb=`prtconf | awk '/Memory size:/ {print $3}'`
+ system_cpu_cores=`psrinfo | wc -l`
+ ;;
+ Darwin)
+ system_memory_in_bytes=`sysctl hw.memsize | awk '{print $2}'`
+ system_memory_in_mb=`expr $system_memory_in_bytes / 1024 / 1024`
+ system_cpu_cores=`sysctl hw.ncpu | awk '{print $2}'`
+ ;;
+ *)
+ # assume reasonable defaults for e.g. a modern desktop or
+ # cheap server
+ system_memory_in_mb="2048"
+ system_cpu_cores="2"
+ ;;
+ esac
+
+ # some systems like the raspberry pi don't report cores, use at least 1
+ if [ "$system_cpu_cores" -lt "1" ]
+ then
+ system_cpu_cores="1"
+ fi
+
+ # set max heap size based on the following
+ # max(min(1/2 ram, 1024MB), min(1/4 ram, 8GB))
+ # calculate 1/2 ram and cap to 1024MB
+ # calculate 1/4 ram and cap to 8192MB
+ # pick the max
+ half_system_memory_in_mb=`expr $system_memory_in_mb / 2`
+ quarter_system_memory_in_mb=`expr $half_system_memory_in_mb / 2`
+ if [ "$half_system_memory_in_mb" -gt "1024" ]
+ then
+ half_system_memory_in_mb="1024"
+ fi
+ if [ "$quarter_system_memory_in_mb" -gt "8192" ]
+ then
+ quarter_system_memory_in_mb="8192"
+ fi
+ if [ "$half_system_memory_in_mb" -gt "$quarter_system_memory_in_mb" ]
+ then
+ max_heap_size_in_mb="$half_system_memory_in_mb"
+ else
+ max_heap_size_in_mb="$quarter_system_memory_in_mb"
+ fi
+ MAX_HEAP_SIZE="${max_heap_size_in_mb}M"
+
+ # Young gen: min(max_sensible_per_modern_cpu_core * num_cores, 1/4 * heap size)
+ max_sensible_yg_per_core_in_mb="100"
+ max_sensible_yg_in_mb=`expr $max_sensible_yg_per_core_in_mb "*" $system_cpu_cores`
+
+ desired_yg_in_mb=`expr $max_heap_size_in_mb / 4`
+
+ if [ "$desired_yg_in_mb" -gt "$max_sensible_yg_in_mb" ]
+ then
+ HEAP_NEWSIZE="${max_sensible_yg_in_mb}M"
+ else
+ HEAP_NEWSIZE="${desired_yg_in_mb}M"
+ fi
+}
+
+# Determine the sort of JVM we'll be running on.
+
+java_ver_output=`"${JAVA:-java}" -version 2>&1`
+
+jvmver=`echo "$java_ver_output" | grep '[openjdk|java] version' | awk -F'"' 'NR==1 {print $2}'`
+JVM_VERSION=${jvmver%_*}
+JVM_PATCH_VERSION=${jvmver#*_}
+
+#if [ "$JVM_VERSION" \< "1.7" ] ; then
+# echo "Cassandra 2.0 and later require Java 7u25 or later."
+# exit 1;
+#fi
+
+#if [ "$JVM_VERSION" \< "1.8" ] && [ "$JVM_PATCH_VERSION" \< "25" ] ; then
+# echo "Cassandra 2.0 and later require Java 7u25 or later."
+# exit 1;
+#fi
+
+
+jvm=`echo "$java_ver_output" | grep -A 1 'java version' | awk 'NR==2 {print $1}'`
+case "$jvm" in
+ OpenJDK)
+ JVM_VENDOR=OpenJDK
+ # this will be "64-Bit" or "32-Bit"
+ JVM_ARCH=`echo "$java_ver_output" | awk 'NR==3 {print $2}'`
+ ;;
+ "Java(TM)")
+ JVM_VENDOR=Oracle
+ # this will be "64-Bit" or "32-Bit"
+ JVM_ARCH=`echo "$java_ver_output" | awk 'NR==3 {print $3}'`
+ ;;
+ *)
+ # Help fill in other JVM values
+ JVM_VENDOR=other
+ JVM_ARCH=unknown
+ ;;
+esac
+
+
+# Override these to set the amount of memory to allocate to the JVM at
+# start-up. For production use you may wish to adjust this for your
+# environment. MAX_HEAP_SIZE is the total amount of memory dedicated
+# to the Java heap; HEAP_NEWSIZE refers to the size of the young
+# generation. Both MAX_HEAP_SIZE and HEAP_NEWSIZE should be either set
+# or not (if you set one, set the other).
+#
+# The main trade-off for the young generation is that the larger it
+# is, the longer GC pause times will be. The shorter it is, the more
+# expensive GC will be (usually).
+#
+# The example HEAP_NEWSIZE assumes a modern 8-core+ machine for decent pause
+# times. If in doubt, and if you do not particularly want to tweak, go with
+# 100 MB per physical CPU core.
+
+#MAX_HEAP_SIZE="4G"
+#HEAP_NEWSIZE="800M"
+
+# Set this to control the amount of arenas per-thread in glibc
+#export MALLOC_ARENA_MAX=4
+
+if [ "x$MAX_HEAP_SIZE" = "x" ] && [ "x$HEAP_NEWSIZE" = "x" ]; then
+ calculate_heap_sizes
+else
+ if [ "x$MAX_HEAP_SIZE" = "x" ] || [ "x$HEAP_NEWSIZE" = "x" ]; then
+ echo "please set or unset MAX_HEAP_SIZE and HEAP_NEWSIZE in pairs (see cassandra-env.sh)"
+ exit 1
+ fi
+fi
+
+if [ "x$MALLOC_ARENA_MAX" = "x" ]
+then
+ export MALLOC_ARENA_MAX=4
+fi
+
+# Specifies the default port over which Cassandra will be available for
+# JMX connections.
+# For security reasons, you should not expose this port to the internet. Firewall it if needed.
+JMX_PORT="7199"
+
+
+# Here we create the arguments that will get passed to the jvm when
+# starting cassandra.
+
+# enable assertions. disabling this in production will give a modest
+# performance benefit (around 5%).
+JVM_OPTS="$JVM_OPTS -ea"
+
+# add the jamm javaagent
+JVM_OPTS="$JVM_OPTS -javaagent:$CASSANDRA_HOME/lib/jamm-0.3.0.jar"
+
+# some JVMs will fill up their heap when accessed via JMX, see CASSANDRA-6541
+JVM_OPTS="$JVM_OPTS -XX:+CMSClassUnloadingEnabled"
+
+# enable thread priorities, primarily so we can give periodic tasks
+# a lower priority to avoid interfering with client workload
+JVM_OPTS="$JVM_OPTS -XX:+UseThreadPriorities"
+# allows lowering thread priority without being root. see
+# http://tech.stolsvik.com/2010/01/linux-java-thread-priorities-workaround.html
+JVM_OPTS="$JVM_OPTS -XX:ThreadPriorityPolicy=42"
+
+# min and max heap sizes should be set to the same value to avoid
+# stop-the-world GC pauses during resize, and so that we can lock the
+# heap in memory on startup to prevent any of it from being swapped
+# out.
+JVM_OPTS="$JVM_OPTS -Xms${MAX_HEAP_SIZE}"
+JVM_OPTS="$JVM_OPTS -Xmx${MAX_HEAP_SIZE}"
+JVM_OPTS="$JVM_OPTS -Xmn${HEAP_NEWSIZE}"
+JVM_OPTS="$JVM_OPTS -XX:+HeapDumpOnOutOfMemoryError"
+
+# set jvm HeapDumpPath with CASSANDRA_HEAPDUMP_DIR
+if [ "x$CASSANDRA_HEAPDUMP_DIR" != "x" ]; then
+ JVM_OPTS="$JVM_OPTS -XX:HeapDumpPath=$CASSANDRA_HEAPDUMP_DIR/cassandra-`date +%s`-pid$$.hprof"
+fi
+
+
+startswith() { [ "${1#$2}" != "$1" ]; }
+
+# Per-thread stack size.
+JVM_OPTS="$JVM_OPTS -Xss256k"
+
+# Larger interned string table, for gossip's benefit (CASSANDRA-6410)
+JVM_OPTS="$JVM_OPTS -XX:StringTableSize=1000003"
+
+# GC tuning options
+JVM_OPTS="$JVM_OPTS -XX:+UseParNewGC"
+JVM_OPTS="$JVM_OPTS -XX:+UseConcMarkSweepGC"
+JVM_OPTS="$JVM_OPTS -XX:+CMSParallelRemarkEnabled"
+JVM_OPTS="$JVM_OPTS -XX:SurvivorRatio=8"
+JVM_OPTS="$JVM_OPTS -XX:MaxTenuringThreshold=1"
+JVM_OPTS="$JVM_OPTS -XX:CMSInitiatingOccupancyFraction=75"
+JVM_OPTS="$JVM_OPTS -XX:+UseCMSInitiatingOccupancyOnly"
+JVM_OPTS="$JVM_OPTS -XX:+UseTLAB"
+JVM_OPTS="$JVM_OPTS -XX:CompileCommandFile=$CASSANDRA_CONF/hotspot_compiler"
+JVM_OPTS="$JVM_OPTS -XX:CMSWaitDuration=10000"
+
+# note: bash evals '1.7.x' as > '1.7' so this is really a >= 1.7 jvm check
+#if { [ "$JVM_VERSION" \> "1.7" ] && [ "$JVM_VERSION" \< "1.8.0" ] && [ "$JVM_PATCH_VERSION" -ge "60" ]; } || [ "$JVM_VERSION" \> "1.8" ] ; then
+# JVM_OPTS="$JVM_OPTS -XX:+CMSParallelInitialMarkEnabled -XX:+CMSEdenChunksRecordAlways -XX:CMSWaitDuration=10000"
+#fi
+
+if [ "$JVM_ARCH" = "64-Bit" ] ; then
+ JVM_OPTS="$JVM_OPTS -XX:+UseCondCardMark"
+fi
+
+# GC logging options -- uncomment to enable
+# JVM_OPTS="$JVM_OPTS -XX:+PrintGCDetails"
+# JVM_OPTS="$JVM_OPTS -XX:+PrintGCDateStamps"
+# JVM_OPTS="$JVM_OPTS -XX:+PrintHeapAtGC"
+# JVM_OPTS="$JVM_OPTS -XX:+PrintTenuringDistribution"
+# JVM_OPTS="$JVM_OPTS -XX:+PrintGCApplicationStoppedTime"
+# JVM_OPTS="$JVM_OPTS -XX:+PrintPromotionFailure"
+# JVM_OPTS="$JVM_OPTS -XX:PrintFLSStatistics=1"
+# JVM_OPTS="$JVM_OPTS -Xloggc:/var/log/cassandra/gc-`date +%s`.log"
+# If you are using JDK 6u34 7u2 or later you can enable GC log rotation
+# don't stick the date in the log name if rotation is on.
+# JVM_OPTS="$JVM_OPTS -Xloggc:/var/log/cassandra/gc.log"
+# JVM_OPTS="$JVM_OPTS -XX:+UseGCLogFileRotation"
+# JVM_OPTS="$JVM_OPTS -XX:NumberOfGCLogFiles=10"
+# JVM_OPTS="$JVM_OPTS -XX:GCLogFileSize=10M"
+
+# Configure the following for JEMallocAllocator and if jemalloc is not available in the system
+# library path (Example: /usr/local/lib/). Usually "make install" will do the right thing.
+# export LD_LIBRARY_PATH=<JEMALLOC_HOME>/lib/
+# JVM_OPTS="$JVM_OPTS -Djava.library.path=<JEMALLOC_HOME>/lib/"
+
+# uncomment to have Cassandra JVM listen for remote debuggers/profilers on port 1414
+# JVM_OPTS="$JVM_OPTS -agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=1414"
+
+# uncomment to have Cassandra JVM log internal method compilation (developers only)
+# JVM_OPTS="$JVM_OPTS -XX:+UnlockDiagnosticVMOptions -XX:+LogCompilation"
+
+# Prefer binding to IPv4 network intefaces (when net.ipv6.bindv6only=1). See
+# http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=6342561 (short version:
+# comment out this entry to enable IPv6 support).
+JVM_OPTS="$JVM_OPTS -Djava.net.preferIPv4Stack=true"
+
+# jmx: metrics and administration interface
+#
+# add this if you're having trouble connecting:
+# JVM_OPTS="$JVM_OPTS -Djava.rmi.server.hostname=<public name>"
+#
+# see
+# https://blogs.oracle.com/jmxetc/entry/troubleshooting_connection_problems_in_jconsole
+# for more on configuring JMX through firewalls, etc. (Short version:
+# get it working with no firewall first.)
+#
+# Cassandra ships with JMX accessible *only* from localhost.
+# To enable remote JMX connections, uncomment lines below
+# with authentication and/or ssl enabled. See https://wiki.apache.org/cassandra/JmxSecurity
+#
+if [ "x$LOCAL_JMX" = "x" ]; then
+ LOCAL_JMX=yes
+fi
+
+if [ "$LOCAL_JMX" = "yes" ]; then
+ JVM_OPTS="$JVM_OPTS -Dcassandra.jmx.local.port=$JMX_PORT -XX:+DisableExplicitGC"
+else
+ JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.port=$JMX_PORT"
+ JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.rmi.port=$JMX_PORT"
+ JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.ssl=false"
+ JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.authenticate=true"
+ JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.password.file=/etc/cassandra/jmxremote.password"
+# JVM_OPTS="$JVM_OPTS -Djavax.net.ssl.keyStore=/path/to/keystore"
+# JVM_OPTS="$JVM_OPTS -Djavax.net.ssl.keyStorePassword=<keystore-password>"
+# JVM_OPTS="$JVM_OPTS -Djavax.net.ssl.trustStore=/path/to/truststore"
+# JVM_OPTS="$JVM_OPTS -Djavax.net.ssl.trustStorePassword=<truststore-password>"
+# JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.ssl.need.client.auth=true"
+# JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.registry.ssl=true"
+# JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.ssl.enabled.protocols=<enabled-protocols>"
+# JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.ssl.enabled.cipher.suites=<enabled-cipher-suites>"
+fi
+
+# To use mx4j, an HTML interface for JMX, add mx4j-tools.jar to the lib/
+# directory.
+# See http://wiki.apache.org/cassandra/Operations#Monitoring_with_MX4J
+# By default mx4j listens on 0.0.0.0:8081. Uncomment the following lines
+# to control its listen address and port.
+#MX4J_ADDRESS="-Dmx4jaddress=127.0.0.1"
+#MX4J_PORT="-Dmx4jport=8081"
+
+JVM_OPTS="$JVM_OPTS $MX4J_ADDRESS"
+JVM_OPTS="$JVM_OPTS $MX4J_PORT"
+JVM_OPTS="$JVM_OPTS $JVM_EXTRA_OPTS"
Propchange: uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra-env.sh
------------------------------------------------------------------------------
svn:executable = *
Added: uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep?rev=1711768&view=auto
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep (added)
+++ uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep Sun Nov 1 14:09:47 2015
@@ -0,0 +1,813 @@
+# Cassandra storage config YAML
+
+#
+# This is prepared for configureation for DUCC via ducc_post_install
+#
+
+# NOTE:
+# See http://wiki.apache.org/cassandra/StorageConfiguration for
+# full explanations of configuration directives
+# /NOTE
+
+# The name of the cluster. This is mainly used to prevent machines in
+# one logical cluster from joining another.
+cluster_name: 'DUCC'
+
+# This defines the number of tokens randomly assigned to this node on the ring
+# The more tokens, relative to other nodes, the larger the proportion of data
+# that this node will store. You probably want all nodes to have the same number
+# of tokens assuming they have equal hardware capability.
+#
+# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility,
+# and will use the initial_token as described below.
+#
+# Specifying initial_token will override this setting on the node's initial start,
+# on subsequent starts, this setting will apply even if initial token is set.
+#
+# If you already have a cluster with 1 token per node, and wish to migrate to
+# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations
+num_tokens: 256
+
+# initial_token allows you to specify tokens manually. While you can use # it with
+# vnodes (num_tokens > 1, above) -- in which case you should provide a
+# comma-separated list -- it's primarily used when adding nodes # to legacy clusters
+# that do not have vnodes enabled.
+# initial_token:
+
+# See http://wiki.apache.org/cassandra/HintedHandoff
+# May either be "true" or "false" to enable globally, or contain a list
+# of data centers to enable per-datacenter.
+# hinted_handoff_enabled: DC1,DC2
+hinted_handoff_enabled: true
+# this defines the maximum amount of time a dead host will have hints
+# generated. After it has been dead this long, new hints for it will not be
+# created until it has been seen alive and gone down again.
+max_hint_window_in_ms: 10800000 # 3 hours
+# Maximum throttle in KBs per second, per delivery thread. This will be
+# reduced proportionally to the number of nodes in the cluster. (If there
+# are two nodes in the cluster, each delivery thread will use the maximum
+# rate; if there are three, each will throttle to half of the maximum,
+# since we expect two nodes to be delivering hints simultaneously.)
+hinted_handoff_throttle_in_kb: 1024
+# Number of threads with which to deliver hints;
+# Consider increasing this number when you have multi-dc deployments, since
+# cross-dc handoff tends to be slower
+max_hints_delivery_threads: 2
+
+# Maximum throttle in KBs per second, total. This will be
+# reduced proportionally to the number of nodes in the cluster.
+batchlog_replay_throttle_in_kb: 1024
+
+# Authentication backend, implementing IAuthenticator; used to identify users
+# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator,
+# PasswordAuthenticator}.
+#
+# - AllowAllAuthenticator performs no checks - set it to disable authentication.
+# - PasswordAuthenticator relies on username/password pairs to authenticate
+# users. It keeps usernames and hashed passwords in system_auth.credentials table.
+# Please increase system_auth keyspace replication factor if you use this authenticator.
+authenticator: PasswordAuthenticator
+
+# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions
+# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer,
+# CassandraAuthorizer}.
+#
+# - AllowAllAuthorizer allows any action to any user - set it to disable authorization.
+# - CassandraAuthorizer stores permissions in system_auth.permissions table. Please
+# increase system_auth keyspace replication factor if you use this authorizer.
+authorizer: AllowAllAuthorizer
+
+# Validity period for permissions cache (fetching permissions can be an
+# expensive operation depending on the authorizer, CassandraAuthorizer is
+# one example). Defaults to 2000, set to 0 to disable.
+# Will be disabled automatically for AllowAllAuthorizer.
+permissions_validity_in_ms: 2000
+
+# Refresh interval for permissions cache (if enabled).
+# After this interval, cache entries become eligible for refresh. Upon next
+# access, an async reload is scheduled and the old value returned until it
+# completes. If permissions_validity_in_ms is non-zero, then this must be
+# also.
+# Defaults to the same value as permissions_validity_in_ms.
+# permissions_update_interval_in_ms: 1000
+
+# The partitioner is responsible for distributing groups of rows (by
+# partition key) across nodes in the cluster. You should leave this
+# alone for new clusters. The partitioner can NOT be changed without
+# reloading all data, so when upgrading you should set this to the
+# same partitioner you were already using.
+#
+# Besides Murmur3Partitioner, partitioners included for backwards
+# compatibility include RandomPartitioner, ByteOrderedPartitioner, and
+# OrderPreservingPartitioner.
+#
+partitioner: org.apache.cassandra.dht.Murmur3Partitioner
+
+# Directories where Cassandra should store data on disk. Cassandra
+# will spread data evenly across them, subject to the granularity of
+# the configured compaction strategy.
+# If not set, the default directory is $CASSANDRA_HOME/data/data.
+data_file_directories:
+ - DUCC_HOME/database/data
+
+# commit log. when running on magnetic HDD, this should be a
+# separate spindle than the data directories.
+# If not set, the default directory is $CASSANDRA_HOME/data/commitlog.
+commitlog_directory: DUCC_HOME/database/commitlog
+
+# policy for data disk failures:
+# die: shut down gossip and client transports and kill the JVM for any fs errors or
+# single-sstable errors, so the node can be replaced.
+# stop_paranoid: shut down gossip and client transports even for single-sstable errors,
+# kill the JVM for errors during startup.
+# stop: shut down gossip and client transports, leaving the node effectively dead, but
+# can still be inspected via JMX, kill the JVM for errors during startup.
+# best_effort: stop using the failed disk and respond to requests based on
+# remaining available sstables. This means you WILL see obsolete
+# data at CL.ONE!
+# ignore: ignore fatal errors and let requests fail, as in pre-1.2 Cassandra
+disk_failure_policy: stop
+
+# policy for commit disk failures:
+# die: shut down gossip and Thrift and kill the JVM, so the node can be replaced.
+# stop: shut down gossip and Thrift, leaving the node effectively dead, but
+# can still be inspected via JMX.
+# stop_commit: shutdown the commit log, letting writes collect but
+# continuing to service reads, as in pre-2.0.5 Cassandra
+# ignore: ignore fatal errors and let the batches fail
+commit_failure_policy: stop
+
+# Maximum size of the key cache in memory.
+#
+# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the
+# minimum, sometimes more. The key cache is fairly tiny for the amount of
+# time it saves, so it's worthwhile to use it at large numbers.
+# The row cache saves even more time, but must contain the entire row,
+# so it is extremely space-intensive. It's best to only use the
+# row cache if you have hot rows or static rows.
+#
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache.
+key_cache_size_in_mb:
+
+# Duration in seconds after which Cassandra should
+# save the key cache. Caches are saved to saved_caches_directory as
+# specified in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 14400 or 4 hours.
+key_cache_save_period: 14400
+
+# Number of keys from the key cache to save
+# Disabled by default, meaning all keys are going to be saved
+# key_cache_keys_to_save: 100
+
+# Maximum size of the row cache in memory.
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is 0, to disable row caching.
+row_cache_size_in_mb: 0
+
+# Duration in seconds after which Cassandra should
+# save the row cache. Caches are saved to saved_caches_directory as specified
+# in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 0 to disable saving the row cache.
+row_cache_save_period: 0
+
+# Number of keys from the row cache to save
+# Disabled by default, meaning all keys are going to be saved
+# row_cache_keys_to_save: 100
+
+# Maximum size of the counter cache in memory.
+#
+# Counter cache helps to reduce counter locks' contention for hot counter cells.
+# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before
+# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration
+# of the lock hold, helping with hot counter cell updates, but will not allow skipping
+# the read entirely. Only the local (clock, count) tuple of a counter cell is kept
+# in memory, not the whole counter, so it's relatively cheap.
+#
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache.
+# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache.
+counter_cache_size_in_mb:
+
+# Duration in seconds after which Cassandra should
+# save the counter cache (keys only). Caches are saved to saved_caches_directory as
+# specified in this configuration file.
+#
+# Default is 7200 or 2 hours.
+counter_cache_save_period: 7200
+
+# Number of keys from the counter cache to save
+# Disabled by default, meaning all keys are going to be saved
+# counter_cache_keys_to_save: 100
+
+# The off-heap memory allocator. Affects storage engine metadata as
+# well as caches. Experiments show that JEMAlloc saves some memory
+# than the native GCC allocator (i.e., JEMalloc is more
+# fragmentation-resistant).
+#
+# Supported values are: NativeAllocator, JEMallocAllocator
+#
+# If you intend to use JEMallocAllocator you have to install JEMalloc as library and
+# modify cassandra-env.sh as directed in the file.
+#
+# Defaults to NativeAllocator
+# memory_allocator: NativeAllocator
+
+# saved caches
+# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches.
+saved_caches_directory: DUCC_HOME/database/saved_caches
+
+# commitlog_sync may be either "periodic" or "batch."
+#
+# When in batch mode, Cassandra won't ack writes until the commit log
+# has been fsynced to disk. It will wait
+# commitlog_sync_batch_window_in_ms milliseconds between fsyncs.
+# This window should be kept short because the writer threads will
+# be unable to do extra work while waiting. (You may need to increase
+# concurrent_writes for the same reason.)
+#
+# commitlog_sync: batch
+# commitlog_sync_batch_window_in_ms: 2
+#
+# the other option is "periodic" where writes may be acked immediately
+# and the CommitLog is simply synced every commitlog_sync_period_in_ms
+# milliseconds.
+commitlog_sync: periodic
+commitlog_sync_period_in_ms: 10000
+
+# The size of the individual commitlog file segments. A commitlog
+# segment may be archived, deleted, or recycled once all the data
+# in it (potentially from each columnfamily in the system) has been
+# flushed to sstables.
+#
+# The default size is 32, which is almost always fine, but if you are
+# archiving commitlog segments (see commitlog_archiving.properties),
+# then you probably want a finer granularity of archiving; 8 or 16 MB
+# is reasonable.
+commitlog_segment_size_in_mb: 32
+
+# Reuse commit log files when possible. The default is false, and this
+# feature will be removed entirely in future versions of Cassandra.
+#commitlog_segment_recycling: false
+
+# any class that implements the SeedProvider interface and has a
+# constructor that takes a Map<String, String> of parameters will do.
+seed_provider:
+ # Addresses of hosts that are deemed contact points.
+ # Cassandra nodes use this list of hosts to find each other and learn
+ # the topology of the ring. You must change this if you are running
+ # multiple nodes!
+ - class_name: org.apache.cassandra.locator.SimpleSeedProvider
+ parameters:
+ # seeds is actually a comma-delimited list of addresses.
+ # Ex: "<ip1>,<ip2>,<ip3>"
+ - seeds: "DUCC_HEAD"
+
+# For workloads with more data than can fit in memory, Cassandra's
+# bottleneck will be reads that need to fetch data from
+# disk. "concurrent_reads" should be set to (16 * number_of_drives) in
+# order to allow the operations to enqueue low enough in the stack
+# that the OS and drives can reorder them. Same applies to
+# "concurrent_counter_writes", since counter writes read the current
+# values before incrementing and writing them back.
+#
+# On the other hand, since writes are almost never IO bound, the ideal
+# number of "concurrent_writes" is dependent on the number of cores in
+# your system; (8 * number_of_cores) is a good rule of thumb.
+concurrent_reads: 32
+concurrent_writes: 32
+concurrent_counter_writes: 32
+
+# Total memory to use for sstable-reading buffers. Defaults to
+# the smaller of 1/4 of heap or 512MB.
+# file_cache_size_in_mb: 512
+
+# Total permitted memory to use for memtables. Cassandra will stop
+# accepting writes when the limit is exceeded until a flush completes,
+# and will trigger a flush based on memtable_cleanup_threshold
+# If omitted, Cassandra will set both to 1/4 the size of the heap.
+# memtable_heap_space_in_mb: 2048
+# memtable_offheap_space_in_mb: 2048
+
+# Ratio of occupied non-flushing memtable size to total permitted size
+# that will trigger a flush of the largest memtable. Lager mct will
+# mean larger flushes and hence less compaction, but also less concurrent
+# flush activity which can make it difficult to keep your disks fed
+# under heavy write load.
+#
+# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1)
+# memtable_cleanup_threshold: 0.11
+
+# Specify the way Cassandra allocates and manages memtable memory.
+# Options are:
+# heap_buffers: on heap nio buffers
+# offheap_buffers: off heap (direct) nio buffers
+# offheap_objects: native memory, eliminating nio buffer heap overhead
+memtable_allocation_type: heap_buffers
+
+# Total space to use for commitlogs. Since commitlog segments are
+# mmapped, and hence use up address space, the default size is 32
+# on 32-bit JVMs, and 8192 on 64-bit JVMs.
+#
+# If space gets above this value (it will round up to the next nearest
+# segment multiple), Cassandra will flush every dirty CF in the oldest
+# segment and remove it. So a small total commitlog space will tend
+# to cause more flush activity on less-active columnfamilies.
+# commitlog_total_space_in_mb: 8192
+
+# This sets the amount of memtable flush writer threads. These will
+# be blocked by disk io, and each one will hold a memtable in memory
+# while blocked.
+#
+# memtable_flush_writers defaults to the smaller of (number of disks,
+# number of cores), with a minimum of 2 and a maximum of 8.
+#
+# If your data directories are backed by SSD, you should increase this
+# to the number of cores.
+#memtable_flush_writers: 8
+
+# A fixed memory pool size in MB for for SSTable index summaries. If left
+# empty, this will default to 5% of the heap size. If the memory usage of
+# all index summaries exceeds this limit, SSTables with low read rates will
+# shrink their index summaries in order to meet this limit. However, this
+# is a best-effort process. In extreme conditions Cassandra may need to use
+# more than this amount of memory.
+index_summary_capacity_in_mb:
+
+# How frequently index summaries should be resampled. This is done
+# periodically to redistribute memory from the fixed-size pool to sstables
+# proportional their recent read rates. Setting to -1 will disable this
+# process, leaving existing index summaries at their current sampling level.
+index_summary_resize_interval_in_minutes: 60
+
+# Whether to, when doing sequential writing, fsync() at intervals in
+# order to force the operating system to flush the dirty
+# buffers. Enable this to avoid sudden dirty buffer flushing from
+# impacting read latencies. Almost always a good idea on SSDs; not
+# necessarily on platters.
+trickle_fsync: false
+trickle_fsync_interval_in_kb: 10240
+
+# TCP port, for commands and data
+# For security reasons, you should not expose this port to the internet. Firewall it if needed.
+storage_port: 7000
+
+# SSL port, for encrypted communication. Unused unless enabled in
+# encryption_options
+# For security reasons, you should not expose this port to the internet. Firewall it if needed.
+ssl_storage_port: 7001
+
+# Address or interface to bind to and tell other Cassandra nodes to connect to.
+# You _must_ change this if you want multiple nodes to be able to communicate!
+#
+# Set listen_address OR listen_interface, not both. Interfaces must correspond
+# to a single address, IP aliasing is not supported.
+#
+# Leaving it blank leaves it up to InetAddress.getLocalHost(). This
+# will always do the Right Thing _if_ the node is properly configured
+# (hostname, name resolution, etc), and the Right Thing is to use the
+# address associated with the hostname (it might not be).
+#
+# Setting listen_address to 0.0.0.0 is always wrong.
+#
+# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address
+# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4
+# address will be used. If true the first ipv6 address will be used. Defaults to false preferring
+# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6.
+listen_address: DUCC_HEAD
+# listen_interface: eth0
+# listen_interface_prefer_ipv6: false
+
+# Address to broadcast to other Cassandra nodes
+# Leaving this blank will set it to the same value as listen_address
+# broadcast_address: 1.2.3.4
+
+# Internode authentication backend, implementing IInternodeAuthenticator;
+# used to allow/disallow connections from peer nodes.
+# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator
+
+# Whether to start the native transport server.
+# Please note that the address on which the native transport is bound is the
+# same as the rpc_address. The port however is different and specified below.
+start_native_transport: true
+# port for the CQL native transport to listen for clients on
+# For security reasons, you should not expose this port to the internet. Firewall it if needed.
+native_transport_port: 9042
+# The maximum threads for handling requests when the native transport is used.
+# This is similar to rpc_max_threads though the default differs slightly (and
+# there is no native_transport_min_threads, idle threads will always be stopped
+# after 30 seconds).
+# native_transport_max_threads: 128
+#
+# The maximum size of allowed frame. Frame (requests) larger than this will
+# be rejected as invalid. The default is 256MB.
+# native_transport_max_frame_size_in_mb: 256
+
+# The maximum number of concurrent client connections.
+# The default is -1, which means unlimited.
+# native_transport_max_concurrent_connections: -1
+
+# The maximum number of concurrent client connections per source ip.
+# The default is -1, which means unlimited.
+# native_transport_max_concurrent_connections_per_ip: -1
+
+# Whether to start the thrift rpc server.
+start_rpc: true
+
+# The address or interface to bind the Thrift RPC service and native transport
+# server to.
+#
+# Set rpc_address OR rpc_interface, not both. Interfaces must correspond
+# to a single address, IP aliasing is not supported.
+#
+# Leaving rpc_address blank has the same effect as on listen_address
+# (i.e. it will be based on the configured hostname of the node).
+#
+# Note that unlike listen_address, you can specify 0.0.0.0, but you must also
+# set broadcast_rpc_address to a value other than 0.0.0.0.
+#
+# For security reasons, you should not expose this port to the internet. Firewall it if needed.
+#
+# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address
+# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4
+# address will be used. If true the first ipv6 address will be used. Defaults to false preferring
+# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6.
+rpc_address: DUCC_HEAD
+# rpc_interface: eth1
+# rpc_interface_prefer_ipv6: false
+
+# port for Thrift to listen for clients on
+rpc_port: 9160
+
+# RPC address to broadcast to drivers and other Cassandra nodes. This cannot
+# be set to 0.0.0.0. If left blank, this will be set to the value of
+# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must
+# be set.
+# broadcast_rpc_address: 1.2.3.4
+
+# enable or disable keepalive on rpc/native connections
+rpc_keepalive: true
+
+# Cassandra provides two out-of-the-box options for the RPC Server:
+#
+# sync -> One thread per thrift connection. For a very large number of clients, memory
+# will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size
+# per thread, and that will correspond to your use of virtual memory (but physical memory
+# may be limited depending on use of stack space).
+#
+# hsha -> Stands for "half synchronous, half asynchronous." All thrift clients are handled
+# asynchronously using a small number of threads that does not vary with the amount
+# of thrift clients (and thus scales well to many clients). The rpc requests are still
+# synchronous (one thread per active request). If hsha is selected then it is essential
+# that rpc_max_threads is changed from the default value of unlimited.
+#
+# The default is sync because on Windows hsha is about 30% slower. On Linux,
+# sync/hsha performance is about the same, with hsha of course using less memory.
+#
+# Alternatively, can provide your own RPC server by providing the fully-qualified class name
+# of an o.a.c.t.TServerFactory that can create an instance of it.
+rpc_server_type: sync
+
+# Uncomment rpc_min|max_thread to set request pool size limits.
+#
+# Regardless of your choice of RPC server (see above), the number of maximum requests in the
+# RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync
+# RPC server, it also dictates the number of clients that can be connected at all).
+#
+# The default is unlimited and thus provides no protection against clients overwhelming the server. You are
+# encouraged to set a maximum that makes sense for you in production, but do keep in mind that
+# rpc_max_threads represents the maximum number of client requests this server may execute concurrently.
+#
+# rpc_min_threads: 16
+# rpc_max_threads: 2048
+
+# uncomment to set socket buffer sizes on rpc connections
+# rpc_send_buff_size_in_bytes:
+# rpc_recv_buff_size_in_bytes:
+
+# Uncomment to set socket buffer size for internode communication
+# Note that when setting this, the buffer size is limited by net.core.wmem_max
+# and when not setting it it is defined by net.ipv4.tcp_wmem
+# See:
+# /proc/sys/net/core/wmem_max
+# /proc/sys/net/core/rmem_max
+# /proc/sys/net/ipv4/tcp_wmem
+# /proc/sys/net/ipv4/tcp_wmem
+# and: man tcp
+# internode_send_buff_size_in_bytes:
+# internode_recv_buff_size_in_bytes:
+
+# Frame size for thrift (maximum message length).
+thrift_framed_transport_size_in_mb: 15
+
+# Set to true to have Cassandra create a hard link to each sstable
+# flushed or streamed locally in a backups/ subdirectory of the
+# keyspace data. Removing these links is the operator's
+# responsibility.
+incremental_backups: false
+
+# Whether or not to take a snapshot before each compaction. Be
+# careful using this option, since Cassandra won't clean up the
+# snapshots for you. Mostly useful if you're paranoid when there
+# is a data format change.
+snapshot_before_compaction: false
+
+# Whether or not a snapshot is taken of the data before keyspace truncation
+# or dropping of column families. The STRONGLY advised default of true
+# should be used to provide data safety. If you set this flag to false, you will
+# lose data on truncation or drop.
+auto_snapshot: true
+
+# When executing a scan, within or across a partition, we need to keep the
+# tombstones seen in memory so we can return them to the coordinator, which
+# will use them to make sure other replicas also know about the deleted rows.
+# With workloads that generate a lot of tombstones, this can cause performance
+# problems and even exaust the server heap.
+# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets)
+# Adjust the thresholds here if you understand the dangers and want to
+# scan more tombstones anyway. These thresholds may also be adjusted at runtime
+# using the StorageService mbean.
+tombstone_warn_threshold: 1000
+tombstone_failure_threshold: 100000
+
+# Granularity of the collation index of rows within a partition.
+# Increase if your rows are large, or if you have a very large
+# number of rows per partition. The competing goals are these:
+# 1) a smaller granularity means more index entries are generated
+# and looking up rows withing the partition by collation column
+# is faster
+# 2) but, Cassandra will keep the collation index in memory for hot
+# rows (as part of the key cache), so a larger granularity means
+# you can cache more hot rows
+column_index_size_in_kb: 64
+
+
+# Log WARN on any batch size exceeding this value. 5kb per batch by default.
+# Caution should be taken on increasing the size of this threshold as it can lead to node instability.
+batch_size_warn_threshold_in_kb: 5
+
+# Number of simultaneous compactions to allow, NOT including
+# validation "compactions" for anti-entropy repair. Simultaneous
+# compactions can help preserve read performance in a mixed read/write
+# workload, by mitigating the tendency of small sstables to accumulate
+# during a single long running compactions. The default is usually
+# fine and if you experience problems with compaction running too
+# slowly or too fast, you should look at
+# compaction_throughput_mb_per_sec first.
+#
+# concurrent_compactors defaults to the smaller of (number of disks,
+# number of cores), with a minimum of 2 and a maximum of 8.
+#
+# If your data directories are backed by SSD, you should increase this
+# to the number of cores.
+#concurrent_compactors: 1
+
+# Throttles compaction to the given total throughput across the entire
+# system. The faster you insert data, the faster you need to compact in
+# order to keep the sstable count down, but in general, setting this to
+# 16 to 32 times the rate you are inserting data is more than sufficient.
+# Setting this to 0 disables throttling. Note that this account for all types
+# of compaction, including validation compaction.
+compaction_throughput_mb_per_sec: 16
+
+# Log a warning when compacting partitions larger than this value
+compaction_large_partition_warning_threshold_mb: 100
+
+# When compacting, the replacement sstable(s) can be opened before they
+# are completely written, and used in place of the prior sstables for
+# any range that has been written. This helps to smoothly transfer reads
+# between the sstables, reducing page cache churn and keeping hot rows hot
+sstable_preemptive_open_interval_in_mb: 50
+
+# Throttles all outbound streaming file transfers on this node to the
+# given total throughput in Mbps. This is necessary because Cassandra does
+# mostly sequential IO when streaming data during bootstrap or repair, which
+# can lead to saturating the network connection and degrading rpc performance.
+# When unset, the default is 200 Mbps or 25 MB/s.
+# stream_throughput_outbound_megabits_per_sec: 200
+
+# Throttles all streaming file transfer between the datacenters,
+# this setting allows users to throttle inter dc stream throughput in addition
+# to throttling all network stream traffic as configured with
+# stream_throughput_outbound_megabits_per_sec
+# inter_dc_stream_throughput_outbound_megabits_per_sec:
+
+# How long the coordinator should wait for read operations to complete
+read_request_timeout_in_ms: 5000
+# How long the coordinator should wait for seq or index scans to complete
+range_request_timeout_in_ms: 10000
+# How long the coordinator should wait for writes to complete
+write_request_timeout_in_ms: 2000
+# How long the coordinator should wait for counter writes to complete
+counter_write_request_timeout_in_ms: 5000
+# How long a coordinator should continue to retry a CAS operation
+# that contends with other proposals for the same row
+cas_contention_timeout_in_ms: 1000
+# How long the coordinator should wait for truncates to complete
+# (This can be much longer, because unless auto_snapshot is disabled
+# we need to flush first so we can snapshot before removing the data.)
+truncate_request_timeout_in_ms: 60000
+# The default timeout for other, miscellaneous operations
+request_timeout_in_ms: 10000
+
+# Enable operation timeout information exchange between nodes to accurately
+# measure request timeouts. If disabled, replicas will assume that requests
+# were forwarded to them instantly by the coordinator, which means that
+# under overload conditions we will waste that much extra time processing
+# already-timed-out requests.
+#
+# Warning: before enabling this property make sure to ntp is installed
+# and the times are synchronized between the nodes.
+cross_node_timeout: false
+
+# Enable socket timeout for streaming operation.
+# When a timeout occurs during streaming, streaming is retried from the start
+# of the current file. This _can_ involve re-streaming an important amount of
+# data, so you should avoid setting the value too low.
+# Default value is 3600000, which means streams timeout after an hour.
+# streaming_socket_timeout_in_ms: 3600000
+
+# phi value that must be reached for a host to be marked down.
+# most users should never need to adjust this.
+# phi_convict_threshold: 8
+
+# endpoint_snitch -- Set this to a class that implements
+# IEndpointSnitch. The snitch has two functions:
+# - it teaches Cassandra enough about your network topology to route
+# requests efficiently
+# - it allows Cassandra to spread replicas around your cluster to avoid
+# correlated failures. It does this by grouping machines into
+# "datacenters" and "racks." Cassandra will do its best not to have
+# more than one replica on the same "rack" (which may not actually
+# be a physical location)
+#
+# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
+# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
+# ARE PLACED.
+#
+# Out of the box, Cassandra provides
+# - SimpleSnitch:
+# Treats Strategy order as proximity. This can improve cache
+# locality when disabling read repair. Only appropriate for
+# single-datacenter deployments.
+# - GossipingPropertyFileSnitch
+# This should be your go-to snitch for production use. The rack
+# and datacenter for the local node are defined in
+# cassandra-rackdc.properties and propagated to other nodes via
+# gossip. If cassandra-topology.properties exists, it is used as a
+# fallback, allowing migration from the PropertyFileSnitch.
+# - PropertyFileSnitch:
+# Proximity is determined by rack and data center, which are
+# explicitly configured in cassandra-topology.properties.
+# - Ec2Snitch:
+# Appropriate for EC2 deployments in a single Region. Loads Region
+# and Availability Zone information from the EC2 API. The Region is
+# treated as the datacenter, and the Availability Zone as the rack.
+# Only private IPs are used, so this will not work across multiple
+# Regions.
+# - Ec2MultiRegionSnitch:
+# Uses public IPs as broadcast_address to allow cross-region
+# connectivity. (Thus, you should set seed addresses to the public
+# IP as well.) You will need to open the storage_port or
+# ssl_storage_port on the public IP firewall. (For intra-Region
+# traffic, Cassandra will switch to the private IP after
+# establishing a connection.)
+# - RackInferringSnitch:
+# Proximity is determined by rack and data center, which are
+# assumed to correspond to the 3rd and 2nd octet of each node's IP
+# address, respectively. Unless this happens to match your
+# deployment conventions, this is best used as an example of
+# writing a custom Snitch class and is provided in that spirit.
+#
+# You can use a custom Snitch by setting this to the full class name
+# of the snitch, which will be assumed to be on your classpath.
+endpoint_snitch: SimpleSnitch
+
+# controls how often to perform the more expensive part of host score
+# calculation
+dynamic_snitch_update_interval_in_ms: 100
+# controls how often to reset all host scores, allowing a bad host to
+# possibly recover
+dynamic_snitch_reset_interval_in_ms: 600000
+# if set greater than zero and read_repair_chance is < 1.0, this will allow
+# 'pinning' of replicas to hosts in order to increase cache capacity.
+# The badness threshold will control how much worse the pinned host has to be
+# before the dynamic snitch will prefer other replicas over it. This is
+# expressed as a double which represents a percentage. Thus, a value of
+# 0.2 means Cassandra would continue to prefer the static snitch values
+# until the pinned host was 20% worse than the fastest.
+dynamic_snitch_badness_threshold: 0.1
+
+# request_scheduler -- Set this to a class that implements
+# RequestScheduler, which will schedule incoming client requests
+# according to the specific policy. This is useful for multi-tenancy
+# with a single Cassandra cluster.
+# NOTE: This is specifically for requests from the client and does
+# not affect inter node communication.
+# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place
+# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of
+# client requests to a node with a separate queue for each
+# request_scheduler_id. The scheduler is further customized by
+# request_scheduler_options as described below.
+request_scheduler: org.apache.cassandra.scheduler.NoScheduler
+
+# Scheduler Options vary based on the type of scheduler
+# NoScheduler - Has no options
+# RoundRobin
+# - throttle_limit -- The throttle_limit is the number of in-flight
+# requests per client. Requests beyond
+# that limit are queued up until
+# running requests can complete.
+# The value of 80 here is twice the number of
+# concurrent_reads + concurrent_writes.
+# - default_weight -- default_weight is optional and allows for
+# overriding the default which is 1.
+# - weights -- Weights are optional and will default to 1 or the
+# overridden default_weight. The weight translates into how
+# many requests are handled during each turn of the
+# RoundRobin, based on the scheduler id.
+#
+# request_scheduler_options:
+# throttle_limit: 80
+# default_weight: 5
+# weights:
+# Keyspace1: 1
+# Keyspace2: 5
+
+# request_scheduler_id -- An identifier based on which to perform
+# the request scheduling. Currently the only valid option is keyspace.
+# request_scheduler_id: keyspace
+
+# Enable or disable inter-node encryption
+# Default settings are TLS v1, RSA 1024-bit keys (it is imperative that
+# users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher
+# suite for authentication, key exchange and encryption of the actual data transfers.
+# Use the DHE/ECDHE ciphers if running in FIPS 140 compliant mode.
+# NOTE: No custom encryption options are enabled at the moment
+# The available internode options are : all, none, dc, rack
+#
+# If set to dc cassandra will encrypt the traffic between the DCs
+# If set to rack cassandra will encrypt the traffic between the racks
+#
+# The passwords used in these options must match the passwords used when generating
+# the keystore and truststore. For instructions on generating these files, see:
+# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore
+#
+server_encryption_options:
+ internode_encryption: none
+ keystore: conf/.keystore
+ keystore_password: cassandra
+ truststore: conf/.truststore
+ truststore_password: cassandra
+ # More advanced defaults below:
+ # protocol: TLS
+ # algorithm: SunX509
+ # store_type: JKS
+ # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA]
+ # require_client_auth: false
+
+# enable or disable client/server encryption.
+client_encryption_options:
+ enabled: false
+ keystore: conf/.keystore
+ keystore_password: cassandra
+ # require_client_auth: false
+ # Set trustore and truststore_password if require_client_auth is true
+ # truststore: conf/.truststore
+ # truststore_password: cassandra
+ # More advanced defaults below:
+ # protocol: TLS
+ # algorithm: SunX509
+ # store_type: JKS
+ # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA]
+
+# internode_compression controls whether traffic between nodes is
+# compressed.
+# can be: all - all traffic is compressed
+# dc - traffic between different datacenters is compressed
+# none - nothing is compressed.
+internode_compression: all
+
+# Enable or disable tcp_nodelay for inter-dc communication.
+# Disabling it will result in larger (but fewer) network packets being sent,
+# reducing overhead from the TCP protocol itself, at the cost of increasing
+# latency if you block for cross-datacenter responses.
+inter_dc_tcp_nodelay: false
+
+# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level
+# Adjust the threshold based on your application throughput requirement
+# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level
+# gc_warn_threshold_in_ms: 1000
Propchange: uima/sandbox/uima-ducc/trunk/src/main/resources/cassandra.yaml.prep
------------------------------------------------------------------------------
svn:executable = *
Modified: uima/sandbox/uima-ducc/trunk/src/main/resources/default.ducc.properties
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/resources/default.ducc.properties?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/resources/default.ducc.properties (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/resources/default.ducc.properties Sun Nov 1 14:09:47 2015
@@ -511,13 +511,9 @@ ducc.flow-controller.specifier=org.apach
# database
-# Directory where the databases and associated stuff is kept, relative to DUCC_HOME. This
-# is ORIENTDB_HOME
+# Directory where the databases and associated stuff is kept, relative to DUCC_HOME.
ducc.database.location = database
-# DB defined config file, relative to DUCC_HOME. Must be in private because it has root pw in plaintext.
-ducc.database.config.file = resources.private/database.xml
-
ducc.database.host = --disabled--
# Name of the database with active state. Svc registry, etc.
@@ -525,15 +521,15 @@ ducc.state.database.url = ${ducc.h
# This class implementes the persistence interface for the services registry
#ducc.service.persistence.impl = org.apache.uima.ducc.database.StateServicesDb
-ducc.service.persistence.impl = org.apache.uima.ducc.common.persistence.services.StateServices
+ducc.service.persistence.impl = org.apache.uima.ducc.common.persistence.services.StateServices
# This class implements the persistence interface for Job, Reservation, Service, and AP instances, plus
# the Orchestrator checkpoint.
#ducc.job.history.impl = org.apache.uima.ducc.database.HistoryManagerDb
-ducc.job.history.impl = org.apache.uima.ducc.transport.event.common.history.HistoryPersistenceManager
+ducc.job.history.impl = org.apache.uima.ducc.transport.event.common.history.HistoryPersistenceManager
-ducc.rm.persistence.impl = org.apache.uima.ducc.common.persistence.rm.NullRmStatePersistence
#ducc.rm.persistence.impl = org.apache.uima.ducc.database.RmStatePersistence
+ducc.rm.persistence.impl = org.apache.uima.ducc.common.persistence.rm.NullRmStatePersistence
# end database things -------------------------------------------------------------------------------
Modified: uima/sandbox/uima-ducc/trunk/src/main/resources/log4j.xml
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/src/main/resources/log4j.xml?rev=1711768&r1=1711767&r2=1711768&view=diff
==============================================================================
--- uima/sandbox/uima-ducc/trunk/src/main/resources/log4j.xml (original)
+++ uima/sandbox/uima-ducc/trunk/src/main/resources/log4j.xml Sun Nov 1 14:09:47 2015
@@ -200,6 +200,10 @@
<appender-ref ref="jderr" />
</category>
+ <category name="com.datastax.driver.core">
+ <priority value="warn"/>
+ </category>
+
<category name="org.apache.activemq">
<priority value="warn"/>
</category>
Added: uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbAlive.java
URL: http://svn.apache.org/viewvc/uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbAlive.java?rev=1711768&view=auto
==============================================================================
--- uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbAlive.java (added)
+++ uima/sandbox/uima-ducc/trunk/uima-ducc-database/src/main/java/org/apache/uima/ducc/database/DbAlive.java Sun Nov 1 14:09:47 2015
@@ -0,0 +1,166 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+*/
+
+package org.apache.uima.ducc.database;
+
+import java.util.Collection;
+
+import com.datastax.driver.core.Cluster;
+import com.datastax.driver.core.Host;
+import com.datastax.driver.core.KeyspaceMetadata;
+import com.datastax.driver.core.Metadata;
+import com.datastax.driver.core.PlainTextAuthProvider;
+import com.datastax.driver.core.Session;
+import com.datastax.driver.core.TableMetadata;
+import com.datastax.driver.core.exceptions.AuthenticationException;
+import com.datastax.driver.core.exceptions.NoHostAvailableException;
+
+public class DbAlive
+{
+ String dburl;
+ String adminid = null;
+ String adminpw = null;
+
+ enum RC {
+ OK {
+ public String message() { return "OK"; }
+ public int rc() { return 0; }
+ },
+ NOT_INITIALIZED {
+ public String message() { return "DB Not Initialized"; }
+ public int rc() { return 1; }
+ },
+ CANT_CONNECT {
+ public String message() { return "DB Cannot Connect"; }
+ public int rc() { return 2; }
+ },
+ NOT_AUTHORIZED {
+ public String message() { return "DB Not Authorized"; }
+ public int rc() { return 3; }
+ },
+ UNKNOWN {
+ public String message() { return "DB Unknown Error"; }
+ public int rc() { return 4; }
+ },
+ ;
+ public abstract String message();
+ public abstract int rc();
+ };
+
+ private Cluster cluster;
+ private Session session;
+
+ public DbAlive(String dburl, String adminid, String adminpw)
+ {
+ this.dburl = dburl;
+ this.adminid = adminid;
+ this.adminpw = adminpw;
+ }
+
+ public RC connect()
+ throws Exception
+ {
+ RC ret = RC.OK;
+ try {
+ PlainTextAuthProvider auth = new PlainTextAuthProvider(adminid, adminpw);
+ cluster = Cluster.builder()
+ .withAuthProvider(auth)
+ .addContactPoint(dburl)
+ .build();
+
+ Metadata metadata = cluster.getMetadata();
+ System.out.println("Connected to cluster: " + metadata.getClusterName());
+ String x = DbCreate.DUCC_KEYSPACE;
+ KeyspaceMetadata duccKs = metadata.getKeyspace(DbCreate.DUCC_KEYSPACE);
+ if ( duccKs == null ) {
+ System.out.println("DUCC keyspace not found.");
+ ret = RC.NOT_INITIALIZED;
+ } else {
+ String tables = "";
+ Collection<TableMetadata> tableset = duccKs.getTables();
+ for ( TableMetadata tmd : tableset ) {
+ tables = tables + tmd.getName() + " ";
+ }
+ System.out.println("Tables found: " + tables);
+ }
+
+ for ( Host host : metadata.getAllHosts() ) {
+ System.out.println(String.format("Datatacenter: %s; Host: %s; Rack: %s\n", host.getDatacenter(), host.getAddress(), host.getRack()));
+ }
+ } catch ( NoHostAvailableException e ) {
+ // If this never clears the db is either not started, or is broken and can't talk
+ System.out.println("Waiting for DB to start ...");
+ ret = RC.CANT_CONNECT;
+ } catch ( AuthenticationException e ) {
+ // If this never clears the db is not correctly configured
+ System.out.println("Waiting for authentication ...");
+ ret = RC.NOT_AUTHORIZED;
+ } catch ( Exception e ) {
+ e.printStackTrace();
+ ret = RC.UNKNOWN;
+ } finally {
+ if ( cluster != null ) cluster.close();
+ }
+ return ret;
+ }
+
+ public void close() {
+ cluster.close();
+ }
+
+ public Session getSession()
+ {
+ return this.session;
+ }
+
+ static void usage()
+ {
+ System.out.println("Usage: DbAlive database_url id pw");
+ System.exit(1);
+ }
+
+ public static void main(String[] args)
+ {
+ if ( args.length != 3 ) {
+ usage();
+ }
+
+ int max = 10; // we'll wait up to 60 seconds: 20 x 3 seconds
+ DbAlive client = null;
+ RC rc = RC.OK;
+ try {
+ client = new DbAlive(args[0], args[1], args[2]);
+ for ( int i = 0; i < max; i++ ) {
+ rc = client.connect();
+ System.out.println(rc.message());
+ if ( rc == RC.OK) {
+ break;
+ } else {
+ try { Thread.sleep(3000); } catch ( Exception e ) {}
+ }
+ }
+ } catch ( Throwable e ) {
+ System.out.println("Errors contacting database");
+ e.printStackTrace();
+ System.exit(rc.rc());
+ }
+ System.exit(rc.rc());
+ }
+
+}